pytest experiments

.devcontainer/devcontainer.json

@@ -12,7 +12,7 @@
 
 	// The optional 'workspaceFolder' property is the path VS Code should open by default when
 	// connected. This is typically a file mount in .devcontainer/docker-compose.yml
-	"workspaceFolder": "/workspaces/langchain",
+	"workspaceFolder": "/workspaces/${localWorkspaceFolderBasename}",
 
 	// Prevent the container from shutting down
 	"overrideCommand": true

.devcontainer/docker-compose.yaml

@@ -6,7 +6,7 @@ services:
       context: ..
     volumes:
    # Update this to wherever you want VS Code to mount the folder of your project
-      - ..:/workspaces/langchain:cached
+      - ..:/workspaces:cached
     networks:
       - langchain-network 
   #   environment:

.github/scripts/check_diff.py

@@ -6,8 +6,8 @@ from typing import Dict
 LANGCHAIN_DIRS = [
     "libs/core",
     "libs/text-splitters",
-    "libs/langchain",
     "libs/community",
+    "libs/langchain",
     "libs/experimental",
 ]
 
@@ -19,7 +19,6 @@ if __name__ == "__main__":
         "test": set(),
         "extended-test": set(),
     }
-    docs_edited = False
 
     if len(files) == 300:
         # max diff length is 300 files - there are likely files missing
@@ -48,17 +47,6 @@ if __name__ == "__main__":
                     found = True
                 if found:
                     dirs_to_run["extended-test"].add(dir_)
-        elif file.startswith("libs/standard-tests"):
-            # TODO: update to include all packages that rely on standard-tests (all partner packages)
-            # note: won't run on external repo partners
-            dirs_to_run["lint"].add("libs/standard-tests")
-            dirs_to_run["test"].add("libs/partners/mistralai")
-            dirs_to_run["test"].add("libs/partners/openai")
-            dirs_to_run["test"].add("libs/partners/anthropic")
-            dirs_to_run["test"].add("libs/partners/ai21")
-            dirs_to_run["test"].add("libs/partners/fireworks")
-            dirs_to_run["test"].add("libs/partners/groq")
-
         elif file.startswith("libs/cli"):
             # todo: add cli makefile
             pass
@@ -77,8 +65,6 @@ if __name__ == "__main__":
                 "an update for this new library!"
             )
         elif any(file.startswith(p) for p in ["docs/", "templates/", "cookbook/"]):
-            if file.startswith("docs/"):
-                docs_edited = True
             dirs_to_run["lint"].add(".")
 
     outputs = {
@@ -87,7 +73,6 @@ if __name__ == "__main__":
         ),
         "dirs-to-test": list(dirs_to_run["test"] | dirs_to_run["extended-test"]),
         "dirs-to-extended-test": list(dirs_to_run["extended-test"]),
-        "docs-edited": "true" if docs_edited else "",
     }
     for key, value in outputs.items():
         json_output = json.dumps(value)

.github/scripts/get_min_versions.py

@@ -13,16 +13,13 @@ MIN_VERSION_LIBS = [
 
 
 def get_min_version(version: str) -> str:
-    # base regex for x.x.x with cases for rc/post/etc
-    # valid strings: https://peps.python.org/pep-0440/#public-version-identifiers
-    vstring = r"\d+(?:\.\d+){0,2}(?:(?:a|b|rc|\.post|\.dev)\d+)?"
     # case ^x.x.x
-    _match = re.match(f"^\\^({vstring})$", version)
+    _match = re.match(r"^\^(\d+(?:\.\d+){0,2})$", version)
     if _match:
         return _match.group(1)
 
     # case >=x.x.x,<y.y.y
-    _match = re.match(f"^>=({vstring}),<({vstring})$", version)
+    _match = re.match(r"^>=(\d+(?:\.\d+){0,2}),<(\d+(?:\.\d+){0,2})$", version)
     if _match:
         _min = _match.group(1)
         _max = _match.group(2)
@@ -30,7 +27,7 @@ def get_min_version(version: str) -> str:
         return _min
 
     # case x.x.x
-    _match = re.match(f"^({vstring})$", version)
+    _match = re.match(r"^(\d+(?:\.\d+){0,2})$", version)
     if _match:
         return _match.group(1)
 
@@ -55,9 +52,6 @@ def get_min_version_from_toml(toml_path: str):
             # Get the version string
             version_string = dependencies[lib]
 
-            if isinstance(version_string, dict):
-                version_string = version_string["version"]
-
             # Use parse_version to get the minimum supported version from version_string
             min_version = get_min_version(version_string)
 

.github/workflows/_integration_test.yml

@@ -58,7 +58,6 @@ jobs:
           MISTRAL_API_KEY: ${{ secrets.MISTRAL_API_KEY }}
           TOGETHER_API_KEY: ${{ secrets.TOGETHER_API_KEY }}
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-          GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
           NVIDIA_API_KEY: ${{ secrets.NVIDIA_API_KEY }}
           GOOGLE_SEARCH_API_KEY: ${{ secrets.GOOGLE_SEARCH_API_KEY }}
           GOOGLE_CSE_ID: ${{ secrets.GOOGLE_CSE_ID }}
@@ -78,7 +77,6 @@ jobs:
           MONGODB_ATLAS_URI: ${{ secrets.MONGODB_ATLAS_URI }}
           VOYAGE_API_KEY: ${{ secrets.VOYAGE_API_KEY }}
           COHERE_API_KEY: ${{ secrets.COHERE_API_KEY }}
-          UPSTAGE_API_KEY: ${{ secrets.UPSTAGE_API_KEY }}
         run: |
           make integration_tests
 

.github/workflows/_release.yml

@@ -13,11 +13,6 @@ on:
         required: true
         type: string
         default: 'libs/langchain'
-      dangerous-nonmaster-release:
-        required: false
-        type: boolean
-        default: false
-        description: "Release from a non-master branch (danger!)"
 
 env:
   PYTHON_VERSION: "3.11"
@@ -25,7 +20,7 @@ env:
 
 jobs:
   build:
-    if: github.ref == 'refs/heads/master' || inputs.dangerous-nonmaster-release
+    if: github.ref == 'refs/heads/master'
     environment: Scheduled testing
     runs-on: ubuntu-latest
 
@@ -80,7 +75,6 @@ jobs:
       ./.github/workflows/_test_release.yml
     with:
       working-directory: ${{ inputs.working-directory }}
-      dangerous-nonmaster-release: ${{ inputs.dangerous-nonmaster-release }}
     secrets: inherit
 
   pre-release-checks:
@@ -118,7 +112,7 @@ jobs:
           PKG_NAME: ${{ needs.build.outputs.pkg-name }}
           VERSION: ${{ needs.build.outputs.version }}
         # Here we use:
-        # - The default regular PyPI index as the *primary* index, meaning
+        # - The default regular PyPI index as the *primary* index, meaning 
         #   that it takes priority (https://pypi.org/simple)
         # - The test PyPI index as an extra index, so that any dependencies that
         #   are not found on test PyPI can be resolved and installed anyway.
@@ -177,7 +171,7 @@ jobs:
         env:
           MIN_VERSIONS: ${{ steps.min-version.outputs.min-versions }}
         run: |
-          poetry run pip install --force-reinstall $MIN_VERSIONS --editable .
+          poetry run pip install $MIN_VERSIONS
           make tests
         working-directory: ${{ inputs.working-directory }}
 
@@ -221,8 +215,6 @@ jobs:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} # for airbyte
           MONGODB_ATLAS_URI: ${{ secrets.MONGODB_ATLAS_URI }}
           VOYAGE_API_KEY: ${{ secrets.VOYAGE_API_KEY }}
-          UPSTAGE_API_KEY: ${{ secrets.UPSTAGE_API_KEY }}
-          FIREWORKS_API_KEY: ${{ secrets.FIREWORKS_API_KEY }}
         run: make integration_tests
         working-directory: ${{ inputs.working-directory }}
 
@@ -298,13 +290,14 @@ jobs:
         with:
           name: dist
           path: ${{ inputs.working-directory }}/dist/
-          
-      - name: Create Tag
+
+      - name: Create Release
         uses: ncipollo/release-action@v1
+        if: ${{ inputs.working-directory == 'libs/langchain' }}
         with:
           artifacts: "dist/*"
           token: ${{ secrets.GITHUB_TOKEN }}
-          generateReleaseNotes: false
-          tag: ${{needs.build.outputs.pkg-name}}==${{ needs.build.outputs.version }}
-          body: "# Release ${{needs.build.outputs.pkg-name}}==${{ needs.build.outputs.version }}\n\nPackage-specific release note generation coming soon."
-          commit: ${{ github.sha }}
+          draft: false
+          generateReleaseNotes: true
+          tag: v${{ needs.build.outputs.version }}
+          commit: master

.github/workflows/_test_release.yml

@@ -7,11 +7,6 @@ on:
         required: true
         type: string
         description: "From which folder this pipeline executes"
-      dangerous-nonmaster-release:
-        required: false
-        type: boolean
-        default: false
-        description: "Release from a non-master branch (danger!)"
 
 env:
   POETRY_VERSION: "1.7.1"
@@ -19,7 +14,7 @@ env:
 
 jobs:
   build:
-    if: github.ref == 'refs/heads/master' || inputs.dangerous-nonmaster-release
+    if: github.ref == 'refs/heads/master'
     runs-on: ubuntu-latest
 
     outputs:

.github/workflows/check_diffs.yml

@@ -36,7 +36,6 @@ jobs:
       dirs-to-lint: ${{ steps.set-matrix.outputs.dirs-to-lint }}
       dirs-to-test: ${{ steps.set-matrix.outputs.dirs-to-test }}
       dirs-to-extended-test: ${{ steps.set-matrix.outputs.dirs-to-extended-test }}
-      docs-edited: ${{ steps.set-matrix.outputs.docs-edited }}
   lint:
     name: cd ${{ matrix.working-directory }}
     needs: [ build ]
@@ -61,9 +60,9 @@ jobs:
       working-directory: ${{ matrix.working-directory }}
     secrets: inherit
 
-  test-doc-imports:
+  test_doc_imports:
     needs: [ build ]
-    if: ${{ needs.build.outputs.dirs-to-test != '[]' || needs.build.outputs.docs-edited }}
+    if: ${{ needs.build.outputs.dirs-to-test != '[]' }}
     uses: ./.github/workflows/_test_doc_imports.yml
     secrets: inherit
 
@@ -141,7 +140,7 @@ jobs:
           echo "$STATUS" | grep 'nothing to commit, working tree clean'
   ci_success:
     name: "CI Success"
-    needs: [build, lint, test, compile-integration-tests, dependencies, extended-tests, test-doc-imports]
+    needs: [build, lint, test, compile-integration-tests, dependencies, extended-tests]
     if: |
       always()
     runs-on: ubuntu-latest

.github/workflows/codespell.yml

@@ -3,9 +3,9 @@ name: CI / cd . / make spell_check
 
 on:
   push:
-    branches: [master, v0.1]
+    branches: [master]
   pull_request:
-    branches: [master, v0.1]
+    branches: [master]
 
 permissions:
   contents: read

.github/workflows/scheduled_test.yml

@@ -10,22 +10,19 @@ env:
 
 jobs:
   build:
+    defaults:
+      run:
+        working-directory: libs/langchain
     runs-on: ubuntu-latest
+    environment: Scheduled testing
     strategy:
-      fail-fast: false
       matrix:
         python-version:
           - "3.8"
+          - "3.9"
+          - "3.10"
           - "3.11"
-        working-directory:
-          - "libs/partners/openai"
-          - "libs/partners/anthropic"
-          - "libs/partners/ai21"
-          - "libs/partners/fireworks"
-          - "libs/partners/groq"
-          - "libs/partners/mistralai"
-          - "libs/partners/together"
-    name: Python ${{ matrix.python-version }} - ${{ matrix.working-directory }}
+    name: Python ${{ matrix.python-version }}
     steps:
       - uses: actions/checkout@v4
 
@@ -34,7 +31,7 @@ jobs:
         with:
           python-version: ${{ matrix.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
-          working-directory: ${{ matrix.working-directory }}
+          working-directory: libs/langchain
           cache-key: scheduled
 
       - name: 'Authenticate to Google Cloud'
@@ -43,15 +40,26 @@ jobs:
         with:
           credentials_json: '${{ secrets.GOOGLE_CREDENTIALS }}'
 
+      - name: Configure AWS Credentials
+        uses: aws-actions/configure-aws-credentials@v4
+        with:
+          aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
+          aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
+          aws-region: ${{ vars.AWS_REGION }}
+
       - name: Install dependencies
-        working-directory: ${{ matrix.working-directory }}
+        working-directory: libs/langchain
         shell: bash
         run: |
           echo "Running scheduled tests, installing dependencies with poetry..."
           poetry install --with=test_integration,test
 
-      - name: Run integration tests
-        working-directory: ${{ matrix.working-directory }}
+      - name: Install deps outside pyproject
+        if: ${{ startsWith(inputs.working-directory, 'libs/community/') }}
+        shell: bash
+        run: poetry run pip install "boto3<2" "google-cloud-aiplatform<2"
+
+      - name: Run tests
         shell: bash
         env:
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
@@ -62,16 +70,11 @@ jobs:
           AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_CHAT_DEPLOYMENT_NAME }}
           AZURE_OPENAI_LLM_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_LLM_DEPLOYMENT_NAME }}
           AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME }}
-          AI21_API_KEY: ${{ secrets.AI21_API_KEY }}
           FIREWORKS_API_KEY: ${{ secrets.FIREWORKS_API_KEY }}
-          GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
-          MISTRAL_API_KEY: ${{ secrets.MISTRAL_API_KEY }}
-          TOGETHER_API_KEY: ${{ secrets.TOGETHER_API_KEY }}
         run: |
-          make integration_test
+          make scheduled_tests
 
       - name: Ensure the tests did not create any additional files
-        working-directory: ${{ matrix.working-directory }}
         shell: bash
         run: |
           set -eu

Makefile

@@ -3,7 +3,7 @@
 ## help: Show this help info.
 help: Makefile
 	@printf "\n\033[1mUsage: make <TARGETS> ...\033[0m\n\n\033[1mTargets:\033[0m\n\n"
-	@sed -n 's/^## //p' $< | awk -F':' '{printf "\033[36m%-30s\033[0m %s\n", $$1, $$2}' | sort | sed -e 's/^/  /'
+	@sed -n 's/^##//p' $< | awk -F':' '{printf "\033[36m%-30s\033[0m %s\n", $$1, $$2}' | sort | sed -e 's/^/ /'
 
 ## all: Default target, shows help.
 all: help
@@ -17,11 +17,16 @@ clean: docs_clean api_docs_clean
 
 ## docs_build: Build the documentation.
 docs_build:
-	cd docs && make build
+	docs/.local_build.sh
 
 ## docs_clean: Clean the documentation build artifacts.
 docs_clean:
-	cd docs && make clean
+	@if [ -d _dist ]; then \
+		rm -r _dist; \
+		echo "Directory _dist has been cleaned."; \
+	else \
+		echo "Nothing to clean."; \
+	fi
 
 ## docs_linkcheck: Run linkchecker on the documentation.
 docs_linkcheck:
@@ -55,12 +60,12 @@ spell_fix:
 
 ## lint: Run linting on the project.
 lint lint_package lint_tests:
-	poetry run ruff check docs templates cookbook
+	poetry run ruff docs templates cookbook
 	poetry run ruff format docs templates cookbook --diff
-	poetry run ruff check --select I docs templates cookbook
+	poetry run ruff --select I docs templates cookbook
 	git grep 'from langchain import' docs/docs templates cookbook | grep -vE 'from langchain import (hub)' && exit 1 || exit 0
 
 ## format: Format the project files.
 format format_diff:
 	poetry run ruff format docs templates cookbook
-	poetry run ruff check --select I --fix docs templates cookbook
+	poetry run ruff --select I --fix docs templates cookbook

README.md

@@ -4,7 +4,7 @@
 
 [![Release Notes](https://img.shields.io/github/release/langchain-ai/langchain)](https://github.com/langchain-ai/langchain/releases)
 [![CI](https://github.com/langchain-ai/langchain/actions/workflows/check_diffs.yml/badge.svg)](https://github.com/langchain-ai/langchain/actions/workflows/check_diffs.yml)
-[![Downloads](https://static.pepy.tech/badge/langchain-core/month)](https://pepy.tech/project/langchain-core)
+[![Downloads](https://static.pepy.tech/badge/langchain/month)](https://pepy.tech/project/langchain)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 [![Twitter](https://img.shields.io/twitter/url/https/twitter.com/langchainai.svg?style=social&label=Follow%20%40LangChainAI)](https://twitter.com/langchainai)
 [![](https://dcbadge.vercel.app/api/server/6adMQxSpJS?compact=true&style=flat)](https://discord.gg/6adMQxSpJS)
@@ -47,7 +47,7 @@ For these applications, LangChain simplifies the entire application lifecycle:
 - **`langchain-community`**: Third party integrations.
   - Some integrations have been further split into **partner packages** that only rely on **`langchain-core`**. Examples include **`langchain_openai`** and **`langchain_anthropic`**.
 - **`langchain`**: Chains, agents, and retrieval strategies that make up an application's cognitive architecture.
-- **[`LangGraph`](https://python.langchain.com/docs/langgraph)**: A library for building robust and stateful multi-actor applications with LLMs by modeling steps as edges and nodes in a graph.
+- **`[LangGraph](https://python.langchain.com/docs/langgraph)`**: A library for building robust and stateful multi-actor applications with LLMs by modeling steps as edges and nodes in a graph.
 
 ### Productionization:
 - **[LangSmith](https://python.langchain.com/docs/langsmith)**: A developer platform that lets you debug, test, evaluate, and monitor chains built on any LLM framework and seamlessly integrates with LangChain.

cookbook/Multi_modal_RAG.ipynb

@@ -464,8 +464,8 @@
     "    Check if the base64 data is an image by looking at the start of the data\n",
     "    \"\"\"\n",
     "    image_signatures = {\n",
-    "        b\"\\xff\\xd8\\xff\": \"jpg\",\n",
-    "        b\"\\x89\\x50\\x4e\\x47\\x0d\\x0a\\x1a\\x0a\": \"png\",\n",
+    "        b\"\\xFF\\xD8\\xFF\": \"jpg\",\n",
+    "        b\"\\x89\\x50\\x4E\\x47\\x0D\\x0A\\x1A\\x0A\": \"png\",\n",
     "        b\"\\x47\\x49\\x46\\x38\": \"gif\",\n",
     "        b\"\\x52\\x49\\x46\\x46\": \"webp\",\n",
     "    }\n",
@@ -604,7 +604,7 @@
    "source": [
     "# Check retrieval\n",
     "query = \"Give me company names that are interesting investments based on EV / NTM and NTM rev growth. Consider EV / NTM multiples vs historical?\"\n",
-    "docs = retriever_multi_vector_img.invoke(query, limit=6)\n",
+    "docs = retriever_multi_vector_img.get_relevant_documents(query, limit=6)\n",
     "\n",
     "# We get 4 docs\n",
     "len(docs)"
@@ -630,7 +630,7 @@
    "source": [
     "# Check retrieval\n",
     "query = \"What are the EV / NTM and NTM rev growth for MongoDB, Cloudflare, and Datadog?\"\n",
-    "docs = retriever_multi_vector_img.invoke(query, limit=6)\n",
+    "docs = retriever_multi_vector_img.get_relevant_documents(query, limit=6)\n",
     "\n",
     "# We get 4 docs\n",
     "len(docs)"

cookbook/Multi_modal_RAG_google.ipynb

@@ -185,7 +185,7 @@
     "    )\n",
     "    # Text summary chain\n",
     "    model = VertexAI(\n",
-    "        temperature=0, model_name=\"gemini-pro\", max_tokens=1024\n",
+    "        temperature=0, model_name=\"gemini-pro\", max_output_tokens=1024\n",
     "    ).with_fallbacks([empty_response])\n",
     "    summarize_chain = {\"element\": lambda x: x} | prompt | model | StrOutputParser()\n",
     "\n",
@@ -254,9 +254,9 @@
     "\n",
     "def image_summarize(img_base64, prompt):\n",
     "    \"\"\"Make image summary\"\"\"\n",
-    "    model = ChatVertexAI(model=\"gemini-pro-vision\", max_tokens=1024)\n",
+    "    model = ChatVertexAI(model_name=\"gemini-pro-vision\", max_output_tokens=1024)\n",
     "\n",
-    "    msg = model.invoke(\n",
+    "    msg = model(\n",
     "        [\n",
     "            HumanMessage(\n",
     "                content=[\n",
@@ -462,8 +462,8 @@
     "    Check if the base64 data is an image by looking at the start of the data\n",
     "    \"\"\"\n",
     "    image_signatures = {\n",
-    "        b\"\\xff\\xd8\\xff\": \"jpg\",\n",
-    "        b\"\\x89\\x50\\x4e\\x47\\x0d\\x0a\\x1a\\x0a\": \"png\",\n",
+    "        b\"\\xFF\\xD8\\xFF\": \"jpg\",\n",
+    "        b\"\\x89\\x50\\x4E\\x47\\x0D\\x0A\\x1A\\x0A\": \"png\",\n",
     "        b\"\\x47\\x49\\x46\\x38\": \"gif\",\n",
     "        b\"\\x52\\x49\\x46\\x46\": \"webp\",\n",
     "    }\n",
@@ -553,7 +553,9 @@
     "    \"\"\"\n",
     "\n",
     "    # Multi-modal LLM\n",
-    "    model = ChatVertexAI(temperature=0, model_name=\"gemini-pro-vision\", max_tokens=1024)\n",
+    "    model = ChatVertexAI(\n",
+    "        temperature=0, model_name=\"gemini-pro-vision\", max_output_tokens=1024\n",
+    "    )\n",
     "\n",
     "    # RAG pipeline\n",
     "    chain = (\n",
@@ -602,7 +604,7 @@
    ],
    "source": [
     "query = \"What are the EV / NTM and NTM rev growth for MongoDB, Cloudflare, and Datadog?\"\n",
-    "docs = retriever_multi_vector_img.invoke(query, limit=1)\n",
+    "docs = retriever_multi_vector_img.get_relevant_documents(query, limit=1)\n",
     "\n",
     "# We get 2 docs\n",
     "len(docs)"

cookbook/RAPTOR.ipynb

@@ -535,9 +535,9 @@
     "    print(f\"--Generated {len(all_clusters)} clusters--\")\n",
     "\n",
     "    # Summarization\n",
-    "    template = \"\"\"Here is a sub-set of LangChain Expression Language doc. \n",
+    "    template = \"\"\"Here is a sub-set of LangChain Expression Langauge doc. \n",
     "    \n",
-    "    LangChain Expression Language provides a way to compose chain in LangChain.\n",
+    "    LangChain Expression Langauge provides a way to compose chain in LangChain.\n",
     "    \n",
     "    Give a detailed summary of the documentation provided.\n",
     "    \n",

cookbook/README.md

@@ -47,7 +47,6 @@ Notebook | Description
 [press_releases.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/press_releases.ipynb) | Retrieve and query company press release data powered by [Kay.ai](https://kay.ai).
 [program_aided_language_model.i...](https://github.com/langchain-ai/langchain/tree/master/cookbook/program_aided_language_model.ipynb) | Implement program-aided language models as described in the provided research paper.
 [qa_citations.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/qa_citations.ipynb) | Different ways to get a model to cite its sources.
-[rag_upstage_layout_analysis_groundedness_check.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/rag_upstage_layout_analysis_groundedness_check.ipynb) | End-to-end RAG example using Upstage Layout Analysis and Groundedness Check.
 [retrieval_in_sql.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/retrieval_in_sql.ipynb) | Perform retrieval-augmented-generation (rag) on a PostgreSQL database using pgvector.
 [sales_agent_with_context.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/sales_agent_with_context.ipynb) | Implement a context-aware ai sales agent, salesgpt, that can have natural sales conversations, interact with other systems, and use a product knowledge base to discuss a company's offerings.
 [self_query_hotel_search.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/self_query_hotel_search.ipynb) | Build a hotel room search feature with self-querying retrieval, using a specific hotel recommendation dataset.
@@ -57,4 +56,3 @@ Notebook | Description
 [two_agent_debate_tools.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/two_agent_debate_tools.ipynb) | Simulate multi-agent dialogues where the agents can utilize various tools.
 [two_player_dnd.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/two_player_dnd.ipynb) | Simulate a two-player dungeons & dragons game, where a dialogue simulator class is used to coordinate the dialogue between the protagonist and the dungeon master.
 [wikibase_agent.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/wikibase_agent.ipynb) | Create a simple wikibase agent that utilizes sparql generation, with testing done on http://wikidata.org.
-[oracleai_demo.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/oracleai_demo.ipynb) | This guide outlines how to utilize Oracle AI Vector Search alongside Langchain for an end-to-end RAG pipeline, providing step-by-step examples. The process includes loading documents from various sources using OracleDocLoader, summarizing them either within or outside the database with OracleSummary, and generating embeddings similarly through OracleEmbeddings. It also covers chunking documents according to specific requirements using Advanced Oracle Capabilities from OracleTextSplitter, and finally, storing and indexing these documents in a Vector Store for querying with OracleVS.

cookbook/Semi_Structured_RAG.ipynb

@@ -75,7 +75,7 @@
     "\n",
     "Apply to the [`LLaMA2`](https://arxiv.org/pdf/2307.09288.pdf) paper. \n",
     "\n",
-    "We use the Unstructured [`partition_pdf`](https://unstructured-io.github.io/unstructured/core/partition.html#partition-pdf), which segments a PDF document by using a layout model. \n",
+    "We use the Unstructured [`partition_pdf`](https://unstructured-io.github.io/unstructured/bricks/partition.html#partition-pdf), which segments a PDF document by using a layout model. \n",
     "\n",
     "This layout model makes it possible to extract elements, such as tables, from pdfs. \n",
     "\n",

cookbook/Semi_structured_and_multi_modal_RAG.ipynb

@@ -562,7 +562,9 @@
    ],
    "source": [
     "# We can retrieve this table\n",
-    "retriever.invoke(\"What are results for LLaMA across across domains / subjects?\")[1]"
+    "retriever.get_relevant_documents(\n",
+    "    \"What are results for LLaMA across across domains / subjects?\"\n",
+    ")[1]"
    ]
   },
   {
@@ -612,7 +614,9 @@
     }
    ],
    "source": [
-    "retriever.invoke(\"Images / figures with playful and creative examples\")[1]"
+    "retriever.get_relevant_documents(\"Images / figures with playful and creative examples\")[\n",
+    "    1\n",
+    "]"
    ]
   },
   {

cookbook/Semi_structured_multi_modal_RAG_LLaMA2.ipynb

@@ -501,7 +501,9 @@
     }
    ],
    "source": [
-    "retriever.invoke(\"Images / figures with playful and creative examples\")[0]"
+    "retriever.get_relevant_documents(\"Images / figures with playful and creative examples\")[\n",
+    "    0\n",
+    "]"
    ]
   },
   {

cookbook/advanced_rag_eval.ipynb

@@ -342,7 +342,7 @@
     "# Testing on retrieval\n",
     "query = \"What percentage of CPI is dedicated to Housing, and how does it compare to the combined percentage of Medical Care, Apparel, and Other Goods and Services?\"\n",
     "suffix_for_images = \" Include any pie charts, graphs, or tables.\"\n",
-    "docs = retriever_multi_vector_img.invoke(query + suffix_for_images)"
+    "docs = retriever_multi_vector_img.get_relevant_documents(query + suffix_for_images)"
    ]
   },
   {
@@ -532,8 +532,8 @@
     "def is_image_data(b64data):\n",
     "    \"\"\"Check if the base64 data is an image by looking at the start of the data.\"\"\"\n",
     "    image_signatures = {\n",
-    "        b\"\\xff\\xd8\\xff\": \"jpg\",\n",
-    "        b\"\\x89\\x50\\x4e\\x47\\x0d\\x0a\\x1a\\x0a\": \"png\",\n",
+    "        b\"\\xFF\\xD8\\xFF\": \"jpg\",\n",
+    "        b\"\\x89\\x50\\x4E\\x47\\x0D\\x0A\\x1A\\x0A\": \"png\",\n",
     "        b\"\\x47\\x49\\x46\\x38\": \"gif\",\n",
     "        b\"\\x52\\x49\\x46\\x46\": \"webp\",\n",
     "    }\n",

cookbook/camel_role_playing.ipynb

@@ -90,7 +90,7 @@
     "    ) -> AIMessage:\n",
     "        messages = self.update_messages(input_message)\n",
     "\n",
-    "        output_message = self.model.invoke(messages)\n",
+    "        output_message = self.model(messages)\n",
     "        self.update_messages(output_message)\n",
     "\n",
     "        return output_message"

cookbook/cql_agent.ipynb

@@ -1,557 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Setup Environment"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Python Modules"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Install the following Python modules:\n",
-    "\n",
-    "```bash\n",
-    "pip install ipykernel python-dotenv cassio pandas langchain_openai langchain langchain-community langchainhub langchain_experimental openai-multi-tool-use-parallel-patch\n",
-    "```"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Load the `.env` File"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Connection is via `cassio` using `auto=True` parameter, and the notebook uses OpenAI. You should create a `.env` file accordingly.\n",
-    "\n",
-    "For Casssandra, set:\n",
-    "```bash\n",
-    "CASSANDRA_CONTACT_POINTS\n",
-    "CASSANDRA_USERNAME\n",
-    "CASSANDRA_PASSWORD\n",
-    "CASSANDRA_KEYSPACE\n",
-    "```\n",
-    "\n",
-    "For Astra, set:\n",
-    "```bash\n",
-    "ASTRA_DB_APPLICATION_TOKEN\n",
-    "ASTRA_DB_DATABASE_ID\n",
-    "ASTRA_DB_KEYSPACE\n",
-    "```\n",
-    "\n",
-    "For example:\n",
-    "\n",
-    "```bash\n",
-    "# Connection to Astra:\n",
-    "ASTRA_DB_DATABASE_ID=a1b2c3d4-...\n",
-    "ASTRA_DB_APPLICATION_TOKEN=AstraCS:...\n",
-    "ASTRA_DB_KEYSPACE=notebooks\n",
-    "\n",
-    "# Also set \n",
-    "OPENAI_API_KEY=sk-....\n",
-    "```\n",
-    "\n",
-    "(You may also modify the below code to directly connect with `cassio`.)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from dotenv import load_dotenv\n",
-    "\n",
-    "load_dotenv(override=True)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Connect to Cassandra"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import os\n",
-    "\n",
-    "import cassio\n",
-    "\n",
-    "cassio.init(auto=True)\n",
-    "session = cassio.config.resolve_session()\n",
-    "if not session:\n",
-    "    raise Exception(\n",
-    "        \"Check environment configuration or manually configure cassio connection parameters\"\n",
-    "    )\n",
-    "\n",
-    "keyspace = os.environ.get(\n",
-    "    \"ASTRA_DB_KEYSPACE\", os.environ.get(\"CASSANDRA_KEYSPACE\", None)\n",
-    ")\n",
-    "if not keyspace:\n",
-    "    raise ValueError(\"a KEYSPACE environment variable must be set\")\n",
-    "\n",
-    "session.set_keyspace(keyspace)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Setup Database"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "This needs to be done one time only!"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Download Data"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "The dataset used is from Kaggle, the [Environmental Sensor Telemetry Data](https://www.kaggle.com/datasets/garystafford/environmental-sensor-data-132k?select=iot_telemetry_data.csv). The next cell will download and unzip the data into a Pandas dataframe. The following cell is instructions to download manually. \n",
-    "\n",
-    "The net result of this section is you should have a Pandas dataframe variable `df`."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "#### Download Automatically"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from io import BytesIO\n",
-    "from zipfile import ZipFile\n",
-    "\n",
-    "import pandas as pd\n",
-    "import requests\n",
-    "\n",
-    "datasetURL = \"https://storage.googleapis.com/kaggle-data-sets/788816/1355729/bundle/archive.zip?X-Goog-Algorithm=GOOG4-RSA-SHA256&X-Goog-Credential=gcp-kaggle-com%40kaggle-161607.iam.gserviceaccount.com%2F20240404%2Fauto%2Fstorage%2Fgoog4_request&X-Goog-Date=20240404T115828Z&X-Goog-Expires=259200&X-Goog-SignedHeaders=host&X-Goog-Signature=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\"\n",
-    "\n",
-    "response = requests.get(datasetURL)\n",
-    "if response.status_code == 200:\n",
-    "    zip_file = ZipFile(BytesIO(response.content))\n",
-    "    csv_file_name = zip_file.namelist()[0]\n",
-    "else:\n",
-    "    print(\"Failed to download the file\")\n",
-    "\n",
-    "with zip_file.open(csv_file_name) as csv_file:\n",
-    "    df = pd.read_csv(csv_file)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "#### Download Manually"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "You can download the `.zip` file and unpack the `.csv` contained within. Comment in the next line, and adjust the path to this `.csv` file appropriately."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# df = pd.read_csv(\"/path/to/iot_telemetry_data.csv\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Load Data into Cassandra"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "This section assumes the existence of a dataframe `df`, the following cell validates its structure. The Download section above creates this object."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "assert df is not None, \"Dataframe 'df' must be set\"\n",
-    "expected_columns = [\n",
-    "    \"ts\",\n",
-    "    \"device\",\n",
-    "    \"co\",\n",
-    "    \"humidity\",\n",
-    "    \"light\",\n",
-    "    \"lpg\",\n",
-    "    \"motion\",\n",
-    "    \"smoke\",\n",
-    "    \"temp\",\n",
-    "]\n",
-    "assert all(\n",
-    "    [column in df.columns for column in expected_columns]\n",
-    "), \"DataFrame does not have the expected columns\""
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Create and load tables:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from datetime import UTC, datetime\n",
-    "\n",
-    "from cassandra.query import BatchStatement\n",
-    "\n",
-    "# Create sensors table\n",
-    "table_query = \"\"\"\n",
-    "CREATE TABLE IF NOT EXISTS iot_sensors (\n",
-    "    device text,\n",
-    "    conditions text,\n",
-    "    room text,\n",
-    "    PRIMARY KEY (device)\n",
-    ")\n",
-    "WITH COMMENT = 'Environmental IoT room sensor metadata.';\n",
-    "\"\"\"\n",
-    "session.execute(table_query)\n",
-    "\n",
-    "pstmt = session.prepare(\n",
-    "    \"\"\"\n",
-    "INSERT INTO iot_sensors (device, conditions, room)\n",
-    "VALUES (?, ?, ?)\n",
-    "\"\"\"\n",
-    ")\n",
-    "\n",
-    "devices = [\n",
-    "    (\"00:0f:00:70:91:0a\", \"stable conditions, cooler and more humid\", \"room 1\"),\n",
-    "    (\"1c:bf:ce:15:ec:4d\", \"highly variable temperature and humidity\", \"room 2\"),\n",
-    "    (\"b8:27:eb:bf:9d:51\", \"stable conditions, warmer and dryer\", \"room 3\"),\n",
-    "]\n",
-    "\n",
-    "for device, conditions, room in devices:\n",
-    "    session.execute(pstmt, (device, conditions, room))\n",
-    "\n",
-    "print(\"Sensors inserted successfully.\")\n",
-    "\n",
-    "# Create data table\n",
-    "table_query = \"\"\"\n",
-    "CREATE TABLE IF NOT EXISTS iot_data (\n",
-    "    day text,\n",
-    "    device text,\n",
-    "    ts timestamp,\n",
-    "    co double,\n",
-    "    humidity double,\n",
-    "    light boolean,\n",
-    "    lpg double,\n",
-    "    motion boolean,\n",
-    "    smoke double,\n",
-    "    temp double,\n",
-    "    PRIMARY KEY ((day, device), ts)\n",
-    ")\n",
-    "WITH COMMENT = 'Data from environmental IoT room sensors. Columns include device identifier, timestamp (ts) of the data collection, carbon monoxide level (co), relative humidity, light presence, LPG concentration, motion detection, smoke concentration, and temperature (temp). Data is partitioned by day and device.';\n",
-    "\"\"\"\n",
-    "session.execute(table_query)\n",
-    "\n",
-    "pstmt = session.prepare(\n",
-    "    \"\"\"\n",
-    "INSERT INTO iot_data (day, device, ts, co, humidity, light, lpg, motion, smoke, temp)\n",
-    "VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?)\n",
-    "\"\"\"\n",
-    ")\n",
-    "\n",
-    "\n",
-    "def insert_data_batch(name, group):\n",
-    "    batch = BatchStatement()\n",
-    "    day, device = name\n",
-    "    print(f\"Inserting batch for day: {day}, device: {device}\")\n",
-    "\n",
-    "    for _, row in group.iterrows():\n",
-    "        timestamp = datetime.fromtimestamp(row[\"ts\"], UTC)\n",
-    "        batch.add(\n",
-    "            pstmt,\n",
-    "            (\n",
-    "                day,\n",
-    "                row[\"device\"],\n",
-    "                timestamp,\n",
-    "                row[\"co\"],\n",
-    "                row[\"humidity\"],\n",
-    "                row[\"light\"],\n",
-    "                row[\"lpg\"],\n",
-    "                row[\"motion\"],\n",
-    "                row[\"smoke\"],\n",
-    "                row[\"temp\"],\n",
-    "            ),\n",
-    "        )\n",
-    "\n",
-    "    session.execute(batch)\n",
-    "\n",
-    "\n",
-    "# Convert columns to appropriate types\n",
-    "df[\"light\"] = df[\"light\"] == \"true\"\n",
-    "df[\"motion\"] = df[\"motion\"] == \"true\"\n",
-    "df[\"ts\"] = df[\"ts\"].astype(float)\n",
-    "df[\"day\"] = df[\"ts\"].apply(\n",
-    "    lambda x: datetime.fromtimestamp(x, UTC).strftime(\"%Y-%m-%d\")\n",
-    ")\n",
-    "\n",
-    "grouped_df = df.groupby([\"day\", \"device\"])\n",
-    "\n",
-    "for name, group in grouped_df:\n",
-    "    insert_data_batch(name, group)\n",
-    "\n",
-    "print(\"Data load complete\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "print(session.keyspace)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Load the Tools"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Python `import` statements for the demo:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.agents import AgentExecutor, create_openai_tools_agent\n",
-    "from langchain_community.agent_toolkits.cassandra_database.toolkit import (\n",
-    "    CassandraDatabaseToolkit,\n",
-    ")\n",
-    "from langchain_community.tools.cassandra_database.prompt import QUERY_PATH_PROMPT\n",
-    "from langchain_community.tools.cassandra_database.tool import (\n",
-    "    GetSchemaCassandraDatabaseTool,\n",
-    "    GetTableDataCassandraDatabaseTool,\n",
-    "    QueryCassandraDatabaseTool,\n",
-    ")\n",
-    "from langchain_community.utilities.cassandra_database import CassandraDatabase\n",
-    "from langchain_openai import ChatOpenAI"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "The `CassandraDatabase` object is loaded from `cassio`, though it does accept a `Session`-type parameter as an alternative."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Create a CassandraDatabase instance\n",
-    "db = CassandraDatabase(include_tables=[\"iot_sensors\", \"iot_data\"])\n",
-    "\n",
-    "# Create the Cassandra Database tools\n",
-    "query_tool = QueryCassandraDatabaseTool(db=db)\n",
-    "schema_tool = GetSchemaCassandraDatabaseTool(db=db)\n",
-    "select_data_tool = GetTableDataCassandraDatabaseTool(db=db)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "The tools can be invoked directly:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Test the tools\n",
-    "print(\"Executing a CQL query:\")\n",
-    "query = \"SELECT * FROM iot_sensors LIMIT 5;\"\n",
-    "result = query_tool.run({\"query\": query})\n",
-    "print(result)\n",
-    "\n",
-    "print(\"\\nGetting the schema for a keyspace:\")\n",
-    "schema = schema_tool.run({\"keyspace\": keyspace})\n",
-    "print(schema)\n",
-    "\n",
-    "print(\"\\nGetting data from a table:\")\n",
-    "table = \"iot_data\"\n",
-    "predicate = \"day = '2020-07-14' and device = 'b8:27:eb:bf:9d:51'\"\n",
-    "data = select_data_tool.run(\n",
-    "    {\"keyspace\": keyspace, \"table\": table, \"predicate\": predicate, \"limit\": 5}\n",
-    ")\n",
-    "print(data)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Agent Configuration"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.agents import Tool\n",
-    "from langchain_experimental.utilities import PythonREPL\n",
-    "\n",
-    "python_repl = PythonREPL()\n",
-    "\n",
-    "repl_tool = Tool(\n",
-    "    name=\"python_repl\",\n",
-    "    description=\"A Python shell. Use this to execute python commands. Input should be a valid python command. If you want to see the output of a value, you should print it out with `print(...)`.\",\n",
-    "    func=python_repl.run,\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain import hub\n",
-    "\n",
-    "llm = ChatOpenAI(temperature=0, model=\"gpt-4-1106-preview\")\n",
-    "toolkit = CassandraDatabaseToolkit(db=db)\n",
-    "\n",
-    "# context = toolkit.get_context()\n",
-    "# tools = toolkit.get_tools()\n",
-    "tools = [schema_tool, select_data_tool, repl_tool]\n",
-    "\n",
-    "input = (\n",
-    "    QUERY_PATH_PROMPT\n",
-    "    + f\"\"\"\n",
-    "\n",
-    "Here is your task: In the {keyspace} keyspace, find the total number of times the temperature of each device has exceeded 23 degrees on July 14, 2020.\n",
-    " Create a summary report including the name of the room. Use Pandas if helpful.\n",
-    "\"\"\"\n",
-    ")\n",
-    "\n",
-    "prompt = hub.pull(\"hwchase17/openai-tools-agent\")\n",
-    "\n",
-    "# messages = [\n",
-    "#     HumanMessagePromptTemplate.from_template(input),\n",
-    "#     AIMessage(content=QUERY_PATH_PROMPT),\n",
-    "#     MessagesPlaceholder(variable_name=\"agent_scratchpad\"),\n",
-    "# ]\n",
-    "\n",
-    "# prompt = ChatPromptTemplate.from_messages(messages)\n",
-    "# print(prompt)\n",
-    "\n",
-    "# Choose the LLM that will drive the agent\n",
-    "# Only certain models support this\n",
-    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-1106\", temperature=0)\n",
-    "\n",
-    "# Construct the OpenAI Tools agent\n",
-    "agent = create_openai_tools_agent(llm, tools, prompt)\n",
-    "\n",
-    "print(\"Available tools:\")\n",
-    "for tool in tools:\n",
-    "    print(\"\\t\" + tool.name + \" - \" + tool.description + \" - \" + str(tool))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)\n",
-    "\n",
-    "response = agent_executor.invoke({\"input\": input})\n",
-    "\n",
-    "print(response[\"output\"])"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.9.1"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 4
-}

cookbook/custom_agent_with_plugin_retrieval.ipynb

@@ -169,7 +169,7 @@
     "\n",
     "def get_tools(query):\n",
     "    # Get documents, which contain the Plugins to use\n",
-    "    docs = retriever.invoke(query)\n",
+    "    docs = retriever.get_relevant_documents(query)\n",
     "    # Get the toolkits, one for each plugin\n",
     "    tool_kits = [toolkits_dict[d.metadata[\"plugin_name\"]] for d in docs]\n",
     "    # Get the tools: a separate NLAChain for each endpoint\n",

cookbook/custom_agent_with_plugin_retrieval_using_plugnplai.ipynb

@@ -193,7 +193,7 @@
     "\n",
     "def get_tools(query):\n",
     "    # Get documents, which contain the Plugins to use\n",
-    "    docs = retriever.invoke(query)\n",
+    "    docs = retriever.get_relevant_documents(query)\n",
     "    # Get the toolkits, one for each plugin\n",
     "    tool_kits = [toolkits_dict[d.metadata[\"plugin_name\"]] for d in docs]\n",
     "    # Get the tools: a separate NLAChain for each endpoint\n",

cookbook/custom_agent_with_tool_retrieval.ipynb

@@ -142,7 +142,7 @@
     "\n",
     "\n",
     "def get_tools(query):\n",
-    "    docs = retriever.invoke(query)\n",
+    "    docs = retriever.get_relevant_documents(query)\n",
     "    return [ALL_TOOLS[d.metadata[\"index\"]] for d in docs]"
    ]
   },

cookbook/forward_looking_retrieval_augmented_generation.ipynb

@@ -362,7 +362,7 @@
    ],
    "source": [
     "llm = OpenAI()\n",
-    "llm.invoke(query)"
+    "llm(query)"
    ]
   },
   {

cookbook/gymnasium_agent_simulation.ipynb

@@ -108,7 +108,7 @@
     "        return obs_message\n",
     "\n",
     "    def _act(self):\n",
-    "        act_message = self.model.invoke(self.message_history)\n",
+    "        act_message = self.model(self.message_history)\n",
     "        self.message_history.append(act_message)\n",
     "        action = int(self.action_parser.parse(act_message.content)[\"action\"])\n",
     "        return action\n",

cookbook/langgraph_crag.ipynb

@@ -206,7 +206,7 @@
     "    print(\"---RETRIEVE---\")\n",
     "    state_dict = state[\"keys\"]\n",
     "    question = state_dict[\"question\"]\n",
-    "    documents = retriever.invoke(question)\n",
+    "    documents = retriever.get_relevant_documents(question)\n",
     "    return {\"keys\": {\"documents\": documents, \"question\": question}}\n",
     "\n",
     "\n",

cookbook/langgraph_self_rag.ipynb

@@ -213,7 +213,7 @@
     "    print(\"---RETRIEVE---\")\n",
     "    state_dict = state[\"keys\"]\n",
     "    question = state_dict[\"question\"]\n",
-    "    documents = retriever.invoke(question)\n",
+    "    documents = retriever.get_relevant_documents(question)\n",
     "    return {\"keys\": {\"documents\": documents, \"question\": question}}\n",
     "\n",
     "\n",

cookbook/multi_modal_RAG_chroma.ipynb

@@ -435,7 +435,7 @@
     "    display(HTML(image_html))\n",
     "\n",
     "\n",
-    "docs = retriever.invoke(\"Woman with children\", k=10)\n",
+    "docs = retriever.get_relevant_documents(\"Woman with children\", k=10)\n",
     "for doc in docs:\n",
     "    if is_base64(doc.page_content):\n",
     "        plt_img_base64(doc.page_content)\n",

cookbook/multi_modal_RAG_vdms.ipynb

@@ -443,7 +443,7 @@
     "\n",
     "\n",
     "query = \"Woman with children\"\n",
-    "docs = retriever.invoke(query, k=10)\n",
+    "docs = retriever.get_relevant_documents(query, k=10)\n",
     "\n",
     "for doc in docs:\n",
     "    if is_base64(doc.page_content):\n",

cookbook/multi_player_dnd.ipynb

@@ -74,7 +74,7 @@
     "        Applies the chatmodel to the message history\n",
     "        and returns the message string\n",
     "        \"\"\"\n",
-    "        message = self.model.invoke(\n",
+    "        message = self.model(\n",
     "            [\n",
     "                self.system_message,\n",
     "                HumanMessage(content=\"\\n\".join(self.message_history + [self.prefix])),\n",

cookbook/multiagent_authoritarian.ipynb

@@ -79,7 +79,7 @@
     "        Applies the chatmodel to the message history\n",
     "        and returns the message string\n",
     "        \"\"\"\n",
-    "        message = self.model.invoke(\n",
+    "        message = self.model(\n",
     "            [\n",
     "                self.system_message,\n",
     "                HumanMessage(content=\"\\n\".join(self.message_history + [self.prefix])),\n",
@@ -234,7 +234,7 @@
     "            termination_clause=self.termination_clause if self.stop else \"\",\n",
     "        )\n",
     "\n",
-    "        self.response = self.model.invoke(\n",
+    "        self.response = self.model(\n",
     "            [\n",
     "                self.system_message,\n",
     "                HumanMessage(content=response_prompt),\n",
@@ -263,7 +263,7 @@
     "            speaker_names=speaker_names,\n",
     "        )\n",
     "\n",
-    "        choice_string = self.model.invoke(\n",
+    "        choice_string = self.model(\n",
     "            [\n",
     "                self.system_message,\n",
     "                HumanMessage(content=choice_prompt),\n",
@@ -299,7 +299,7 @@
     "                ),\n",
     "                next_speaker=self.next_speaker,\n",
     "            )\n",
-    "            message = self.model.invoke(\n",
+    "            message = self.model(\n",
     "                [\n",
     "                    self.system_message,\n",
     "                    HumanMessage(content=next_prompt),\n",

cookbook/multiagent_bidding.ipynb

@@ -71,7 +71,7 @@
     "        Applies the chatmodel to the message history\n",
     "        and returns the message string\n",
     "        \"\"\"\n",
-    "        message = self.model.invoke(\n",
+    "        message = self.model(\n",
     "            [\n",
     "                self.system_message,\n",
     "                HumanMessage(content=\"\\n\".join(self.message_history + [self.prefix])),\n",
@@ -164,7 +164,7 @@
     "            message_history=\"\\n\".join(self.message_history),\n",
     "            recent_message=self.message_history[-1],\n",
     "        )\n",
-    "        bid_string = self.model.invoke([SystemMessage(content=prompt)]).content\n",
+    "        bid_string = self.model([SystemMessage(content=prompt)]).content\n",
     "        return bid_string"
    ]
   },

cookbook/oracleai_demo.ipynb

@@ -1,872 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# Oracle AI Vector Search with Document Processing\n",
-    "Oracle AI Vector Search is designed for Artificial Intelligence (AI) workloads that allows you to query data based on semantics, rather than keywords.\n",
-    "One of the biggest benefit of Oracle AI Vector Search is that semantic search on unstructured data can be combined with relational search on business data in one single system. This is not only powerful but also significantly more effective because you don't need to add a specialized vector database, eliminating the pain of data fragmentation between multiple systems.\n",
-    "\n",
-    "In addition, because Oracle has been building database technologies for so long, your vectors can benefit from all of Oracle Database's most powerful features, like the following:\n",
-    "\n",
-    " * Partitioning Support\n",
-    " * Real Application Clusters scalability\n",
-    " * Exadata smart scans\n",
-    " * Shard processing across geographically distributed databases\n",
-    " * Transactions\n",
-    " * Parallel SQL\n",
-    " * Disaster recovery\n",
-    " * Security\n",
-    " * Oracle Machine Learning\n",
-    " * Oracle Graph Database\n",
-    " * Oracle Spatial and Graph\n",
-    " * Oracle Blockchain\n",
-    " * JSON\n",
-    "\n",
-    "This guide demonstrates how Oracle AI Vector Search can be used with Langchain to serve an end-to-end RAG pipeline. This guide goes through examples of:\n",
-    "\n",
-    " * Loading the documents from various sources using OracleDocLoader\n",
-    " * Summarizing them within/outside the database using OracleSummary\n",
-    " * Generating embeddings for them within/outside the database using OracleEmbeddings\n",
-    " * Chunking them according to different requirements using Advanced Oracle Capabilities from OracleTextSplitter\n",
-    " * Storing and Indexing them in a Vector Store and querying them for queries in OracleVS"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Prerequisites\n",
-    "\n",
-    "Please install Oracle Python Client driver to use Langchain with Oracle AI Vector Search. "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# pip install oracledb"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Create Demo User\n",
-    "First, create a demo user with all the required privileges. "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 37,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Connection successful!\n",
-      "User setup done!\n"
-     ]
-    }
-   ],
-   "source": [
-    "import sys\n",
-    "\n",
-    "import oracledb\n",
-    "\n",
-    "# please update with your username, password, hostname and service_name\n",
-    "# please make sure this user has sufficient privileges to perform all below\n",
-    "username = \"\"\n",
-    "password = \"\"\n",
-    "dsn = \"\"\n",
-    "\n",
-    "try:\n",
-    "    conn = oracledb.connect(user=username, password=password, dsn=dsn)\n",
-    "    print(\"Connection successful!\")\n",
-    "\n",
-    "    cursor = conn.cursor()\n",
-    "    cursor.execute(\n",
-    "        \"\"\"\n",
-    "    begin\n",
-    "        -- drop user\n",
-    "        begin\n",
-    "            execute immediate 'drop user testuser cascade';\n",
-    "        exception\n",
-    "            when others then\n",
-    "                dbms_output.put_line('Error setting up user.');\n",
-    "        end;\n",
-    "        execute immediate 'create user testuser identified by testuser';\n",
-    "        execute immediate 'grant connect, unlimited tablespace, create credential, create procedure, create any index to testuser';\n",
-    "        execute immediate 'create or replace directory DEMO_PY_DIR as ''/scratch/hroy/view_storage/hroy_devstorage/demo/orachain''';\n",
-    "        execute immediate 'grant read, write on directory DEMO_PY_DIR to public';\n",
-    "        execute immediate 'grant create mining model to testuser';\n",
-    "\n",
-    "        -- network access\n",
-    "        begin\n",
-    "            DBMS_NETWORK_ACL_ADMIN.APPEND_HOST_ACE(\n",
-    "                host => '*',\n",
-    "                ace => xs$ace_type(privilege_list => xs$name_list('connect'),\n",
-    "                                principal_name => 'testuser',\n",
-    "                                principal_type => xs_acl.ptype_db));\n",
-    "        end;\n",
-    "    end;\n",
-    "    \"\"\"\n",
-    "    )\n",
-    "    print(\"User setup done!\")\n",
-    "    cursor.close()\n",
-    "    conn.close()\n",
-    "except Exception as e:\n",
-    "    print(\"User setup failed!\")\n",
-    "    cursor.close()\n",
-    "    conn.close()\n",
-    "    sys.exit(1)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Process Documents using Oracle AI\n",
-    "Let's think about a scenario that the users have some documents in Oracle Database or in a file system. They want to use the data for Oracle AI Vector Search using Langchain.\n",
-    "\n",
-    "For that, the users need to do some document preprocessing. The first step would be to read the documents, generate their summary(if needed) and then chunk/split them if needed. After that, they need to generate the embeddings for those chunks and store into Oracle AI Vector Store. Finally, the users will perform some semantic queries on those data. \n",
-    "\n",
-    "Oracle AI Vector Search Langchain library provides a range of document processing functionalities including document loading, splitting, generating summary and embeddings.\n",
-    "\n",
-    "In the following sections, we will go through how to use Oracle AI Langchain APIs to achieve each of these functionalities individually. "
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Connect to Demo User\n",
-    "The following sample code will show how to connect to Oracle Database. "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 45,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Connection successful!\n"
-     ]
-    }
-   ],
-   "source": [
-    "import sys\n",
-    "\n",
-    "import oracledb\n",
-    "\n",
-    "# please update with your username, password, hostname and service_name\n",
-    "username = \"\"\n",
-    "password = \"\"\n",
-    "dsn = \"\"\n",
-    "\n",
-    "try:\n",
-    "    conn = oracledb.connect(user=username, password=password, dsn=dsn)\n",
-    "    print(\"Connection successful!\")\n",
-    "except Exception as e:\n",
-    "    print(\"Connection failed!\")\n",
-    "    sys.exit(1)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Populate a Demo Table\n",
-    "Create a demo table and insert some sample documents."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 46,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Table created and populated.\n"
-     ]
-    }
-   ],
-   "source": [
-    "try:\n",
-    "    cursor = conn.cursor()\n",
-    "\n",
-    "    drop_table_sql = \"\"\"drop table demo_tab\"\"\"\n",
-    "    cursor.execute(drop_table_sql)\n",
-    "\n",
-    "    create_table_sql = \"\"\"create table demo_tab (id number, data clob)\"\"\"\n",
-    "    cursor.execute(create_table_sql)\n",
-    "\n",
-    "    insert_row_sql = \"\"\"insert into demo_tab values (:1, :2)\"\"\"\n",
-    "    rows_to_insert = [\n",
-    "        (\n",
-    "            1,\n",
-    "            \"If the answer to any preceding questions is yes, then the database stops the search and allocates space from the specified tablespace; otherwise, space is allocated from the database default shared temporary tablespace.\",\n",
-    "        ),\n",
-    "        (\n",
-    "            2,\n",
-    "            \"A tablespace can be online (accessible) or offline (not accessible) whenever the database is open.\\nA tablespace is usually online so that its data is available to users. The SYSTEM tablespace and temporary tablespaces cannot be taken offline.\",\n",
-    "        ),\n",
-    "        (\n",
-    "            3,\n",
-    "            \"The database stores LOBs differently from other data types. Creating a LOB column implicitly creates a LOB segment and a LOB index. The tablespace containing the LOB segment and LOB index, which are always stored together, may be different from the tablespace containing the table.\\nSometimes the database can store small amounts of LOB data in the table itself rather than in a separate LOB segment.\",\n",
-    "        ),\n",
-    "    ]\n",
-    "    cursor.executemany(insert_row_sql, rows_to_insert)\n",
-    "\n",
-    "    conn.commit()\n",
-    "\n",
-    "    print(\"Table created and populated.\")\n",
-    "    cursor.close()\n",
-    "except Exception as e:\n",
-    "    print(\"Table creation failed.\")\n",
-    "    cursor.close()\n",
-    "    conn.close()\n",
-    "    sys.exit(1)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "\n",
-    "\n",
-    "Now that we have a demo user and a demo table with some data, we just need to do one more setup. For embedding and summary, we have a few provider options that the users can choose from such as database, 3rd party providers like ocigenai, huggingface, openai, etc. If the users choose to use 3rd party provider, they need to create a credential with corresponding authentication information. On the other hand, if the users choose to use 'database' as provider, they need to load an onnx model to Oracle Database for embeddings; however, for summary, they don't need to do anything."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Load ONNX Model\n",
-    "\n",
-    "To generate embeddings, Oracle provides a few provider options for users to choose from. The users can choose 'database' provider or some 3rd party providers like OCIGENAI, HuggingFace, etc.\n",
-    "\n",
-    "***Note*** If the users choose database option, they need to load an ONNX model to Oracle Database. The users do not need to load an ONNX model to Oracle Database if they choose to use 3rd party provider to generate embeddings.\n",
-    "\n",
-    "One of the core benefits of using an ONNX model is that the users do not need to transfer their data to 3rd party to generate embeddings. And also, since it does not involve any network or REST API calls, it may provide better performance.\n",
-    "\n",
-    "Here is the sample code to load an ONNX model to Oracle Database:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 47,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "ONNX model loaded.\n"
-     ]
-    }
-   ],
-   "source": [
-    "from langchain_community.embeddings.oracleai import OracleEmbeddings\n",
-    "\n",
-    "# please update with your related information\n",
-    "# make sure that you have onnx file in the system\n",
-    "onnx_dir = \"DEMO_PY_DIR\"\n",
-    "onnx_file = \"tinybert.onnx\"\n",
-    "model_name = \"demo_model\"\n",
-    "\n",
-    "try:\n",
-    "    OracleEmbeddings.load_onnx_model(conn, onnx_dir, onnx_file, model_name)\n",
-    "    print(\"ONNX model loaded.\")\n",
-    "except Exception as e:\n",
-    "    print(\"ONNX model loading failed!\")\n",
-    "    sys.exit(1)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Create Credential\n",
-    "\n",
-    "On the other hand, if the users choose to use 3rd party provider to generate embeddings and summary, they need to create credential to access 3rd party provider's end points.\n",
-    "\n",
-    "***Note:*** The users do not need to create any credential if they choose to use 'database' provider to generate embeddings and summary. Should the users choose to 3rd party provider, they need to create credential for the 3rd party provider they want to use. \n",
-    "\n",
-    "Here is a sample example:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "try:\n",
-    "    cursor = conn.cursor()\n",
-    "    cursor.execute(\n",
-    "        \"\"\"\n",
-    "       declare\n",
-    "           jo json_object_t;\n",
-    "       begin\n",
-    "           -- HuggingFace\n",
-    "           dbms_vector_chain.drop_credential(credential_name  => 'HF_CRED');\n",
-    "           jo := json_object_t();\n",
-    "           jo.put('access_token', '<access_token>');\n",
-    "           dbms_vector_chain.create_credential(\n",
-    "               credential_name   =>  'HF_CRED',\n",
-    "               params            => json(jo.to_string));\n",
-    "\n",
-    "           -- OCIGENAI\n",
-    "           dbms_vector_chain.drop_credential(credential_name  => 'OCI_CRED');\n",
-    "           jo := json_object_t();\n",
-    "           jo.put('user_ocid','<user_ocid>');\n",
-    "           jo.put('tenancy_ocid','<tenancy_ocid>');\n",
-    "           jo.put('compartment_ocid','<compartment_ocid>');\n",
-    "           jo.put('private_key','<private_key>');\n",
-    "           jo.put('fingerprint','<fingerprint>');\n",
-    "           dbms_vector_chain.create_credential(\n",
-    "               credential_name   => 'OCI_CRED',\n",
-    "               params            => json(jo.to_string));\n",
-    "       end;\n",
-    "       \"\"\"\n",
-    "    )\n",
-    "    cursor.close()\n",
-    "    print(\"Credentials created.\")\n",
-    "except Exception as ex:\n",
-    "    cursor.close()\n",
-    "    raise"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Load Documents\n",
-    "The users can load the documents from Oracle Database or a file system or both. They just need to set the loader parameters accordingly. Please refer to the Oracle AI Vector Search Guide book for complete information about these parameters.\n",
-    "\n",
-    "The main benefit of using OracleDocLoader is that it can handle 150+ different file formats. You don't need to use different types of loader for different file formats. Here is the list formats that we support: [Oracle Text Supported Document Formats](https://docs.oracle.com/en/database/oracle/oracle-database/23/ccref/oracle-text-supported-document-formats.html)\n",
-    "\n",
-    "The following sample code will show how to do that:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 48,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Number of docs loaded: 3\n"
-     ]
-    }
-   ],
-   "source": [
-    "from langchain_community.document_loaders.oracleai import OracleDocLoader\n",
-    "from langchain_core.documents import Document\n",
-    "\n",
-    "# loading from Oracle Database table\n",
-    "# make sure you have the table with this specification\n",
-    "loader_params = {}\n",
-    "loader_params = {\n",
-    "    \"owner\": \"testuser\",\n",
-    "    \"tablename\": \"demo_tab\",\n",
-    "    \"colname\": \"data\",\n",
-    "}\n",
-    "\n",
-    "\"\"\" load the docs \"\"\"\n",
-    "loader = OracleDocLoader(conn=conn, params=loader_params)\n",
-    "docs = loader.load()\n",
-    "\n",
-    "\"\"\" verify \"\"\"\n",
-    "print(f\"Number of docs loaded: {len(docs)}\")\n",
-    "# print(f\"Document-0: {docs[0].page_content}\") # content"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Generate Summary\n",
-    "Now that the user loaded the documents, they may want to generate a summary for each document. The Oracle AI Vector Search Langchain library provides an API to do that. There are a few summary generation provider options including Database, OCIGENAI, HuggingFace and so on. The users can choose their preferred provider to generate a summary. Like before, they just need to set the summary parameters accordingly. Please refer to the Oracle AI Vector Search Guide book for complete information about these parameters."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "***Note:*** The users may need to set proxy if they want to use some 3rd party summary generation providers other than Oracle's in-house and default provider: 'database'. If you don't have proxy, please remove the proxy parameter when you instantiate the OracleSummary."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 22,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# proxy to be used when we instantiate summary and embedder object\n",
-    "proxy = \"\""
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "The following sample code will show how to generate summary:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 49,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Number of Summaries: 3\n"
-     ]
-    }
-   ],
-   "source": [
-    "from langchain_community.utilities.oracleai import OracleSummary\n",
-    "from langchain_core.documents import Document\n",
-    "\n",
-    "# using 'database' provider\n",
-    "summary_params = {\n",
-    "    \"provider\": \"database\",\n",
-    "    \"glevel\": \"S\",\n",
-    "    \"numParagraphs\": 1,\n",
-    "    \"language\": \"english\",\n",
-    "}\n",
-    "\n",
-    "# get the summary instance\n",
-    "# Remove proxy if not required\n",
-    "summ = OracleSummary(conn=conn, params=summary_params, proxy=proxy)\n",
-    "\n",
-    "list_summary = []\n",
-    "for doc in docs:\n",
-    "    summary = summ.get_summary(doc.page_content)\n",
-    "    list_summary.append(summary)\n",
-    "\n",
-    "\"\"\" verify \"\"\"\n",
-    "print(f\"Number of Summaries: {len(list_summary)}\")\n",
-    "# print(f\"Summary-0: {list_summary[0]}\") #content"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Split Documents\n",
-    "The documents can be in different sizes: small, medium, large, or very large. The users like to split/chunk their documents into smaller pieces to generate embeddings. There are lots of different splitting customizations the users can do. Please refer to the Oracle AI Vector Search Guide book for complete information about these parameters.\n",
-    "\n",
-    "The following sample code will show how to do that:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 50,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Number of Chunks: 3\n"
-     ]
-    }
-   ],
-   "source": [
-    "from langchain_community.document_loaders.oracleai import OracleTextSplitter\n",
-    "from langchain_core.documents import Document\n",
-    "\n",
-    "# split by default parameters\n",
-    "splitter_params = {\"normalize\": \"all\"}\n",
-    "\n",
-    "\"\"\" get the splitter instance \"\"\"\n",
-    "splitter = OracleTextSplitter(conn=conn, params=splitter_params)\n",
-    "\n",
-    "list_chunks = []\n",
-    "for doc in docs:\n",
-    "    chunks = splitter.split_text(doc.page_content)\n",
-    "    list_chunks.extend(chunks)\n",
-    "\n",
-    "\"\"\" verify \"\"\"\n",
-    "print(f\"Number of Chunks: {len(list_chunks)}\")\n",
-    "# print(f\"Chunk-0: {list_chunks[0]}\") # content"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Generate Embeddings\n",
-    "Now that the documents are chunked as per requirements, the users may want to generate embeddings for these chunks. Oracle AI Vector Search provides a number of ways to generate embeddings. The users can load an ONNX embedding model to Oracle Database and use it to generate embeddings or use some 3rd party API's end points to generate embeddings. Please refer to the Oracle AI Vector Search Guide book for complete information about these parameters."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "***Note:*** The users may need to set proxy if they want to use some 3rd party embedding generation providers other than 'database' provider (aka using ONNX model)."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# proxy to be used when we instantiate summary and embedder object\n",
-    "proxy = \"\""
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "The following sample code will show how to generate embeddings:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 51,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Number of embeddings: 3\n"
-     ]
-    }
-   ],
-   "source": [
-    "from langchain_community.embeddings.oracleai import OracleEmbeddings\n",
-    "from langchain_core.documents import Document\n",
-    "\n",
-    "# using ONNX model loaded to Oracle Database\n",
-    "embedder_params = {\"provider\": \"database\", \"model\": \"demo_model\"}\n",
-    "\n",
-    "# get the embedding instance\n",
-    "# Remove proxy if not required\n",
-    "embedder = OracleEmbeddings(conn=conn, params=embedder_params, proxy=proxy)\n",
-    "\n",
-    "embeddings = []\n",
-    "for doc in docs:\n",
-    "    chunks = splitter.split_text(doc.page_content)\n",
-    "    for chunk in chunks:\n",
-    "        embed = embedder.embed_query(chunk)\n",
-    "        embeddings.append(embed)\n",
-    "\n",
-    "\"\"\" verify \"\"\"\n",
-    "print(f\"Number of embeddings: {len(embeddings)}\")\n",
-    "# print(f\"Embedding-0: {embeddings[0]}\") # content"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Create Oracle AI Vector Store\n",
-    "Now that you know how to use Oracle AI Langchain library APIs individually to process the documents, let us show how to integrate with Oracle AI Vector Store to facilitate the semantic searches."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "First, let's import all the dependencies."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 52,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import sys\n",
-    "\n",
-    "import oracledb\n",
-    "from langchain_community.document_loaders.oracleai import (\n",
-    "    OracleDocLoader,\n",
-    "    OracleTextSplitter,\n",
-    ")\n",
-    "from langchain_community.embeddings.oracleai import OracleEmbeddings\n",
-    "from langchain_community.utilities.oracleai import OracleSummary\n",
-    "from langchain_community.vectorstores import oraclevs\n",
-    "from langchain_community.vectorstores.oraclevs import OracleVS\n",
-    "from langchain_community.vectorstores.utils import DistanceStrategy\n",
-    "from langchain_core.documents import Document"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Next, let's combine all document processing stages together. Here is the sample code below:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 53,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Connection successful!\n",
-      "ONNX model loaded.\n",
-      "Number of total chunks with metadata: 3\n"
-     ]
-    }
-   ],
-   "source": [
-    "\"\"\"\n",
-    "In this sample example, we will use 'database' provider for both summary and embeddings.\n",
-    "So, we don't need to do the followings:\n",
-    "    - set proxy for 3rd party providers\n",
-    "    - create credential for 3rd party providers\n",
-    "\n",
-    "If you choose to use 3rd party provider, \n",
-    "please follow the necessary steps for proxy and credential.\n",
-    "\"\"\"\n",
-    "\n",
-    "# oracle connection\n",
-    "# please update with your username, password, hostname, and service_name\n",
-    "username = \"\"\n",
-    "password = \"\"\n",
-    "dsn = \"\"\n",
-    "\n",
-    "try:\n",
-    "    conn = oracledb.connect(user=username, password=password, dsn=dsn)\n",
-    "    print(\"Connection successful!\")\n",
-    "except Exception as e:\n",
-    "    print(\"Connection failed!\")\n",
-    "    sys.exit(1)\n",
-    "\n",
-    "\n",
-    "# load onnx model\n",
-    "# please update with your related information\n",
-    "onnx_dir = \"DEMO_PY_DIR\"\n",
-    "onnx_file = \"tinybert.onnx\"\n",
-    "model_name = \"demo_model\"\n",
-    "try:\n",
-    "    OracleEmbeddings.load_onnx_model(conn, onnx_dir, onnx_file, model_name)\n",
-    "    print(\"ONNX model loaded.\")\n",
-    "except Exception as e:\n",
-    "    print(\"ONNX model loading failed!\")\n",
-    "    sys.exit(1)\n",
-    "\n",
-    "\n",
-    "# params\n",
-    "# please update necessary fields with related information\n",
-    "loader_params = {\n",
-    "    \"owner\": \"testuser\",\n",
-    "    \"tablename\": \"demo_tab\",\n",
-    "    \"colname\": \"data\",\n",
-    "}\n",
-    "summary_params = {\n",
-    "    \"provider\": \"database\",\n",
-    "    \"glevel\": \"S\",\n",
-    "    \"numParagraphs\": 1,\n",
-    "    \"language\": \"english\",\n",
-    "}\n",
-    "splitter_params = {\"normalize\": \"all\"}\n",
-    "embedder_params = {\"provider\": \"database\", \"model\": \"demo_model\"}\n",
-    "\n",
-    "# instantiate loader, summary, splitter, and embedder\n",
-    "loader = OracleDocLoader(conn=conn, params=loader_params)\n",
-    "summary = OracleSummary(conn=conn, params=summary_params)\n",
-    "splitter = OracleTextSplitter(conn=conn, params=splitter_params)\n",
-    "embedder = OracleEmbeddings(conn=conn, params=embedder_params)\n",
-    "\n",
-    "# process the documents\n",
-    "chunks_with_mdata = []\n",
-    "for id, doc in enumerate(docs, start=1):\n",
-    "    summ = summary.get_summary(doc.page_content)\n",
-    "    chunks = splitter.split_text(doc.page_content)\n",
-    "    for ic, chunk in enumerate(chunks, start=1):\n",
-    "        chunk_metadata = doc.metadata.copy()\n",
-    "        chunk_metadata[\"id\"] = chunk_metadata[\"_oid\"] + \"$\" + str(id) + \"$\" + str(ic)\n",
-    "        chunk_metadata[\"document_id\"] = str(id)\n",
-    "        chunk_metadata[\"document_summary\"] = str(summ[0])\n",
-    "        chunks_with_mdata.append(\n",
-    "            Document(page_content=str(chunk), metadata=chunk_metadata)\n",
-    "        )\n",
-    "\n",
-    "\"\"\" verify \"\"\"\n",
-    "print(f\"Number of total chunks with metadata: {len(chunks_with_mdata)}\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "At this point, we have processed the documents and generated chunks with metadata. Next, we will create Oracle AI Vector Store with those chunks.\n",
-    "\n",
-    "Here is the sample code how to do that:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 55,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Vector Store Table: oravs\n"
-     ]
-    }
-   ],
-   "source": [
-    "# create Oracle AI Vector Store\n",
-    "vectorstore = OracleVS.from_documents(\n",
-    "    chunks_with_mdata,\n",
-    "    embedder,\n",
-    "    client=conn,\n",
-    "    table_name=\"oravs\",\n",
-    "    distance_strategy=DistanceStrategy.DOT_PRODUCT,\n",
-    ")\n",
-    "\n",
-    "\"\"\" verify \"\"\"\n",
-    "print(f\"Vector Store Table: {vectorstore.table_name}\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "The above example creates a vector store with DOT_PRODUCT distance strategy. \n",
-    "\n",
-    "However, the users can create Oracle AI Vector Store provides different distance strategies. Please see the [comprehensive guide](/docs/integrations/vectorstores/oracle) for more information."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Now that we have embeddings stored in vector stores, let's create an index on them to get better semantic search performance during query time.\n",
-    "\n",
-    "***Note*** If you are getting some insufficient memory error, please increase ***vector_memory_size*** in your database.\n",
-    "\n",
-    "Here is the sample code to create an index:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 56,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "oraclevs.create_index(\n",
-    "    conn, vectorstore, params={\"idx_name\": \"hnsw_oravs\", \"idx_type\": \"HNSW\"}\n",
-    ")\n",
-    "\n",
-    "print(\"Index created.\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "The above example creates a default HNSW index on the embeddings stored in 'oravs' table. The users can set different parameters as per their requirements. Please refer to the Oracle AI Vector Search Guide book for complete information about these parameters.\n",
-    "\n",
-    "Also, there are different types of vector indices that the users can create. Please see the [comprehensive guide](/docs/integrations/vectorstores/oracle) for more information.\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Perform Semantic Search\n",
-    "All set!\n",
-    "\n",
-    "We have processed the documents, stored them to vector store, and then created index to get better query performance. Now let's do some semantic searches.\n",
-    "\n",
-    "Here is the sample code for this:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 58,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "[Document(page_content='The database stores LOBs differently from other data types. Creating a LOB column implicitly creates a LOB segment and a LOB index. The tablespace containing the LOB segment and LOB index, which are always stored together, may be different from the tablespace containing the table. Sometimes the database can store small amounts of LOB data in the table itself rather than in a separate LOB segment.', metadata={'_oid': '662f2f257677f3c2311a8ff999fd34e5', '_rowid': 'AAAR/xAAEAAAAAnAAC', 'id': '662f2f257677f3c2311a8ff999fd34e5$3$1', 'document_id': '3', 'document_summary': 'Sometimes the database can store small amounts of LOB data in the table itself rather than in a separate LOB segment.\\n\\n'})]\n",
-      "[]\n",
-      "[(Document(page_content='The database stores LOBs differently from other data types. Creating a LOB column implicitly creates a LOB segment and a LOB index. The tablespace containing the LOB segment and LOB index, which are always stored together, may be different from the tablespace containing the table. Sometimes the database can store small amounts of LOB data in the table itself rather than in a separate LOB segment.', metadata={'_oid': '662f2f257677f3c2311a8ff999fd34e5', '_rowid': 'AAAR/xAAEAAAAAnAAC', 'id': '662f2f257677f3c2311a8ff999fd34e5$3$1', 'document_id': '3', 'document_summary': 'Sometimes the database can store small amounts of LOB data in the table itself rather than in a separate LOB segment.\\n\\n'}), 0.055675752460956573)]\n",
-      "[]\n",
-      "[Document(page_content='If the answer to any preceding questions is yes, then the database stops the search and allocates space from the specified tablespace; otherwise, space is allocated from the database default shared temporary tablespace.', metadata={'_oid': '662f2f253acf96b33b430b88699490a2', '_rowid': 'AAAR/xAAEAAAAAnAAA', 'id': '662f2f253acf96b33b430b88699490a2$1$1', 'document_id': '1', 'document_summary': 'If the answer to any preceding questions is yes, then the database stops the search and allocates space from the specified tablespace; otherwise, space is allocated from the database default shared temporary tablespace.\\n\\n'})]\n",
-      "[Document(page_content='If the answer to any preceding questions is yes, then the database stops the search and allocates space from the specified tablespace; otherwise, space is allocated from the database default shared temporary tablespace.', metadata={'_oid': '662f2f253acf96b33b430b88699490a2', '_rowid': 'AAAR/xAAEAAAAAnAAA', 'id': '662f2f253acf96b33b430b88699490a2$1$1', 'document_id': '1', 'document_summary': 'If the answer to any preceding questions is yes, then the database stops the search and allocates space from the specified tablespace; otherwise, space is allocated from the database default shared temporary tablespace.\\n\\n'})]\n"
-     ]
-    }
-   ],
-   "source": [
-    "query = \"What is Oracle AI Vector Store?\"\n",
-    "filter = {\"document_id\": [\"1\"]}\n",
-    "\n",
-    "# Similarity search without a filter\n",
-    "print(vectorstore.similarity_search(query, 1))\n",
-    "\n",
-    "# Similarity search with a filter\n",
-    "print(vectorstore.similarity_search(query, 1, filter=filter))\n",
-    "\n",
-    "# Similarity search with relevance score\n",
-    "print(vectorstore.similarity_search_with_score(query, 1))\n",
-    "\n",
-    "# Similarity search with relevance score with filter\n",
-    "print(vectorstore.similarity_search_with_score(query, 1, filter=filter))\n",
-    "\n",
-    "# Max marginal relevance search\n",
-    "print(vectorstore.max_marginal_relevance_search(query, 1, fetch_k=20, lambda_mult=0.5))\n",
-    "\n",
-    "# Max marginal relevance search with filter\n",
-    "print(\n",
-    "    vectorstore.max_marginal_relevance_search(\n",
-    "        query, 1, fetch_k=20, lambda_mult=0.5, filter=filter\n",
-    "    )\n",
-    ")"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.9"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 4
-}

cookbook/petting_zoo.ipynb

@@ -129,7 +129,7 @@
     "        return obs_message\n",
     "\n",
     "    def _act(self):\n",
-    "        act_message = self.model.invoke(self.message_history)\n",
+    "        act_message = self.model(self.message_history)\n",
     "        self.message_history.append(act_message)\n",
     "        action = int(self.action_parser.parse(act_message.content)[\"action\"])\n",
     "        return action\n",

cookbook/rag_semantic_chunking_azureaidocintelligence.ipynb

@@ -168,7 +168,7 @@
     "\n",
     "retriever = vector_store.as_retriever(search_type=\"similarity\", search_kwargs={\"k\": 3})\n",
     "\n",
-    "retrieved_docs = retriever.invoke(\"<your question>\")\n",
+    "retrieved_docs = retriever.get_relevant_documents(\"<your question>\")\n",
     "\n",
     "print(retrieved_docs[0].page_content)\n",
     "\n",

cookbook/rag_upstage_layout_analysis_groundedness_check.ipynb

@@ -1,80 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# RAG using Upstage Layout Analysis and Groundedness Check\n",
-    "This example illustrates RAG using [Upstage](https://python.langchain.com/docs/integrations/providers/upstage/) Layout Analysis and Groundedness Check."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from typing import List\n",
-    "\n",
-    "from langchain_community.vectorstores import DocArrayInMemorySearch\n",
-    "from langchain_core.output_parsers import StrOutputParser\n",
-    "from langchain_core.prompts import ChatPromptTemplate\n",
-    "from langchain_core.runnables import RunnablePassthrough\n",
-    "from langchain_core.runnables.base import RunnableSerializable\n",
-    "from langchain_upstage import (\n",
-    "    ChatUpstage,\n",
-    "    UpstageEmbeddings,\n",
-    "    UpstageGroundednessCheck,\n",
-    "    UpstageLayoutAnalysisLoader,\n",
-    ")\n",
-    "\n",
-    "model = ChatUpstage()\n",
-    "\n",
-    "files = [\"/PATH/TO/YOUR/FILE.pdf\", \"/PATH/TO/YOUR/FILE2.pdf\"]\n",
-    "\n",
-    "loader = UpstageLayoutAnalysisLoader(file_path=files, split=\"element\")\n",
-    "\n",
-    "docs = loader.load()\n",
-    "\n",
-    "vectorstore = DocArrayInMemorySearch.from_documents(docs, embedding=UpstageEmbeddings())\n",
-    "retriever = vectorstore.as_retriever()\n",
-    "\n",
-    "template = \"\"\"Answer the question based only on the following context:\n",
-    "{context}\n",
-    "\n",
-    "Question: {question}\n",
-    "\"\"\"\n",
-    "prompt = ChatPromptTemplate.from_template(template)\n",
-    "output_parser = StrOutputParser()\n",
-    "\n",
-    "retrieved_docs = retriever.get_relevant_documents(\"How many parameters in SOLAR model?\")\n",
-    "\n",
-    "groundedness_check = UpstageGroundednessCheck()\n",
-    "groundedness = \"\"\n",
-    "while groundedness != \"grounded\":\n",
-    "    chain: RunnableSerializable = RunnablePassthrough() | prompt | model | output_parser\n",
-    "\n",
-    "    result = chain.invoke(\n",
-    "        {\n",
-    "            \"context\": retrieved_docs,\n",
-    "            \"question\": \"How many parameters in SOLAR model?\",\n",
-    "        }\n",
-    "    )\n",
-    "\n",
-    "    groundedness = groundedness_check.invoke(\n",
-    "        {\n",
-    "            \"context\": retrieved_docs,\n",
-    "            \"answer\": result,\n",
-    "        }\n",
-    "    )"
-   ]
-  }
- ],
- "metadata": {
-  "language_info": {
-   "name": "python"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}

cookbook/self_query_hotel_search.ipynb

@@ -355,15 +355,15 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "attribute_info[-2][\"description\"] += (\n",
-    "    f\". Valid values are {sorted(latest_price['starrating'].value_counts().index.tolist())}\"\n",
-    ")\n",
-    "attribute_info[3][\"description\"] += (\n",
-    "    f\". Valid values are {sorted(latest_price['maxoccupancy'].value_counts().index.tolist())}\"\n",
-    ")\n",
-    "attribute_info[-3][\"description\"] += (\n",
-    "    f\". Valid values are {sorted(latest_price['country'].value_counts().index.tolist())}\"\n",
-    ")"
+    "attribute_info[-2][\n",
+    "    \"description\"\n",
+    "] += f\". Valid values are {sorted(latest_price['starrating'].value_counts().index.tolist())}\"\n",
+    "attribute_info[3][\n",
+    "    \"description\"\n",
+    "] += f\". Valid values are {sorted(latest_price['maxoccupancy'].value_counts().index.tolist())}\"\n",
+    "attribute_info[-3][\n",
+    "    \"description\"\n",
+    "] += f\". Valid values are {sorted(latest_price['country'].value_counts().index.tolist())}\""
    ]
   },
   {
@@ -688,9 +688,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "attribute_info[-3][\"description\"] += (\n",
-    "    \". NOTE: Only use the 'eq' operator if a specific country is mentioned. If a region is mentioned, include all relevant countries in filter.\"\n",
-    ")\n",
+    "attribute_info[-3][\n",
+    "    \"description\"\n",
+    "] += \". NOTE: Only use the 'eq' operator if a specific country is mentioned. If a region is mentioned, include all relevant countries in filter.\"\n",
     "chain = load_query_constructor_runnable(\n",
     "    ChatOpenAI(model=\"gpt-3.5-turbo\", temperature=0),\n",
     "    doc_contents,\n",
@@ -1227,7 +1227,7 @@
     }
    ],
    "source": [
-    "results = retriever.invoke(\n",
+    "results = retriever.get_relevant_documents(\n",
     "    \"I want to stay somewhere highly rated along the coast. I want a room with a patio and a fireplace.\"\n",
     ")\n",
     "for res in results:\n",

cookbook/sharedmemory_for_tools.ipynb

@@ -22,8 +22,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain import hub\n",
-    "from langchain.agents import AgentExecutor, Tool, ZeroShotAgent, create_react_agent\n",
+    "from langchain.agents import AgentExecutor, Tool, ZeroShotAgent\n",
     "from langchain.chains import LLMChain\n",
     "from langchain.memory import ConversationBufferMemory, ReadOnlySharedMemory\n",
     "from langchain.prompts import PromptTemplate\n",
@@ -85,7 +84,19 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "prompt = hub.pull(\"hwchase17/react\")"
+    "prefix = \"\"\"Have a conversation with a human, answering the following questions as best you can. You have access to the following tools:\"\"\"\n",
+    "suffix = \"\"\"Begin!\"\n",
+    "\n",
+    "{chat_history}\n",
+    "Question: {input}\n",
+    "{agent_scratchpad}\"\"\"\n",
+    "\n",
+    "prompt = ZeroShotAgent.create_prompt(\n",
+    "    tools,\n",
+    "    prefix=prefix,\n",
+    "    suffix=suffix,\n",
+    "    input_variables=[\"input\", \"chat_history\", \"agent_scratchpad\"],\n",
+    ")"
    ]
   },
   {
@@ -103,14 +114,16 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "model = OpenAI()\n",
-    "agent = create_react_agent(model, tools, prompt)\n",
-    "agent_executor = AgentExecutor(agent=agent, tools=tools, memory=memory)"
+    "llm_chain = LLMChain(llm=OpenAI(temperature=0), prompt=prompt)\n",
+    "agent = ZeroShotAgent(llm_chain=llm_chain, tools=tools, verbose=True)\n",
+    "agent_chain = AgentExecutor.from_agent_and_tools(\n",
+    "    agent=agent, tools=tools, verbose=True, memory=memory\n",
+    ")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 36,
+   "execution_count": 6,
    "id": "ca4bc1fb",
    "metadata": {},
    "outputs": [
@@ -120,15 +133,15 @@
      "text": [
       "\n",
       "\n",
-      "\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
-      "\u001B[32;1m\u001B[1;3mThought: I should research ChatGPT to answer this question.\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3mThought: I should research ChatGPT to answer this question.\n",
       "Action: Search\n",
-      "Action Input: \"ChatGPT\"\u001B[0m\n",
-      "Observation: \u001B[36;1m\u001B[1;3mNov 30, 2022 ... We've trained a model called ChatGPT which interacts in a conversational way. The dialogue format makes it possible for ChatGPT to answer ... ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large ... ChatGPT. We've trained a model called ChatGPT which interacts in a conversational way. The dialogue format makes it possible for ChatGPT to answer ... Feb 2, 2023 ... ChatGPT, the popular chatbot from OpenAI, is estimated to have reached 100 million monthly active users in January, just two months after ... 2 days ago ... ChatGPT recently launched a new version of its own plagiarism detection tool, with hopes that it will squelch some of the criticism around how ... An API for accessing new AI models developed by OpenAI. Feb 19, 2023 ... ChatGPT is an AI chatbot system that OpenAI released in November to show off and test what a very large, powerful AI system can accomplish. You ... ChatGPT is fine-tuned from GPT-3.5, a language model trained to produce text. ChatGPT was optimized for dialogue by using Reinforcement Learning with Human ... 3 days ago ... Visual ChatGPT connects ChatGPT and a series of Visual Foundation Models to enable sending and receiving images during chatting. Dec 1, 2022 ... ChatGPT is a natural language processing tool driven by AI technology that allows you to have human-like conversations and much more with a ...\u001B[0m\n",
-      "Thought:\u001B[32;1m\u001B[1;3m I now know the final answer.\n",
-      "Final Answer: ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large language models and is optimized for dialogue by using Reinforcement Learning with Human-in-the-Loop. It is also capable of sending and receiving images during chatting.\u001B[0m\n",
+      "Action Input: \"ChatGPT\"\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3mNov 30, 2022 ... We've trained a model called ChatGPT which interacts in a conversational way. The dialogue format makes it possible for ChatGPT to answer ... ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large ... ChatGPT. We've trained a model called ChatGPT which interacts in a conversational way. The dialogue format makes it possible for ChatGPT to answer ... Feb 2, 2023 ... ChatGPT, the popular chatbot from OpenAI, is estimated to have reached 100 million monthly active users in January, just two months after ... 2 days ago ... ChatGPT recently launched a new version of its own plagiarism detection tool, with hopes that it will squelch some of the criticism around how ... An API for accessing new AI models developed by OpenAI. Feb 19, 2023 ... ChatGPT is an AI chatbot system that OpenAI released in November to show off and test what a very large, powerful AI system can accomplish. You ... ChatGPT is fine-tuned from GPT-3.5, a language model trained to produce text. ChatGPT was optimized for dialogue by using Reinforcement Learning with Human ... 3 days ago ... Visual ChatGPT connects ChatGPT and a series of Visual Foundation Models to enable sending and receiving images during chatting. Dec 1, 2022 ... ChatGPT is a natural language processing tool driven by AI technology that allows you to have human-like conversations and much more with a ...\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
+      "Final Answer: ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large language models and is optimized for dialogue by using Reinforcement Learning with Human-in-the-Loop. It is also capable of sending and receiving images during chatting.\u001b[0m\n",
       "\n",
-      "\u001B[1m> Finished chain.\u001B[0m\n"
+      "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
     },
     {
@@ -140,40 +153,10 @@
      "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
-    },
-    {
-     "ename": "KeyboardInterrupt",
-     "evalue": "",
-     "output_type": "error",
-     "traceback": [
-      "\u001B[0;31m---------------------------------------------------------------------------\u001B[0m",
-      "\u001B[0;31mKeyboardInterrupt\u001B[0m                         Traceback (most recent call last)",
-      "Cell \u001B[0;32mIn[36], line 1\u001B[0m\n\u001B[0;32m----> 1\u001B[0m \u001B[43magent_executor\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43minvoke\u001B[49m\u001B[43m(\u001B[49m\u001B[43m{\u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43minput\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m:\u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43mWhat is ChatGPT?\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m}\u001B[49m\u001B[43m)\u001B[49m\n",
-      "File \u001B[0;32m~/code/langchain/libs/langchain/langchain/chains/base.py:163\u001B[0m, in \u001B[0;36mChain.invoke\u001B[0;34m(self, input, config, **kwargs)\u001B[0m\n\u001B[1;32m    161\u001B[0m \u001B[38;5;28;01mexcept\u001B[39;00m \u001B[38;5;167;01mBaseException\u001B[39;00m \u001B[38;5;28;01mas\u001B[39;00m e:\n\u001B[1;32m    162\u001B[0m     run_manager\u001B[38;5;241m.\u001B[39mon_chain_error(e)\n\u001B[0;32m--> 163\u001B[0m     \u001B[38;5;28;01mraise\u001B[39;00m e\n\u001B[1;32m    164\u001B[0m run_manager\u001B[38;5;241m.\u001B[39mon_chain_end(outputs)\n\u001B[1;32m    166\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m include_run_info:\n",
-      "File \u001B[0;32m~/code/langchain/libs/langchain/langchain/chains/base.py:153\u001B[0m, in \u001B[0;36mChain.invoke\u001B[0;34m(self, input, config, **kwargs)\u001B[0m\n\u001B[1;32m    150\u001B[0m \u001B[38;5;28;01mtry\u001B[39;00m:\n\u001B[1;32m    151\u001B[0m     \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_validate_inputs(inputs)\n\u001B[1;32m    152\u001B[0m     outputs \u001B[38;5;241m=\u001B[39m (\n\u001B[0;32m--> 153\u001B[0m         \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_call\u001B[49m\u001B[43m(\u001B[49m\u001B[43minputs\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mrun_manager\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mrun_manager\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m    154\u001B[0m         \u001B[38;5;28;01mif\u001B[39;00m new_arg_supported\n\u001B[1;32m    155\u001B[0m         \u001B[38;5;28;01melse\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_call(inputs)\n\u001B[1;32m    156\u001B[0m     )\n\u001B[1;32m    158\u001B[0m     final_outputs: Dict[\u001B[38;5;28mstr\u001B[39m, Any] \u001B[38;5;241m=\u001B[39m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mprep_outputs(\n\u001B[1;32m    159\u001B[0m         inputs, outputs, return_only_outputs\n\u001B[1;32m    160\u001B[0m     )\n\u001B[1;32m    161\u001B[0m \u001B[38;5;28;01mexcept\u001B[39;00m \u001B[38;5;167;01mBaseException\u001B[39;00m \u001B[38;5;28;01mas\u001B[39;00m e:\n",
-      "File \u001B[0;32m~/code/langchain/libs/langchain/langchain/agents/agent.py:1432\u001B[0m, in \u001B[0;36mAgentExecutor._call\u001B[0;34m(self, inputs, run_manager)\u001B[0m\n\u001B[1;32m   1430\u001B[0m \u001B[38;5;66;03m# We now enter the agent loop (until it returns something).\u001B[39;00m\n\u001B[1;32m   1431\u001B[0m \u001B[38;5;28;01mwhile\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_should_continue(iterations, time_elapsed):\n\u001B[0;32m-> 1432\u001B[0m     next_step_output \u001B[38;5;241m=\u001B[39m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_take_next_step\u001B[49m\u001B[43m(\u001B[49m\n\u001B[1;32m   1433\u001B[0m \u001B[43m        \u001B[49m\u001B[43mname_to_tool_map\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1434\u001B[0m \u001B[43m        \u001B[49m\u001B[43mcolor_mapping\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1435\u001B[0m \u001B[43m        \u001B[49m\u001B[43minputs\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1436\u001B[0m \u001B[43m        \u001B[49m\u001B[43mintermediate_steps\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1437\u001B[0m \u001B[43m        \u001B[49m\u001B[43mrun_manager\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mrun_manager\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1438\u001B[0m \u001B[43m    \u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m   1439\u001B[0m     \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;28misinstance\u001B[39m(next_step_output, AgentFinish):\n\u001B[1;32m   1440\u001B[0m         \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_return(\n\u001B[1;32m   1441\u001B[0m             next_step_output, intermediate_steps, run_manager\u001B[38;5;241m=\u001B[39mrun_manager\n\u001B[1;32m   1442\u001B[0m         )\n",
-      "File \u001B[0;32m~/code/langchain/libs/langchain/langchain/agents/agent.py:1138\u001B[0m, in \u001B[0;36mAgentExecutor._take_next_step\u001B[0;34m(self, name_to_tool_map, color_mapping, inputs, intermediate_steps, run_manager)\u001B[0m\n\u001B[1;32m   1129\u001B[0m \u001B[38;5;28;01mdef\u001B[39;00m \u001B[38;5;21m_take_next_step\u001B[39m(\n\u001B[1;32m   1130\u001B[0m     \u001B[38;5;28mself\u001B[39m,\n\u001B[1;32m   1131\u001B[0m     name_to_tool_map: Dict[\u001B[38;5;28mstr\u001B[39m, BaseTool],\n\u001B[0;32m   (...)\u001B[0m\n\u001B[1;32m   1135\u001B[0m     run_manager: Optional[CallbackManagerForChainRun] \u001B[38;5;241m=\u001B[39m \u001B[38;5;28;01mNone\u001B[39;00m,\n\u001B[1;32m   1136\u001B[0m ) \u001B[38;5;241m-\u001B[39m\u001B[38;5;241m>\u001B[39m Union[AgentFinish, List[Tuple[AgentAction, \u001B[38;5;28mstr\u001B[39m]]]:\n\u001B[1;32m   1137\u001B[0m     \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_consume_next_step(\n\u001B[0;32m-> 1138\u001B[0m         [\n\u001B[1;32m   1139\u001B[0m             a\n\u001B[1;32m   1140\u001B[0m             \u001B[38;5;28;01mfor\u001B[39;00m a \u001B[38;5;129;01min\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_iter_next_step(\n\u001B[1;32m   1141\u001B[0m                 name_to_tool_map,\n\u001B[1;32m   1142\u001B[0m                 color_mapping,\n\u001B[1;32m   1143\u001B[0m                 inputs,\n\u001B[1;32m   1144\u001B[0m                 intermediate_steps,\n\u001B[1;32m   1145\u001B[0m                 run_manager,\n\u001B[1;32m   1146\u001B[0m             )\n\u001B[1;32m   1147\u001B[0m         ]\n\u001B[1;32m   1148\u001B[0m     )\n",
-      "File \u001B[0;32m~/code/langchain/libs/langchain/langchain/agents/agent.py:1138\u001B[0m, in \u001B[0;36m<listcomp>\u001B[0;34m(.0)\u001B[0m\n\u001B[1;32m   1129\u001B[0m \u001B[38;5;28;01mdef\u001B[39;00m \u001B[38;5;21m_take_next_step\u001B[39m(\n\u001B[1;32m   1130\u001B[0m     \u001B[38;5;28mself\u001B[39m,\n\u001B[1;32m   1131\u001B[0m     name_to_tool_map: Dict[\u001B[38;5;28mstr\u001B[39m, BaseTool],\n\u001B[0;32m   (...)\u001B[0m\n\u001B[1;32m   1135\u001B[0m     run_manager: Optional[CallbackManagerForChainRun] \u001B[38;5;241m=\u001B[39m \u001B[38;5;28;01mNone\u001B[39;00m,\n\u001B[1;32m   1136\u001B[0m ) \u001B[38;5;241m-\u001B[39m\u001B[38;5;241m>\u001B[39m Union[AgentFinish, List[Tuple[AgentAction, \u001B[38;5;28mstr\u001B[39m]]]:\n\u001B[1;32m   1137\u001B[0m     \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_consume_next_step(\n\u001B[0;32m-> 1138\u001B[0m         [\n\u001B[1;32m   1139\u001B[0m             a\n\u001B[1;32m   1140\u001B[0m             \u001B[38;5;28;01mfor\u001B[39;00m a \u001B[38;5;129;01min\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_iter_next_step(\n\u001B[1;32m   1141\u001B[0m                 name_to_tool_map,\n\u001B[1;32m   1142\u001B[0m                 color_mapping,\n\u001B[1;32m   1143\u001B[0m                 inputs,\n\u001B[1;32m   1144\u001B[0m                 intermediate_steps,\n\u001B[1;32m   1145\u001B[0m                 run_manager,\n\u001B[1;32m   1146\u001B[0m             )\n\u001B[1;32m   1147\u001B[0m         ]\n\u001B[1;32m   1148\u001B[0m     )\n",
-      "File \u001B[0;32m~/code/langchain/libs/langchain/langchain/agents/agent.py:1223\u001B[0m, in \u001B[0;36mAgentExecutor._iter_next_step\u001B[0;34m(self, name_to_tool_map, color_mapping, inputs, intermediate_steps, run_manager)\u001B[0m\n\u001B[1;32m   1221\u001B[0m     \u001B[38;5;28;01myield\u001B[39;00m agent_action\n\u001B[1;32m   1222\u001B[0m \u001B[38;5;28;01mfor\u001B[39;00m agent_action \u001B[38;5;129;01min\u001B[39;00m actions:\n\u001B[0;32m-> 1223\u001B[0m     \u001B[38;5;28;01myield\u001B[39;00m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_perform_agent_action\u001B[49m\u001B[43m(\u001B[49m\n\u001B[1;32m   1224\u001B[0m \u001B[43m        \u001B[49m\u001B[43mname_to_tool_map\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mcolor_mapping\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43magent_action\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mrun_manager\u001B[49m\n\u001B[1;32m   1225\u001B[0m \u001B[43m    \u001B[49m\u001B[43m)\u001B[49m\n",
-      "File \u001B[0;32m~/code/langchain/libs/langchain/langchain/agents/agent.py:1245\u001B[0m, in \u001B[0;36mAgentExecutor._perform_agent_action\u001B[0;34m(self, name_to_tool_map, color_mapping, agent_action, run_manager)\u001B[0m\n\u001B[1;32m   1243\u001B[0m         tool_run_kwargs[\u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mllm_prefix\u001B[39m\u001B[38;5;124m\"\u001B[39m] \u001B[38;5;241m=\u001B[39m \u001B[38;5;124m\"\u001B[39m\u001B[38;5;124m\"\u001B[39m\n\u001B[1;32m   1244\u001B[0m     \u001B[38;5;66;03m# We then call the tool on the tool input to get an observation\u001B[39;00m\n\u001B[0;32m-> 1245\u001B[0m     observation \u001B[38;5;241m=\u001B[39m \u001B[43mtool\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mrun\u001B[49m\u001B[43m(\u001B[49m\n\u001B[1;32m   1246\u001B[0m \u001B[43m        \u001B[49m\u001B[43magent_action\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mtool_input\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1247\u001B[0m \u001B[43m        \u001B[49m\u001B[43mverbose\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mverbose\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1248\u001B[0m \u001B[43m        \u001B[49m\u001B[43mcolor\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mcolor\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1249\u001B[0m \u001B[43m        \u001B[49m\u001B[43mcallbacks\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mrun_manager\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mget_child\u001B[49m\u001B[43m(\u001B[49m\u001B[43m)\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;28;43;01mif\u001B[39;49;00m\u001B[43m \u001B[49m\u001B[43mrun_manager\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;28;43;01melse\u001B[39;49;00m\u001B[43m \u001B[49m\u001B[38;5;28;43;01mNone\u001B[39;49;00m\u001B[43m,\u001B[49m\n\u001B[1;32m   1250\u001B[0m \u001B[43m        \u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43mtool_run_kwargs\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1251\u001B[0m \u001B[43m    \u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m   1252\u001B[0m \u001B[38;5;28;01melse\u001B[39;00m:\n\u001B[1;32m   1253\u001B[0m     tool_run_kwargs \u001B[38;5;241m=\u001B[39m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39magent\u001B[38;5;241m.\u001B[39mtool_run_logging_kwargs()\n",
-      "File \u001B[0;32m~/code/langchain/libs/core/langchain_core/tools.py:422\u001B[0m, in \u001B[0;36mBaseTool.run\u001B[0;34m(self, tool_input, verbose, start_color, color, callbacks, tags, metadata, run_name, run_id, **kwargs)\u001B[0m\n\u001B[1;32m    420\u001B[0m \u001B[38;5;28;01mexcept\u001B[39;00m (\u001B[38;5;167;01mException\u001B[39;00m, \u001B[38;5;167;01mKeyboardInterrupt\u001B[39;00m) \u001B[38;5;28;01mas\u001B[39;00m e:\n\u001B[1;32m    421\u001B[0m     run_manager\u001B[38;5;241m.\u001B[39mon_tool_error(e)\n\u001B[0;32m--> 422\u001B[0m     \u001B[38;5;28;01mraise\u001B[39;00m e\n\u001B[1;32m    423\u001B[0m \u001B[38;5;28;01melse\u001B[39;00m:\n\u001B[1;32m    424\u001B[0m     run_manager\u001B[38;5;241m.\u001B[39mon_tool_end(observation, color\u001B[38;5;241m=\u001B[39mcolor, name\u001B[38;5;241m=\u001B[39m\u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mname, \u001B[38;5;241m*\u001B[39m\u001B[38;5;241m*\u001B[39mkwargs)\n",
-      "File \u001B[0;32m~/code/langchain/libs/core/langchain_core/tools.py:381\u001B[0m, in \u001B[0;36mBaseTool.run\u001B[0;34m(self, tool_input, verbose, start_color, color, callbacks, tags, metadata, run_name, run_id, **kwargs)\u001B[0m\n\u001B[1;32m    378\u001B[0m     parsed_input \u001B[38;5;241m=\u001B[39m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_parse_input(tool_input)\n\u001B[1;32m    379\u001B[0m     tool_args, tool_kwargs \u001B[38;5;241m=\u001B[39m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_to_args_and_kwargs(parsed_input)\n\u001B[1;32m    380\u001B[0m     observation \u001B[38;5;241m=\u001B[39m (\n\u001B[0;32m--> 381\u001B[0m         \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_run\u001B[49m\u001B[43m(\u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43mtool_args\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mrun_manager\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mrun_manager\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43mtool_kwargs\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m    382\u001B[0m         \u001B[38;5;28;01mif\u001B[39;00m new_arg_supported\n\u001B[1;32m    383\u001B[0m         \u001B[38;5;28;01melse\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_run(\u001B[38;5;241m*\u001B[39mtool_args, \u001B[38;5;241m*\u001B[39m\u001B[38;5;241m*\u001B[39mtool_kwargs)\n\u001B[1;32m    384\u001B[0m     )\n\u001B[1;32m    385\u001B[0m \u001B[38;5;28;01mexcept\u001B[39;00m ValidationError \u001B[38;5;28;01mas\u001B[39;00m e:\n\u001B[1;32m    386\u001B[0m     \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;129;01mnot\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mhandle_validation_error:\n",
-      "File \u001B[0;32m~/code/langchain/libs/core/langchain_core/tools.py:588\u001B[0m, in \u001B[0;36mTool._run\u001B[0;34m(self, run_manager, *args, **kwargs)\u001B[0m\n\u001B[1;32m    579\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mfunc:\n\u001B[1;32m    580\u001B[0m     new_argument_supported \u001B[38;5;241m=\u001B[39m signature(\u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mfunc)\u001B[38;5;241m.\u001B[39mparameters\u001B[38;5;241m.\u001B[39mget(\u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mcallbacks\u001B[39m\u001B[38;5;124m\"\u001B[39m)\n\u001B[1;32m    581\u001B[0m     \u001B[38;5;28;01mreturn\u001B[39;00m (\n\u001B[1;32m    582\u001B[0m         \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mfunc(\n\u001B[1;32m    583\u001B[0m             \u001B[38;5;241m*\u001B[39margs,\n\u001B[1;32m    584\u001B[0m             callbacks\u001B[38;5;241m=\u001B[39mrun_manager\u001B[38;5;241m.\u001B[39mget_child() \u001B[38;5;28;01mif\u001B[39;00m run_manager \u001B[38;5;28;01melse\u001B[39;00m \u001B[38;5;28;01mNone\u001B[39;00m,\n\u001B[1;32m    585\u001B[0m             \u001B[38;5;241m*\u001B[39m\u001B[38;5;241m*\u001B[39mkwargs,\n\u001B[1;32m    586\u001B[0m         )\n\u001B[1;32m    587\u001B[0m         \u001B[38;5;28;01mif\u001B[39;00m new_argument_supported\n\u001B[0;32m--> 588\u001B[0m         \u001B[38;5;28;01melse\u001B[39;00m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mfunc\u001B[49m\u001B[43m(\u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43margs\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43mkwargs\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m    589\u001B[0m     )\n\u001B[1;32m    590\u001B[0m \u001B[38;5;28;01mraise\u001B[39;00m \u001B[38;5;167;01mNotImplementedError\u001B[39;00m(\u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mTool does not support sync\u001B[39m\u001B[38;5;124m\"\u001B[39m)\n",
-      "File \u001B[0;32m~/code/langchain/libs/community/langchain_community/utilities/google_search.py:94\u001B[0m, in \u001B[0;36mGoogleSearchAPIWrapper.run\u001B[0;34m(self, query)\u001B[0m\n\u001B[1;32m     92\u001B[0m \u001B[38;5;250m\u001B[39m\u001B[38;5;124;03m\"\"\"Run query through GoogleSearch and parse result.\"\"\"\u001B[39;00m\n\u001B[1;32m     93\u001B[0m snippets \u001B[38;5;241m=\u001B[39m []\n\u001B[0;32m---> 94\u001B[0m results \u001B[38;5;241m=\u001B[39m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_google_search_results\u001B[49m\u001B[43m(\u001B[49m\u001B[43mquery\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mnum\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mk\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m     95\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;28mlen\u001B[39m(results) \u001B[38;5;241m==\u001B[39m \u001B[38;5;241m0\u001B[39m:\n\u001B[1;32m     96\u001B[0m     \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mNo good Google Search Result was found\u001B[39m\u001B[38;5;124m\"\u001B[39m\n",
-      "File \u001B[0;32m~/code/langchain/libs/community/langchain_community/utilities/google_search.py:62\u001B[0m, in \u001B[0;36mGoogleSearchAPIWrapper._google_search_results\u001B[0;34m(self, search_term, **kwargs)\u001B[0m\n\u001B[1;32m     60\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39msiterestrict:\n\u001B[1;32m     61\u001B[0m     cse \u001B[38;5;241m=\u001B[39m cse\u001B[38;5;241m.\u001B[39msiterestrict()\n\u001B[0;32m---> 62\u001B[0m res \u001B[38;5;241m=\u001B[39m \u001B[43mcse\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mlist\u001B[49m\u001B[43m(\u001B[49m\u001B[43mq\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43msearch_term\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mcx\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mgoogle_cse_id\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43mkwargs\u001B[49m\u001B[43m)\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mexecute\u001B[49m\u001B[43m(\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m     63\u001B[0m \u001B[38;5;28;01mreturn\u001B[39;00m res\u001B[38;5;241m.\u001B[39mget(\u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mitems\u001B[39m\u001B[38;5;124m\"\u001B[39m, [])\n",
-      "File \u001B[0;32m~/code/langchain/.venv/lib/python3.10/site-packages/googleapiclient/_helpers.py:130\u001B[0m, in \u001B[0;36mpositional.<locals>.positional_decorator.<locals>.positional_wrapper\u001B[0;34m(*args, **kwargs)\u001B[0m\n\u001B[1;32m    128\u001B[0m     \u001B[38;5;28;01melif\u001B[39;00m positional_parameters_enforcement \u001B[38;5;241m==\u001B[39m POSITIONAL_WARNING:\n\u001B[1;32m    129\u001B[0m         logger\u001B[38;5;241m.\u001B[39mwarning(message)\n\u001B[0;32m--> 130\u001B[0m \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[43mwrapped\u001B[49m\u001B[43m(\u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43margs\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43mkwargs\u001B[49m\u001B[43m)\u001B[49m\n",
-      "File \u001B[0;32m~/code/langchain/.venv/lib/python3.10/site-packages/googleapiclient/http.py:923\u001B[0m, in \u001B[0;36mHttpRequest.execute\u001B[0;34m(self, http, num_retries)\u001B[0m\n\u001B[1;32m    920\u001B[0m     \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mheaders[\u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mcontent-length\u001B[39m\u001B[38;5;124m\"\u001B[39m] \u001B[38;5;241m=\u001B[39m \u001B[38;5;28mstr\u001B[39m(\u001B[38;5;28mlen\u001B[39m(\u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mbody))\n\u001B[1;32m    922\u001B[0m \u001B[38;5;66;03m# Handle retries for server-side errors.\u001B[39;00m\n\u001B[0;32m--> 923\u001B[0m resp, content \u001B[38;5;241m=\u001B[39m \u001B[43m_retry_request\u001B[49m\u001B[43m(\u001B[49m\n\u001B[1;32m    924\u001B[0m \u001B[43m    \u001B[49m\u001B[43mhttp\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    925\u001B[0m \u001B[43m    \u001B[49m\u001B[43mnum_retries\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    926\u001B[0m \u001B[43m    \u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43mrequest\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m,\u001B[49m\n\u001B[1;32m    927\u001B[0m \u001B[43m    \u001B[49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_sleep\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    928\u001B[0m \u001B[43m    \u001B[49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_rand\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    929\u001B[0m \u001B[43m    \u001B[49m\u001B[38;5;28;43mstr\u001B[39;49m\u001B[43m(\u001B[49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43muri\u001B[49m\u001B[43m)\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    930\u001B[0m \u001B[43m    \u001B[49m\u001B[43mmethod\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[38;5;28;43mstr\u001B[39;49m\u001B[43m(\u001B[49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mmethod\u001B[49m\u001B[43m)\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    931\u001B[0m \u001B[43m    \u001B[49m\u001B[43mbody\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mbody\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    932\u001B[0m \u001B[43m    \u001B[49m\u001B[43mheaders\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mheaders\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    933\u001B[0m \u001B[43m\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m    935\u001B[0m \u001B[38;5;28;01mfor\u001B[39;00m callback \u001B[38;5;129;01min\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mresponse_callbacks:\n\u001B[1;32m    936\u001B[0m     callback(resp)\n",
-      "File \u001B[0;32m~/code/langchain/.venv/lib/python3.10/site-packages/googleapiclient/http.py:191\u001B[0m, in \u001B[0;36m_retry_request\u001B[0;34m(http, num_retries, req_type, sleep, rand, uri, method, *args, **kwargs)\u001B[0m\n\u001B[1;32m    189\u001B[0m \u001B[38;5;28;01mtry\u001B[39;00m:\n\u001B[1;32m    190\u001B[0m     exception \u001B[38;5;241m=\u001B[39m \u001B[38;5;28;01mNone\u001B[39;00m\n\u001B[0;32m--> 191\u001B[0m     resp, content \u001B[38;5;241m=\u001B[39m \u001B[43mhttp\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mrequest\u001B[49m\u001B[43m(\u001B[49m\u001B[43muri\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mmethod\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43margs\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43mkwargs\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m    192\u001B[0m \u001B[38;5;66;03m# Retry on SSL errors and socket timeout errors.\u001B[39;00m\n\u001B[1;32m    193\u001B[0m \u001B[38;5;28;01mexcept\u001B[39;00m _ssl_SSLError \u001B[38;5;28;01mas\u001B[39;00m ssl_error:\n",
-      "File \u001B[0;32m~/code/langchain/.venv/lib/python3.10/site-packages/httplib2/__init__.py:1724\u001B[0m, in \u001B[0;36mHttp.request\u001B[0;34m(self, uri, method, body, headers, redirections, connection_type)\u001B[0m\n\u001B[1;32m   1722\u001B[0m             content \u001B[38;5;241m=\u001B[39m \u001B[38;5;124mb\u001B[39m\u001B[38;5;124m\"\u001B[39m\u001B[38;5;124m\"\u001B[39m\n\u001B[1;32m   1723\u001B[0m         \u001B[38;5;28;01melse\u001B[39;00m:\n\u001B[0;32m-> 1724\u001B[0m             (response, content) \u001B[38;5;241m=\u001B[39m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_request\u001B[49m\u001B[43m(\u001B[49m\n\u001B[1;32m   1725\u001B[0m \u001B[43m                \u001B[49m\u001B[43mconn\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mauthority\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43muri\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mrequest_uri\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mmethod\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mbody\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mheaders\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mredirections\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mcachekey\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1726\u001B[0m \u001B[43m            \u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m   1727\u001B[0m \u001B[38;5;28;01mexcept\u001B[39;00m \u001B[38;5;167;01mException\u001B[39;00m \u001B[38;5;28;01mas\u001B[39;00m e:\n\u001B[1;32m   1728\u001B[0m     is_timeout \u001B[38;5;241m=\u001B[39m \u001B[38;5;28misinstance\u001B[39m(e, socket\u001B[38;5;241m.\u001B[39mtimeout)\n",
-      "File \u001B[0;32m~/code/langchain/.venv/lib/python3.10/site-packages/httplib2/__init__.py:1444\u001B[0m, in \u001B[0;36mHttp._request\u001B[0;34m(self, conn, host, absolute_uri, request_uri, method, body, headers, redirections, cachekey)\u001B[0m\n\u001B[1;32m   1441\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m auth:\n\u001B[1;32m   1442\u001B[0m     auth\u001B[38;5;241m.\u001B[39mrequest(method, request_uri, headers, body)\n\u001B[0;32m-> 1444\u001B[0m (response, content) \u001B[38;5;241m=\u001B[39m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_conn_request\u001B[49m\u001B[43m(\u001B[49m\u001B[43mconn\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mrequest_uri\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mmethod\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mbody\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mheaders\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m   1446\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m auth:\n\u001B[1;32m   1447\u001B[0m     \u001B[38;5;28;01mif\u001B[39;00m auth\u001B[38;5;241m.\u001B[39mresponse(response, body):\n",
-      "File \u001B[0;32m~/code/langchain/.venv/lib/python3.10/site-packages/httplib2/__init__.py:1366\u001B[0m, in \u001B[0;36mHttp._conn_request\u001B[0;34m(self, conn, request_uri, method, body, headers)\u001B[0m\n\u001B[1;32m   1364\u001B[0m \u001B[38;5;28;01mtry\u001B[39;00m:\n\u001B[1;32m   1365\u001B[0m     \u001B[38;5;28;01mif\u001B[39;00m conn\u001B[38;5;241m.\u001B[39msock \u001B[38;5;129;01mis\u001B[39;00m \u001B[38;5;28;01mNone\u001B[39;00m:\n\u001B[0;32m-> 1366\u001B[0m         \u001B[43mconn\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mconnect\u001B[49m\u001B[43m(\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m   1367\u001B[0m     conn\u001B[38;5;241m.\u001B[39mrequest(method, request_uri, body, headers)\n\u001B[1;32m   1368\u001B[0m \u001B[38;5;28;01mexcept\u001B[39;00m socket\u001B[38;5;241m.\u001B[39mtimeout:\n",
-      "File \u001B[0;32m~/code/langchain/.venv/lib/python3.10/site-packages/httplib2/__init__.py:1156\u001B[0m, in \u001B[0;36mHTTPSConnectionWithTimeout.connect\u001B[0;34m(self)\u001B[0m\n\u001B[1;32m   1154\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m has_timeout(\u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mtimeout):\n\u001B[1;32m   1155\u001B[0m     sock\u001B[38;5;241m.\u001B[39msettimeout(\u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mtimeout)\n\u001B[0;32m-> 1156\u001B[0m \u001B[43msock\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mconnect\u001B[49m\u001B[43m(\u001B[49m\u001B[43m(\u001B[49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mhost\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mport\u001B[49m\u001B[43m)\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m   1158\u001B[0m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39msock \u001B[38;5;241m=\u001B[39m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_context\u001B[38;5;241m.\u001B[39mwrap_socket(sock, server_hostname\u001B[38;5;241m=\u001B[39m\u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mhost)\n\u001B[1;32m   1160\u001B[0m \u001B[38;5;66;03m# Python 3.3 compatibility: emulate the check_hostname behavior\u001B[39;00m\n",
-      "\u001B[0;31mKeyboardInterrupt\u001B[0m: "
-     ]
     }
    ],
    "source": [
-    "agent_executor.invoke({\"input\": \"What is ChatGPT?\"})"
+    "agent_chain.run(input=\"What is ChatGPT?\")"
    ]
   },
   {
@@ -196,15 +179,15 @@
      "text": [
       "\n",
       "\n",
-      "\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
-      "\u001B[32;1m\u001B[1;3mThought: I need to find out who developed ChatGPT\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3mThought: I need to find out who developed ChatGPT\n",
       "Action: Search\n",
-      "Action Input: Who developed ChatGPT\u001B[0m\n",
-      "Observation: \u001B[36;1m\u001B[1;3mChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large ... Feb 15, 2023 ... Who owns Chat GPT? Chat GPT is owned and developed by AI research and deployment company, OpenAI. The organization is headquartered in San ... Feb 8, 2023 ... ChatGPT is an AI chatbot developed by San Francisco-based startup OpenAI. OpenAI was co-founded in 2015 by Elon Musk and Sam Altman and is ... Dec 7, 2022 ... ChatGPT is an AI chatbot designed and developed by OpenAI. The bot works by generating text responses based on human-user input, like questions ... Jan 12, 2023 ... In 2019, Microsoft invested $1 billion in OpenAI, the tiny San Francisco company that designed ChatGPT. And in the years since, it has quietly ... Jan 25, 2023 ... The inside story of ChatGPT: How OpenAI founder Sam Altman built the world's hottest technology with billions from Microsoft. Dec 3, 2022 ... ChatGPT went viral on social media for its ability to do anything from code to write essays. · The company that created the AI chatbot has a ... Jan 17, 2023 ... While many Americans were nursing hangovers on New Year's Day, 22-year-old Edward Tian was working feverishly on a new app to combat misuse ... ChatGPT is a language model created by OpenAI, an artificial intelligence research laboratory consisting of a team of researchers and engineers focused on ... 1 day ago ... Everyone is talking about ChatGPT, developed by OpenAI. This is such a great tool that has helped to make AI more accessible to a wider ...\u001B[0m\n",
-      "Thought:\u001B[32;1m\u001B[1;3m I now know the final answer\n",
-      "Final Answer: ChatGPT was developed by OpenAI.\u001B[0m\n",
+      "Action Input: Who developed ChatGPT\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3mChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large ... Feb 15, 2023 ... Who owns Chat GPT? Chat GPT is owned and developed by AI research and deployment company, OpenAI. The organization is headquartered in San ... Feb 8, 2023 ... ChatGPT is an AI chatbot developed by San Francisco-based startup OpenAI. OpenAI was co-founded in 2015 by Elon Musk and Sam Altman and is ... Dec 7, 2022 ... ChatGPT is an AI chatbot designed and developed by OpenAI. The bot works by generating text responses based on human-user input, like questions ... Jan 12, 2023 ... In 2019, Microsoft invested $1 billion in OpenAI, the tiny San Francisco company that designed ChatGPT. And in the years since, it has quietly ... Jan 25, 2023 ... The inside story of ChatGPT: How OpenAI founder Sam Altman built the world's hottest technology with billions from Microsoft. Dec 3, 2022 ... ChatGPT went viral on social media for its ability to do anything from code to write essays. · The company that created the AI chatbot has a ... Jan 17, 2023 ... While many Americans were nursing hangovers on New Year's Day, 22-year-old Edward Tian was working feverishly on a new app to combat misuse ... ChatGPT is a language model created by OpenAI, an artificial intelligence research laboratory consisting of a team of researchers and engineers focused on ... 1 day ago ... Everyone is talking about ChatGPT, developed by OpenAI. This is such a great tool that has helped to make AI more accessible to a wider ...\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
+      "Final Answer: ChatGPT was developed by OpenAI.\u001b[0m\n",
       "\n",
-      "\u001B[1m> Finished chain.\u001B[0m\n"
+      "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
     },
     {
@@ -219,7 +202,7 @@
     }
    ],
    "source": [
-    "agent_executor.invoke({\"input\": \"Who developed it?\"})"
+    "agent_chain.run(input=\"Who developed it?\")"
    ]
   },
   {
@@ -234,14 +217,14 @@
      "text": [
       "\n",
       "\n",
-      "\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
-      "\u001B[32;1m\u001B[1;3mThought: I need to simplify the conversation for a 5 year old.\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3mThought: I need to simplify the conversation for a 5 year old.\n",
       "Action: Summary\n",
-      "Action Input: My daughter 5 years old\u001B[0m\n",
+      "Action Input: My daughter 5 years old\u001b[0m\n",
       "\n",
-      "\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
+      "\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
       "Prompt after formatting:\n",
-      "\u001B[32;1m\u001B[1;3mThis is a conversation between a human and a bot:\n",
+      "\u001b[32;1m\u001b[1;3mThis is a conversation between a human and a bot:\n",
       "\n",
       "Human: What is ChatGPT?\n",
       "AI: ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large language models and is optimized for dialogue by using Reinforcement Learning with Human-in-the-Loop. It is also capable of sending and receiving images during chatting.\n",
@@ -249,16 +232,16 @@
       "AI: ChatGPT was developed by OpenAI.\n",
       "\n",
       "Write a summary of the conversation for My daughter 5 years old:\n",
-      "\u001B[0m\n",
+      "\u001b[0m\n",
       "\n",
-      "\u001B[1m> Finished chain.\u001B[0m\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
       "\n",
-      "Observation: \u001B[33;1m\u001B[1;3m\n",
-      "The conversation was about ChatGPT, an artificial intelligence chatbot. It was created by OpenAI and can send and receive images while chatting.\u001B[0m\n",
-      "Thought:\u001B[32;1m\u001B[1;3m I now know the final answer.\n",
-      "Final Answer: ChatGPT is an artificial intelligence chatbot created by OpenAI that can send and receive images while chatting.\u001B[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3m\n",
+      "The conversation was about ChatGPT, an artificial intelligence chatbot. It was created by OpenAI and can send and receive images while chatting.\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
+      "Final Answer: ChatGPT is an artificial intelligence chatbot created by OpenAI that can send and receive images while chatting.\u001b[0m\n",
       "\n",
-      "\u001B[1m> Finished chain.\u001B[0m\n"
+      "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
     },
     {
@@ -273,8 +256,8 @@
     }
    ],
    "source": [
-    "agent_executor.invoke(\n",
-    "    {\"input\": \"Thanks. Summarize the conversation, for my daughter 5 years old.\"}\n",
+    "agent_chain.run(\n",
+    "    input=\"Thanks. Summarize the conversation, for my daughter 5 years old.\"\n",
     ")"
    ]
   },
@@ -306,17 +289,9 @@
     }
    ],
    "source": [
-    "print(agent_executor.memory.buffer)"
+    "print(agent_chain.memory.buffer)"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "id": "84ca95c30e262e00",
-   "metadata": {
-    "collapsed": false
-   },
-   "source": []
-  },
   {
    "cell_type": "markdown",
    "id": "cc3d0aa4",
@@ -365,9 +340,25 @@
     "    ),\n",
     "]\n",
     "\n",
-    "prompt = hub.pull(\"hwchase17/react\")\n",
-    "agent = create_react_agent(model, tools, prompt)\n",
-    "agent_executor = AgentExecutor(agent=agent, tools=tools, memory=memory)"
+    "prefix = \"\"\"Have a conversation with a human, answering the following questions as best you can. You have access to the following tools:\"\"\"\n",
+    "suffix = \"\"\"Begin!\"\n",
+    "\n",
+    "{chat_history}\n",
+    "Question: {input}\n",
+    "{agent_scratchpad}\"\"\"\n",
+    "\n",
+    "prompt = ZeroShotAgent.create_prompt(\n",
+    "    tools,\n",
+    "    prefix=prefix,\n",
+    "    suffix=suffix,\n",
+    "    input_variables=[\"input\", \"chat_history\", \"agent_scratchpad\"],\n",
+    ")\n",
+    "\n",
+    "llm_chain = LLMChain(llm=OpenAI(temperature=0), prompt=prompt)\n",
+    "agent = ZeroShotAgent(llm_chain=llm_chain, tools=tools, verbose=True)\n",
+    "agent_chain = AgentExecutor.from_agent_and_tools(\n",
+    "    agent=agent, tools=tools, verbose=True, memory=memory\n",
+    ")"
    ]
   },
   {
@@ -382,15 +373,15 @@
      "text": [
       "\n",
       "\n",
-      "\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
-      "\u001B[32;1m\u001B[1;3mThought: I should research ChatGPT to answer this question.\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3mThought: I should research ChatGPT to answer this question.\n",
       "Action: Search\n",
-      "Action Input: \"ChatGPT\"\u001B[0m\n",
-      "Observation: \u001B[36;1m\u001B[1;3mNov 30, 2022 ... We've trained a model called ChatGPT which interacts in a conversational way. The dialogue format makes it possible for ChatGPT to answer ... ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large ... ChatGPT. We've trained a model called ChatGPT which interacts in a conversational way. The dialogue format makes it possible for ChatGPT to answer ... Feb 2, 2023 ... ChatGPT, the popular chatbot from OpenAI, is estimated to have reached 100 million monthly active users in January, just two months after ... 2 days ago ... ChatGPT recently launched a new version of its own plagiarism detection tool, with hopes that it will squelch some of the criticism around how ... An API for accessing new AI models developed by OpenAI. Feb 19, 2023 ... ChatGPT is an AI chatbot system that OpenAI released in November to show off and test what a very large, powerful AI system can accomplish. You ... ChatGPT is fine-tuned from GPT-3.5, a language model trained to produce text. ChatGPT was optimized for dialogue by using Reinforcement Learning with Human ... 3 days ago ... Visual ChatGPT connects ChatGPT and a series of Visual Foundation Models to enable sending and receiving images during chatting. Dec 1, 2022 ... ChatGPT is a natural language processing tool driven by AI technology that allows you to have human-like conversations and much more with a ...\u001B[0m\n",
-      "Thought:\u001B[32;1m\u001B[1;3m I now know the final answer.\n",
-      "Final Answer: ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large language models and is optimized for dialogue by using Reinforcement Learning with Human-in-the-Loop. It is also capable of sending and receiving images during chatting.\u001B[0m\n",
+      "Action Input: \"ChatGPT\"\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3mNov 30, 2022 ... We've trained a model called ChatGPT which interacts in a conversational way. The dialogue format makes it possible for ChatGPT to answer ... ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large ... ChatGPT. We've trained a model called ChatGPT which interacts in a conversational way. The dialogue format makes it possible for ChatGPT to answer ... Feb 2, 2023 ... ChatGPT, the popular chatbot from OpenAI, is estimated to have reached 100 million monthly active users in January, just two months after ... 2 days ago ... ChatGPT recently launched a new version of its own plagiarism detection tool, with hopes that it will squelch some of the criticism around how ... An API for accessing new AI models developed by OpenAI. Feb 19, 2023 ... ChatGPT is an AI chatbot system that OpenAI released in November to show off and test what a very large, powerful AI system can accomplish. You ... ChatGPT is fine-tuned from GPT-3.5, a language model trained to produce text. ChatGPT was optimized for dialogue by using Reinforcement Learning with Human ... 3 days ago ... Visual ChatGPT connects ChatGPT and a series of Visual Foundation Models to enable sending and receiving images during chatting. Dec 1, 2022 ... ChatGPT is a natural language processing tool driven by AI technology that allows you to have human-like conversations and much more with a ...\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
+      "Final Answer: ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large language models and is optimized for dialogue by using Reinforcement Learning with Human-in-the-Loop. It is also capable of sending and receiving images during chatting.\u001b[0m\n",
       "\n",
-      "\u001B[1m> Finished chain.\u001B[0m\n"
+      "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
     },
     {
@@ -405,7 +396,7 @@
     }
    ],
    "source": [
-    "agent_executor.invoke({\"input\": \"What is ChatGPT?\"})"
+    "agent_chain.run(input=\"What is ChatGPT?\")"
    ]
   },
   {
@@ -420,15 +411,15 @@
      "text": [
       "\n",
       "\n",
-      "\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
-      "\u001B[32;1m\u001B[1;3mThought: I need to find out who developed ChatGPT\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3mThought: I need to find out who developed ChatGPT\n",
       "Action: Search\n",
-      "Action Input: Who developed ChatGPT\u001B[0m\n",
-      "Observation: \u001B[36;1m\u001B[1;3mChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large ... Feb 15, 2023 ... Who owns Chat GPT? Chat GPT is owned and developed by AI research and deployment company, OpenAI. The organization is headquartered in San ... Feb 8, 2023 ... ChatGPT is an AI chatbot developed by San Francisco-based startup OpenAI. OpenAI was co-founded in 2015 by Elon Musk and Sam Altman and is ... Dec 7, 2022 ... ChatGPT is an AI chatbot designed and developed by OpenAI. The bot works by generating text responses based on human-user input, like questions ... Jan 12, 2023 ... In 2019, Microsoft invested $1 billion in OpenAI, the tiny San Francisco company that designed ChatGPT. And in the years since, it has quietly ... Jan 25, 2023 ... The inside story of ChatGPT: How OpenAI founder Sam Altman built the world's hottest technology with billions from Microsoft. Dec 3, 2022 ... ChatGPT went viral on social media for its ability to do anything from code to write essays. · The company that created the AI chatbot has a ... Jan 17, 2023 ... While many Americans were nursing hangovers on New Year's Day, 22-year-old Edward Tian was working feverishly on a new app to combat misuse ... ChatGPT is a language model created by OpenAI, an artificial intelligence research laboratory consisting of a team of researchers and engineers focused on ... 1 day ago ... Everyone is talking about ChatGPT, developed by OpenAI. This is such a great tool that has helped to make AI more accessible to a wider ...\u001B[0m\n",
-      "Thought:\u001B[32;1m\u001B[1;3m I now know the final answer\n",
-      "Final Answer: ChatGPT was developed by OpenAI.\u001B[0m\n",
+      "Action Input: Who developed ChatGPT\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3mChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large ... Feb 15, 2023 ... Who owns Chat GPT? Chat GPT is owned and developed by AI research and deployment company, OpenAI. The organization is headquartered in San ... Feb 8, 2023 ... ChatGPT is an AI chatbot developed by San Francisco-based startup OpenAI. OpenAI was co-founded in 2015 by Elon Musk and Sam Altman and is ... Dec 7, 2022 ... ChatGPT is an AI chatbot designed and developed by OpenAI. The bot works by generating text responses based on human-user input, like questions ... Jan 12, 2023 ... In 2019, Microsoft invested $1 billion in OpenAI, the tiny San Francisco company that designed ChatGPT. And in the years since, it has quietly ... Jan 25, 2023 ... The inside story of ChatGPT: How OpenAI founder Sam Altman built the world's hottest technology with billions from Microsoft. Dec 3, 2022 ... ChatGPT went viral on social media for its ability to do anything from code to write essays. · The company that created the AI chatbot has a ... Jan 17, 2023 ... While many Americans were nursing hangovers on New Year's Day, 22-year-old Edward Tian was working feverishly on a new app to combat misuse ... ChatGPT is a language model created by OpenAI, an artificial intelligence research laboratory consisting of a team of researchers and engineers focused on ... 1 day ago ... Everyone is talking about ChatGPT, developed by OpenAI. This is such a great tool that has helped to make AI more accessible to a wider ...\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
+      "Final Answer: ChatGPT was developed by OpenAI.\u001b[0m\n",
       "\n",
-      "\u001B[1m> Finished chain.\u001B[0m\n"
+      "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
     },
     {
@@ -443,7 +434,7 @@
     }
    ],
    "source": [
-    "agent_executor.invoke({\"input\": \"Who developed it?\"})"
+    "agent_chain.run(input=\"Who developed it?\")"
    ]
   },
   {
@@ -458,14 +449,14 @@
      "text": [
       "\n",
       "\n",
-      "\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
-      "\u001B[32;1m\u001B[1;3mThought: I need to simplify the conversation for a 5 year old.\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3mThought: I need to simplify the conversation for a 5 year old.\n",
       "Action: Summary\n",
-      "Action Input: My daughter 5 years old\u001B[0m\n",
+      "Action Input: My daughter 5 years old\u001b[0m\n",
       "\n",
-      "\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
+      "\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
       "Prompt after formatting:\n",
-      "\u001B[32;1m\u001B[1;3mThis is a conversation between a human and a bot:\n",
+      "\u001b[32;1m\u001b[1;3mThis is a conversation between a human and a bot:\n",
       "\n",
       "Human: What is ChatGPT?\n",
       "AI: ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large language models and is optimized for dialogue by using Reinforcement Learning with Human-in-the-Loop. It is also capable of sending and receiving images during chatting.\n",
@@ -473,16 +464,16 @@
       "AI: ChatGPT was developed by OpenAI.\n",
       "\n",
       "Write a summary of the conversation for My daughter 5 years old:\n",
-      "\u001B[0m\n",
+      "\u001b[0m\n",
       "\n",
-      "\u001B[1m> Finished chain.\u001B[0m\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
       "\n",
-      "Observation: \u001B[33;1m\u001B[1;3m\n",
-      "The conversation was about ChatGPT, an artificial intelligence chatbot developed by OpenAI. It is designed to have conversations with humans and can also send and receive images.\u001B[0m\n",
-      "Thought:\u001B[32;1m\u001B[1;3m I now know the final answer.\n",
-      "Final Answer: ChatGPT is an artificial intelligence chatbot developed by OpenAI that can have conversations with humans and send and receive images.\u001B[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3m\n",
+      "The conversation was about ChatGPT, an artificial intelligence chatbot developed by OpenAI. It is designed to have conversations with humans and can also send and receive images.\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
+      "Final Answer: ChatGPT is an artificial intelligence chatbot developed by OpenAI that can have conversations with humans and send and receive images.\u001b[0m\n",
       "\n",
-      "\u001B[1m> Finished chain.\u001B[0m\n"
+      "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
     },
     {
@@ -497,8 +488,8 @@
     }
    ],
    "source": [
-    "agent_executor.invoke(\n",
-    "    {\"input\": \"Thanks. Summarize the conversation, for my daughter 5 years old.\"}\n",
+    "agent_chain.run(\n",
+    "    input=\"Thanks. Summarize the conversation, for my daughter 5 years old.\"\n",
     ")"
    ]
   },
@@ -533,7 +524,7 @@
     }
    ],
    "source": [
-    "print(agent_executor.memory.buffer)"
+    "print(agent_chain.memory.buffer)"
    ]
   }
  ],

cookbook/sql_db_qa.mdx

@@ -647,7 +647,7 @@ Sometimes you may not have the luxury of using OpenAI or other service-hosted la
 import logging
 import torch
 from transformers import AutoTokenizer, GPT2TokenizerFast, pipeline, AutoModelForSeq2SeqLM, AutoModelForCausalLM
-from langchain_huggingface import HuggingFacePipeline
+from langchain_community.llms import HuggingFacePipeline
 
 # Note: This model requires a large GPU, e.g. an 80GB A100. See documentation for other ways to run private non-OpenAI models.
 model_id = "google/flan-ul2"
@@ -992,7 +992,7 @@ Now that you have some examples (with manually corrected output SQL), you can do
 ```python
 from langchain.prompts import FewShotPromptTemplate, PromptTemplate
 from langchain.chains.sql_database.prompt import _sqlite_prompt, PROMPT_SUFFIX
-from langchain_huggingface import HuggingFaceEmbeddings
+from langchain_community.embeddings.huggingface import HuggingFaceEmbeddings
 from langchain.prompts.example_selector.semantic_similarity import SemanticSimilarityExampleSelector
 from langchain_community.vectorstores import Chroma
 

cookbook/tool_call_messages.ipynb

@@ -1,199 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "c48812ed-35bd-4fbe-9a2c-6c7335e5645e",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_anthropic import ChatAnthropic\n",
-    "from langchain_core.runnables import ConfigurableField\n",
-    "from langchain_core.tools import tool\n",
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "\n",
-    "@tool\n",
-    "def multiply(x: float, y: float) -> float:\n",
-    "    \"\"\"Multiply 'x' times 'y'.\"\"\"\n",
-    "    return x * y\n",
-    "\n",
-    "\n",
-    "@tool\n",
-    "def exponentiate(x: float, y: float) -> float:\n",
-    "    \"\"\"Raise 'x' to the 'y'.\"\"\"\n",
-    "    return x**y\n",
-    "\n",
-    "\n",
-    "@tool\n",
-    "def add(x: float, y: float) -> float:\n",
-    "    \"\"\"Add 'x' and 'y'.\"\"\"\n",
-    "    return x + y\n",
-    "\n",
-    "\n",
-    "tools = [multiply, exponentiate, add]\n",
-    "\n",
-    "gpt35 = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0).bind_tools(tools)\n",
-    "claude3 = ChatAnthropic(model=\"claude-3-sonnet-20240229\").bind_tools(tools)\n",
-    "llm_with_tools = gpt35.configurable_alternatives(\n",
-    "    ConfigurableField(id=\"llm\"), default_key=\"gpt35\", claude3=claude3\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "9c186263-1b98-4cb2-b6d1-71f65eb0d811",
-   "metadata": {},
-   "source": [
-    "# LangGraph"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "28fc2c60-7dbc-428a-8983-1a6a15ea30d2",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import operator\n",
-    "from typing import Annotated, Sequence, TypedDict\n",
-    "\n",
-    "from langchain_core.messages import AIMessage, BaseMessage, HumanMessage, ToolMessage\n",
-    "from langchain_core.runnables import RunnableLambda\n",
-    "from langgraph.graph import END, StateGraph\n",
-    "\n",
-    "\n",
-    "class AgentState(TypedDict):\n",
-    "    messages: Annotated[Sequence[BaseMessage], operator.add]\n",
-    "\n",
-    "\n",
-    "def should_continue(state):\n",
-    "    return \"continue\" if state[\"messages\"][-1].tool_calls else \"end\"\n",
-    "\n",
-    "\n",
-    "def call_model(state, config):\n",
-    "    return {\"messages\": [llm_with_tools.invoke(state[\"messages\"], config=config)]}\n",
-    "\n",
-    "\n",
-    "def _invoke_tool(tool_call):\n",
-    "    tool = {tool.name: tool for tool in tools}[tool_call[\"name\"]]\n",
-    "    return ToolMessage(tool.invoke(tool_call[\"args\"]), tool_call_id=tool_call[\"id\"])\n",
-    "\n",
-    "\n",
-    "tool_executor = RunnableLambda(_invoke_tool)\n",
-    "\n",
-    "\n",
-    "def call_tools(state):\n",
-    "    last_message = state[\"messages\"][-1]\n",
-    "    return {\"messages\": tool_executor.batch(last_message.tool_calls)}\n",
-    "\n",
-    "\n",
-    "workflow = StateGraph(AgentState)\n",
-    "workflow.add_node(\"agent\", call_model)\n",
-    "workflow.add_node(\"action\", call_tools)\n",
-    "workflow.set_entry_point(\"agent\")\n",
-    "workflow.add_conditional_edges(\n",
-    "    \"agent\",\n",
-    "    should_continue,\n",
-    "    {\n",
-    "        \"continue\": \"action\",\n",
-    "        \"end\": END,\n",
-    "    },\n",
-    ")\n",
-    "workflow.add_edge(\"action\", \"agent\")\n",
-    "graph = workflow.compile()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "3710e724-2595-4625-ba3a-effb81e66e4a",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'messages': [HumanMessage(content=\"what's 3 plus 5 raised to the 2.743. also what's 17.24 - 918.1241\"),\n",
-       "  AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_6yMU2WsS4Bqgi1WxFHxtfJRc', 'function': {'arguments': '{\"x\": 8, \"y\": 2.743}', 'name': 'exponentiate'}, 'type': 'function'}, {'id': 'call_GAL3dQiKFF9XEV0RrRLPTvVp', 'function': {'arguments': '{\"x\": 17.24, \"y\": -918.1241}', 'name': 'add'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 58, 'prompt_tokens': 168, 'total_tokens': 226}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': 'fp_b28b39ffa8', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-528302fc-7acf-4c11-82c4-119ccf40c573-0', tool_calls=[{'name': 'exponentiate', 'args': {'x': 8, 'y': 2.743}, 'id': 'call_6yMU2WsS4Bqgi1WxFHxtfJRc'}, {'name': 'add', 'args': {'x': 17.24, 'y': -918.1241}, 'id': 'call_GAL3dQiKFF9XEV0RrRLPTvVp'}]),\n",
-       "  ToolMessage(content='300.03770462067547', tool_call_id='call_6yMU2WsS4Bqgi1WxFHxtfJRc'),\n",
-       "  ToolMessage(content='-900.8841', tool_call_id='call_GAL3dQiKFF9XEV0RrRLPTvVp'),\n",
-       "  AIMessage(content='The result of \\\\(3 + 5^{2.743}\\\\) is approximately 300.04, and the result of \\\\(17.24 - 918.1241\\\\) is approximately -900.88.', response_metadata={'token_usage': {'completion_tokens': 44, 'prompt_tokens': 251, 'total_tokens': 295}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': 'fp_b28b39ffa8', 'finish_reason': 'stop', 'logprobs': None}, id='run-d1161669-ed09-4b18-94bd-6d8530df5aa8-0')]}"
-      ]
-     },
-     "execution_count": 4,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "graph.invoke(\n",
-    "    {\n",
-    "        \"messages\": [\n",
-    "            HumanMessage(\n",
-    "                \"what's 3 plus 5 raised to the 2.743. also what's 17.24 - 918.1241\"\n",
-    "            )\n",
-    "        ]\n",
-    "    }\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "073c074e-d722-42e0-85ec-c62c079207e4",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'messages': [HumanMessage(content=\"what's 3 plus 5 raised to the 2.743. also what's 17.24 - 918.1241\"),\n",
-       "  AIMessage(content=[{'text': \"Okay, let's break this down into two parts:\", 'type': 'text'}, {'id': 'toolu_01DEhqcXkXTtzJAiZ7uMBeDC', 'input': {'x': 3, 'y': 5}, 'name': 'add', 'type': 'tool_use'}], response_metadata={'id': 'msg_01AkLGH8sxMHaH15yewmjwkF', 'model': 'claude-3-sonnet-20240229', 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'input_tokens': 450, 'output_tokens': 81}}, id='run-f35bfae8-8ded-4f8a-831b-0940d6ad16b6-0', tool_calls=[{'name': 'add', 'args': {'x': 3, 'y': 5}, 'id': 'toolu_01DEhqcXkXTtzJAiZ7uMBeDC'}]),\n",
-       "  ToolMessage(content='8.0', tool_call_id='toolu_01DEhqcXkXTtzJAiZ7uMBeDC'),\n",
-       "  AIMessage(content=[{'id': 'toolu_013DyMLrvnrto33peAKMGMr1', 'input': {'x': 8.0, 'y': 2.743}, 'name': 'exponentiate', 'type': 'tool_use'}], response_metadata={'id': 'msg_015Fmp8aztwYcce2JDAFfce3', 'model': 'claude-3-sonnet-20240229', 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'input_tokens': 545, 'output_tokens': 75}}, id='run-48aaeeeb-a1e5-48fd-a57a-6c3da2907b47-0', tool_calls=[{'name': 'exponentiate', 'args': {'x': 8.0, 'y': 2.743}, 'id': 'toolu_013DyMLrvnrto33peAKMGMr1'}]),\n",
-       "  ToolMessage(content='300.03770462067547', tool_call_id='toolu_013DyMLrvnrto33peAKMGMr1'),\n",
-       "  AIMessage(content=[{'text': 'So 3 plus 5 raised to the 2.743 power is 300.04.\\n\\nFor the second part:', 'type': 'text'}, {'id': 'toolu_01UTmMrGTmLpPrPCF1rShN46', 'input': {'x': 17.24, 'y': -918.1241}, 'name': 'add', 'type': 'tool_use'}], response_metadata={'id': 'msg_015TkhfRBENPib2RWAxkieH6', 'model': 'claude-3-sonnet-20240229', 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'input_tokens': 638, 'output_tokens': 105}}, id='run-45fb62e3-d102-4159-881d-241c5dbadeed-0', tool_calls=[{'name': 'add', 'args': {'x': 17.24, 'y': -918.1241}, 'id': 'toolu_01UTmMrGTmLpPrPCF1rShN46'}]),\n",
-       "  ToolMessage(content='-900.8841', tool_call_id='toolu_01UTmMrGTmLpPrPCF1rShN46'),\n",
-       "  AIMessage(content='Therefore, 17.24 - 918.1241 = -900.8841', response_metadata={'id': 'msg_01LgKnRuUcSyADCpxv9tPoYD', 'model': 'claude-3-sonnet-20240229', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 759, 'output_tokens': 24}}, id='run-1008254e-ccd1-497c-8312-9550dd77bd08-0')]}"
-      ]
-     },
-     "execution_count": 5,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "graph.invoke(\n",
-    "    {\n",
-    "        \"messages\": [\n",
-    "            HumanMessage(\n",
-    "                \"what's 3 plus 5 raised to the 2.743. also what's 17.24 - 918.1241\"\n",
-    "            )\n",
-    "        ]\n",
-    "    },\n",
-    "    config={\"configurable\": {\"llm\": \"claude3\"}},\n",
-    ")"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.10.4"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

cookbook/two_agent_debate_tools.ipynb

@@ -84,7 +84,7 @@
     "        Applies the chatmodel to the message history\n",
     "        and returns the message string\n",
     "        \"\"\"\n",
-    "        message = self.model.invoke(\n",
+    "        message = self.model(\n",
     "            [\n",
     "                self.system_message,\n",
     "                HumanMessage(content=\"\\n\".join(self.message_history + [self.prefix])),\n",

cookbook/two_player_dnd.ipynb

@@ -70,7 +70,7 @@
     "        Applies the chatmodel to the message history\n",
     "        and returns the message string\n",
     "        \"\"\"\n",
-    "        message = self.model.invoke(\n",
+    "        message = self.model(\n",
     "            [\n",
     "                self.system_message,\n",
     "                HumanMessage(content=\"\\n\".join(self.message_history + [self.prefix])),\n",

docs/.gitignore

@@ -1,3 +1,2 @@
 /.quarto/
 src/supabase.d.ts
-build

docs/.local_build.sh

@@ -0,0 +1,24 @@
+#!/usr/bin/env bash
+
+set -o errexit
+set -o nounset
+set -o pipefail
+set -o xtrace
+
+SCRIPT_DIR="$(cd "$(dirname "$0")"; pwd)"
+cd "${SCRIPT_DIR}"
+
+mkdir -p ../_dist
+rsync -ruv --exclude node_modules --exclude api_reference --exclude .venv --exclude .docusaurus . ../_dist
+cd ../_dist
+poetry run python scripts/model_feat_table.py
+cp ../cookbook/README.md src/pages/cookbook.mdx
+mkdir -p docs/templates
+cp ../templates/docs/INDEX.md docs/templates/index.md
+poetry run python scripts/copy_templates.py
+wget -q https://raw.githubusercontent.com/langchain-ai/langserve/main/README.md -O docs/langserve.md
+wget -q https://raw.githubusercontent.com/langchain-ai/langgraph/main/README.md -O docs/langgraph.md
+
+yarn
+
+poetry run quarto preview docs

docs/Makefile

@@ -1,85 +0,0 @@
-# we build the docs in these stages:
-# 1. install vercel and python dependencies
-# 2. copy files from "source dir" to "intermediate dir"
-# 2. generate files like model feat table, etc in "intermediate dir"
-# 3. copy files to their right spots (e.g. langserve readme) in "intermediate dir"
-# 4. build the docs from "intermediate dir" to "output dir"
-
-SOURCE_DIR = docs/
-INTERMEDIATE_DIR = build/intermediate/docs
-
-OUTPUT_NEW_DIR = build/output-new
-OUTPUT_NEW_DOCS_DIR = $(OUTPUT_NEW_DIR)/docs
-
-PYTHON = .venv/bin/python
-
-PARTNER_DEPS_LIST := $(shell find ../libs/partners -mindepth 1 -maxdepth 1 -type d -exec test -e "{}/pyproject.toml" \; -print | grep -vE "airbyte|ibm" | tr '\n' ' ')
-
-PORT ?= 3001
-
-clean:
-	rm -rf build
-
-install-vercel-deps:
-	yum -y update
-	yum install gcc bzip2-devel libffi-devel zlib-devel wget tar gzip rsync -y
-
-install-py-deps:
-	python3 -m venv .venv
-	$(PYTHON) -m pip install --upgrade pip
-	$(PYTHON) -m pip install --upgrade uv
-	$(PYTHON) -m uv pip install -r vercel_requirements.txt
-	$(PYTHON) -m uv pip install --editable $(PARTNER_DEPS_LIST)
-
-generate-files:
-	mkdir -p $(INTERMEDIATE_DIR)
-	cp -r $(SOURCE_DIR)/* $(INTERMEDIATE_DIR)
-	mkdir -p $(INTERMEDIATE_DIR)/templates
-	cp ../templates/docs/INDEX.md $(INTERMEDIATE_DIR)/templates/index.md
-	cp ../cookbook/README.md $(INTERMEDIATE_DIR)/cookbook.mdx
-
-	$(PYTHON) scripts/model_feat_table.py $(INTERMEDIATE_DIR)
-
-	$(PYTHON) scripts/copy_templates.py $(INTERMEDIATE_DIR)
-
-	wget -q https://raw.githubusercontent.com/langchain-ai/langserve/main/README.md -O $(INTERMEDIATE_DIR)/langserve.md
-	$(PYTHON) scripts/resolve_local_links.py $(INTERMEDIATE_DIR)/langserve.md https://github.com/langchain-ai/langserve/tree/main/
-
-	wget -q https://raw.githubusercontent.com/langchain-ai/langgraph/main/README.md -O $(INTERMEDIATE_DIR)/langgraph.md
-	$(PYTHON) scripts/resolve_local_links.py $(INTERMEDIATE_DIR)/langgraph.md https://github.com/langchain-ai/langgraph/tree/main/
-
-copy-infra:
-	mkdir -p $(OUTPUT_NEW_DIR)
-	cp -r src $(OUTPUT_NEW_DIR)
-	cp vercel.json $(OUTPUT_NEW_DIR)
-	cp babel.config.js $(OUTPUT_NEW_DIR)
-	cp -r data $(OUTPUT_NEW_DIR)
-	cp docusaurus.config.js $(OUTPUT_NEW_DIR)
-	cp package.json $(OUTPUT_NEW_DIR)
-	cp sidebars.js $(OUTPUT_NEW_DIR)
-	cp -r static $(OUTPUT_NEW_DIR)
-	cp yarn.lock $(OUTPUT_NEW_DIR)
-
-render:
-	$(PYTHON) scripts/notebook_convert.py $(INTERMEDIATE_DIR) $(OUTPUT_NEW_DOCS_DIR)
-
-md-sync:
-	rsync -avm --include="*/" --include="*.mdx" --include="*.md" --include="*.png" --exclude="*" $(INTERMEDIATE_DIR)/ $(OUTPUT_NEW_DOCS_DIR)
-
-generate-references:
-	$(PYTHON) scripts/generate_api_reference_links.py --docs_dir $(OUTPUT_NEW_DOCS_DIR)
-
-build: install-py-deps generate-files copy-infra render md-sync generate-references
-
-vercel-build: install-vercel-deps build
-	rm -rf docs
-	mv $(OUTPUT_NEW_DOCS_DIR) docs
-	rm -rf build
-	yarn run docusaurus build
-	mv build v0.2
-	mkdir build
-	mv v0.2 build
-	mv build/v0.2/404.html build
-
-start:
-	cd $(OUTPUT_NEW_DIR) && yarn && yarn start --port=$(PORT)

docs/api_reference/_static/css/custom.css

@@ -12,8 +12,7 @@ pre {
   }
 }
 
-#my-component-root *,
-#headlessui-portal-root * {
+#my-component-root *, #headlessui-portal-root * {
   z-index: 10000;
 }
 

docs/api_reference/create_api_rst.py

@@ -359,14 +359,9 @@ def main(dirs: Optional[list] = None) -> None:
         dirs = [
             dir_
             for dir_ in os.listdir(ROOT_DIR / "libs")
-            if dir_ not in ("cli", "partners", "standard-tests")
-        ]
-        dirs += [
-            dir_
-            for dir_ in os.listdir(ROOT_DIR / "libs" / "partners")
-            if os.path.isdir(dir_)
-            and "pyproject.toml" in os.listdir(ROOT_DIR / "libs" / "partners" / dir_)
+            if dir_ not in ("cli", "partners")
         ]
+        dirs += os.listdir(ROOT_DIR / "libs" / "partners")
     for dir_ in dirs:
         # Skip any hidden directories
         # Some of these could be present by mistake in the code base

docs/api_reference/themes/scikit-learn-modern/static/css/theme.css

@@ -1398,20 +1398,3 @@ table.sk-sponsor-table td {
 .highlight .vi { color: #bb60d5 } /* Name.Variable.Instance */
 .highlight .vm { color: #bb60d5 } /* Name.Variable.Magic */
 .highlight .il { color: #208050 } /* Literal.Number.Integer.Long */
-
-/** Custom styles overriding certain values */
-
-div.sk-sidebar-toc-wrapper {
-  width: unset;
-  overflow-x: auto;
-}
-
-div.sk-sidebar-toc-wrapper > [aria-label="rellinks"] {
-  position: sticky;
-  left: 0;
-}
-
-.navbar-nav .dropdown-menu {
-  max-height: 80vh;
-  overflow-y: auto;
-}

docs/code-block-loader.js

@@ -0,0 +1,76 @@
+/* eslint-disable prefer-template */
+/* eslint-disable no-param-reassign */
+// eslint-disable-next-line import/no-extraneous-dependencies
+const babel = require("@babel/core");
+const path = require("path");
+const fs = require("fs");
+
+/**
+ *
+ * @param {string|Buffer} content Content of the resource file
+ * @param {object} [map] SourceMap data consumable by https://github.com/mozilla/source-map
+ * @param {any} [meta] Meta data, could be anything
+ */
+async function webpackLoader(content, map, meta) {
+  const cb = this.async();
+
+  if (!this.resourcePath.endsWith(".ts")) {
+    cb(null, JSON.stringify({ content, imports: [] }), map, meta);
+    return;
+  }
+
+  try {
+    const result = await babel.parseAsync(content, {
+      sourceType: "module",
+      filename: this.resourcePath,
+    });
+
+    const imports = [];
+
+    result.program.body.forEach((node) => {
+      if (node.type === "ImportDeclaration") {
+        const source = node.source.value;
+
+        if (!source.startsWith("langchain")) {
+          return;
+        }
+
+        node.specifiers.forEach((specifier) => {
+          if (specifier.type === "ImportSpecifier") {
+            const local = specifier.local.name;
+            const imported = specifier.imported.name;
+            imports.push({ local, imported, source });
+          } else {
+            throw new Error("Unsupported import type");
+          }
+        });
+      }
+    });
+
+    imports.forEach((imp) => {
+      const { imported, source } = imp;
+      const moduleName = source.split("/").slice(1).join("_");
+      const docsPath = path.resolve(__dirname, "docs", "api", moduleName);
+      const available = fs.readdirSync(docsPath, { withFileTypes: true });
+      const found = available.find(
+        (dirent) =>
+          dirent.isDirectory() &&
+          fs.existsSync(path.resolve(docsPath, dirent.name, imported + ".md"))
+      );
+      if (found) {
+        imp.docs =
+          "/" + path.join("docs", "api", moduleName, found.name, imported);
+      } else {
+        throw new Error(
+          `Could not find docs for ${source}.${imported} in docs/api/`
+        );
+      }
+    });
+
+    cb(null, JSON.stringify({ content, imports }), map, meta);
+  } catch (err) {
+    cb(err);
+  }
+}
+
+module.exports = webpackLoader;

docs/docs/additional_resources/arxiv_references.mdx

@@ -1,519 +0,0 @@
-# arXiv
-            
-LangChain implements the latest research in the field of Natural Language Processing.
-This page contains `arXiv` papers referenced in the LangChain Documentation and API Reference.
-
-## Summary
-
-| arXiv id / Title | Authors | Published date 🔻 | LangChain Documentation and API Reference |
-|------------------|---------|-------------------|-------------------------|
-| `2307.03172v3` [Lost in the Middle: How Language Models Use Long Contexts](http://arxiv.org/abs/2307.03172v3) | Nelson F. Liu, Kevin Lin, John Hewitt,  et al. | 2023-07-06 | `Docs:` [docs/modules/data_connection/retrievers/long_context_reorder](https://python.langchain.com/docs/modules/data_connection/retrievers/long_context_reorder)
-| `2305.08291v1` [Large Language Model Guided Tree-of-Thought](http://arxiv.org/abs/2305.08291v1) | Jieyi Long | 2023-05-15 | `API:` [langchain_experimental.tot](https://api.python.langchain.com/en/latest/experimental_api_reference.html#module-langchain_experimental.tot)
-| `2305.06983v2` [Active Retrieval Augmented Generation](http://arxiv.org/abs/2305.06983v2) | Zhengbao Jiang, Frank F. Xu, Luyu Gao,  et al. | 2023-05-11 | `Docs:` [docs/modules/chains](https://python.langchain.com/docs/modules/chains)
-| `2303.17580v4` [HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face](http://arxiv.org/abs/2303.17580v4) | Yongliang Shen, Kaitao Song, Xu Tan,  et al. | 2023-03-30 | `API:` [langchain_experimental.autonomous_agents](https://api.python.langchain.com/en/latest/experimental_api_reference.html#module-langchain_experimental.autonomous_agents)
-| `2303.08774v6` [GPT-4 Technical Report](http://arxiv.org/abs/2303.08774v6) | OpenAI, Josh Achiam, Steven Adler,  et al. | 2023-03-15 | `Docs:` [docs/integrations/vectorstores/mongodb_atlas](https://python.langchain.com/docs/integrations/vectorstores/mongodb_atlas)
-| `2301.10226v4` [A Watermark for Large Language Models](http://arxiv.org/abs/2301.10226v4) | John Kirchenbauer, Jonas Geiping, Yuxin Wen,  et al. | 2023-01-24 | `API:` [langchain_community.llms...HuggingFaceTextGenInference](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference.html#langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference), [langchain_community.llms...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_community.llms...OCIModelDeploymentTGI](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.oci_data_science_model_deployment_endpoint.OCIModelDeploymentTGI.html#langchain_community.llms.oci_data_science_model_deployment_endpoint.OCIModelDeploymentTGI)
-| `2212.10496v1` [Precise Zero-Shot Dense Retrieval without Relevance Labels](http://arxiv.org/abs/2212.10496v1) | Luyu Gao, Xueguang Ma, Jimmy Lin,  et al. | 2022-12-20 | `Docs:` [docs/use_cases/query_analysis/techniques/hyde](https://python.langchain.com/docs/use_cases/query_analysis/techniques/hyde), `API:` [langchain.chains...HypotheticalDocumentEmbedder](https://api.python.langchain.com/en/latest/chains/langchain.chains.hyde.base.HypotheticalDocumentEmbedder.html#langchain.chains.hyde.base.HypotheticalDocumentEmbedder)
-| `2212.08073v1` [Constitutional AI: Harmlessness from AI Feedback](http://arxiv.org/abs/2212.08073v1) | Yuntao Bai, Saurav Kadavath, Sandipan Kundu,  et al. | 2022-12-15 | `Docs:` [docs/guides/productionization/evaluation/string/criteria_eval_chain](https://python.langchain.com/docs/guides/productionization/evaluation/string/criteria_eval_chain)
-| `2212.07425v3` [Robust and Explainable Identification of Logical Fallacies in Natural Language Arguments](http://arxiv.org/abs/2212.07425v3) | Zhivar Sourati, Vishnu Priya Prasanna Venkatesh, Darshan Deshpande,  et al. | 2022-12-12 | `API:` [langchain_experimental.fallacy_removal](https://api.python.langchain.com/en/latest/experimental_api_reference.html#module-langchain_experimental.fallacy_removal)
-| `2211.13892v2` [Complementary Explanations for Effective In-Context Learning](http://arxiv.org/abs/2211.13892v2) | Xi Ye, Srinivasan Iyer, Asli Celikyilmaz,  et al. | 2022-11-25 | `API:` [langchain_core.example_selectors...MaxMarginalRelevanceExampleSelector](https://api.python.langchain.com/en/latest/example_selectors/langchain_core.example_selectors.semantic_similarity.MaxMarginalRelevanceExampleSelector.html#langchain_core.example_selectors.semantic_similarity.MaxMarginalRelevanceExampleSelector)
-| `2211.10435v2` [PAL: Program-aided Language Models](http://arxiv.org/abs/2211.10435v2) | Luyu Gao, Aman Madaan, Shuyan Zhou,  et al. | 2022-11-18 | `API:` [langchain_experimental.pal_chain...PALChain](https://api.python.langchain.com/en/latest/pal_chain/langchain_experimental.pal_chain.base.PALChain.html#langchain_experimental.pal_chain.base.PALChain), [langchain_experimental.pal_chain](https://api.python.langchain.com/en/latest/experimental_api_reference.html#module-langchain_experimental.pal_chain)
-| `2209.10785v2` [Deep Lake: a Lakehouse for Deep Learning](http://arxiv.org/abs/2209.10785v2) | Sasun Hambardzumyan, Abhinav Tuli, Levon Ghukasyan,  et al. | 2022-09-22 | `Docs:` [docs/integrations/providers/activeloop_deeplake](https://python.langchain.com/docs/integrations/providers/activeloop_deeplake)
-| `2205.12654v1` [Bitext Mining Using Distilled Sentence Representations for Low-Resource Languages](http://arxiv.org/abs/2205.12654v1) | Kevin Heffernan, Onur Çelebi, Holger Schwenk | 2022-05-25 | `API:` [langchain_community.embeddings...LaserEmbeddings](https://api.python.langchain.com/en/latest/embeddings/langchain_community.embeddings.laser.LaserEmbeddings.html#langchain_community.embeddings.laser.LaserEmbeddings)
-| `2204.00498v1` [Evaluating the Text-to-SQL Capabilities of Large Language Models](http://arxiv.org/abs/2204.00498v1) | Nitarshan Rajkumar, Raymond Li, Dzmitry Bahdanau | 2022-03-15 | `Docs:` [docs/use_cases/sql/quickstart](https://python.langchain.com/docs/use_cases/sql/quickstart), `API:` [langchain_community.utilities...SQLDatabase](https://api.python.langchain.com/en/latest/utilities/langchain_community.utilities.sql_database.SQLDatabase.html#langchain_community.utilities.sql_database.SQLDatabase), [langchain_community.utilities...SparkSQL](https://api.python.langchain.com/en/latest/utilities/langchain_community.utilities.spark_sql.SparkSQL.html#langchain_community.utilities.spark_sql.SparkSQL)
-| `2202.00666v5` [Locally Typical Sampling](http://arxiv.org/abs/2202.00666v5) | Clara Meister, Tiago Pimentel, Gian Wiher,  et al. | 2022-02-01 | `API:` [langchain_community.llms...HuggingFaceTextGenInference](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference.html#langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference), [langchain_community.llms...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint)
-| `2103.00020v1` [Learning Transferable Visual Models From Natural Language Supervision](http://arxiv.org/abs/2103.00020v1) | Alec Radford, Jong Wook Kim, Chris Hallacy,  et al. | 2021-02-26 | `API:` [langchain_experimental.open_clip](https://api.python.langchain.com/en/latest/experimental_api_reference.html#module-langchain_experimental.open_clip)
-| `1909.05858v2` [CTRL: A Conditional Transformer Language Model for Controllable Generation](http://arxiv.org/abs/1909.05858v2) | Nitish Shirish Keskar, Bryan McCann, Lav R. Varshney,  et al. | 2019-09-11 | `API:` [langchain_community.llms...HuggingFaceTextGenInference](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference.html#langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference), [langchain_community.llms...HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint)
-| `1908.10084v1` [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](http://arxiv.org/abs/1908.10084v1) | Nils Reimers, Iryna Gurevych | 2019-08-27 | `Docs:` [docs/integrations/text_embedding/sentence_transformers](https://python.langchain.com/docs/integrations/text_embedding/sentence_transformers)
-
-## Lost in the Middle: How Language Models Use Long Contexts
-
-- **arXiv id:** 2307.03172v3
-- **Title:** Lost in the Middle: How Language Models Use Long Contexts
-- **Authors:** Nelson F. Liu, Kevin Lin, John Hewitt,  et al.
-- **Published Date:** 2023-07-06
-- **URL:** http://arxiv.org/abs/2307.03172v3
-- **LangChain Documentation:** [docs/modules/data_connection/retrievers/long_context_reorder](https://python.langchain.com/docs/modules/data_connection/retrievers/long_context_reorder)
-
-
-**Abstract:** While recent language models have the ability to take long contexts as input,
-relatively little is known about how well they use longer context. We analyze
-the performance of language models on two tasks that require identifying
-relevant information in their input contexts: multi-document question answering
-and key-value retrieval. We find that performance can degrade significantly
-when changing the position of relevant information, indicating that current
-language models do not robustly make use of information in long input contexts.
-In particular, we observe that performance is often highest when relevant
-information occurs at the beginning or end of the input context, and
-significantly degrades when models must access relevant information in the
-middle of long contexts, even for explicitly long-context models. Our analysis
-provides a better understanding of how language models use their input context
-and provides new evaluation protocols for future long-context language models.
-                
-## Large Language Model Guided Tree-of-Thought
-
-- **arXiv id:** 2305.08291v1
-- **Title:** Large Language Model Guided Tree-of-Thought
-- **Authors:** Jieyi Long
-- **Published Date:** 2023-05-15
-- **URL:** http://arxiv.org/abs/2305.08291v1
-
-- **LangChain API Reference:** [langchain_experimental.tot](https://api.python.langchain.com/en/latest/experimental_api_reference.html#module-langchain_experimental.tot)
-
-**Abstract:** In this paper, we introduce the Tree-of-Thought (ToT) framework, a novel
-approach aimed at improving the problem-solving capabilities of auto-regressive
-large language models (LLMs). The ToT technique is inspired by the human mind's
-approach for solving complex reasoning tasks through trial and error. In this
-process, the human mind explores the solution space through a tree-like thought
-process, allowing for backtracking when necessary. To implement ToT as a
-software system, we augment an LLM with additional modules including a prompter
-agent, a checker module, a memory module, and a ToT controller. In order to
-solve a given problem, these modules engage in a multi-round conversation with
-the LLM. The memory module records the conversation and state history of the
-problem solving process, which allows the system to backtrack to the previous
-steps of the thought-process and explore other directions from there. To verify
-the effectiveness of the proposed technique, we implemented a ToT-based solver
-for the Sudoku Puzzle. Experimental results show that the ToT framework can
-significantly increase the success rate of Sudoku puzzle solving. Our
-implementation of the ToT-based Sudoku solver is available on GitHub:
-\url{https://github.com/jieyilong/tree-of-thought-puzzle-solver}.
-                
-## Active Retrieval Augmented Generation
-
-- **arXiv id:** 2305.06983v2
-- **Title:** Active Retrieval Augmented Generation
-- **Authors:** Zhengbao Jiang, Frank F. Xu, Luyu Gao,  et al.
-- **Published Date:** 2023-05-11
-- **URL:** http://arxiv.org/abs/2305.06983v2
-- **LangChain Documentation:** [docs/modules/chains](https://python.langchain.com/docs/modules/chains)
-
-
-**Abstract:** Despite the remarkable ability of large language models (LMs) to comprehend
-and generate language, they have a tendency to hallucinate and create factually
-inaccurate output. Augmenting LMs by retrieving information from external
-knowledge resources is one promising solution. Most existing retrieval
-augmented LMs employ a retrieve-and-generate setup that only retrieves
-information once based on the input. This is limiting, however, in more general
-scenarios involving generation of long texts, where continually gathering
-information throughout generation is essential. In this work, we provide a
-generalized view of active retrieval augmented generation, methods that
-actively decide when and what to retrieve across the course of the generation.
-We propose Forward-Looking Active REtrieval augmented generation (FLARE), a
-generic method which iteratively uses a prediction of the upcoming sentence to
-anticipate future content, which is then utilized as a query to retrieve
-relevant documents to regenerate the sentence if it contains low-confidence
-tokens. We test FLARE along with baselines comprehensively over 4 long-form
-knowledge-intensive generation tasks/datasets. FLARE achieves superior or
-competitive performance on all tasks, demonstrating the effectiveness of our
-method. Code and datasets are available at https://github.com/jzbjyb/FLARE.
-                
-## HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face
-
-- **arXiv id:** 2303.17580v4
-- **Title:** HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face
-- **Authors:** Yongliang Shen, Kaitao Song, Xu Tan,  et al.
-- **Published Date:** 2023-03-30
-- **URL:** http://arxiv.org/abs/2303.17580v4
-
-- **LangChain API Reference:** [langchain_experimental.autonomous_agents](https://api.python.langchain.com/en/latest/experimental_api_reference.html#module-langchain_experimental.autonomous_agents)
-
-**Abstract:** Solving complicated AI tasks with different domains and modalities is a key
-step toward artificial general intelligence. While there are numerous AI models
-available for various domains and modalities, they cannot handle complicated AI
-tasks autonomously. Considering large language models (LLMs) have exhibited
-exceptional abilities in language understanding, generation, interaction, and
-reasoning, we advocate that LLMs could act as a controller to manage existing
-AI models to solve complicated AI tasks, with language serving as a generic
-interface to empower this. Based on this philosophy, we present HuggingGPT, an
-LLM-powered agent that leverages LLMs (e.g., ChatGPT) to connect various AI
-models in machine learning communities (e.g., Hugging Face) to solve AI tasks.
-Specifically, we use ChatGPT to conduct task planning when receiving a user
-request, select models according to their function descriptions available in
-Hugging Face, execute each subtask with the selected AI model, and summarize
-the response according to the execution results. By leveraging the strong
-language capability of ChatGPT and abundant AI models in Hugging Face,
-HuggingGPT can tackle a wide range of sophisticated AI tasks spanning different
-modalities and domains and achieve impressive results in language, vision,
-speech, and other challenging tasks, which paves a new way towards the
-realization of artificial general intelligence.
-                
-## GPT-4 Technical Report
-
-- **arXiv id:** 2303.08774v6
-- **Title:** GPT-4 Technical Report
-- **Authors:** OpenAI, Josh Achiam, Steven Adler,  et al.
-- **Published Date:** 2023-03-15
-- **URL:** http://arxiv.org/abs/2303.08774v6
-- **LangChain Documentation:** [docs/integrations/vectorstores/mongodb_atlas](https://python.langchain.com/docs/integrations/vectorstores/mongodb_atlas)
-
-
-**Abstract:** We report the development of GPT-4, a large-scale, multimodal model which can
-accept image and text inputs and produce text outputs. While less capable than
-humans in many real-world scenarios, GPT-4 exhibits human-level performance on
-various professional and academic benchmarks, including passing a simulated bar
-exam with a score around the top 10% of test takers. GPT-4 is a
-Transformer-based model pre-trained to predict the next token in a document.
-The post-training alignment process results in improved performance on measures
-of factuality and adherence to desired behavior. A core component of this
-project was developing infrastructure and optimization methods that behave
-predictably across a wide range of scales. This allowed us to accurately
-predict some aspects of GPT-4's performance based on models trained with no
-more than 1/1,000th the compute of GPT-4.
-                
-## A Watermark for Large Language Models
-
-- **arXiv id:** 2301.10226v4
-- **Title:** A Watermark for Large Language Models
-- **Authors:** John Kirchenbauer, Jonas Geiping, Yuxin Wen,  et al.
-- **Published Date:** 2023-01-24
-- **URL:** http://arxiv.org/abs/2301.10226v4
-
-- **LangChain API Reference:** [langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference.html#langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference), [langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint), [langchain_community.llms.oci_data_science_model_deployment_endpoint.OCIModelDeploymentTGI](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.oci_data_science_model_deployment_endpoint.OCIModelDeploymentTGI.html#langchain_community.llms.oci_data_science_model_deployment_endpoint.OCIModelDeploymentTGI)
-
-**Abstract:** Potential harms of large language models can be mitigated by watermarking
-model output, i.e., embedding signals into generated text that are invisible to
-humans but algorithmically detectable from a short span of tokens. We propose a
-watermarking framework for proprietary language models. The watermark can be
-embedded with negligible impact on text quality, and can be detected using an
-efficient open-source algorithm without access to the language model API or
-parameters. The watermark works by selecting a randomized set of "green" tokens
-before a word is generated, and then softly promoting use of green tokens
-during sampling. We propose a statistical test for detecting the watermark with
-interpretable p-values, and derive an information-theoretic framework for
-analyzing the sensitivity of the watermark. We test the watermark using a
-multi-billion parameter model from the Open Pretrained Transformer (OPT)
-family, and discuss robustness and security.
-                
-## Precise Zero-Shot Dense Retrieval without Relevance Labels
-
-- **arXiv id:** 2212.10496v1
-- **Title:** Precise Zero-Shot Dense Retrieval without Relevance Labels
-- **Authors:** Luyu Gao, Xueguang Ma, Jimmy Lin,  et al.
-- **Published Date:** 2022-12-20
-- **URL:** http://arxiv.org/abs/2212.10496v1
-- **LangChain Documentation:** [docs/use_cases/query_analysis/techniques/hyde](https://python.langchain.com/docs/use_cases/query_analysis/techniques/hyde)
-- **LangChain API Reference:** [langchain.chains.hyde.base.HypotheticalDocumentEmbedder](https://api.python.langchain.com/en/latest/chains/langchain.chains.hyde.base.HypotheticalDocumentEmbedder.html#langchain.chains.hyde.base.HypotheticalDocumentEmbedder)
-
-**Abstract:** While dense retrieval has been shown effective and efficient across tasks and
-languages, it remains difficult to create effective fully zero-shot dense
-retrieval systems when no relevance label is available. In this paper, we
-recognize the difficulty of zero-shot learning and encoding relevance. Instead,
-we propose to pivot through Hypothetical Document Embeddings~(HyDE). Given a
-query, HyDE first zero-shot instructs an instruction-following language model
-(e.g. InstructGPT) to generate a hypothetical document. The document captures
-relevance patterns but is unreal and may contain false details. Then, an
-unsupervised contrastively learned encoder~(e.g. Contriever) encodes the
-document into an embedding vector. This vector identifies a neighborhood in the
-corpus embedding space, where similar real documents are retrieved based on
-vector similarity. This second step ground the generated document to the actual
-corpus, with the encoder's dense bottleneck filtering out the incorrect
-details. Our experiments show that HyDE significantly outperforms the
-state-of-the-art unsupervised dense retriever Contriever and shows strong
-performance comparable to fine-tuned retrievers, across various tasks (e.g. web
-search, QA, fact verification) and languages~(e.g. sw, ko, ja).
-                
-## Constitutional AI: Harmlessness from AI Feedback
-
-- **arXiv id:** 2212.08073v1
-- **Title:** Constitutional AI: Harmlessness from AI Feedback
-- **Authors:** Yuntao Bai, Saurav Kadavath, Sandipan Kundu,  et al.
-- **Published Date:** 2022-12-15
-- **URL:** http://arxiv.org/abs/2212.08073v1
-- **LangChain Documentation:** [docs/guides/productionization/evaluation/string/criteria_eval_chain](https://python.langchain.com/docs/guides/productionization/evaluation/string/criteria_eval_chain)
-
-
-**Abstract:** As AI systems become more capable, we would like to enlist their help to
-supervise other AIs. We experiment with methods for training a harmless AI
-assistant through self-improvement, without any human labels identifying
-harmful outputs. The only human oversight is provided through a list of rules
-or principles, and so we refer to the method as 'Constitutional AI'. The
-process involves both a supervised learning and a reinforcement learning phase.
-In the supervised phase we sample from an initial model, then generate
-self-critiques and revisions, and then finetune the original model on revised
-responses. In the RL phase, we sample from the finetuned model, use a model to
-evaluate which of the two samples is better, and then train a preference model
-from this dataset of AI preferences. We then train with RL using the preference
-model as the reward signal, i.e. we use 'RL from AI Feedback' (RLAIF). As a
-result we are able to train a harmless but non-evasive AI assistant that
-engages with harmful queries by explaining its objections to them. Both the SL
-and RL methods can leverage chain-of-thought style reasoning to improve the
-human-judged performance and transparency of AI decision making. These methods
-make it possible to control AI behavior more precisely and with far fewer human
-labels.
-                
-## Robust and Explainable Identification of Logical Fallacies in Natural Language Arguments
-
-- **arXiv id:** 2212.07425v3
-- **Title:** Robust and Explainable Identification of Logical Fallacies in Natural Language Arguments
-- **Authors:** Zhivar Sourati, Vishnu Priya Prasanna Venkatesh, Darshan Deshpande,  et al.
-- **Published Date:** 2022-12-12
-- **URL:** http://arxiv.org/abs/2212.07425v3
-
-- **LangChain API Reference:** [langchain_experimental.fallacy_removal](https://api.python.langchain.com/en/latest/experimental_api_reference.html#module-langchain_experimental.fallacy_removal)
-
-**Abstract:** The spread of misinformation, propaganda, and flawed argumentation has been
-amplified in the Internet era. Given the volume of data and the subtlety of
-identifying violations of argumentation norms, supporting information analytics
-tasks, like content moderation, with trustworthy methods that can identify
-logical fallacies is essential. In this paper, we formalize prior theoretical
-work on logical fallacies into a comprehensive three-stage evaluation framework
-of detection, coarse-grained, and fine-grained classification. We adapt
-existing evaluation datasets for each stage of the evaluation. We employ three
-families of robust and explainable methods based on prototype reasoning,
-instance-based reasoning, and knowledge injection. The methods combine language
-models with background knowledge and explainable mechanisms. Moreover, we
-address data sparsity with strategies for data augmentation and curriculum
-learning. Our three-stage framework natively consolidates prior datasets and
-methods from existing tasks, like propaganda detection, serving as an
-overarching evaluation testbed. We extensively evaluate these methods on our
-datasets, focusing on their robustness and explainability. Our results provide
-insight into the strengths and weaknesses of the methods on different
-components and fallacy classes, indicating that fallacy identification is a
-challenging task that may require specialized forms of reasoning to capture
-various classes. We share our open-source code and data on GitHub to support
-further work on logical fallacy identification.
-                
-## Complementary Explanations for Effective In-Context Learning
-
-- **arXiv id:** 2211.13892v2
-- **Title:** Complementary Explanations for Effective In-Context Learning
-- **Authors:** Xi Ye, Srinivasan Iyer, Asli Celikyilmaz,  et al.
-- **Published Date:** 2022-11-25
-- **URL:** http://arxiv.org/abs/2211.13892v2
-
-- **LangChain API Reference:** [langchain_core.example_selectors.semantic_similarity.MaxMarginalRelevanceExampleSelector](https://api.python.langchain.com/en/latest/example_selectors/langchain_core.example_selectors.semantic_similarity.MaxMarginalRelevanceExampleSelector.html#langchain_core.example_selectors.semantic_similarity.MaxMarginalRelevanceExampleSelector)
-
-**Abstract:** Large language models (LLMs) have exhibited remarkable capabilities in
-learning from explanations in prompts, but there has been limited understanding
-of exactly how these explanations function or why they are effective. This work
-aims to better understand the mechanisms by which explanations are used for
-in-context learning. We first study the impact of two different factors on the
-performance of prompts with explanations: the computation trace (the way the
-solution is decomposed) and the natural language used to express the prompt. By
-perturbing explanations on three controlled tasks, we show that both factors
-contribute to the effectiveness of explanations. We further study how to form
-maximally effective sets of explanations for solving a given test query. We
-find that LLMs can benefit from the complementarity of the explanation set:
-diverse reasoning skills shown by different exemplars can lead to better
-performance. Therefore, we propose a maximal marginal relevance-based exemplar
-selection approach for constructing exemplar sets that are both relevant as
-well as complementary, which successfully improves the in-context learning
-performance across three real-world tasks on multiple LLMs.
-                
-## PAL: Program-aided Language Models
-
-- **arXiv id:** 2211.10435v2
-- **Title:** PAL: Program-aided Language Models
-- **Authors:** Luyu Gao, Aman Madaan, Shuyan Zhou,  et al.
-- **Published Date:** 2022-11-18
-- **URL:** http://arxiv.org/abs/2211.10435v2
-
-- **LangChain API Reference:** [langchain_experimental.pal_chain.base.PALChain](https://api.python.langchain.com/en/latest/pal_chain/langchain_experimental.pal_chain.base.PALChain.html#langchain_experimental.pal_chain.base.PALChain), [langchain_experimental.pal_chain](https://api.python.langchain.com/en/latest/experimental_api_reference.html#module-langchain_experimental.pal_chain)
-
-**Abstract:** Large language models (LLMs) have recently demonstrated an impressive ability
-to perform arithmetic and symbolic reasoning tasks, when provided with a few
-examples at test time ("few-shot prompting"). Much of this success can be
-attributed to prompting methods such as "chain-of-thought'', which employ LLMs
-for both understanding the problem description by decomposing it into steps, as
-well as solving each step of the problem. While LLMs seem to be adept at this
-sort of step-by-step decomposition, LLMs often make logical and arithmetic
-mistakes in the solution part, even when the problem is decomposed correctly.
-In this paper, we present Program-Aided Language models (PAL): a novel approach
-that uses the LLM to read natural language problems and generate programs as
-the intermediate reasoning steps, but offloads the solution step to a runtime
-such as a Python interpreter. With PAL, decomposing the natural language
-problem into runnable steps remains the only learning task for the LLM, while
-solving is delegated to the interpreter. We demonstrate this synergy between a
-neural LLM and a symbolic interpreter across 13 mathematical, symbolic, and
-algorithmic reasoning tasks from BIG-Bench Hard and other benchmarks. In all
-these natural language reasoning tasks, generating code using an LLM and
-reasoning using a Python interpreter leads to more accurate results than much
-larger models. For example, PAL using Codex achieves state-of-the-art few-shot
-accuracy on the GSM8K benchmark of math word problems, surpassing PaLM-540B
-which uses chain-of-thought by absolute 15% top-1. Our code and data are
-publicly available at http://reasonwithpal.com/ .
-                
-## Deep Lake: a Lakehouse for Deep Learning
-
-- **arXiv id:** 2209.10785v2
-- **Title:** Deep Lake: a Lakehouse for Deep Learning
-- **Authors:** Sasun Hambardzumyan, Abhinav Tuli, Levon Ghukasyan,  et al.
-- **Published Date:** 2022-09-22
-- **URL:** http://arxiv.org/abs/2209.10785v2
-- **LangChain Documentation:** [docs/integrations/providers/activeloop_deeplake](https://python.langchain.com/docs/integrations/providers/activeloop_deeplake)
-
-
-**Abstract:** Traditional data lakes provide critical data infrastructure for analytical
-workloads by enabling time travel, running SQL queries, ingesting data with
-ACID transactions, and visualizing petabyte-scale datasets on cloud storage.
-They allow organizations to break down data silos, unlock data-driven
-decision-making, improve operational efficiency, and reduce costs. However, as
-deep learning usage increases, traditional data lakes are not well-designed for
-applications such as natural language processing (NLP), audio processing,
-computer vision, and applications involving non-tabular datasets. This paper
-presents Deep Lake, an open-source lakehouse for deep learning applications
-developed at Activeloop. Deep Lake maintains the benefits of a vanilla data
-lake with one key difference: it stores complex data, such as images, videos,
-annotations, as well as tabular data, in the form of tensors and rapidly
-streams the data over the network to (a) Tensor Query Language, (b) in-browser
-visualization engine, or (c) deep learning frameworks without sacrificing GPU
-utilization. Datasets stored in Deep Lake can be accessed from PyTorch,
-TensorFlow, JAX, and integrate with numerous MLOps tools.
-                
-## Bitext Mining Using Distilled Sentence Representations for Low-Resource Languages
-
-- **arXiv id:** 2205.12654v1
-- **Title:** Bitext Mining Using Distilled Sentence Representations for Low-Resource Languages
-- **Authors:** Kevin Heffernan, Onur Çelebi, Holger Schwenk
-- **Published Date:** 2022-05-25
-- **URL:** http://arxiv.org/abs/2205.12654v1
-
-- **LangChain API Reference:** [langchain_community.embeddings.laser.LaserEmbeddings](https://api.python.langchain.com/en/latest/embeddings/langchain_community.embeddings.laser.LaserEmbeddings.html#langchain_community.embeddings.laser.LaserEmbeddings)
-
-**Abstract:** Scaling multilingual representation learning beyond the hundred most frequent
-languages is challenging, in particular to cover the long tail of low-resource
-languages. A promising approach has been to train one-for-all multilingual
-models capable of cross-lingual transfer, but these models often suffer from
-insufficient capacity and interference between unrelated languages. Instead, we
-move away from this approach and focus on training multiple language (family)
-specific representations, but most prominently enable all languages to still be
-encoded in the same representational space. To achieve this, we focus on
-teacher-student training, allowing all encoders to be mutually compatible for
-bitext mining, and enabling fast learning of new languages. We introduce a new
-teacher-student training scheme which combines supervised and self-supervised
-training, allowing encoders to take advantage of monolingual training data,
-which is valuable in the low-resource setting.
-  Our approach significantly outperforms the original LASER encoder. We study
-very low-resource languages and handle 50 African languages, many of which are
-not covered by any other model. For these languages, we train sentence
-encoders, mine bitexts, and validate the bitexts by training NMT systems.
-                
-## Evaluating the Text-to-SQL Capabilities of Large Language Models
-
-- **arXiv id:** 2204.00498v1
-- **Title:** Evaluating the Text-to-SQL Capabilities of Large Language Models
-- **Authors:** Nitarshan Rajkumar, Raymond Li, Dzmitry Bahdanau
-- **Published Date:** 2022-03-15
-- **URL:** http://arxiv.org/abs/2204.00498v1
-- **LangChain Documentation:** [docs/use_cases/sql/quickstart](https://python.langchain.com/docs/use_cases/sql/quickstart)
-- **LangChain API Reference:** [langchain_community.utilities.sql_database.SQLDatabase](https://api.python.langchain.com/en/latest/utilities/langchain_community.utilities.sql_database.SQLDatabase.html#langchain_community.utilities.sql_database.SQLDatabase), [langchain_community.utilities.spark_sql.SparkSQL](https://api.python.langchain.com/en/latest/utilities/langchain_community.utilities.spark_sql.SparkSQL.html#langchain_community.utilities.spark_sql.SparkSQL)
-
-**Abstract:** We perform an empirical evaluation of Text-to-SQL capabilities of the Codex
-language model. We find that, without any finetuning, Codex is a strong
-baseline on the Spider benchmark; we also analyze the failure modes of Codex in
-this setting. Furthermore, we demonstrate on the GeoQuery and Scholar
-benchmarks that a small number of in-domain examples provided in the prompt
-enables Codex to perform better than state-of-the-art models finetuned on such
-few-shot examples.
-                
-## Locally Typical Sampling
-
-- **arXiv id:** 2202.00666v5
-- **Title:** Locally Typical Sampling
-- **Authors:** Clara Meister, Tiago Pimentel, Gian Wiher,  et al.
-- **Published Date:** 2022-02-01
-- **URL:** http://arxiv.org/abs/2202.00666v5
-
-- **LangChain API Reference:** [langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference.html#langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference), [langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint)
-
-**Abstract:** Today's probabilistic language generators fall short when it comes to
-producing coherent and fluent text despite the fact that the underlying models
-perform well under standard metrics, e.g., perplexity. This discrepancy has
-puzzled the language generation community for the last few years. In this work,
-we posit that the abstraction of natural language generation as a discrete
-stochastic process--which allows for an information-theoretic analysis--can
-provide new insights into the behavior of probabilistic language generators,
-e.g., why high-probability texts can be dull or repetitive. Humans use language
-as a means of communicating information, aiming to do so in a simultaneously
-efficient and error-minimizing manner; in fact, psycholinguistics research
-suggests humans choose each word in a string with this subconscious goal in
-mind. We formally define the set of strings that meet this criterion: those for
-which each word has an information content close to the expected information
-content, i.e., the conditional entropy of our model. We then propose a simple
-and efficient procedure for enforcing this criterion when generating from
-probabilistic models, which we call locally typical sampling. Automatic and
-human evaluations show that, in comparison to nucleus and top-k sampling,
-locally typical sampling offers competitive performance (in both abstractive
-summarization and story generation) in terms of quality while consistently
-reducing degenerate repetitions.
-                
-## Learning Transferable Visual Models From Natural Language Supervision
-
-- **arXiv id:** 2103.00020v1
-- **Title:** Learning Transferable Visual Models From Natural Language Supervision
-- **Authors:** Alec Radford, Jong Wook Kim, Chris Hallacy,  et al.
-- **Published Date:** 2021-02-26
-- **URL:** http://arxiv.org/abs/2103.00020v1
-
-- **LangChain API Reference:** [langchain_experimental.open_clip](https://api.python.langchain.com/en/latest/experimental_api_reference.html#module-langchain_experimental.open_clip)
-
-**Abstract:** State-of-the-art computer vision systems are trained to predict a fixed set
-of predetermined object categories. This restricted form of supervision limits
-their generality and usability since additional labeled data is needed to
-specify any other visual concept. Learning directly from raw text about images
-is a promising alternative which leverages a much broader source of
-supervision. We demonstrate that the simple pre-training task of predicting
-which caption goes with which image is an efficient and scalable way to learn
-SOTA image representations from scratch on a dataset of 400 million (image,
-text) pairs collected from the internet. After pre-training, natural language
-is used to reference learned visual concepts (or describe new ones) enabling
-zero-shot transfer of the model to downstream tasks. We study the performance
-of this approach by benchmarking on over 30 different existing computer vision
-datasets, spanning tasks such as OCR, action recognition in videos,
-geo-localization, and many types of fine-grained object classification. The
-model transfers non-trivially to most tasks and is often competitive with a
-fully supervised baseline without the need for any dataset specific training.
-For instance, we match the accuracy of the original ResNet-50 on ImageNet
-zero-shot without needing to use any of the 1.28 million training examples it
-was trained on. We release our code and pre-trained model weights at
-https://github.com/OpenAI/CLIP.
-                
-## CTRL: A Conditional Transformer Language Model for Controllable Generation
-
-- **arXiv id:** 1909.05858v2
-- **Title:** CTRL: A Conditional Transformer Language Model for Controllable Generation
-- **Authors:** Nitish Shirish Keskar, Bryan McCann, Lav R. Varshney,  et al.
-- **Published Date:** 2019-09-11
-- **URL:** http://arxiv.org/abs/1909.05858v2
-
-- **LangChain API Reference:** [langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference.html#langchain_community.llms.huggingface_text_gen_inference.HuggingFaceTextGenInference), [langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint)
-
-**Abstract:** Large-scale language models show promising text generation capabilities, but
-users cannot easily control particular aspects of the generated text. We
-release CTRL, a 1.63 billion-parameter conditional transformer language model,
-trained to condition on control codes that govern style, content, and
-task-specific behavior. Control codes were derived from structure that
-naturally co-occurs with raw text, preserving the advantages of unsupervised
-learning while providing more explicit control over text generation. These
-codes also allow CTRL to predict which parts of the training data are most
-likely given a sequence. This provides a potential method for analyzing large
-amounts of data via model-based source attribution. We have released multiple
-full-sized, pretrained versions of CTRL at https://github.com/salesforce/ctrl.
-                
-## Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
-
-- **arXiv id:** 1908.10084v1
-- **Title:** Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
-- **Authors:** Nils Reimers, Iryna Gurevych
-- **Published Date:** 2019-08-27
-- **URL:** http://arxiv.org/abs/1908.10084v1
-- **LangChain Documentation:** [docs/integrations/text_embedding/sentence_transformers](https://python.langchain.com/docs/integrations/text_embedding/sentence_transformers)
-
-
-**Abstract:** BERT (Devlin et al., 2018) and RoBERTa (Liu et al., 2019) has set a new
-state-of-the-art performance on sentence-pair regression tasks like semantic
-textual similarity (STS). However, it requires that both sentences are fed into
-the network, which causes a massive computational overhead: Finding the most
-similar pair in a collection of 10,000 sentences requires about 50 million
-inference computations (~65 hours) with BERT. The construction of BERT makes it
-unsuitable for semantic similarity search as well as for unsupervised tasks
-like clustering.
-  In this publication, we present Sentence-BERT (SBERT), a modification of the
-pretrained BERT network that use siamese and triplet network structures to
-derive semantically meaningful sentence embeddings that can be compared using
-cosine-similarity. This reduces the effort for finding the most similar pair
-from 65 hours with BERT / RoBERTa to about 5 seconds with SBERT, while
-maintaining the accuracy from BERT.
-  We evaluate SBERT and SRoBERTa on common STS tasks and transfer learning
-tasks, where it outperforms other state-of-the-art sentence embeddings methods.
-                

docs/docs/additional_resources/tutorials.mdx

@@ -1,10 +1,14 @@
-# 3rd Party Tutorials
+# Tutorials
+
+## Books and Handbooks
+
+- [Generative AI with LangChain](https://www.amazon.com/Generative-AI-LangChain-language-ChatGPT/dp/1835083463/ref=sr_1_1?crid=1GMOMH0G7GLR&keywords=generative+ai+with+langchain&qid=1703247181&sprefix=%2Caps%2C298&sr=8-1) by [Ben Auffrath](https://www.amazon.com/stores/Ben-Auffarth/author/B08JQKSZ7D?ref=ap_rdr&store_ref=ap_rdr&isDramIntegrated=true&shoppingPortalEnabled=true), ©️ 2023 Packt Publishing
+- [LangChain AI Handbook](https://www.pinecone.io/learn/langchain/) By **James Briggs** and **Francisco Ingham**
+- [LangChain Cheatsheet](https://pub.towardsai.net/langchain-cheatsheet-all-secrets-on-a-single-page-8be26b721cde) by **Ivan Reznikov**
+
 
 ##  Tutorials
 
-### [LangChain v 0.1 by LangChain.ai](https://www.youtube.com/playlist?list=PLfaIDFEXuae0gBSJ9T0w7cu7iJZbH3T31)
-### [Build with Langchain - Advanced by LangChain.ai](https://www.youtube.com/playlist?list=PLfaIDFEXuae06tclDATrMYY0idsTdLg9v)
-### [LangGraph by LangChain.ai](https://www.youtube.com/playlist?list=PLfaIDFEXuae16n2TWUkKq5PgJ0w6Pkwtg)
 ### [by Greg Kamradt](https://www.youtube.com/playlist?list=PLqZXAkvF1bPNQER9mLmDbntNfSpzdDIU5)
 ### [by Sam Witteveen](https://www.youtube.com/playlist?list=PL8motc6AQftk1Bs42EW45kwYbyJ4jOdiZ)
 ### [by James Briggs](https://www.youtube.com/playlist?list=PLIUOU7oqGTLieV9uTIFMm6_4PXg-hlN6F)
@@ -12,6 +16,7 @@
 ### [by Mayo Oshin](https://www.youtube.com/@chatwithdata/search?query=langchain)
 ### [by 1 little Coder](https://www.youtube.com/playlist?list=PLpdmBGJ6ELUK-v0MK-t4wZmVEbxM5xk6L)
 
+
 ## Courses
 
 ### Featured courses on Deeplearning.AI
@@ -24,14 +29,12 @@
 ### Online courses
 
 - [Udemy](https://www.udemy.com/courses/search/?q=langchain)
-- [DataCamp](https://www.datacamp.com/courses/developing-llm-applications-with-langchain)
 - [Pluralsight](https://www.pluralsight.com/search?q=langchain)
 - [Coursera](https://www.coursera.org/search?query=langchain)
 - [Maven](https://maven.com/courses?query=langchain)
 - [Udacity](https://www.udacity.com/catalog/all/any-price/any-school/any-skill/any-difficulty/any-duration/any-type/relevance/page-1?searchValue=langchain)
 - [LinkedIn Learning](https://www.linkedin.com/search/results/learning/?keywords=langchain)
 - [edX](https://www.edx.org/search?q=langchain)
-- [freeCodeCamp](https://www.youtube.com/@freecodecamp/search?query=langchain)
 
 ## Short Tutorials
 
@@ -40,11 +43,7 @@
 - [by Rabbitmetrics](https://youtu.be/aywZrzNaKjs)
 - [by Ivan Reznikov](https://medium.com/@ivanreznikov/langchain-101-course-updated-668f7b41d6cb)
 
-## Books and Handbooks
-
-- [Generative AI with LangChain](https://www.amazon.com/Generative-AI-LangChain-language-ChatGPT/dp/1835083463/ref=sr_1_1?crid=1GMOMH0G7GLR&keywords=generative+ai+with+langchain&qid=1703247181&sprefix=%2Caps%2C298&sr=8-1) by [Ben Auffrath](https://www.amazon.com/stores/Ben-Auffarth/author/B08JQKSZ7D?ref=ap_rdr&store_ref=ap_rdr&isDramIntegrated=true&shoppingPortalEnabled=true), ©️ 2023 Packt Publishing
-- [LangChain AI Handbook](https://www.pinecone.io/learn/langchain/) By **James Briggs** and **Francisco Ingham**
-- [LangChain Cheatsheet](https://pub.towardsai.net/langchain-cheatsheet-all-secrets-on-a-single-page-8be26b721cde) by **Ivan Reznikov**
+## [Documentation: Use cases](/docs/use_cases)
 
 ---------------------
 

docs/docs/changelog/core.mdx

@@ -1,10 +1,27 @@
 # langchain-core
 
-## 0.1.x
+## 0.1.7 (Jan 5, 2024)
+
+#### Deleted
+
+No deletions.
 
 #### Deprecated
 
 - `BaseChatModel` methods `__call__`, `call_as_llm`, `predict`, `predict_messages`. Will be removed in 0.2.0. Use `BaseChatModel.invoke` instead.
 - `BaseChatModel` methods `apredict`, `apredict_messages`. Will be removed in 0.2.0. Use `BaseChatModel.ainvoke` instead.
 - `BaseLLM` methods `__call__, `predict`, `predict_messages`. Will be removed in 0.2.0. Use `BaseLLM.invoke` instead.
-- `BaseLLM` methods `apredict`, `apredict_messages`. Will be removed in 0.2.0. Use `BaseLLM.ainvoke` instead.
+- `BaseLLM` methods `apredict`, `apredict_messages`. Will be removed in 0.2.0. Use `BaseLLM.ainvoke` instead.
+
+#### Fixed
+
+- Restrict recursive URL scraping: [#15559](https://github.com/langchain-ai/langchain/pull/15559)
+
+#### Added
+
+No additions.
+
+#### Beta
+
+- Marked `langchain_core.load.load` and `langchain_core.load.loads` as beta.
+- Marked `langchain_core.beta.runnables.context.ContextGet` and `langchain_core.beta.runnables.context.ContextSet` as beta.

docs/docs/changelog/langchain.mdx

@@ -1,73 +1,16 @@
 # langchain
 
-## 0.2.0
-
-### Deleted
-
-As of release 0.2.0, `langchain` is required to be integration-agnostic. This means that code in `langchain`  should not by default instantiate any specific chat models, llms, embedding models, vectorstores etc; instead, the user will be required to specify those explicitly.
-
-The following functions and classes require an explicit LLM to be passed as an argument:
-
-- `langchain.agents.agent_toolkits.vectorstore.toolkit.VectorStoreToolkit`
-- `langchain.agents.agent_toolkits.vectorstore.toolkit.VectorStoreRouterToolkit`
-- `langchain.chains.openai_functions.get_openapi_chain`
-- `langchain.chains.router.MultiRetrievalQAChain.from_retrievers`
-- `langchain.indexes.VectorStoreIndexWrapper.query`
-- `langchain.indexes.VectorStoreIndexWrapper.query_with_sources`
-- `langchain.indexes.VectorStoreIndexWrapper.aquery_with_sources`
-- `langchain.chains.flare.FlareChain`
-
-The following classes now require passing an explicit Embedding model as an argument:
-
-- `langchain.indexes.VectostoreIndexCreator`
-
-The following code has been removed:
-
-- `langchain.natbot.NatBotChain.from_default` removed in favor of the `from_llm` class method.
-
-### Deprecated
-
-We have two main types of deprecations:
-
-1. Code that was moved from `langchain` into another package (e.g, `langchain-community`)
-
-If you try to import it from `langchain`, the import will keep on working, but will raise a deprecation warning. The warning will provide a replacement import statement.
-
-```python
-python -c "from langchain.document_loaders.markdown import UnstructuredMarkdownLoader"
-
-```
-
-```python
-LangChainDeprecationWarning: Importing UnstructuredMarkdownLoader from langchain.document_loaders is deprecated. Please replace deprecated imports:
-
->> from langchain.document_loaders import UnstructuredMarkdownLoader
-
-with new imports of:
-
->> from langchain_community.document_loaders import UnstructuredMarkdownLoader
-```
-
-We will continue supporting the imports in `langchain` until release 0.4 as long as the relevant package where the code lives is installed. (e.g., as long as `langchain_community` is installed.)
-
-However, we advise for users to not rely on these imports and instead migrate to the new imports. To help with this process, we’re releasing a migration script via the LangChain CLI. See further instructions in migration guide.
-
-1. Code that has better alternatives available and will eventually be removed, so there’s only a single way to do things. (e.g., `predict_messages` method in ChatModels has been deprecated in favor of `invoke`).
-
-Many of these were marked for removal in 0.2. We have bumped the removal to 0.3.
-
-
 ## 0.1.0 (Jan 5, 2024)
 
-### Deleted
+#### Deleted
 
 No deletions.
 
-### Deprecated
+#### Deprecated
 
 Deprecated classes and methods will be removed in 0.2.0
 
-| Deprecated                      | Alternative                       | Reason                                         |
+| Deprecated                | Alternative                       | Reason                                         |
 |---------------------------------|-----------------------------------|------------------------------------------------|
 | ChatVectorDBChain               | ConversationalRetrievalChain      | More general to all retrievers                 |
 | create_ernie_fn_chain           | create_ernie_fn_runnable          | Use LCEL under the hood                        |

docs/docs/concepts.mdx

@@ -1,574 +0,0 @@
-# Conceptual guide
-
-import ThemedImage from '@theme/ThemedImage';
-import useBaseUrl from '@docusaurus/useBaseUrl';
-
-This section contains introductions to key parts of LangChain.
-
-## Architecture
-
-LangChain as a framework consists of a number of packages.
-
-### `langchain-core`
-This package contains base abstractions of different components and ways to compose them together.
-The interfaces for core components like LLMs, vectorstores, retrievers and more are defined here.
-No third party integrations are defined here.
-The dependencies are kept purposefully very lightweight.
-
-### Partner packages
-
-While the long tail of integrations are in `langchain-community`, we split popular integrations into their own packages (e.g. `langchain-openai`, `langchain-anthropic`, etc).
-This was done in order to improve support for these important integrations.
-
-### `langchain`
-
-The main `langchain` package contains chains, agents, and retrieval strategies that make up an application's cognitive architecture.
-These are NOT third party integrations.
-All chains, agents, and retrieval strategies here are NOT specific to any one integration, but rather generic across all integrations.
-
-### `langchain-community`
-
-This package contains third party integrations that are maintained by the LangChain community.
-Key partner packages are separated out (see below).
-This contains all integrations for various components (LLMs, vectorstores, retrievers).
-All dependencies in this package are optional to keep the package as lightweight as possible.
-
-### [`langgraph`](/docs/langgraph)
-
-`langgraph` is an extension of `langchain` aimed at
-building robust and stateful multi-actor applications with LLMs by modeling steps as edges and nodes in a graph.
-
-LangGraph exposes high level interfaces for creating common types of agents, as well as a low-level API for constructing more contr
-
-### [`langserve`](/docs/langserve)
-
-A package to deploy LangChain chains as REST APIs. Makes it easy to get a production ready API up and running.
-
-### [LangSmith](/docs/langsmith)
-
-A developer platform that lets you debug, test, evaluate, and monitor LLM applications.
-
-<ThemedImage
-  alt="Diagram outlining the hierarchical organization of the LangChain framework, displaying the interconnected parts across multiple layers."
-  sources={{
-    light: useBaseUrl('/svg/langchain_stack.svg'),
-    dark: useBaseUrl('/svg/langchain_stack_dark.svg'),
-  }}
-  title="LangChain Framework Overview"
-/>
-
-## LangChain Expression Language (LCEL)
-
-LangChain Expression Language, or LCEL, is a declarative way to chain LangChain components.
-LCEL was designed from day 1 to **support putting prototypes in production, with no code changes**, from the simplest “prompt + LLM” chain to the most complex chains (we’ve seen folks successfully run LCEL chains with 100s of steps in production). To highlight a few of the reasons you might want to use LCEL:
-
-**First-class streaming support**
-When you build your chains with LCEL you get the best possible time-to-first-token (time elapsed until the first chunk of output comes out). For some chains this means eg. we stream tokens straight from an LLM to a streaming output parser, and you get back parsed, incremental chunks of output at the same rate as the LLM provider outputs the raw tokens.
-
-**Async support**
-Any chain built with LCEL can be called both with the synchronous API (eg. in your Jupyter notebook while prototyping) as well as with the asynchronous API (eg. in a [LangServe](/docs/langsmith) server). This enables using the same code for prototypes and in production, with great performance, and the ability to handle many concurrent requests in the same server.
-
-**Optimized parallel execution**
-Whenever your LCEL chains have steps that can be executed in parallel (eg if you fetch documents from multiple retrievers) we automatically do it, both in the sync and the async interfaces, for the smallest possible latency.
-
-**Retries and fallbacks**
-Configure retries and fallbacks for any part of your LCEL chain. This is a great way to make your chains more reliable at scale. We’re currently working on adding streaming support for retries/fallbacks, so you can get the added reliability without any latency cost.
-
-**Access intermediate results**
-For more complex chains it’s often very useful to access the results of intermediate steps even before the final output is produced. This can be used to let end-users know something is happening, or even just to debug your chain. You can stream intermediate results, and it’s available on every [LangServe](/docs/langserve) server.
-
-**Input and output schemas**
-Input and output schemas give every LCEL chain Pydantic and JSONSchema schemas inferred from the structure of your chain. This can be used for validation of inputs and outputs, and is an integral part of LangServe.
-
-[**Seamless LangSmith tracing**](/docs/langsmith)
-As your chains get more and more complex, it becomes increasingly important to understand what exactly is happening at every step.
-With LCEL, **all** steps are automatically logged to [LangSmith](/docs/langsmith/) for maximum observability and debuggability.
-
-[**Seamless LangServe deployment**](/docs/langserve)
-Any chain created with LCEL can be easily deployed using [LangServe](/docs/langserve).
-
-### Runnable interface
-
-To make it as easy as possible to create custom chains, we've implemented a ["Runnable"](https://api.python.langchain.com/en/stable/runnables/langchain_core.runnables.base.Runnable.html#langchain_core.runnables.base.Runnable) protocol. Many LangChain components implement the `Runnable` protocol, including chat models, LLMs, output parsers, retrievers, prompt templates, and more. There are also several useful primitives for working with runnables, which you can read about below.
-
-This is a standard interface, which makes it easy to define custom chains as well as invoke them in a standard way.
-The standard interface includes:
-
-- [`stream`](#stream): stream back chunks of the response
-- [`invoke`](#invoke): call the chain on an input
-- [`batch`](#batch): call the chain on a list of inputs
-
-These also have corresponding async methods that should be used with [asyncio](https://docs.python.org/3/library/asyncio.html) `await` syntax for concurrency:
-
-- `astream`: stream back chunks of the response async
-- `ainvoke`: call the chain on an input async
-- `abatch`: call the chain on a list of inputs async
-- `astream_log`: stream back intermediate steps as they happen, in addition to the final response
-- `astream_events`: **beta** stream events as they happen in the chain (introduced in `langchain-core` 0.1.14)
-
-The **input type** and **output type** varies by component:
-
-| Component | Input Type | Output Type |
-| --- | --- | --- |
-| Prompt | Dictionary | PromptValue |
-| ChatModel | Single string, list of chat messages or a PromptValue | ChatMessage |
-| LLM | Single string, list of chat messages or a PromptValue | String |
-| OutputParser | The output of an LLM or ChatModel | Depends on the parser |
-| Retriever | Single string | List of Documents |
-| Tool | Single string or dictionary, depending on the tool | Depends on the tool |
-
-
-All runnables expose input and output **schemas** to inspect the inputs and outputs:
-- `input_schema`: an input Pydantic model auto-generated from the structure of the Runnable
-- `output_schema`: an output Pydantic model auto-generated from the structure of the Runnable
-
-## Components
-
-LangChain provides standard, extendable interfaces and external integrations for various components useful for building with LLMs.
-Some components LangChain implements, some components we rely on third-party integrations for, and others are a mix.
-
-### Chat models
-
-Language models that use a sequence of messages as inputs and return chat messages as outputs (as opposed to using plain text).
-These are traditionally newer models (older models are generally `LLMs`, see above).
-Chat models support the assignment of distinct roles to conversation messages, helping to distinguish messages from the AI, users, and instructions such as system messages.
-
-Although the underlying models are messages in, message out, the LangChain wrappers also allow these models to take a string as input. This means you can easily use chat models in place of LLMs.
-
-When a string is passed in as input, it is converted to a HumanMessage and then passed to the underlying model.
-
-LangChain does not provide any ChatModels, rather we rely on third party integrations.
-
-We have some standardized parameters when constructing ChatModels:
-- `model`: the name of the model
-
-ChatModels also accept other parameters that are specific to that integration.
-
-:::important
-**Tool Calling** Some chat models have been fine-tuned for tool calling and provide a dedicated API for tool calling.
-Generally, such models are better at tool calling than non-fine-tuned models, and are recommended for use cases that require tool calling.
-Please see the [tool calling section](/docs/concepts/#functiontool-calling) for more information.
-:::
-
-### LLMs
-
-Language models that takes a string as input and returns a string.
-These are traditionally older models (newer models generally are `ChatModels`, see below).
-
-Although the underlying models are string in, string out, the LangChain wrappers also allow these models to take messages as input.
-This makes them interchangeable with ChatModels.
-When messages are passed in as input, they will be formatted into a string under the hood before being passed to the underlying model.
-
-LangChain does not provide any LLMs, rather we rely on third party integrations.
-
-### Messages
-
-Some language models take a list of messages as input and return a message.
-There are a few different types of messages.
-All messages have a `role`, `content`, and `response_metadata` property.
-
-The `role` describes WHO is saying the message.
-LangChain has different message classes for different roles.
-
-The `content` property describes the content of the message.
-This can be a few different things:
-
-- A string (most models deal this type of content)
-- A List of dictionaries (this is used for multi-modal input, where the dictionary contains information about that input type and that input location)
-
-#### HumanMessage
-
-This represents a message from the user.
-
-#### AIMessage
-
-This represents a message from the model. In addition to the `content` property, these messages also have:
-
-**`response_metadata`**
-
-The `response_metadata` property contains additional metadata about the response. The data here is often specific to each model provider.
-This is where information like log-probs and token usage may be stored.
-
-**`tool_calls`**
-
-These represent a decision from an language model to call a tool. They are included as part of an `AIMessage` output.
-They can be accessed from there with the `.tool_calls` property.
-
-This property returns a list of dictionaries. Each dictionary has the following keys:
-
-- `name`: The name of the tool that should be called.
-- `args`: The arguments to that tool.
-- `id`: The id of that tool call.
-
-#### SystemMessage
-
-This represents a system message, which tells the model how to behave. Not every model provider supports this.
-
-#### FunctionMessage
-
-This represents the result of a function call. In addition to `role` and `content`, this message has a `name` parameter which conveys the name of the function that was called to produce this result.
-
-#### ToolMessage
-
-This represents the result of a tool call. This is distinct from a FunctionMessage in order to match OpenAI's `function` and `tool` message types. In addition to `role` and `content`, this message has a `tool_call_id` parameter which conveys the id of the call to the tool that was called to produce this result.
-
-
-### Prompt templates
-Prompt templates help to translate user input and parameters into instructions for a language model.
-This can be used to guide a model's response, helping it understand the context and generate relevant and coherent language-based output.
-
-Prompt Templates take as input a dictionary, where each key represents a variable in the prompt template to fill in.
-
-Prompt Templates output a PromptValue. This PromptValue can be passed to an LLM or a ChatModel, and can also be cast to a string or a list of messages.
-The reason this PromptValue exists is to make it easy to switch between strings and messages.
-
-There are a few different types of prompt templates
-
-#### String PromptTemplates
-
-These prompt templates are used to format a single string, and generally are used for simpler inputs.
-For example, a common way to construct and use a PromptTemplate is as follows:
-
-```python
-from langchain_core.prompts import PromptTemplate
-
-prompt_template = PromptTemplate.from_template("Tell me a joke about {topic}")
-
-prompt_template.invoke({"topic": "cats"})
-```
-
-#### ChatPromptTemplates
-
-These prompt templates are used to format a list of messages. These "templates" consist of a list of templates themselves.
-For example, a common way to construct and use a ChatPromptTemplate is as follows:
-
-```python
-from langchain_core.prompts import ChatPromptTemplate
-
-prompt_template = ChatPromptTemplate.from_messages([
-    ("system", "You are a helpful assistant"),
-    ("user", "Tell me a joke about {topic}")
-])
-
-prompt_template.invoke({"topic": "cats"})
-```
-
-In the above example, this ChatPromptTemplate will construct two messages when called.
-The first is a system message, that has no variables to format.
-The second is a HumanMessage, and will be formatted by the `topic` variable the user passes in.
-
-#### MessagesPlaceholder
-
-This prompt template is responsible for adding a list of messages in a particular place.
-In the above ChatPromptTemplate, we saw how we could format two messages, each one a string.
-But what if we wanted the user to pass in a list of messages that we would slot into a particular spot?
-This is how you use MessagesPlaceholder.
-
-```python
-from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
-from langchain_core.messages import HumanMessage
-
-prompt_template = ChatPromptTemplate.from_messages([
-    ("system", "You are a helpful assistant"),
-    MessagesPlaceholder("msgs")
-])
-
-prompt_template.invoke({"msgs": [HumanMessage(content="hi!")]})
-```
-
-This will produce a list of two messages, the first one being a system message, and the second one being the HumanMessage we passed in.
-If we had passed in 5 messages, then it would have produced 6 messages in total (the system message plus the 5 passed in).
-This is useful for letting a list of messages be slotted into a particular spot.
-
-An alternative way to accomplish the same thing without using the `MessagesPlaceholder` class explicitly is:
-
-```python
-prompt_template = ChatPromptTemplate.from_messages([
-    ("system", "You are a helpful assistant"),
-    ("placeholder", "{msgs}") # <-- This is the changed part
-])
-```
-
-### Example selectors
-One common prompting technique for achieving better performance is to include examples as part of the prompt.
-This gives the language model concrete examples of how it should behave.
-Sometimes these examples are hardcoded into the prompt, but for more advanced situations it may be nice to dynamically select them.
-Example Selectors are classes responsible for selecting and then formatting examples into prompts.
-
-
-### Output parsers
-
-:::note
-
-The information here refers to parsers that take a text output from a model try to parse it into a more structured representation.
-More and more models are supporting function (or tool) calling, which handles this automatically.
-It is recommended to use function/tool calling rather than output parsing.
-See documentation for that [here](/docs/concepts/#function-tool-calling).
-
-:::
-
-Responsible for taking the output of a model and transforming it to a more suitable format for downstream tasks.
-Useful when you are using LLMs to generate structured data, or to normalize output from chat models and LLMs.
-
-LangChain has lots of different types of output parsers. This is a list of output parsers LangChain supports. The table below has various pieces of information:
-
-**Name**: The name of the output parser
-
-**Supports Streaming**: Whether the output parser supports streaming.
-
-**Has Format Instructions**: Whether the output parser has format instructions. This is generally available except when (a) the desired schema is not specified in the prompt but rather in other parameters (like OpenAI function calling), or (b) when the OutputParser wraps another OutputParser.
-
-**Calls LLM**: Whether this output parser itself calls an LLM. This is usually only done by output parsers that attempt to correct misformatted output.
-
-**Input Type**: Expected input type. Most output parsers work on both strings and messages, but some (like OpenAI Functions) need a message with specific kwargs.
-
-**Output Type**: The output type of the object returned by the parser.
-
-**Description**: Our commentary on this output parser and when to use it.
-
-| Name            | Supports Streaming | Has Format Instructions       | Calls LLM | Input Type                       | Output Type          | Description                                                                                                                                                                                                                                              |
-|-----------------|--------------------|-------------------------------|-----------|----------------------------------|----------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
-| [JSON](https://api.python.langchain.com/en/latest/output_parsers/langchain_core.output_parsers.json.JsonOutputParser.html#langchain_core.output_parsers.json.JsonOutputParser)            | ✅                  | ✅                             |           | `str` \| `Message`               | JSON object          | Returns a JSON object as specified. You can specify a Pydantic model and it will return JSON for that model. Probably the most reliable output parser for getting structured data that does NOT use function calling.                                    |
-| [XML](https://api.python.langchain.com/en/latest/output_parsers/langchain_core.output_parsers.xml.XMLOutputParser.html#langchain_core.output_parsers.xml.XMLOutputParser)            | ✅                  | ✅                             |           | `str` \| `Message`                 | `dict`               | Returns a dictionary of tags. Use when XML output is needed. Use with models that are good at writing XML (like Anthropic's).                                                                                                                            |
-| [CSV](https://api.python.langchain.com/en/latest/output_parsers/langchain_core.output_parsers.list.CommaSeparatedListOutputParser.html#langchain_core.output_parsers.list.CommaSeparatedListOutputParser)           | ✅                  | ✅                             |           | `str` \| `Message`                 | `List[str]`          | Returns a list of comma separated values.                                                                                                                                                                                                                |
-| [OutputFixing](https://api.python.langchain.com/en/latest/output_parsers/langchain.output_parsers.fix.OutputFixingParser.html#langchain.output_parsers.fix.OutputFixingParser)    |                    |                               | ✅         | `str` \| `Message`                 |                      | Wraps another output parser. If that output parser errors, then this will pass the error message and the bad output to an LLM and ask it to fix the output.                                                                                              |
-| [RetryWithError](https://api.python.langchain.com/en/latest/output_parsers/langchain.output_parsers.retry.RetryWithErrorOutputParser.html#langchain.output_parsers.retry.RetryWithErrorOutputParser)  |                    |                               | ✅         | `str` \| `Message`                 |                      | Wraps another output parser. If that output parser errors, then this will pass the original inputs, the bad output, and the error message to an LLM and ask it to fix it. Compared to OutputFixingParser, this one also sends the original instructions. |
-| [Pydantic](https://api.python.langchain.com/en/latest/output_parsers/langchain_core.output_parsers.pydantic.PydanticOutputParser.html#langchain_core.output_parsers.pydantic.PydanticOutputParser)        |                    | ✅                             |           | `str` \| `Message`                 | `pydantic.BaseModel` | Takes a user defined Pydantic model and returns data in that format.                                                                                                                                                                                     |
-| [YAML](https://api.python.langchain.com/en/latest/output_parsers/langchain.output_parsers.yaml.YamlOutputParser.html#langchain.output_parsers.yaml.YamlOutputParser)        |                    | ✅                             |           | `str` \| `Message`                 | `pydantic.BaseModel` | Takes a user defined Pydantic model and returns data in that format. Uses YAML to encode it.                                                                                                                                                                                    |
-| [PandasDataFrame](https://api.python.langchain.com/en/latest/output_parsers/langchain.output_parsers.pandas_dataframe.PandasDataFrameOutputParser.html#langchain.output_parsers.pandas_dataframe.PandasDataFrameOutputParser) |                    | ✅                             |           | `str` \| `Message`                 | `dict`               | Useful for doing operations with pandas DataFrames.                                                                                                                                                                                                      |
-| [Enum](https://api.python.langchain.com/en/latest/output_parsers/langchain.output_parsers.enum.EnumOutputParser.html#langchain.output_parsers.enum.EnumOutputParser)            |                    | ✅                             |           | `str` \| `Message`                 | `Enum`               | Parses response into one of the provided enum values.                                                                                                                                                                                                    |
-| [Datetime](https://api.python.langchain.com/en/latest/output_parsers/langchain.output_parsers.datetime.DatetimeOutputParser.html#langchain.output_parsers.datetime.DatetimeOutputParser)        |                    | ✅                             |           | `str` \| `Message`                 | `datetime.datetime`  | Parses response into a datetime string.                                                                                                                                                                                                                  |
-| [Structured](https://api.python.langchain.com/en/latest/output_parsers/langchain.output_parsers.structured.StructuredOutputParser.html#langchain.output_parsers.structured.StructuredOutputParser)      |                    | ✅                             |           | `str` \| `Message`                 | `Dict[str, str]`     | An output parser that returns structured information. It is less powerful than other output parsers since it only allows for fields to be strings. This can be useful when you are working with smaller LLMs.                                            |
-
-### Chat history
-Most LLM applications have a conversational interface.
-An essential component of a conversation is being able to refer to information introduced earlier in the conversation.
-At bare minimum, a conversational system should be able to access some window of past messages directly.
-
-The concept of `ChatHistory` refers to a class in LangChain which can be used to wrap an arbitrary chain.
-This `ChatHistory` will keep track of inputs and outputs of the underlying chain, and append them as messages to a message database
-Future interactions will then load those messages and pass them into the chain as part of the input.
-
-### Documents
-
-A Document object in LangChain contains information about some data. It has two attributes:
-
-- `page_content: str`: The content of this document. Currently is only a string.
-- `metadata: dict`: Arbitrary metadata associated with this document. Can track the document id, file name, etc.
-
-### Document loaders
-
-These classes load Document objects. LangChain has hundreds of integrations with various data sources to load data from: Slack, Notion, Google Drive, etc.
-
-Each DocumentLoader has its own specific parameters, but they can all be invoked in the same way with the `.load` method.
-An example use case is as follows:
-
-```python
-from langchain_community.document_loaders.csv_loader import CSVLoader
-
-loader = CSVLoader(
-    ...  # <-- Integration specific parameters here
-)
-data = loader.load()
-```
-
-### Text splitters
-
-Once you've loaded documents, you'll often want to transform them to better suit your application. The simplest example is you may want to split a long document into smaller chunks that can fit into your model's context window. LangChain has a number of built-in document transformers that make it easy to split, combine, filter, and otherwise manipulate documents.
-
-When you want to deal with long pieces of text, it is necessary to split up that text into chunks. As simple as this sounds, there is a lot of potential complexity here. Ideally, you want to keep the semantically related pieces of text together. What "semantically related" means could depend on the type of text. This notebook showcases several ways to do that.
-
-At a high level, text splitters work as following:
-
-1. Split the text up into small, semantically meaningful chunks (often sentences).
-2. Start combining these small chunks into a larger chunk until you reach a certain size (as measured by some function).
-3. Once you reach that size, make that chunk its own piece of text and then start creating a new chunk of text with some overlap (to keep context between chunks).
-
-That means there are two different axes along which you can customize your text splitter:
-
-1. How the text is split
-2. How the chunk size is measured
-
-### Embedding models
-The Embeddings class is a class designed for interfacing with text embedding models. There are lots of embedding model providers (OpenAI, Cohere, Hugging Face, etc) - this class is designed to provide a standard interface for all of them.
-
-Embeddings create a vector representation of a piece of text. This is useful because it means we can think about text in the vector space, and do things like semantic search where we look for pieces of text that are most similar in the vector space.
-
-The base Embeddings class in LangChain provides two methods: one for embedding documents and one for embedding a query. The former takes as input multiple texts, while the latter takes a single text. The reason for having these as two separate methods is that some embedding providers have different embedding methods for documents (to be searched over) vs queries (the search query itself).
-
-### Vector stores
-One of the most common ways to store and search over unstructured data is to embed it and store the resulting embedding vectors,
-and then at query time to embed the unstructured query and retrieve the embedding vectors that are 'most similar' to the embedded query.
-A vector store takes care of storing embedded data and performing vector search for you.
-
-Vector stores can be converted to the retriever interface by doing:
-
-```python
-vectorstore = MyVectorStore()
-retriever = vectorstore.as_retriever()
-```
-
-### Retrievers
-A retriever is an interface that returns documents given an unstructured query.
-It is more general than a vector store.
-A retriever does not need to be able to store documents, only to return (or retrieve) them.
-Retrievers can be created from vectorstores, but are also broad enough to include [Wikipedia search](/docs/integrations/retrievers/wikipedia/) and [Amazon Kendra](/docs/integrations/retrievers/amazon_kendra_retriever/).
-
-Retrievers accept a string query as input and return a list of Document's as output.
-
-### Tools
-
-Tools are interfaces that an agent, a chain, or a chat model / LLM can use to interact with the world.
-
-A tool consists of the following components:
-
-1. The name of the tool
-2. A description of what the tool does
-3. JSON schema of what the inputs to the tool are
-4. The function to call
-5. Whether the result of a tool should be returned directly to the user (only relevant for agents)
-
-The name, description and JSON schema are provided as context
-to the LLM, allowing the LLM to determine how to use the tool
-appropriately.
-
-Given a list of available tools and a prompt, an LLM can request
-that one or more tools be invoked with appropriate arguments.
-
-Generally, when designing tools to be used by a chat model or LLM, it is important to keep in mind the following:
-
-- Chat models that have been fine-tuned for tool calling will be better at tool calling than non-fine-tuned models.
-- Non fine-tuned models may not be able to use tools at all, especially if the tools are complex or require multiple tool calls.
-- Models will perform better if the tools have well-chosen names, descriptions, and JSON schemas.
-- Simpler tools are generally easier for models to use than more complex tools.
-
-### Toolkits
-
-Toolkits are collections of tools that are designed to be used together for specific tasks. They have convenient loading methods.
-
-All Toolkits expose a `get_tools` method which returns a list of tools.
-You can therefore do:
-
-```python
-# Initialize a toolkit
-toolkit = ExampleTookit(...)
-
-# Get list of tools
-tools = toolkit.get_tools()
-```
-
-### Agents
-
-By themselves, language models can't take actions - they just output text.
-A big use case for LangChain is creating **agents**.
-Agents are systems that use an LLM as a reasoning enginer to determine which actions to take and what the inputs to those actions should be.
-The results of those actions can then be fed back into the agent and it determine whether more actions are needed, or whether it is okay to finish.
-
-[LangGraph](https://github.com/langchain-ai/langgraph) is an extension of LangChain specifically aimed at creating highly controllable and customizable agents.
-Please check out that documentation for a more in depth overview of agent concepts.
-
-There is a legacy agent concept in LangChain that we are moving towards deprecating: `AgentExecutor`.
-AgentExecutor was essentially a runtime for agents.
-It was a great place to get started, however, it was not flexible enough as you started to have more customized agents.
-In order to solve that we built LangGraph to be this flexible, highly-controllable runtime.
-
-If you are still using AgentExecutor, do not fear: we still have a guide on [how to use AgentExecutor](/docs/how_to/agent_executor).
-It is recommended, however, that you start to transition to LangGraph.
-In order to assist in this we have put together a [transition guide on how to do so](/docs/how_to/migrate_agent)
-
-## Techniques
-
-### Function/tool calling
-
-:::info
-We use the term tool calling interchangeably with function calling. Although
-function calling is sometimes meant to refer to invocations of a single function,
-we treat all models as though they can return multiple tool or function calls in
-each message.
-:::
-
-Tool calling allows a model to respond to a given prompt by generating output that
-matches a user-defined schema. While the name implies that the model is performing
-some action, this is actually not the case! The model is coming up with the
-arguments to a tool, and actually running the tool (or not) is up to the user -
-for example, if you want to [extract output matching some schema](/docs/tutorials/extraction)
-from unstructured text, you could give the model an "extraction" tool that takes
-parameters matching the desired schema, then treat the generated output as your final
-result.
-
-A tool call includes a name, arguments dict, and an optional identifier. The
-arguments dict is structured `{argument_name: argument_value}`.
-
-Many LLM providers, including [Anthropic](https://www.anthropic.com/),
-[Cohere](https://cohere.com/), [Google](https://cloud.google.com/vertex-ai),
-[Mistral](https://mistral.ai/), [OpenAI](https://openai.com/), and others,
-support variants of a tool calling feature. These features typically allow requests
-to the LLM to include available tools and their schemas, and for responses to include
-calls to these tools. For instance, given a search engine tool, an LLM might handle a
-query by first issuing a call to the search engine. The system calling the LLM can
-receive the tool call, execute it, and return the output to the LLM to inform its
-response. LangChain includes a suite of [built-in tools](/docs/integrations/tools/)
-and supports several methods for defining your own [custom tools](/docs/how_to/custom_tools).
-
-LangChain provides a standardized interface for tool calling that is consistent across different models.
-
-The standard interface consists of:
-
-* `ChatModel.bind_tools()`: a method for specifying which tools are available for a model to call.
-* `AIMessage.tool_calls`: an attribute on the `AIMessage` returned from the model for accessing the tool calls requested by the model.
-
-There are two main use cases for function/tool calling:
-
-- [How to return structured data from an LLM](/docs/how_to/structured_output/)
-- [How to use a model to call tools](/docs/how_to/tool_calling/)
-
-### Retrieval
-
-LangChain provides several advanced retrieval types. A full list is below, along with the following information:
-
-**Name**: Name of the retrieval algorithm.
-
-**Index Type**: Which index type (if any) this relies on.
-
-**Uses an LLM**: Whether this retrieval method uses an LLM.
-
-**When to Use**: Our commentary on when you should considering using this retrieval method.
-
-**Description**: Description of what this retrieval algorithm is doing.
-
-| Name                      | Index Type                   | Uses an LLM               | When to Use                                                                                                                                   | Description                                                                                                                                                                                                                                                                                      |
-|---------------------------|------------------------------|---------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
-| [Vectorstore](/docs/how_to/vectorstore_retriever/)               | Vectorstore                  | No                        | If you are just getting started and looking for something quick and easy.                                                                     | This is the simplest method and the one that is easiest to get started with. It involves creating embeddings for each piece of text.                                                                                                                                                             |
-| [ParentDocument](/docs/how_to/parent_document_retriever/)            | Vectorstore + Document Store | No                        | If your pages have lots of smaller pieces of distinct information that are best indexed by themselves, but best retrieved all together.       | This involves indexing multiple chunks for each document. Then you find the chunks that are most similar in embedding space, but you retrieve the whole parent document and return that (rather than individual chunks).                                                                         |
-| [Multi Vector](/docs/how_to/multi_vector/)              | Vectorstore + Document Store | Sometimes during indexing | If you are able to extract information from documents that you think is more relevant to index than the text itself.                          | This involves creating multiple vectors for each document. Each vector could be created in a myriad of ways - examples include summaries of the text and hypothetical questions.                                                                                                                 |
-| [Self Query](/docs/how_to/self_query/)               | Vectorstore                  | Yes                       | If users are asking questions that are better answered by fetching documents based on metadata rather than similarity with the text.          | This uses an LLM to transform user input into two things: (1) a string to look up semantically, (2) a metadata filer to go along with it. This is useful because oftentimes questions are about the METADATA of documents (not the content itself).                                              |
-| [Contextual Compression](/docs/how_to/contextual_compression/)    | Any                          | Sometimes                 | If you are finding that your retrieved documents contain too much irrelevant information and are distracting the LLM.                         | This puts a post-processing step on top of another retriever and extracts only the most relevant information from retrieved documents. This can be done with embeddings or an LLM.                                                                                                               |
-| [Time-Weighted Vectorstore](/docs/how_to/time_weighted_vectorstore/) | Vectorstore                  | No                        | If you have timestamps associated with your documents, and you want to retrieve the most recent ones                                          | This fetches documents based on a combination of semantic similarity (as in normal vector retrieval) and recency (looking at timestamps of indexed documents)                                                                                                                                    |
-| [Multi-Query Retriever](/docs/how_to/MultiQueryRetriever/)     | Any                          | Yes                       | If users are asking questions that are complex and require multiple pieces of distinct information to respond                                 | This uses an LLM to generate multiple queries from the original one. This is useful when the original query needs pieces of information about multiple topics to be properly answered. By generating multiple queries, we can then fetch documents for each of them.                             |
-| [Ensemble](/docs/how_to/ensemble_retriever/)                  | Any                          | No                        | If you have multiple retrieval methods and want to try combining them.                                                                        | This fetches documents from multiple retrievers and then combines them.                                                                                                                                                                                                                          |
-
-
-### Text splitting
-
-LangChain offers many different types of `text splitters`.
-These all live in the `langchain-text-splitters` package.
-
-Table columns:
-
-- **Name**: Name of the text splitter
-- **Classes**: Classes that implement this text splitter
-- **Splits On**: How this text splitter splits text
-- **Adds Metadata**: Whether or not this text splitter adds metadata about where each chunk came from.
-- **Description**: Description of the splitter, including recommendation on when to use it.
-
-
-| Name     | Classes                                                                                                                                                                                                             | Splits On                                                   | Adds Metadata | Description                                                                                                                                                                                                                                                                  |
-|----------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------|---------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
-| Recursive | [RecursiveCharacterTextSplitter](/docs/how_to/recursive_text_splitter/), [RecursiveJsonSplitter](/docs/how_to/recursive_json_splitter/) | A list of user defined characters     |               | Recursively splits text. This splitting is trying to keep related pieces of text next to each other. This is the `recommended way` to start splitting text.                                                                                                                    |
-| HTML      | [HTMLHeaderTextSplitter](/docs/how_to/HTML_header_metadata_splitter/), [HTMLSectionSplitter](/docs/how_to/HTML_section_aware_splitter/)          | HTML specific characters                                                                                                 | ✅             | Splits text based on HTML-specific characters. Notably, this adds in relevant information about where that chunk came from (based on the HTML)                                                                                                                               |
-| Markdown  | [MarkdownHeaderTextSplitter](/docs/how_to/markdown_header_metadata_splitter/),                                                                                                           | Markdown specific characters                                                                                    | ✅             | Splits text based on Markdown-specific characters. Notably, this adds in relevant information about where that chunk came from (based on the Markdown)                                                                                                                       |
-| Code      | [many languages](/docs/how_to/code_splitter/)                                                                                                                                 | Code (Python, JS) specific characters                                                                           |               | Splits text based on characters specific to coding languages. 15 different languages are available to choose from.                                                                                                                                                           |
-| Token    | [many classes](/docs/how_to/split_by_token/)                                                                                                                                  | Tokens                                                                                                          |               | Splits text on tokens. There exist a few different ways to measure tokens.                                                                                                                                                                                                   |
-| Character  | [CharacterTextSplitter](/docs/how_to/character_text_splitter/)                                                                                                                | A user defined character                                                                                        |               | Splits text based on a user defined character. One of the simpler methods.                                                                                                                                                                                                   |
-| Semantic Chunker (Experimental) | [SemanticChunker](/docs/how_to/semantic-chunker/)                                                                                                                             | Sentences                                                                                                       |               | First splits on sentences. Then combines ones next to each other if they are semantically similar enough. Taken from [Greg Kamradt](https://github.com/FullStackRetrieval-com/RetrievalTutorials/blob/main/tutorials/LevelsOfTextSplitting/5_Levels_Of_Text_Splitting.ipynb) |
-| Integration: AI21 Semantic | [AI21SemanticTextSplitter](/docs/integrations/document_transformers/ai21_semantic_text_splitter/)                                                                                                                    |    ✅           | Identifies distinct topics that form coherent pieces of text and splits along those.                                                                                                                                                                                         |

docs/docs/contributing/documentation/style_guide.mdx

@@ -16,15 +16,15 @@ LangChain's documentation aspires to follow the [Diataxis framework](https://dia
 Under this framework, all documentation falls under one of four categories:
 
 - **Tutorials**: Lessons that take the reader by the hand through a series of conceptual steps to complete a project.
-  - An example of this is our [LCEL streaming guide](/docs/how_to/streaming).
-  - Our guides on [custom components](/docs/how_to/custom_chat_model) is another one.
+  - An example of this is our [LCEL streaming guide](/docs/expression_language/streaming).
+  - Our guides on [custom components](/docs/modules/model_io/chat/custom_chat_model) is another one.
 - **How-to guides**: Guides that take the reader through the steps required to solve a real-world problem.
-  - The clearest examples of this are our [Use case](/docs/how_to#use-cases) quickstart pages.
+  - The clearest examples of this are our [Use case](/docs/use_cases/) quickstart pages.
 - **Reference**: Technical descriptions of the machinery and how to operate it.
-  - Our [Runnable interface](/docs/concepts#interface) page is an example of this.
+  - Our [Runnable interface](/docs/expression_language/interface) page is an example of this.
   - The [API reference pages](https://api.python.langchain.com/) are another.
 - **Explanation**: Explanations that clarify and illuminate a particular topic.
-  - The [LCEL primitives pages](/docs/how_to/sequence) are an example of this.
+  - The [LCEL primitives pages](/docs/expression_language/primitives/sequence) are an example of this.
 
 Each category serves a distinct purpose and requires a specific approach to writing and structuring the content.
 
@@ -35,14 +35,14 @@ when contributing new documentation:
 
 ### Getting started
 
-The [getting started section](/docs/introduction) includes a high-level introduction to LangChain, a quickstart that
+The [getting started section](/docs/get_started/introduction) includes a high-level introduction to LangChain, a quickstart that
 tours LangChain's various features, and logistical instructions around installation and project setup.
 
 It contains elements of **How-to guides** and **Explanations**.
 
 ### Use cases
 
-[Use cases](/docs/how_to#use-cases) are guides that are meant to show how to use LangChain to accomplish a specific task (RAG, information extraction, etc.).
+[Use cases](/docs/use_cases/) are guides that are meant to show how to use LangChain to accomplish a specific task (RAG, information extraction, etc.).
 The quickstarts should be good entrypoints for first-time LangChain developers who prefer to learn by getting something practical prototyped,
 then taking the pieces apart retrospectively. These should mirror what LangChain is good at.
 
@@ -55,7 +55,7 @@ The below sections are listed roughly in order of increasing level of abstractio
 
 ### Expression Language
 
-[LangChain Expression Language (LCEL)](/docs/concepts#langchain-expression-language) is the fundamental way that most LangChain components fit together, and this section is designed to teach
+[LangChain Expression Language (LCEL)](/docs/expression_language/) is the fundamental way that most LangChain components fit together, and this section is designed to teach
 developers how to use it to build with LangChain's primitives effectively.
 
 This section should contains **Tutorials** that teach how to stream and use LCEL primitives for more abstract tasks, **Explanations** of specific behaviors,
@@ -63,7 +63,7 @@ and some **References** for how to use different methods in the Runnable interfa
 
 ### Components
 
-The [components section](/docs/concepts) covers concepts one level of abstraction higher than LCEL.
+The [components section](/docs/modules) covers concepts one level of abstraction higher than LCEL.
 Abstract base classes like `BaseChatModel` and `BaseRetriever` should be covered here, as well as core implementations of these base classes,
 such as `ChatPromptTemplate` and `RecursiveCharacterTextSplitter`. Customization guides belong here too.
 
@@ -88,7 +88,7 @@ Concepts covered in `Integrations` should generally exist in `langchain_communit
 
 ### Guides and Ecosystem
 
-The [Guides](/docs/tutorials) and [Ecosystem](/docs/langsmith/) sections should contain guides that address higher-level problems than the sections above.
+The [Guides](/docs/guides) and [Ecosystem](/docs/langsmith/) sections should contain guides that address higher-level problems than the sections above.
 This includes, but is not limited to, considerations around productionization and development workflows.
 
 These should contain mostly **How-to guides**, **Explanations**, and **Tutorials**.
@@ -102,7 +102,7 @@ LangChain's API references. Should act as **References** (as the name implies) w
 We have set up our docs to assist a new developer to LangChain. Let's walk through the intended path:
 
 - The developer lands on https://python.langchain.com, and reads through the introduction and the diagram.
-- If they are just curious, they may be drawn to the [Quickstart](/docs/tutorials/llm_chain) to get a high-level tour of what LangChain contains.
+- If they are just curious, they may be drawn to the [Quickstart](/docs/get_started/quickstart) to get a high-level tour of what LangChain contains.
 - If they have a specific task in mind that they want to accomplish, they will be drawn to the Use-Case section. The use-case should provide a good, concrete hook that shows the value LangChain can provide them and be a good entrypoint to the framework.
 - They can then move to learn more about the fundamentals of LangChain through the Expression Language sections.
 - Next, they can learn about LangChain's various components and integrations.

docs/docs/contributing/integrations.mdx

@@ -190,9 +190,12 @@ Maintainer steps (Contributors should **not** do these):
 
 ## Partner package in external repo
 
-Partner packages in external repos must be coordinated between the LangChain team and
-the partner organization to ensure that they are maintained and updated.
+If you are creating a partner package in an external repo, you should follow the same steps as above, 
+but you will need to set up your own CI/CD and package management.
 
-If you're interested in creating a partner package in an external repo, please start
-with one in the LangChain repo, and then reach out to the LangChain team to discuss
-how to move it to an external repo.
+Name your package as `langchain-{partner}-{integration}`.
+
+Still, you have to create the `libs/partners/{partner}-{integration}` folder in the `LangChain` monorepo
+and add a `README.md` file with a link to the external repo. 
+See this [example](https://github.com/langchain-ai/langchain/tree/master/libs/partners/google-genai).
+This allows keeping track of all the partner packages in the `LangChain` documentation.

docs/docs/contributing/repo_structure.mdx

@@ -6,7 +6,7 @@ sidebar_position: 0.5
 If you plan on contributing to LangChain code or documentation, it can be useful
 to understand the high level structure of the repository.
 
-LangChain is organized as a [monorepo](https://en.wikipedia.org/wiki/Monorepo) that contains multiple packages.
+LangChain is organized as a [monorep](https://en.wikipedia.org/wiki/Monorepo) that contains multiple packages.
 
 Here's the structure visualized as a tree:
 

docs/docs/expression_language/cookbook/code_writing.ipynb

@@ -0,0 +1,139 @@
+{
+ "cells": [
+  {
+   "cell_type": "raw",
+   "id": "1e997ab7",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "sidebar_class_name: hidden\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f09fd305",
+   "metadata": {},
+   "source": [
+    "# Code writing\n",
+    "\n",
+    "Example of how to use LCEL to write Python code."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0653c7c7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install --upgrade --quiet  langchain-core langchain-experimental langchain-openai"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "bd7c259a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.output_parsers import StrOutputParser\n",
+    "from langchain_core.prompts import (\n",
+    "    ChatPromptTemplate,\n",
+    ")\n",
+    "from langchain_experimental.utilities import PythonREPL\n",
+    "from langchain_openai import ChatOpenAI"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "73795d2d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "template = \"\"\"Write some python code to solve the user's problem. \n",
+    "\n",
+    "Return only python code in Markdown format, e.g.:\n",
+    "\n",
+    "```python\n",
+    "....\n",
+    "```\"\"\"\n",
+    "prompt = ChatPromptTemplate.from_messages([(\"system\", template), (\"human\", \"{input}\")])\n",
+    "\n",
+    "model = ChatOpenAI()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "42859e8a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def _sanitize_output(text: str):\n",
+    "    _, after = text.split(\"```python\")\n",
+    "    return after.split(\"```\")[0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "5ded1a86",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chain = prompt | model | StrOutputParser() | _sanitize_output | PythonREPL().run"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "208c2b75",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Python REPL can execute arbitrary code. Use with caution.\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'4\\n'"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain.invoke({\"input\": \"whats 2 plus 2\"})"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/expression_language/cookbook/multiple_chains.ipynb

@@ -0,0 +1,267 @@
+{
+ "cells": [
+  {
+   "cell_type": "raw",
+   "id": "877102d1-02ea-4fa3-8ec7-a08e242b95b3",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "sidebar_position: 2\n",
+    "title: Multiple chains\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0f2bf8d3",
+   "metadata": {},
+   "source": [
+    "Runnables can easily be used to string together multiple Chains"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "id": "0f316b5c",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install --upgrade --quiet  langchain langchain-openai"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "d65d4e9e",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'El país donde se encuentra la ciudad de Honolulu, donde nació Barack Obama, el 44º Presidente de los Estados Unidos, es Estados Unidos. Honolulu se encuentra en la isla de Oahu, en el estado de Hawái.'"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from operator import itemgetter\n",
+    "\n",
+    "from langchain_core.output_parsers import StrOutputParser\n",
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "prompt1 = ChatPromptTemplate.from_template(\"what is the city {person} is from?\")\n",
+    "prompt2 = ChatPromptTemplate.from_template(\n",
+    "    \"what country is the city {city} in? respond in {language}\"\n",
+    ")\n",
+    "\n",
+    "model = ChatOpenAI()\n",
+    "\n",
+    "chain1 = prompt1 | model | StrOutputParser()\n",
+    "\n",
+    "chain2 = (\n",
+    "    {\"city\": chain1, \"language\": itemgetter(\"language\")}\n",
+    "    | prompt2\n",
+    "    | model\n",
+    "    | StrOutputParser()\n",
+    ")\n",
+    "\n",
+    "chain2.invoke({\"person\": \"obama\", \"language\": \"spanish\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "878f8176",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.runnables import RunnablePassthrough\n",
+    "\n",
+    "prompt1 = ChatPromptTemplate.from_template(\n",
+    "    \"generate a {attribute} color. Return the name of the color and nothing else:\"\n",
+    ")\n",
+    "prompt2 = ChatPromptTemplate.from_template(\n",
+    "    \"what is a fruit of color: {color}. Return the name of the fruit and nothing else:\"\n",
+    ")\n",
+    "prompt3 = ChatPromptTemplate.from_template(\n",
+    "    \"what is a country with a flag that has the color: {color}. Return the name of the country and nothing else:\"\n",
+    ")\n",
+    "prompt4 = ChatPromptTemplate.from_template(\n",
+    "    \"What is the color of {fruit} and the flag of {country}?\"\n",
+    ")\n",
+    "\n",
+    "model_parser = model | StrOutputParser()\n",
+    "\n",
+    "color_generator = (\n",
+    "    {\"attribute\": RunnablePassthrough()} | prompt1 | {\"color\": model_parser}\n",
+    ")\n",
+    "color_to_fruit = prompt2 | model_parser\n",
+    "color_to_country = prompt3 | model_parser\n",
+    "question_generator = (\n",
+    "    color_generator | {\"fruit\": color_to_fruit, \"country\": color_to_country} | prompt4\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "d621a870",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "ChatPromptValue(messages=[HumanMessage(content='What is the color of strawberry and the flag of China?', additional_kwargs={}, example=False)])"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "question_generator.invoke(\"warm\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "b4a9812b-bead-4fd9-ae27-0b8be57e5dc1",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='The color of an apple is typically red or green. The flag of China is predominantly red with a large yellow star in the upper left corner and four smaller yellow stars surrounding it.', additional_kwargs={}, example=False)"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "prompt = question_generator.invoke(\"warm\")\n",
+    "model.invoke(prompt)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6d75a313-f1c8-4e94-9a17-24e0bf4a2bdc",
+   "metadata": {},
+   "source": [
+    "### Branching and Merging\n",
+    "\n",
+    "You may want the output of one component to be processed by 2 or more other components. [RunnableParallels](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.base.RunnableParallel.html#langchain_core.runnables.base.RunnableParallel) let you split or fork the chain so multiple components can process the input in parallel. Later, other components can join or merge the results to synthesize a final response. This type of chain creates a computation graph that looks like the following:\n",
+    "\n",
+    "```text\n",
+    "     Input\n",
+    "      / \\\n",
+    "     /   \\\n",
+    " Branch1 Branch2\n",
+    "     \\   /\n",
+    "      \\ /\n",
+    "      Combine\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "247fa0bd-4596-4063-8cb3-1d7fc119d982",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "planner = (\n",
+    "    ChatPromptTemplate.from_template(\"Generate an argument about: {input}\")\n",
+    "    | ChatOpenAI()\n",
+    "    | StrOutputParser()\n",
+    "    | {\"base_response\": RunnablePassthrough()}\n",
+    ")\n",
+    "\n",
+    "arguments_for = (\n",
+    "    ChatPromptTemplate.from_template(\n",
+    "        \"List the pros or positive aspects of {base_response}\"\n",
+    "    )\n",
+    "    | ChatOpenAI()\n",
+    "    | StrOutputParser()\n",
+    ")\n",
+    "arguments_against = (\n",
+    "    ChatPromptTemplate.from_template(\n",
+    "        \"List the cons or negative aspects of {base_response}\"\n",
+    "    )\n",
+    "    | ChatOpenAI()\n",
+    "    | StrOutputParser()\n",
+    ")\n",
+    "\n",
+    "final_responder = (\n",
+    "    ChatPromptTemplate.from_messages(\n",
+    "        [\n",
+    "            (\"ai\", \"{original_response}\"),\n",
+    "            (\"human\", \"Pros:\\n{results_1}\\n\\nCons:\\n{results_2}\"),\n",
+    "            (\"system\", \"Generate a final response given the critique\"),\n",
+    "        ]\n",
+    "    )\n",
+    "    | ChatOpenAI()\n",
+    "    | StrOutputParser()\n",
+    ")\n",
+    "\n",
+    "chain = (\n",
+    "    planner\n",
+    "    | {\n",
+    "        \"results_1\": arguments_for,\n",
+    "        \"results_2\": arguments_against,\n",
+    "        \"original_response\": itemgetter(\"base_response\"),\n",
+    "    }\n",
+    "    | final_responder\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "2564f310-0674-4bb1-9c4e-d7848ca73511",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'While Scrum has its potential cons and challenges, many organizations have successfully embraced and implemented this project management framework to great effect. The cons mentioned above can be mitigated or overcome with proper training, support, and a commitment to continuous improvement. It is also important to note that not all cons may be applicable to every organization or project.\\n\\nFor example, while Scrum may be complex initially, with proper training and guidance, teams can quickly grasp the concepts and practices. The lack of predictability can be mitigated by implementing techniques such as velocity tracking and release planning. The limited documentation can be addressed by maintaining a balance between lightweight documentation and clear communication among team members. The dependency on team collaboration can be improved through effective communication channels and regular team-building activities.\\n\\nScrum can be scaled and adapted to larger projects by using frameworks like Scrum of Scrums or LeSS (Large Scale Scrum). Concerns about speed versus quality can be addressed by incorporating quality assurance practices, such as continuous integration and automated testing, into the Scrum process. Scope creep can be managed by having a well-defined and prioritized product backlog, and a strong product owner can be developed through training and mentorship.\\n\\nResistance to change can be overcome by providing proper education and communication to stakeholders and involving them in the decision-making process. Ultimately, the cons of Scrum can be seen as opportunities for growth and improvement, and with the right mindset and support, they can be effectively managed.\\n\\nIn conclusion, while Scrum may have its challenges and potential cons, the benefits and advantages it offers in terms of collaboration, flexibility, adaptability, transparency, and customer satisfaction make it a widely adopted and successful project management framework. With proper implementation and continuous improvement, organizations can leverage Scrum to drive innovation, efficiency, and project success.'"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain.invoke({\"input\": \"scrum\"})"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "poetry-venv",
+   "language": "python",
+   "name": "poetry-venv"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/expression_language/cookbook/prompt_llm_parser.ipynb

@@ -0,0 +1,436 @@
+{
+ "cells": [
+  {
+   "cell_type": "raw",
+   "id": "abf7263d-3a62-4016-b5d5-b157f92f2070",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "sidebar_position: 0\n",
+    "title: Prompt + LLM\n",
+    "---\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9a434f2b-9405-468c-9dfd-254d456b57a6",
+   "metadata": {},
+   "source": [
+    "The most common and valuable composition is taking:\n",
+    "\n",
+    "``PromptTemplate`` / ``ChatPromptTemplate`` -> ``LLM`` / ``ChatModel`` -> ``OutputParser``\n",
+    "\n",
+    "Almost any other chains you build will use this building block."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "93aa2c87",
+   "metadata": {},
+   "source": [
+    "## PromptTemplate + LLM\n",
+    "\n",
+    "The simplest composition is just combining a prompt and model to create a chain that takes user input, adds it to a prompt, passes it to a model, and returns the raw model output.\n",
+    "\n",
+    "Note, you can mix and match PromptTemplate/ChatPromptTemplates and LLMs/ChatModels as you like here."
+   ]
+  },
+  {
+   "cell_type": "raw",
+   "id": "ef79a54b",
+   "metadata": {},
+   "source": [
+    "%pip install --upgrade --quiet  langchain langchain-openai"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "466b65b3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "prompt = ChatPromptTemplate.from_template(\"tell me a joke about {foo}\")\n",
+    "model = ChatOpenAI()\n",
+    "chain = prompt | model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "e3d0a6cd",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=\"Why don't bears wear shoes?\\n\\nBecause they have bear feet!\", additional_kwargs={}, example=False)"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain.invoke({\"foo\": \"bears\"})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7eb9ef50",
+   "metadata": {},
+   "source": [
+    "Often times we want to attach kwargs that'll be passed to each model call. Here are a few examples of that:"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0b1d8f88",
+   "metadata": {},
+   "source": [
+    "### Attaching Stop Sequences"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "562a06bf",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chain = prompt | model.bind(stop=[\"\\n\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "43f5d04c",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='Why did the bear never wear shoes?', additional_kwargs={}, example=False)"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain.invoke({\"foo\": \"bears\"})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f3eaf88a",
+   "metadata": {},
+   "source": [
+    "### Attaching Function Call information"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "f94b71b2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "functions = [\n",
+    "    {\n",
+    "        \"name\": \"joke\",\n",
+    "        \"description\": \"A joke\",\n",
+    "        \"parameters\": {\n",
+    "            \"type\": \"object\",\n",
+    "            \"properties\": {\n",
+    "                \"setup\": {\"type\": \"string\", \"description\": \"The setup for the joke\"},\n",
+    "                \"punchline\": {\n",
+    "                    \"type\": \"string\",\n",
+    "                    \"description\": \"The punchline for the joke\",\n",
+    "                },\n",
+    "            },\n",
+    "            \"required\": [\"setup\", \"punchline\"],\n",
+    "        },\n",
+    "    }\n",
+    "]\n",
+    "chain = prompt | model.bind(function_call={\"name\": \"joke\"}, functions=functions)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "decf7710",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='', additional_kwargs={'function_call': {'name': 'joke', 'arguments': '{\\n  \"setup\": \"Why don\\'t bears wear shoes?\",\\n  \"punchline\": \"Because they have bear feet!\"\\n}'}}, example=False)"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain.invoke({\"foo\": \"bears\"}, config={})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9098c5ed",
+   "metadata": {},
+   "source": [
+    "## PromptTemplate + LLM + OutputParser\n",
+    "\n",
+    "We can also add in an output parser to easily transform the raw LLM/ChatModel output into a more workable format"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "cc194c78",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.output_parsers import StrOutputParser\n",
+    "\n",
+    "chain = prompt | model | StrOutputParser()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "77acf448",
+   "metadata": {},
+   "source": [
+    "Notice that this now returns a string - a much more workable format for downstream tasks"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "e3d69a18",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "\"Why don't bears wear shoes?\\n\\nBecause they have bear feet!\""
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain.invoke({\"foo\": \"bears\"})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c01864e5",
+   "metadata": {},
+   "source": [
+    "### Functions Output Parser\n",
+    "\n",
+    "When you specify the function to return, you may just want to parse that directly"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "ad0dd88e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.output_parsers.openai_functions import JsonOutputFunctionsParser\n",
+    "\n",
+    "chain = (\n",
+    "    prompt\n",
+    "    | model.bind(function_call={\"name\": \"joke\"}, functions=functions)\n",
+    "    | JsonOutputFunctionsParser()\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "1e7aa8eb",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'setup': \"Why don't bears like fast food?\",\n",
+       " 'punchline': \"Because they can't catch it!\"}"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain.invoke({\"foo\": \"bears\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "d4aa1a01",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.output_parsers.openai_functions import JsonKeyOutputFunctionsParser\n",
+    "\n",
+    "chain = (\n",
+    "    prompt\n",
+    "    | model.bind(function_call={\"name\": \"joke\"}, functions=functions)\n",
+    "    | JsonKeyOutputFunctionsParser(key_name=\"setup\")\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "8b6df9ba",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "\"Why don't bears wear shoes?\""
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain.invoke({\"foo\": \"bears\"})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "023fbccb-ef7d-489e-a9ba-f98e17283d51",
+   "metadata": {},
+   "source": [
+    "## Simplifying input\n",
+    "\n",
+    "To make invocation even simpler, we can add a `RunnableParallel` to take care of creating the prompt input dict for us:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "9601c0f0-71f9-4bd4-a672-7bd04084b018",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.runnables import RunnableParallel, RunnablePassthrough\n",
+    "\n",
+    "map_ = RunnableParallel(foo=RunnablePassthrough())\n",
+    "chain = (\n",
+    "    map_\n",
+    "    | prompt\n",
+    "    | model.bind(function_call={\"name\": \"joke\"}, functions=functions)\n",
+    "    | JsonKeyOutputFunctionsParser(key_name=\"setup\")\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "7ec4f154-fda5-4847-9220-41aa902fdc33",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "\"Why don't bears wear shoes?\""
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain.invoke(\"bears\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "def00bfe-0f83-4805-8c8f-8a53f99fa8ea",
+   "metadata": {},
+   "source": [
+    "Since we're composing our map with another Runnable, we can even use some syntactic sugar and just use a dict:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "7bf3846a-02ee-41a3-ba1b-a708827d4f3a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chain = (\n",
+    "    {\"foo\": RunnablePassthrough()}\n",
+    "    | prompt\n",
+    "    | model.bind(function_call={\"name\": \"joke\"}, functions=functions)\n",
+    "    | JsonKeyOutputFunctionsParser(key_name=\"setup\")\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "e566d6a1-538d-4cb5-a210-a63e082e4c74",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "\"Why don't bears like fast food?\""
+      ]
+     },
+     "execution_count": 22,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain.invoke(\"bears\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/expression_language/get_started.ipynb

@@ -0,0 +1,537 @@
+{
+ "cells": [
+  {
+   "cell_type": "raw",
+   "id": "366a0e68-fd67-4fe5-a292-5c33733339ea",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "sidebar_position: 0\n",
+    "title: Get started\n",
+    "keywords: [chain.invoke]\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "befa7fd1",
+   "metadata": {},
+   "source": [
+    "LCEL makes it easy to build complex chains from basic components, and supports out of the box functionality such as streaming, parallelism, and logging."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9a9acd2e",
+   "metadata": {},
+   "source": [
+    "## Basic example: prompt + model + output parser\n",
+    "\n",
+    "The most basic and common use case is chaining a prompt template and a model together. To see how this works, let's create a chain that takes a topic and generates a joke:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "278b0027",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install --upgrade --quiet  langchain-core langchain-community langchain-openai"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c3d54f72",
+   "metadata": {},
+   "source": [
+    "```{=mdx}\n",
+    "import ChatModelTabs from \"@theme/ChatModelTabs\";\n",
+    "\n",
+    "<ChatModelTabs openaiParams={`model=\"gpt-4\"`} />\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f9eed8e8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# | output: false\n",
+    "# | echo: false\n",
+    "\n",
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "model = ChatOpenAI(model=\"gpt-4\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "466b65b3",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "\"Why don't ice creams ever get invited to parties?\\n\\nBecause they always drip when things heat up!\""
+      ]
+     },
+     "execution_count": 1,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain_core.output_parsers import StrOutputParser\n",
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "\n",
+    "prompt = ChatPromptTemplate.from_template(\"tell me a short joke about {topic}\")\n",
+    "output_parser = StrOutputParser()\n",
+    "\n",
+    "chain = prompt | model | output_parser\n",
+    "\n",
+    "chain.invoke({\"topic\": \"ice cream\"})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "81c502c5-85ee-4f36-aaf4-d6e350b7792f",
+   "metadata": {},
+   "source": [
+    "Notice this line of the code, where we piece together these different components into a single chain using LCEL:\n",
+    "\n",
+    "```\n",
+    "chain = prompt | model | output_parser\n",
+    "```\n",
+    "\n",
+    "The `|` symbol is similar to a [unix pipe operator](https://en.wikipedia.org/wiki/Pipeline_(Unix)), which chains together the different components, feeding the output from one component as input into the next component. \n",
+    "\n",
+    "In this chain the user input is passed to the prompt template, then the prompt template output is passed to the model, then the model output is passed to the output parser. Let's take a look at each component individually to really understand what's going on."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "aa1b77fa",
+   "metadata": {},
+   "source": [
+    "### 1. Prompt\n",
+    "\n",
+    "`prompt` is a `BasePromptTemplate`, which means it takes in a dictionary of template variables and produces a `PromptValue`. A `PromptValue` is a wrapper around a completed prompt that can be passed to either an `LLM` (which takes a string as input) or `ChatModel` (which takes a sequence of messages as input). It can work with either language model type because it defines logic both for producing `BaseMessage`s and for producing a string."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "b8656990",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "ChatPromptValue(messages=[HumanMessage(content='tell me a short joke about ice cream')])"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "prompt_value = prompt.invoke({\"topic\": \"ice cream\"})\n",
+    "prompt_value"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "e6034488",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[HumanMessage(content='tell me a short joke about ice cream')]"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "prompt_value.to_messages()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "60565463",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Human: tell me a short joke about ice cream'"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "prompt_value.to_string()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "577f0f76",
+   "metadata": {},
+   "source": [
+    "### 2. Model\n",
+    "\n",
+    "The `PromptValue` is then passed to `model`. In this case our `model` is a `ChatModel`, meaning it will output a `BaseMessage`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "33cf5f72",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=\"Why don't ice creams ever get invited to parties?\\n\\nBecause they always bring a melt down!\")"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "message = model.invoke(prompt_value)\n",
+    "message"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "327e7db8",
+   "metadata": {},
+   "source": [
+    "If our `model` was an `LLM`, it would output a string."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "8feb05da",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'\\n\\nRobot: Why did the ice cream truck break down? Because it had a meltdown!'"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain_openai import OpenAI\n",
+    "\n",
+    "llm = OpenAI(model=\"gpt-3.5-turbo-instruct\")\n",
+    "llm.invoke(prompt_value)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "91847478",
+   "metadata": {},
+   "source": [
+    "### 3. Output parser\n",
+    "\n",
+    "And lastly we pass our `model` output to the `output_parser`, which is a `BaseOutputParser` meaning it takes either a string or a \n",
+    "`BaseMessage` as input. The specific `StrOutputParser` simply converts any input into a string."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "533e59a8",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "\"Why did the ice cream go to therapy? \\n\\nBecause it had too many toppings and couldn't find its cone-fidence!\""
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "output_parser.invoke(message)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9851e842",
+   "metadata": {},
+   "source": [
+    "### 4. Entire Pipeline\n",
+    "\n",
+    "To follow the steps along:\n",
+    "\n",
+    "1. We pass in user input on the desired topic as `{\"topic\": \"ice cream\"}`\n",
+    "2. The `prompt` component takes the user input, which is then used to construct a PromptValue after using the `topic` to construct the prompt. \n",
+    "3. The `model` component takes the generated prompt, and passes into the OpenAI LLM model for evaluation. The generated output from the model is a `ChatMessage` object. \n",
+    "4. Finally, the `output_parser` component takes in a `ChatMessage`, and transforms this into a Python string, which is returned from the invoke method. \n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c4873109",
+   "metadata": {},
+   "source": [
+    "```mermaid\n",
+    "graph LR\n",
+    "    A(Input: topic=ice cream) --> |Dict| B(PromptTemplate)\n",
+    "    B -->|PromptValue| C(ChatModel)    \n",
+    "    C -->|ChatMessage| D(StrOutputParser)\n",
+    "    D --> |String| F(Result)\n",
+    "```\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "fe63534d",
+   "metadata": {},
+   "source": [
+    ":::info\n",
+    "\n",
+    "Note that if you’re curious about the output of any components, you can always test out a smaller version of the chain such as `prompt` or `prompt | model` to see the intermediate results:\n",
+    "\n",
+    ":::"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "11089b6f-23f8-474f-97ec-8cae8d0ca6d4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "input = {\"topic\": \"ice cream\"}\n",
+    "\n",
+    "prompt.invoke(input)\n",
+    "# > ChatPromptValue(messages=[HumanMessage(content='tell me a short joke about ice cream')])\n",
+    "\n",
+    "(prompt | model).invoke(input)\n",
+    "# > AIMessage(content=\"Why did the ice cream go to therapy?\\nBecause it had too many toppings and couldn't cone-trol itself!\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "cc7d3b9d-e400-4c9b-9188-f29dac73e6bb",
+   "metadata": {},
+   "source": [
+    "## RAG Search Example\n",
+    "\n",
+    "For our next example, we want to run a retrieval-augmented generation chain to add some context when responding to questions."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b8fe8eb4",
+   "metadata": {},
+   "source": [
+    "```{=mdx}\n",
+    "<ChatModelTabs />\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "662426e8-4316-41dc-8312-9b58edc7e0c9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Requires:\n",
+    "# pip install langchain docarray tiktoken\n",
+    "\n",
+    "from langchain_community.vectorstores import DocArrayInMemorySearch\n",
+    "from langchain_core.output_parsers import StrOutputParser\n",
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "from langchain_core.runnables import RunnableParallel, RunnablePassthrough\n",
+    "from langchain_openai import OpenAIEmbeddings\n",
+    "\n",
+    "vectorstore = DocArrayInMemorySearch.from_texts(\n",
+    "    [\"harrison worked at kensho\", \"bears like to eat honey\"],\n",
+    "    embedding=OpenAIEmbeddings(),\n",
+    ")\n",
+    "retriever = vectorstore.as_retriever()\n",
+    "\n",
+    "template = \"\"\"Answer the question based only on the following context:\n",
+    "{context}\n",
+    "\n",
+    "Question: {question}\n",
+    "\"\"\"\n",
+    "prompt = ChatPromptTemplate.from_template(template)\n",
+    "output_parser = StrOutputParser()\n",
+    "\n",
+    "setup_and_retrieval = RunnableParallel(\n",
+    "    {\"context\": retriever, \"question\": RunnablePassthrough()}\n",
+    ")\n",
+    "chain = setup_and_retrieval | prompt | model | output_parser\n",
+    "\n",
+    "chain.invoke(\"where did harrison work?\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f0999140-6001-423b-970b-adf1dfdb4dec",
+   "metadata": {},
+   "source": [
+    "In this case, the composed chain is: "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5b88e9bb-f04a-4a56-87ec-19a0e6350763",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chain = setup_and_retrieval | prompt | model | output_parser"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6e929e15-40a5-4569-8969-384f636cab87",
+   "metadata": {},
+   "source": [
+    "To explain this, we first can see that the prompt template above takes in `context` and `question` as values to be substituted in the prompt. Before building the prompt template, we want to retrieve relevant documents to the search and include them as part of the context. \n",
+    "\n",
+    "As a preliminary step, we’ve setup the retriever using an in memory store, which can retrieve documents based on a query. This is a runnable component as well that can be chained together with other components, but you can also try to run it separately:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a7319ef6-613b-4638-ad7d-4a2183702c1d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "retriever.invoke(\"where did harrison work?\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e6833844-f1c4-444c-a3d2-31b3c6b31d46",
+   "metadata": {},
+   "source": [
+    "We then use the `RunnableParallel` to prepare the expected inputs into the prompt by using the entries for the retrieved documents as well as the original user question, using the retriever for document search, and RunnablePassthrough to pass the user’s question:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "dcbca26b-d6b9-4c24-806c-1ec8fdaab4ed",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "setup_and_retrieval = RunnableParallel(\n",
+    "    {\"context\": retriever, \"question\": RunnablePassthrough()}\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "68c721c1-048b-4a64-9d78-df54fe465992",
+   "metadata": {},
+   "source": [
+    "To review, the complete chain is:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1d5115a7-7b8e-458b-b936-26cc87ee81c4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "setup_and_retrieval = RunnableParallel(\n",
+    "    {\"context\": retriever, \"question\": RunnablePassthrough()}\n",
+    ")\n",
+    "chain = setup_and_retrieval | prompt | model | output_parser"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "5c6f5f74-b387-48a0-bedd-1fae202cd10a",
+   "metadata": {},
+   "source": [
+    "With the flow being:\n",
+    "\n",
+    "1. The first steps create a `RunnableParallel` object with two entries.  The first entry, `context` will include the document results fetched by the retriever. The second entry, `question` will contain the user’s original question. To pass on the question, we use `RunnablePassthrough` to copy this entry. \n",
+    "2. Feed the dictionary from the step above to the `prompt` component. It then takes the user input which is `question` as well as the retrieved document which is `context` to construct a prompt and output a PromptValue. \n",
+    "3. The `model` component takes the generated prompt, and passes into the OpenAI LLM model for evaluation. The generated output from the model is a `ChatMessage` object. \n",
+    "4. Finally, the `output_parser` component takes in a `ChatMessage`, and transforms this into a Python string, which is returned from the invoke method.\n",
+    "\n",
+    "```mermaid\n",
+    "graph LR\n",
+    "    A(Question) --> B(RunnableParallel)\n",
+    "    B -->|Question| C(Retriever)\n",
+    "    B -->|Question| D(RunnablePassThrough)\n",
+    "    C -->|context=retrieved docs| E(PromptTemplate)\n",
+    "    D -->|question=Question| E\n",
+    "    E -->|PromptValue| F(ChatModel)    \n",
+    "    F -->|ChatMessage| G(StrOutputParser)\n",
+    "    G --> |String| H(Result)\n",
+    "```\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8c2438df-164e-4bbe-b5f4-461695e45b0f",
+   "metadata": {},
+   "source": [
+    "## Next steps\n",
+    "\n",
+    "We recommend reading our [Advantages of LCEL](/docs/expression_language/why) section next to see a side-by-side comparison of the code needed to produce common functionality with and without LCEL."
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.0"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/expression_language/how_to/decorator.ipynb

@@ -0,0 +1,136 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "b45110ef",
+   "metadata": {},
+   "source": [
+    "# Create a runnable with the @chain decorator\n",
+    "\n",
+    "You can also turn an arbitrary function into a chain by adding a `@chain` decorator. This is functionaly equivalent to wrapping in a [`RunnableLambda`](/docs/expression_language/primitives/functions).\n",
+    "\n",
+    "This will have the benefit of improved observability by tracing your chain correctly. Any calls to runnables inside this function will be traced as nested childen.\n",
+    "\n",
+    "It will also allow you to use this as any other runnable, compose it in chain, etc.\n",
+    "\n",
+    "Let's take a look at this in action!"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "23b2b564",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install --upgrade --quiet  langchain langchain-openai"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "d9370420",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.output_parsers import StrOutputParser\n",
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "from langchain_core.runnables import chain\n",
+    "from langchain_openai import ChatOpenAI"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "b7f74f7e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prompt1 = ChatPromptTemplate.from_template(\"Tell me a joke about {topic}\")\n",
+    "prompt2 = ChatPromptTemplate.from_template(\"What is the subject of this joke: {joke}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "2b0365c4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "@chain\n",
+    "def custom_chain(text):\n",
+    "    prompt_val1 = prompt1.invoke({\"topic\": text})\n",
+    "    output1 = ChatOpenAI().invoke(prompt_val1)\n",
+    "    parsed_output1 = StrOutputParser().invoke(output1)\n",
+    "    chain2 = prompt2 | ChatOpenAI() | StrOutputParser()\n",
+    "    return chain2.invoke({\"joke\": parsed_output1})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "904d6872",
+   "metadata": {},
+   "source": [
+    "`custom_chain` is now a runnable, meaning you will need to use `invoke`"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "6448bdd3",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'The subject of this joke is bears.'"
+      ]
+     },
+     "execution_count": 21,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "custom_chain.invoke(\"bears\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "aa767ea9",
+   "metadata": {},
+   "source": [
+    "If you check out your LangSmith traces, you should see a `custom_chain` trace in there, with the calls to OpenAI nested underneath"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f1245bdc",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/expression_language/how_to/inspect.ipynb

@@ -5,21 +5,11 @@
    "id": "8c5eb99a",
    "metadata": {},
    "source": [
-    "# How to inspect runnables\n",
+    "# Inspect your runnables\n",
     "\n",
-    ":::info Prerequisites\n",
+    "Once you create a runnable with LCEL, you may often want to inspect it to get a better sense for what is going on. This notebook covers some methods for doing so.\n",
     "\n",
-    "This guide assumes familiarity with the following concepts:\n",
-    "- [LangChain Expression Language (LCEL)](/docs/concepts/#langchain-expression-language)\n",
-    "- [Chaining runnables](/docs/how_to/sequence/)\n",
-    "\n",
-    ":::\n",
-    "\n",
-    "Once you create a runnable with [LangChain Expression Language](/docs/concepts/#langchain-expression-language), you may often want to inspect it to get a better sense for what is going on. This notebook covers some methods for doing so.\n",
-    "\n",
-    "This guide shows some ways you can programmatically introspect the internal steps of chains. If you are instead interested in debugging issues in your chain, see [this section](/docs/how_to/debugging) instead.\n",
-    "\n",
-    "First, let's create an example chain. We will create one that does retrieval:"
+    "First, let's create an example LCEL. We will create one that does retrieval"
    ]
   },
   {
@@ -29,7 +19,21 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install -qU langchain langchain-openai faiss-cpu tiktoken"
+    "%pip install --upgrade --quiet  langchain langchain-openai faiss-cpu tiktoken"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "a88f4b24",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.prompts import ChatPromptTemplate\n",
+    "from langchain_community.vectorstores import FAISS\n",
+    "from langchain_core.output_parsers import StrOutputParser\n",
+    "from langchain_core.runnables import RunnablePassthrough\n",
+    "from langchain_openai import ChatOpenAI, OpenAIEmbeddings"
    ]
   },
   {
@@ -39,12 +43,6 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.prompts import ChatPromptTemplate\n",
-    "from langchain_community.vectorstores import FAISS\n",
-    "from langchain_core.output_parsers import StrOutputParser\n",
-    "from langchain_core.runnables import RunnablePassthrough\n",
-    "from langchain_openai import ChatOpenAI, OpenAIEmbeddings\n",
-    "\n",
     "vectorstore = FAISS.from_texts(\n",
     "    [\"harrison worked at kensho\"], embedding=OpenAIEmbeddings()\n",
     ")\n",
@@ -57,8 +55,16 @@
     "\"\"\"\n",
     "prompt = ChatPromptTemplate.from_template(template)\n",
     "\n",
-    "model = ChatOpenAI()\n",
-    "\n",
+    "model = ChatOpenAI()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "70e3fe93",
+   "metadata": {},
+   "outputs": [],
+   "source": [
     "chain = (\n",
     "    {\"context\": retriever, \"question\": RunnablePassthrough()}\n",
     "    | prompt\n",
@@ -74,7 +80,7 @@
    "source": [
     "## Get a graph\n",
     "\n",
-    "You can use the `get_graph()` method to get a graph representation of the runnable:"
+    "You can get a graph of the runnable"
    ]
   },
   {
@@ -94,7 +100,7 @@
    "source": [
     "## Print a graph\n",
     "\n",
-    "While that is not super legible, you can use the `print_ascii()` method to show that graph in a way that's easier to understand:"
+    "While that is not super legible, you can print it to get a display that's easier to understand"
    ]
   },
   {
@@ -160,7 +166,7 @@
    "source": [
     "## Get the prompts\n",
     "\n",
-    "You may want to see just the prompts that are used in a chain with the `get_prompts()` method:"
+    "An important part of every chain is the prompts that are used. You can get the prompts present in the chain:"
    ]
   },
   {
@@ -184,18 +190,6 @@
     "chain.get_prompts()"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "id": "c5a74bd5",
-   "metadata": {},
-   "source": [
-    "## Next steps\n",
-    "\n",
-    "You've now learned how to introspect your composed LCEL chains.\n",
-    "\n",
-    "Next, check out the other how-to guides on runnables in this section, or the related how-to guide on [debugging your chains](/docs/how_to/debugging)."
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -221,7 +215,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.10.1"
   }
  },
  "nbformat": 4,

docs/docs/expression_language/how_to/message_history.ipynb

@@ -5,26 +5,15 @@
    "id": "6a4becbd-238e-4c1d-a02d-08e61fbc3763",
    "metadata": {},
    "source": [
-    "# How to add message history\n",
+    "# Add message history (memory)\n",
     "\n",
-    ":::info Prerequisites\n",
+    "The `RunnableWithMessageHistory` lets us add message history to certain types of chains. It wraps another Runnable and manages the chat message history for it.\n",
     "\n",
-    "This guide assumes familiarity with the following concepts:\n",
-    "- [LangChain Expression Language (LCEL)](/docs/concepts/#langchain-expression-language)\n",
-    "- [Chaining runnables](/docs/how_to/sequence/)\n",
-    "- [Configuring chain parameters at runtime](/docs/how_to/configure)\n",
-    "- [Prompt templates](/docs/concepts/#prompt-templates)\n",
-    "- [Chat Messages](/docs/concepts/#message-types)\n",
+    "Specifically, it can be used for any Runnable that takes as input one of\n",
     "\n",
-    ":::\n",
-    "\n",
-    "Passing conversation state into and out a chain is vital when building a chatbot. The [`RunnableWithMessageHistory`](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.history.RunnableWithMessageHistory.html#langchain_core.runnables.history.RunnableWithMessageHistory) class lets us add message history to certain types of chains. It wraps another Runnable and manages the chat message history for it.\n",
-    "\n",
-    "Specifically, it can be used for any Runnable that takes as input one of:\n",
-    "\n",
-    "* a sequence of [`BaseMessages`](/docs/concepts/#message-types)\n",
-    "* a dict with a key that takes a sequence of `BaseMessages`\n",
-    "* a dict with a key that takes the latest message(s) as a string or sequence of `BaseMessages`, and a separate key that takes historical messages\n",
+    "* a sequence of `BaseMessage`\n",
+    "* a dict with a key that takes a sequence of `BaseMessage`\n",
+    "* a dict with a key that takes the latest message(s) as a string or sequence of `BaseMessage`, and a separate key that takes historical messages\n",
     "\n",
     "And returns as output one of\n",
     "\n",
@@ -32,42 +21,12 @@
     "* a sequence of `BaseMessage`\n",
     "* a dict with a key that contains a sequence of `BaseMessage`\n",
     "\n",
-    "Let's take a look at some examples to see how it works. First we construct a runnable (which here accepts a dict as input and returns a message as output):\n",
-    "\n",
-    "```{=mdx}\n",
-    "import ChatModelTabs from \"@theme/ChatModelTabs\";\n",
-    "\n",
-    "<ChatModelTabs\n",
-    "  customVarName=\"llm\"\n",
-    "/>\n",
-    "```"
+    "Let's take a look at some examples to see how it works. First we construct a runnable (which here accepts a dict as input and returns a message as output):"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 1,
-   "id": "6489f585",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# | output: false\n",
-    "# | echo: false\n",
-    "\n",
-    "%pip install -qU langchain langchain_anthropic\n",
-    "\n",
-    "import os\n",
-    "from getpass import getpass\n",
-    "\n",
-    "from langchain_anthropic import ChatAnthropic\n",
-    "\n",
-    "os.environ[\"ANTHROPIC_API_KEY\"] = getpass()\n",
-    "\n",
-    "model = ChatAnthropic(model=\"claude-3-haiku-20240307\", temperature=0)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
    "id": "2ed413b4-33a1-48ee-89b0-2d4917ec101a",
    "metadata": {},
    "outputs": [],
@@ -75,6 +34,7 @@
     "from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder\n",
     "from langchain_openai.chat_models import ChatOpenAI\n",
     "\n",
+    "model = ChatOpenAI()\n",
     "prompt = ChatPromptTemplate.from_messages(\n",
     "    [\n",
     "        (\n",
@@ -116,7 +76,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 2,
    "id": "54348d02-d8ee-440c-bbf9-41bc0fbbc46c",
    "metadata": {},
    "outputs": [],
@@ -154,17 +114,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 3,
    "id": "01384412-f08e-4634-9edb-3f46f475b582",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "AIMessage(content='Cosine is a trigonometric function that represents the ratio of the adjacent side to the hypotenuse of a right triangle.', response_metadata={'id': 'msg_017rAM9qrBTSdJ5i1rwhB7bT', 'model': 'claude-3-haiku-20240307', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 32, 'output_tokens': 31}}, id='run-65e94a5e-a804-40de-ba88-d01b6cd06864-0')"
+       "AIMessage(content='Cosine is a trigonometric function that calculates the ratio of the adjacent side to the hypotenuse of a right triangle.')"
       ]
      },
-     "execution_count": 4,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -178,17 +138,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 4,
    "id": "954688a2-9a3f-47ee-a9e8-fa0c83e69477",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "AIMessage(content='Cosine is a trigonometric function that represents the ratio of the adjacent side to the hypotenuse of a right triangle.', response_metadata={'id': 'msg_017hK1Q63ganeQZ9wdeqruLP', 'model': 'claude-3-haiku-20240307', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 68, 'output_tokens': 31}}, id='run-a42177ef-b04a-4968-8606-446fb465b943-0')"
+       "AIMessage(content='Cosine is a mathematical function used to calculate the length of a side in a right triangle.')"
       ]
      },
-     "execution_count": 5,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -203,17 +163,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 5,
    "id": "39350d7c-2641-4744-bc2a-fd6a57c4ea90",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "AIMessage(content=\"I'm an AI assistant skilled in mathematics. How can I help you with a math-related task?\", response_metadata={'id': 'msg_01AYwfQ6SH5qz8ZQMW3nYtGU', 'model': 'claude-3-haiku-20240307', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 28, 'output_tokens': 24}}, id='run-c57d93e3-305f-4c0e-bdb9-ef82f5b49f61-0')"
+       "AIMessage(content='I can help with math problems. What do you need assistance with?')"
       ]
      },
-     "execution_count": 6,
+     "execution_count": 5,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -236,21 +196,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 6,
    "id": "1c89daee-deff-4fdf-86a3-178f7d8ef536",
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content='Hello! How can I assist you with math today?', response_metadata={'id': 'msg_01UdhnwghuSE7oRM57STFhHL', 'model': 'claude-3-haiku-20240307', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 27, 'output_tokens': 14}}, id='run-3d53f67a-4ea7-4d78-8e67-37db43d4af5d-0')"
-      ]
-     },
-     "execution_count": 7,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
     "from langchain_core.runnables import ConfigurableFieldSpec\n",
     "\n",
@@ -286,8 +235,16 @@
     "            is_shared=True,\n",
     "        ),\n",
     "    ],\n",
-    ")\n",
-    "\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "65c5622e-09b8-4f2f-8c8a-2dab0fd040fa",
+   "metadata": {},
+   "outputs": [],
+   "source": [
     "with_message_history.invoke(\n",
     "    {\"ability\": \"math\", \"input\": \"Hello\"},\n",
     "    config={\"configurable\": {\"user_id\": \"123\", \"conversation_id\": \"1\"}},\n",
@@ -314,17 +271,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 7,
    "id": "17733d4f-3a32-4055-9d44-5d58b9446a26",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "{'output_message': AIMessage(content='Simone de Beauvoir was a prominent French existentialist philosopher who had some key beliefs about free will:\\n\\n1. Radical Freedom: De Beauvoir believed that humans have radical freedom - the ability to choose and define themselves through their actions. She rejected determinism and believed that we are not simply products of our biology, upbringing, or social circumstances.\\n\\n2. Ambiguity of the Human Condition: However, de Beauvoir also recognized the ambiguity of the human condition. While we have radical freedom, we are also situated beings constrained by our facticity (our given circumstances and limitations). This creates a tension and anguish in the human experience.\\n\\n3. Responsibility and Bad Faith: With this radical freedom comes great responsibility. De Beauvoir criticized \"bad faith\" - the tendency of people to deny their freedom and responsibility by making excuses or hiding behind social roles and norms.\\n\\n4. Ethical Engagement: For de Beauvoir, true freedom and authenticity required ethical engagement with the world and with others. We must take responsibility for our choices and their impact on others.\\n\\nOverall, de Beauvoir saw free will as a core aspect of the human condition, but one that is fraught with difficulty and ambiguity. Her philosophy emphasized the importance of owning our freedom and using it to ethically shape our lives and world.', response_metadata={'id': 'msg_01A78LdxxsCm6uR8vcAdMQBt', 'model': 'claude-3-haiku-20240307', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 20, 'output_tokens': 293}}, id='run-9447a229-5d17-4b20-a48b-7507b78b225a-0')}"
+       "{'output_message': AIMessage(content=\"Simone de Beauvoir believed in the existence of free will. She argued that individuals have the ability to make choices and determine their own actions, even in the face of social and cultural constraints. She rejected the idea that individuals are purely products of their environment or predetermined by biology or destiny. Instead, she emphasized the importance of personal responsibility and the need for individuals to actively engage in creating their own lives and defining their own existence. De Beauvoir believed that freedom and agency come from recognizing one's own freedom and actively exercising it in the pursuit of personal and collective liberation.\")}"
       ]
      },
-     "execution_count": 9,
+     "execution_count": 7,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -333,7 +290,7 @@
     "from langchain_core.messages import HumanMessage\n",
     "from langchain_core.runnables import RunnableParallel\n",
     "\n",
-    "chain = RunnableParallel({\"output_message\": model})\n",
+    "chain = RunnableParallel({\"output_message\": ChatOpenAI()})\n",
     "\n",
     "\n",
     "def get_session_history(session_id: str) -> BaseChatMessageHistory:\n",
@@ -356,17 +313,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 8,
    "id": "efb57ef5-91f9-426b-84b9-b77f071a9dd7",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "{'output_message': AIMessage(content=\"Simone de Beauvoir's views on free will were quite similar, but not identical, to those of her long-time partner Jean-Paul Sartre, another prominent existentialist philosopher.\\n\\nKey similarities:\\n\\n1. Radical Freedom: Both de Beauvoir and Sartre believed that humans have radical, unconditioned freedom to choose and define themselves.\\n\\n2. Rejection of Determinism: They both rejected deterministic views that see humans as products of their circumstances or biology.\\n\\n3. Emphasis on Responsibility: They agreed that with radical freedom comes great responsibility for one's choices and their consequences.\\n\\nKey differences:\\n\\n1. Ambiguity of the Human Condition: While Sartre emphasized the pure, unconditioned nature of human freedom, de Beauvoir recognized the ambiguity of the human condition - our freedom is constrained by our facticity (circumstances).\\n\\n2. Ethical Engagement: De Beauvoir placed more emphasis on the importance of ethical engagement with the world and others, whereas Sartre's focus was more on the individual's freedom.\\n\\n3. Gendered Perspectives: As a woman, de Beauvoir's perspective was more attuned to issues of gender and the lived experience of women, which shaped her views on freedom and ethics.\\n\\nSo in summary, while Sartre and de Beauvoir shared a core existentialist philosophy centered on radical human freedom, de Beauvoir's thought incorporated a greater recognition of the ambiguity and ethical dimensions of the human condition. This reflected her distinct feminist and phenomenological approach.\", response_metadata={'id': 'msg_01U6X3KNPufVg3zFvnx24eKq', 'model': 'claude-3-haiku-20240307', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 324, 'output_tokens': 338}}, id='run-c4a984bd-33c6-4e26-a4d1-d58b666d065c-0')}"
+       "{'output_message': AIMessage(content='Simone de Beauvoir\\'s views on free will were closely aligned with those of her contemporary and partner Jean-Paul Sartre. Both de Beauvoir and Sartre were existentialist philosophers who emphasized the importance of individual freedom and the rejection of determinism. They believed that human beings have the capacity to transcend their circumstances and create their own meaning and values.\\n\\nSartre, in his famous work \"Being and Nothingness,\" argued that human beings are condemned to be free, meaning that we are burdened with the responsibility of making choices and defining ourselves in a world that lacks inherent meaning. Like de Beauvoir, Sartre believed that individuals have the ability to exercise their freedom and make choices in the face of external and internal constraints.\\n\\nWhile there may be some nuanced differences in their philosophical writings, overall, de Beauvoir and Sartre shared a similar belief in the existence of free will and the importance of individual agency in shaping one\\'s own life.')}"
       ]
      },
-     "execution_count": 10,
+     "execution_count": 8,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -388,25 +345,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": null,
    "id": "e45bcd95-e31f-4a9a-967a-78f96e8da881",
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "RunnableWithMessageHistory(bound=RunnableBinding(bound=RunnableBinding(bound=RunnableLambda(_enter_history), config={'run_name': 'load_history'})\n",
-       "| RunnableBinding(bound=ChatAnthropic(model='claude-3-haiku-20240307', temperature=0.0, anthropic_api_url='https://api.anthropic.com', anthropic_api_key=SecretStr('**********'), _client=<anthropic.Anthropic object at 0x1077ff5b0>, _async_client=<anthropic.AsyncAnthropic object at 0x1321c71f0>), config_factories=[<function Runnable.with_listeners.<locals>.<lambda> at 0x1473dd000>]), config={'run_name': 'RunnableWithMessageHistory'}), get_session_history=<function get_session_history at 0x1374c7be0>, history_factory_config=[ConfigurableFieldSpec(id='session_id', annotation=<class 'str'>, name='Session ID', description='Unique identifier for a session.', default='', is_shared=True, dependencies=None)])"
-      ]
-     },
-     "execution_count": 12,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
     "RunnableWithMessageHistory(\n",
-    "    model,\n",
+    "    ChatOpenAI(),\n",
     "    get_session_history,\n",
     ")"
    ]
@@ -421,30 +366,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": null,
    "id": "27157f15-9fb0-4167-9870-f4d7f234b3cb",
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "RunnableWithMessageHistory(bound=RunnableBinding(bound=RunnableBinding(bound=RunnableAssign(mapper={\n",
-       "  input_messages: RunnableBinding(bound=RunnableLambda(_enter_history), config={'run_name': 'load_history'})\n",
-       "}), config={'run_name': 'insert_history'})\n",
-       "| RunnableBinding(bound=RunnableLambda(itemgetter('input_messages'))\n",
-       "  | ChatAnthropic(model='claude-3-haiku-20240307', temperature=0.0, anthropic_api_url='https://api.anthropic.com', anthropic_api_key=SecretStr('**********'), _client=<anthropic.Anthropic object at 0x1077ff5b0>, _async_client=<anthropic.AsyncAnthropic object at 0x1321c71f0>), config_factories=[<function Runnable.with_listeners.<locals>.<lambda> at 0x1473df6d0>]), config={'run_name': 'RunnableWithMessageHistory'}), get_session_history=<function get_session_history at 0x1374c7be0>, input_messages_key='input_messages', history_factory_config=[ConfigurableFieldSpec(id='session_id', annotation=<class 'str'>, name='Session ID', description='Unique identifier for a session.', default='', is_shared=True, dependencies=None)])"
-      ]
-     },
-     "execution_count": 13,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
     "from operator import itemgetter\n",
     "\n",
     "RunnableWithMessageHistory(\n",
-    "    itemgetter(\"input_messages\") | model,\n",
+    "    itemgetter(\"input_messages\") | ChatOpenAI(),\n",
     "    get_session_history,\n",
     "    input_messages_key=\"input_messages\",\n",
     ")"
@@ -499,7 +429,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 9,
    "id": "cd6a250e-17fe-4368-a39d-1fe6b2cbde68",
    "metadata": {},
    "outputs": [],
@@ -522,7 +452,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 2,
    "id": "2afc1556-8da1-4499-ba11-983b66c58b18",
    "metadata": {},
    "outputs": [],
@@ -541,7 +471,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 10,
    "id": "ca7c64d8-e138-4ef8-9734-f82076c47d80",
    "metadata": {},
    "outputs": [],
@@ -571,7 +501,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 11,
    "id": "a85bcc22-ca4c-4ad5-9440-f94be7318f3e",
    "metadata": {},
    "outputs": [
@@ -595,7 +525,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 12,
    "id": "ab29abd3-751f-41ce-a1b0-53f6b565e79d",
    "metadata": {},
    "outputs": [
@@ -636,18 +566,6 @@
    "source": [
     "Looking at the Langsmith trace for the second call, we can see that when constructing the prompt, a \"history\" variable has been injected which is a list of two messages (our first input and first output)."
    ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "fd510b68",
-   "metadata": {},
-   "source": [
-    "## Next steps\n",
-    "\n",
-    "You have now learned one way to manage message history for a runnable.\n",
-    "\n",
-    "To learn more, see the other how-to guides on runnables in this section."
-   ]
   }
  ],
  "metadata": {
@@ -666,7 +584,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.10.13"
   }
  },
  "nbformat": 4,

docs/docs/expression_language/how_to/routing.ipynb

@@ -7,6 +7,7 @@
    "source": [
     "---\n",
     "sidebar_position: 3\n",
+    "title: \"Route logic based on input\"\n",
     "keywords: [RunnableBranch, LCEL]\n",
     "---"
    ]
@@ -16,25 +17,16 @@
    "id": "4b47436a",
    "metadata": {},
    "source": [
-    "# How to route execution within a chain\n",
+    "# Dynamically route logic based on input\n",
     "\n",
-    ":::info Prerequisites\n",
+    "This notebook covers how to do routing in the LangChain Expression Language.\n",
     "\n",
-    "This guide assumes familiarity with the following concepts:\n",
-    "- [LangChain Expression Language (LCEL)](/docs/concepts/#langchain-expression-language)\n",
-    "- [Chaining runnables](/docs/how_to/sequence/)\n",
-    "- [Configuring chain parameters at runtime](/docs/how_to/configure)\n",
-    "- [Prompt templates](/docs/concepts/#prompt-templates)\n",
-    "- [Chat Messages](/docs/concepts/#message-types)\n",
-    "\n",
-    ":::\n",
-    "\n",
-    "Routing allows you to create non-deterministic chains where the output of a previous step defines the next step. Routing can help provide structure and consistency around interactions with models by allowing you to define states and use information related to those states as context to model calls.\n",
+    "Routing allows you to create non-deterministic chains where the output of a previous step defines the next step. Routing helps provide structure and consistency around interactions with LLMs.\n",
     "\n",
     "There are two ways to perform routing:\n",
     "\n",
-    "1. Conditionally return runnables from a [`RunnableLambda`](/docs/how_to/functions) (recommended)\n",
-    "2. Using a `RunnableBranch` (legacy)\n",
+    "1. Conditionally return runnables from a [`RunnableLambda`](/docs/expression_language/primitives/functions) (recommended)\n",
+    "2. Using a `RunnableBranch`.\n",
     "\n",
     "We'll illustrate both methods using a two step sequence where the first step classifies an input question as being about `LangChain`, `Anthropic`, or `Other`, then routes to a corresponding prompt chain."
    ]
@@ -438,18 +430,6 @@
     "print(chain.invoke(\"What's a path integral\"))"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "id": "ff40bcb3",
-   "metadata": {},
-   "source": [
-    "## Next steps\n",
-    "\n",
-    "You've now learned how to add routing to your composed LCEL chains.\n",
-    "\n",
-    "Next, check out the other how-to guides on runnables in this section."
-   ]
-  },
   {
    "cell_type": "markdown",
    "id": "927b7498",
@@ -473,7 +453,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.10.5"
   }
  },
  "nbformat": 4,

docs/docs/expression_language/index.mdx

@@ -0,0 +1,33 @@
+---
+sidebar_class_name: hidden
+---
+
+# LangChain Expression Language (LCEL)
+
+LangChain Expression Language, or LCEL, is a declarative way to easily compose chains together.
+LCEL was designed from day 1 to **support putting prototypes in production, with no code changes**, from the simplest “prompt + LLM” chain to the most complex chains (we’ve seen folks successfully run LCEL chains with 100s of steps in production). To highlight a few of the reasons you might want to use LCEL:
+
+[**First-class streaming support**](/docs/expression_language/streaming)
+When you build your chains with LCEL you get the best possible time-to-first-token (time elapsed until the first chunk of output comes out). For some chains this means eg. we stream tokens straight from an LLM to a streaming output parser, and you get back parsed, incremental chunks of output at the same rate as the LLM provider outputs the raw tokens.
+
+[**Async support**](/docs/expression_language/interface)
+Any chain built with LCEL can be called both with the synchronous API (eg. in your Jupyter notebook while prototyping) as well as with the asynchronous API (eg. in a [LangServe](/docs/langsmith) server). This enables using the same code for prototypes and in production, with great performance, and the ability to handle many concurrent requests in the same server.
+
+[**Optimized parallel execution**](/docs/expression_language/primitives/parallel)
+Whenever your LCEL chains have steps that can be executed in parallel (eg if you fetch documents from multiple retrievers) we automatically do it, both in the sync and the async interfaces, for the smallest possible latency.
+
+[**Retries and fallbacks**](/docs/guides/productionization/fallbacks)
+Configure retries and fallbacks for any part of your LCEL chain. This is a great way to make your chains more reliable at scale. We’re currently working on adding streaming support for retries/fallbacks, so you can get the added reliability without any latency cost.
+
+[**Access intermediate results**](/docs/expression_language/interface#async-stream-events-beta)
+For more complex chains it’s often very useful to access the results of intermediate steps even before the final output is produced. This can be used to let end-users know something is happening, or even just to debug your chain. You can stream intermediate results, and it’s available on every [LangServe](/docs/langserve) server.
+
+[**Input and output schemas**](/docs/expression_language/interface#input-schema)
+Input and output schemas give every LCEL chain Pydantic and JSONSchema schemas inferred from the structure of your chain. This can be used for validation of inputs and outputs, and is an integral part of LangServe.
+
+[**Seamless LangSmith tracing**](/docs/langsmith)
+As your chains get more and more complex, it becomes increasingly important to understand what exactly is happening at every step.
+With LCEL, **all** steps are automatically logged to [LangSmith](/docs/langsmith/) for maximum observability and debuggability.
+
+[**Seamless LangServe deployment**](/docs/langserve)
+Any chain created with LCEL can be easily deployed using [LangServe](/docs/langserve).

docs/docs/expression_language/primitives/assign.ipynb

@@ -6,6 +6,7 @@
    "source": [
     "---\n",
     "sidebar_position: 6\n",
+    "title: \"Assign: Add values to state\"\n",
     "keywords: [RunnablePassthrough, assign, LCEL]\n",
     "---"
    ]
@@ -14,38 +15,32 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# How to add values to a chain's state\n",
+    "# Adding values to chain state\n",
     "\n",
-    ":::info Prerequisites\n",
+    "The `RunnablePassthrough.assign(...)` static method takes an input value and adds the extra arguments passed to the assign function.\n",
     "\n",
-    "This guide assumes familiarity with the following concepts:\n",
-    "- [LangChain Expression Language (LCEL)](/docs/concepts/#langchain-expression-language)\n",
-    "- [Chaining runnables](/docs/how_to/sequence/)\n",
-    "- [Calling runnables in parallel](/docs/how_to/parallel/)\n",
-    "- [Custom functions](/docs/how_to/functions/)\n",
-    "- [Passing data through](/docs/how_to/passthrough)\n",
-    "\n",
-    ":::\n",
-    "\n",
-    "An alternate way of [passing data through](/docs/how_to/passthrough) steps of a chain is to leave the current values of the chain state unchanged while assigning a new value under a given key. The [`RunnablePassthrough.assign()`](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.passthrough.RunnablePassthrough.html#langchain_core.runnables.passthrough.RunnablePassthrough.assign) static method takes an input value and adds the extra arguments passed to the assign function.\n",
-    "\n",
-    "This is useful in the common [LangChain Expression Language](/docs/concepts/#langchain-expression-language) pattern of additively creating a dictionary to use as input to a later step.\n",
+    "This is useful when additively creating a dictionary to use as input to a later step, which is a common LCEL pattern.\n",
     "\n",
     "Here's an example:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\u001b[33mWARNING: You are using pip version 22.0.4; however, version 24.0 is available.\n",
+      "You should consider upgrading via the '/Users/jacoblee/.pyenv/versions/3.10.5/bin/python -m pip install --upgrade pip' command.\u001b[0m\u001b[33m\n",
+      "\u001b[0mNote: you may need to restart the kernel to use updated packages.\n"
+     ]
+    }
+   ],
    "source": [
-    "%pip install --upgrade --quiet langchain langchain-openai\n",
-    "\n",
-    "import os\n",
-    "from getpass import getpass\n",
-    "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = getpass()"
+    "%pip install --upgrade --quiet langchain langchain-openai"
    ]
   },
   {
@@ -90,12 +85,12 @@
     "\n",
     "## Streaming\n",
     "\n",
-    "One convenient feature of this method is that it allows values to pass through as soon as they are available. To show this off, we'll use `RunnablePassthrough.assign()` to immediately return source docs in a retrieval chain:"
+    "One nice feature of this method is that it allows values to pass through as soon as they are available. To show this off, we'll use `RunnablePassthrough.assign()` to immediately return source docs in a retrieval chain:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [
     {
@@ -152,13 +147,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "We can see that the first chunk contains the original `\"question\"` since that is immediately available. The second chunk contains `\"context\"` since the retriever finishes second. Finally, the output from the `generation_chain` streams in chunks as soon as it is available.\n",
-    "\n",
-    "## Next steps\n",
-    "\n",
-    "Now you've learned how to pass data through your chains to help to help format the data flowing through your chains.\n",
-    "\n",
-    "To learn more, see the other how-to guides on runnables in this section."
+    "We can see that the first chunk contains the original `\"question\"` since that is immediately available. The second chunk contains `\"context\"` since the retriever finishes second. Finally, the output from the `generation_chain` streams in chunks as soon as it is available."
    ]
   },
   {
@@ -169,7 +158,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": "Python 3",
    "language": "python",
    "name": "python3"
   },
@@ -183,9 +172,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.10.5"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 4
+ "nbformat_minor": 2
 }

docs/docs/expression_language/primitives/binding.ipynb

@@ -7,6 +7,7 @@
    "source": [
     "---\n",
     "sidebar_position: 2\n",
+    "title: \"Binding: Attach runtime args\"\n",
     "keywords: [RunnableBinding, LCEL]\n",
     "---"
    ]
@@ -16,22 +17,11 @@
    "id": "711752cb-4f15-42a3-9838-a0c67f397771",
    "metadata": {},
    "source": [
-    "# How to attach runtime arguments to a Runnable\n",
+    "# Binding: Attach runtime args\n",
     "\n",
-    ":::info Prerequisites\n",
+    "Sometimes we want to invoke a Runnable within a Runnable sequence with constant arguments that are not part of the output of the preceding Runnable in the sequence, and which are not part of the user input. We can use `Runnable.bind()` to pass these arguments in.\n",
     "\n",
-    "This guide assumes familiarity with the following concepts:\n",
-    "- [LangChain Expression Language (LCEL)](/docs/concepts/#langchain-expression-language)\n",
-    "- [Chaining runnables](/docs/how_to/sequence/)\n",
-    "- [Tool calling](/docs/how_to/tool_calling/)\n",
-    "\n",
-    ":::\n",
-    "\n",
-    "Sometimes we want to invoke a [`Runnable`](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.base.Runnable.html) within a [RunnableSequence](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.base.RunnableSequence.html) with constant arguments that are not part of the output of the preceding Runnable in the sequence, and which are not part of the user input. We can use the [`Runnable.bind()`](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.base.Runnable.html#langchain_core.runnables.base.Runnable.bind) method to set these arguments ahead of time.\n",
-    "\n",
-    "## Binding stop sequences\n",
-    "\n",
-    "Suppose we have a simple prompt + model chain:"
+    "Suppose we have a simple prompt + model sequence:"
    ]
   },
   {
@@ -41,20 +31,25 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# | output: false\n",
-    "# | echo: false\n",
-    "\n",
-    "%pip install -qU langchain langchain_openai\n",
-    "\n",
-    "import os\n",
-    "from getpass import getpass\n",
-    "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = getpass()"
+    "%pip install --upgrade --quiet  langchain langchain-openai"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 1,
+   "id": "950297ed-2d67-4091-8ea7-1d412d259d04",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.output_parsers import StrOutputParser\n",
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "from langchain_core.runnables import RunnablePassthrough\n",
+    "from langchain_openai import ChatOpenAI"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
    "id": "f3fdf86d-155f-4587-b7cd-52d363970c1d",
    "metadata": {},
    "outputs": [
@@ -64,21 +59,19 @@
      "text": [
       "EQUATION: x^3 + 7 = 12\n",
       "\n",
-      "SOLUTION: \n",
-      "Subtract 7 from both sides:\n",
+      "SOLUTION:\n",
+      "Subtracting 7 from both sides of the equation, we get:\n",
+      "x^3 = 12 - 7\n",
       "x^3 = 5\n",
       "\n",
-      "Take the cube root of both sides:\n",
-      "x = ∛5\n"
+      "Taking the cube root of both sides, we get:\n",
+      "x = ∛5\n",
+      "\n",
+      "Therefore, the solution to the equation x^3 + 7 = 12 is x = ∛5.\n"
      ]
     }
    ],
    "source": [
-    "from langchain_core.output_parsers import StrOutputParser\n",
-    "from langchain_core.prompts import ChatPromptTemplate\n",
-    "from langchain_core.runnables import RunnablePassthrough\n",
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
     "prompt = ChatPromptTemplate.from_messages(\n",
     "    [\n",
     "        (\n",
@@ -88,9 +81,7 @@
     "        (\"human\", \"{equation_statement}\"),\n",
     "    ]\n",
     ")\n",
-    "\n",
     "model = ChatOpenAI(temperature=0)\n",
-    "\n",
     "runnable = (\n",
     "    {\"equation_statement\": RunnablePassthrough()} | prompt | model | StrOutputParser()\n",
     ")\n",
@@ -103,12 +94,12 @@
    "id": "929c9aba-a4a0-462c-adac-2cfc2156e117",
    "metadata": {},
    "source": [
-    "and want to call the model with certain `stop` words so that we shorten the output as is useful in certain types of prompting techniques. While we can pass some arguments into the constructor, other runtime args use the `.bind()` method as follows:"
+    "and want to call the model with certain `stop` words:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 12,
    "id": "32e0484a-78c5-4570-a00b-20d597245a96",
    "metadata": {},
    "outputs": [
@@ -129,25 +120,92 @@
     "    | model.bind(stop=\"SOLUTION\")\n",
     "    | StrOutputParser()\n",
     ")\n",
-    "\n",
     "print(runnable.invoke(\"x raised to the third plus seven equals 12\"))"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "f4bd641f-6b58-4ca9-a544-f69095428f16",
+   "metadata": {},
+   "source": [
+    "## Attaching OpenAI functions\n",
+    "\n",
+    "One particularly useful application of binding is to attach OpenAI functions to a compatible OpenAI model:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "f66a0fe4-fde0-4706-8863-d60253f211c7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "function = {\n",
+    "    \"name\": \"solver\",\n",
+    "    \"description\": \"Formulates and solves an equation\",\n",
+    "    \"parameters\": {\n",
+    "        \"type\": \"object\",\n",
+    "        \"properties\": {\n",
+    "            \"equation\": {\n",
+    "                \"type\": \"string\",\n",
+    "                \"description\": \"The algebraic expression of the equation\",\n",
+    "            },\n",
+    "            \"solution\": {\n",
+    "                \"type\": \"string\",\n",
+    "                \"description\": \"The solution to the equation\",\n",
+    "            },\n",
+    "        },\n",
+    "        \"required\": [\"equation\", \"solution\"],\n",
+    "    },\n",
+    "}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "f381f969-df8e-48a3-bf5c-d0397cfecde0",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='', additional_kwargs={'function_call': {'name': 'solver', 'arguments': '{\\n\"equation\": \"x^3 + 7 = 12\",\\n\"solution\": \"x = ∛5\"\\n}'}}, example=False)"
+      ]
+     },
+     "execution_count": 22,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Need gpt-4 to solve this one correctly\n",
+    "prompt = ChatPromptTemplate.from_messages(\n",
+    "    [\n",
+    "        (\n",
+    "            \"system\",\n",
+    "            \"Write out the following equation using algebraic symbols then solve it.\",\n",
+    "        ),\n",
+    "        (\"human\", \"{equation_statement}\"),\n",
+    "    ]\n",
+    ")\n",
+    "model = ChatOpenAI(model=\"gpt-4\", temperature=0).bind(\n",
+    "    function_call={\"name\": \"solver\"}, functions=[function]\n",
+    ")\n",
+    "runnable = {\"equation_statement\": RunnablePassthrough()} | prompt | model\n",
+    "runnable.invoke(\"x raised to the third plus seven equals 12\")"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "f07d7528-9269-4d6f-b12e-3669592a9e03",
    "metadata": {},
    "source": [
-    "What you can bind to a Runnable will depend on the extra parameters you can pass when invoking it.\n",
-    "\n",
-    "## Attaching OpenAI tools\n",
-    "\n",
-    "Another common use-case is tool calling. While you should generally use the [`.bind_tools()`](/docs/how_to/tool_calling/) method for tool-calling models, you can also bind provider-specific args directly if you want lower level control:"
+    "## Attaching OpenAI tools"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 5,
    "id": "2cdeeb4c-0c1f-43da-bd58-4f591d9e0671",
    "metadata": {},
    "outputs": [],
@@ -176,17 +234,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 9,
    "id": "2b65beab-48bb-46ff-a5a4-ef8ac95a513c",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_z0OU2CytqENVrRTI6T8DkI3u', 'function': {'arguments': '{\"location\": \"San Francisco, CA\", \"unit\": \"celsius\"}', 'name': 'get_current_weather'}, 'type': 'function'}, {'id': 'call_ft96IJBh0cMKkQWrZjNg4bsw', 'function': {'arguments': '{\"location\": \"New York, NY\", \"unit\": \"celsius\"}', 'name': 'get_current_weather'}, 'type': 'function'}, {'id': 'call_tfbtGgCLmuBuWgZLvpPwvUMH', 'function': {'arguments': '{\"location\": \"Los Angeles, CA\", \"unit\": \"celsius\"}', 'name': 'get_current_weather'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 84, 'prompt_tokens': 85, 'total_tokens': 169}, 'model_name': 'gpt-3.5-turbo-1106', 'system_fingerprint': 'fp_77a673219d', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-d57ad5fa-b52a-4822-bc3e-74f838697e18-0', tool_calls=[{'name': 'get_current_weather', 'args': {'location': 'San Francisco, CA', 'unit': 'celsius'}, 'id': 'call_z0OU2CytqENVrRTI6T8DkI3u'}, {'name': 'get_current_weather', 'args': {'location': 'New York, NY', 'unit': 'celsius'}, 'id': 'call_ft96IJBh0cMKkQWrZjNg4bsw'}, {'name': 'get_current_weather', 'args': {'location': 'Los Angeles, CA', 'unit': 'celsius'}, 'id': 'call_tfbtGgCLmuBuWgZLvpPwvUMH'}])"
+       "AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_zHN0ZHwrxM7nZDdqTp6dkPko', 'function': {'arguments': '{\"location\": \"San Francisco, CA\", \"unit\": \"celsius\"}', 'name': 'get_current_weather'}, 'type': 'function'}, {'id': 'call_aqdMm9HBSlFW9c9rqxTa7eQv', 'function': {'arguments': '{\"location\": \"New York, NY\", \"unit\": \"celsius\"}', 'name': 'get_current_weather'}, 'type': 'function'}, {'id': 'call_cx8E567zcLzYV2WSWVgO63f1', 'function': {'arguments': '{\"location\": \"Los Angeles, CA\", \"unit\": \"celsius\"}', 'name': 'get_current_weather'}, 'type': 'function'}]})"
       ]
      },
-     "execution_count": 5,
+     "execution_count": 9,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -195,27 +253,13 @@
     "model = ChatOpenAI(model=\"gpt-3.5-turbo-1106\").bind(tools=tools)\n",
     "model.invoke(\"What's the weather in SF, NYC and LA?\")"
    ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "095001f7",
-   "metadata": {},
-   "source": [
-    "## Next steps\n",
-    "\n",
-    "You now know how to bind runtime arguments to a Runnable.\n",
-    "\n",
-    "To learn more, see the other how-to guides on runnables in this section, including:\n",
-    "\n",
-    "- [Using configurable fields and alternatives](/docs/how_to/configure) to change parameters of a step in a chain, or even swap out entire steps, at runtime"
-   ]
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": "poetry-venv",
    "language": "python",
-   "name": "python3"
+   "name": "poetry-venv"
   },
   "language_info": {
    "codemirror_mode": {

docs/docs/expression_language/primitives/configure.ipynb

@@ -7,6 +7,7 @@
    "source": [
     "---\n",
     "sidebar_position: 7\n",
+    "title: \"Configure runtime chain internals\"\n",
     "keywords: [ConfigurableField, configurable_fields, ConfigurableAlternatives, configurable_alternatives, LCEL]\n",
     "---"
    ]
@@ -16,24 +17,16 @@
    "id": "39eaf61b",
    "metadata": {},
    "source": [
-    "# How to configure runtime chain internals\n",
+    "# Configure chain internals at runtime\n",
     "\n",
-    ":::info Prerequisites\n",
-    "\n",
-    "This guide assumes familiarity with the following concepts:\n",
-    "- [LangChain Expression Language (LCEL)](/docs/concepts/#langchain-expression-language)\n",
-    "- [Chaining runnables](/docs/how_to/sequence/)\n",
-    "- [Binding runtime arguments](/docs/how_to/binding/)\n",
-    "\n",
-    ":::\n",
-    "\n",
-    "Sometimes you may want to experiment with, or even expose to the end user, multiple different ways of doing things within your chains.\n",
-    "This can include tweaking parameters such as temperature or even swapping out one model for another.\n",
+    "Oftentimes you may want to experiment with, or even expose to the end user, multiple different ways of doing things.\n",
     "In order to make this experience as easy as possible, we have defined two methods.\n",
     "\n",
-    "- A `configurable_fields` method. This lets you configure particular fields of a runnable.\n",
-    "  - This is related to the [`.bind`](/docs/how_to/binding) method on runnables, but allows you to specify parameters for a given step in a chain at runtime rather than specifying them beforehand.\n",
-    "- A `configurable_alternatives` method. With this method, you can list out alternatives for any particular runnable that can be set during runtime, and swap them for those specified alternatives."
+    "First, a `configurable_fields` method. \n",
+    "This lets you configure particular fields of a runnable.\n",
+    "\n",
+    "Second, a `configurable_alternatives` method.\n",
+    "With this method, you can list out alternatives for any particular runnable that can be set during runtime."
    ]
   },
   {
@@ -41,53 +34,34 @@
    "id": "f2347a11",
    "metadata": {},
    "source": [
-    "## Configurable Fields\n",
-    "\n",
-    "Let's walk through an example that configures chat model fields like temperature at runtime:"
+    "## Configuration Fields"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a06f6e2d",
+   "metadata": {},
+   "source": [
+    "### With LLMs\n",
+    "With LLMs we can configure things like temperature"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "id": "40ed76a2",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\u001b[33mWARNING: You are using pip version 22.0.4; however, version 24.0 is available.\n",
-      "You should consider upgrading via the '/Users/jacoblee/.pyenv/versions/3.10.5/bin/python -m pip install --upgrade pip' command.\u001b[0m\u001b[33m\n",
-      "\u001b[0mNote: you may need to restart the kernel to use updated packages.\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
-    "%pip install --upgrade --quiet langchain langchain-openai\n",
-    "\n",
-    "import os\n",
-    "from getpass import getpass\n",
-    "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = getpass()"
+    "%pip install --upgrade --quiet  langchain langchain-openai"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 35,
    "id": "7ba735f4",
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content='17', response_metadata={'token_usage': {'completion_tokens': 1, 'prompt_tokens': 11, 'total_tokens': 12}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': 'fp_c2295e73ad', 'finish_reason': 'stop', 'logprobs': None}, id='run-ba26a0da-0a69-4533-ab7f-21178a73d303-0')"
-      ]
-     },
-     "execution_count": 2,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
     "from langchain.prompts import PromptTemplate\n",
     "from langchain_core.runnables import ConfigurableField\n",
@@ -99,32 +73,43 @@
     "        name=\"LLM Temperature\",\n",
     "        description=\"The temperature of the LLM\",\n",
     "    )\n",
-    ")\n",
-    "\n",
-    "model.invoke(\"pick a random number\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "b0f74589",
-   "metadata": {},
-   "source": [
-    "Above, we defined `temperature` as a [`ConfigurableField`](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.utils.ConfigurableField.html#langchain_core.runnables.utils.ConfigurableField) that we can set at runtime. To do so, we use the [`with_config`](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.base.Runnable.html#langchain_core.runnables.base.Runnable.with_config) method like this:"
+    ")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 38,
+   "id": "63a71165",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='7')"
+      ]
+     },
+     "execution_count": 38,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "model.invoke(\"pick a random number\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
    "id": "4f83245c",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "AIMessage(content='12', response_metadata={'token_usage': {'completion_tokens': 1, 'prompt_tokens': 11, 'total_tokens': 12}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': 'fp_c2295e73ad', 'finish_reason': 'stop', 'logprobs': None}, id='run-ba8422ad-be77-4cb1-ac45-ad0aae74e3d9-0')"
+       "AIMessage(content='34')"
       ]
      },
-     "execution_count": 3,
+     "execution_count": 39,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -138,48 +123,54 @@
    "id": "9da1fcd2",
    "metadata": {},
    "source": [
-    "Note that the passed `llm_temperature` entry in the dict has the same key as the `id` of the `ConfigurableField`.\n",
-    "\n",
-    "We can also do this to affect just one step that's part of a chain:"
+    "We can also do this when its used as part of a chain"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 40,
    "id": "e75ae678",
    "metadata": {},
+   "outputs": [],
+   "source": [
+    "prompt = PromptTemplate.from_template(\"Pick a random number above {x}\")\n",
+    "chain = prompt | model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 41,
+   "id": "44886071",
+   "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "AIMessage(content='27', response_metadata={'token_usage': {'completion_tokens': 1, 'prompt_tokens': 14, 'total_tokens': 15}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': 'fp_c2295e73ad', 'finish_reason': 'stop', 'logprobs': None}, id='run-ecd4cadd-1b72-4f92-b9a0-15e08091f537-0')"
+       "AIMessage(content='57')"
       ]
      },
-     "execution_count": 4,
+     "execution_count": 41,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "prompt = PromptTemplate.from_template(\"Pick a random number above {x}\")\n",
-    "chain = prompt | model\n",
-    "\n",
     "chain.invoke({\"x\": 0})"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 42,
    "id": "c09fac15",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "AIMessage(content='35', response_metadata={'token_usage': {'completion_tokens': 1, 'prompt_tokens': 14, 'total_tokens': 15}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': 'fp_c2295e73ad', 'finish_reason': 'stop', 'logprobs': None}, id='run-a916602b-3460-46d3-a4a8-7c926ec747c0-0')"
+       "AIMessage(content='6')"
       ]
      },
-     "execution_count": 5,
+     "execution_count": 42,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -200,9 +191,35 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 43,
+   "id": "7d5836b2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.runnables.hub import HubRunnable"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 46,
    "id": "9a9ea077",
    "metadata": {},
+   "outputs": [],
+   "source": [
+    "prompt = HubRunnable(\"rlm/rag-prompt\").configurable_fields(\n",
+    "    owner_repo_commit=ConfigurableField(\n",
+    "        id=\"hub_commit\",\n",
+    "        name=\"Hub Commit\",\n",
+    "        description=\"The Hub commit to pull from\",\n",
+    "    )\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 47,
+   "id": "c4a62cee",
+   "metadata": {},
    "outputs": [
     {
      "data": {
@@ -210,28 +227,18 @@
        "ChatPromptValue(messages=[HumanMessage(content=\"You are an assistant for question-answering tasks. Use the following pieces of retrieved context to answer the question. If you don't know the answer, just say that you don't know. Use three sentences maximum and keep the answer concise.\\nQuestion: foo \\nContext: bar \\nAnswer:\")])"
       ]
      },
-     "execution_count": 6,
+     "execution_count": 47,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "from langchain.runnables.hub import HubRunnable\n",
-    "\n",
-    "prompt = HubRunnable(\"rlm/rag-prompt\").configurable_fields(\n",
-    "    owner_repo_commit=ConfigurableField(\n",
-    "        id=\"hub_commit\",\n",
-    "        name=\"Hub Commit\",\n",
-    "        description=\"The Hub commit to pull from\",\n",
-    "    )\n",
-    ")\n",
-    "\n",
     "prompt.invoke({\"question\": \"foo\", \"context\": \"bar\"})"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 49,
    "id": "f33f3cf2",
    "metadata": {},
    "outputs": [
@@ -241,7 +248,7 @@
        "ChatPromptValue(messages=[HumanMessage(content=\"[INST]<<SYS>> You are an assistant for question-answering tasks. Use the following pieces of retrieved context to answer the question. If you don't know the answer, just say that you don't know. Use three sentences maximum and keep the answer concise.<</SYS>> \\nQuestion: foo \\nContext: bar \\nAnswer: [/INST]\")])"
       ]
      },
-     "execution_count": 7,
+     "execution_count": 49,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -266,32 +273,22 @@
    "id": "ac733d35",
    "metadata": {},
    "source": [
-    "The `configurable_alternatives()` method allows us to swap out steps in a chain with an alternative. Below, we swap out one chat model for another:"
+    "### With LLMs\n",
+    "\n",
+    "Let's take a look at doing this with LLMs"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
-   "id": "3db59f45",
+   "execution_count": 4,
+   "id": "430ab8cc",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\u001b[33mWARNING: You are using pip version 22.0.4; however, version 24.0 is available.\n",
-      "You should consider upgrading via the '/Users/jacoblee/.pyenv/versions/3.10.5/bin/python -m pip install --upgrade pip' command.\u001b[0m\u001b[33m\n",
-      "\u001b[0mNote: you may need to restart the kernel to use updated packages.\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
-    "%pip install --upgrade --quiet langchain-anthropic\n",
-    "\n",
-    "import os\n",
-    "from getpass import getpass\n",
-    "\n",
-    "os.environ[\"ANTHROPIC_API_KEY\"] = getpass()"
+    "from langchain.prompts import PromptTemplate\n",
+    "from langchain_community.chat_models import ChatAnthropic\n",
+    "from langchain_core.runnables import ConfigurableField\n",
+    "from langchain_openai import ChatOpenAI"
    ]
   },
   {
@@ -299,27 +296,9 @@
    "execution_count": 18,
    "id": "71248a9f",
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content=\"Here's a bear joke for you:\\n\\nWhy don't bears wear socks? \\nBecause they have bear feet!\\n\\nHow's that? I tried to come up with a simple, silly pun-based joke about bears. Puns and wordplay are a common way to create humorous bear jokes. Let me know if you'd like to hear another one!\", response_metadata={'id': 'msg_018edUHh5fUbWdiimhrC3dZD', 'model': 'claude-3-haiku-20240307', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 13, 'output_tokens': 80}}, id='run-775bc58c-28d7-4e6b-a268-48fa6661f02f-0')"
-      ]
-     },
-     "execution_count": 18,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
-    "from langchain.prompts import PromptTemplate\n",
-    "from langchain_anthropic import ChatAnthropic\n",
-    "from langchain_core.runnables import ConfigurableField\n",
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "llm = ChatAnthropic(\n",
-    "    model=\"claude-3-haiku-20240307\", temperature=0\n",
-    ").configurable_alternatives(\n",
+    "llm = ChatAnthropic(temperature=0).configurable_alternatives(\n",
     "    # This gives this field an id\n",
     "    # When configuring the end runnable, we can then use this id to configure this field\n",
     "    ConfigurableField(id=\"llm\"),\n",
@@ -333,25 +312,44 @@
     "    # You can add more configuration options here\n",
     ")\n",
     "prompt = PromptTemplate.from_template(\"Tell me a joke about {topic}\")\n",
-    "chain = prompt | llm\n",
-    "\n",
+    "chain = prompt | llm"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "e598b1f1",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=\" Here's a silly joke about bears:\\n\\nWhat do you call a bear with no teeth?\\nA gummy bear!\")"
+      ]
+     },
+     "execution_count": 19,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
     "# By default it will call Anthropic\n",
     "chain.invoke({\"topic\": \"bears\"})"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 20,
    "id": "48b45337",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "AIMessage(content=\"Why don't bears like fast food?\\n\\nBecause they can't catch it!\", response_metadata={'token_usage': {'completion_tokens': 15, 'prompt_tokens': 13, 'total_tokens': 28}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': 'fp_c2295e73ad', 'finish_reason': 'stop', 'logprobs': None}, id='run-7bdaa992-19c9-4f0d-9a0c-1f326bc992d4-0')"
+       "AIMessage(content=\"Sure, here's a bear joke for you:\\n\\nWhy don't bears wear shoes?\\n\\nBecause they already have bear feet!\")"
       ]
      },
-     "execution_count": 19,
+     "execution_count": 20,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -363,17 +361,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 21,
    "id": "42647fb7",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "AIMessage(content=\"Here's a bear joke for you:\\n\\nWhy don't bears wear socks? \\nBecause they have bear feet!\\n\\nHow's that? I tried to come up with a simple, silly pun-based joke about bears. Puns and wordplay are a common way to create humorous bear jokes. Let me know if you'd like to hear another one!\", response_metadata={'id': 'msg_01BZvbmnEPGBtcxRWETCHkct', 'model': 'claude-3-haiku-20240307', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 13, 'output_tokens': 80}}, id='run-59b6ee44-a1cd-41b8-a026-28ee67cdd718-0')"
+       "AIMessage(content=\" Here's a silly joke about bears:\\n\\nWhat do you call a bear with no teeth?\\nA gummy bear!\")"
       ]
      },
-     "execution_count": 20,
+     "execution_count": 21,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -395,23 +393,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 25,
    "id": "9f6a7c6c",
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content=\"Here's a bear joke for you:\\n\\nWhy don't bears wear socks? \\nBecause they have bear feet!\", response_metadata={'id': 'msg_01DtM1cssjNFZYgeS3gMZ49H', 'model': 'claude-3-haiku-20240307', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 13, 'output_tokens': 28}}, id='run-8199af7d-ea31-443d-b064-483693f2e0a1-0')"
-      ]
-     },
-     "execution_count": 22,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
-    "llm = ChatAnthropic(model=\"claude-3-haiku-20240307\", temperature=0)\n",
+    "llm = ChatAnthropic(temperature=0)\n",
     "prompt = PromptTemplate.from_template(\n",
     "    \"Tell me a joke about {topic}\"\n",
     ").configurable_alternatives(\n",
@@ -425,25 +412,44 @@
     "    poem=PromptTemplate.from_template(\"Write a short poem about {topic}\"),\n",
     "    # You can add more configuration options here\n",
     ")\n",
-    "chain = prompt | llm\n",
-    "\n",
+    "chain = prompt | llm"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "id": "97eda915",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=\" Here's a silly joke about bears:\\n\\nWhat do you call a bear with no teeth?\\nA gummy bear!\")"
+      ]
+     },
+     "execution_count": 26,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
     "# By default it will write a joke\n",
     "chain.invoke({\"topic\": \"bears\"})"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 27,
    "id": "927297a1",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "AIMessage(content=\"Here is a short poem about bears:\\n\\nMajestic bears, strong and true,\\nRoaming the forests, wild and free.\\nPowerful paws, fur soft and brown,\\nCommanding respect, nature's crown.\\n\\nForaging for berries, fishing streams,\\nProtecting their young, fierce and keen.\\nMighty bears, a sight to behold,\\nGuardians of the wilderness, untold.\\n\\nIn the wild they reign supreme,\\nEmbodying nature's grand theme.\\nBears, a symbol of strength and grace,\\nCaptivating all who see their face.\", response_metadata={'id': 'msg_01Wck3qPxrjURtutvtodaJFn', 'model': 'claude-3-haiku-20240307', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 13, 'output_tokens': 134}}, id='run-69414a1e-51d7-4bec-a307-b34b7d61025e-0')"
+       "AIMessage(content=' Here is a short poem about bears:\\n\\nThe bears awaken from their sleep\\nAnd lumber out into the deep\\nForests filled with trees so tall\\nForaging for food before nightfall \\nTheir furry coats and claws so sharp\\nSniffing for berries and fish to nab\\nLumbering about without a care\\nThe mighty grizzly and black bear\\nProud creatures, wild and free\\nRuling their domain majestically\\nWandering the woods they call their own\\nBefore returning to their dens alone')"
       ]
      },
-     "execution_count": 23,
+     "execution_count": 27,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -466,25 +472,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 25,
+   "execution_count": 28,
    "id": "97538c23",
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content=\"In the forest deep and wide,\\nBears roam with grace and pride.\\nWith fur as dark as night,\\nThey rule the land with all their might.\\n\\nIn winter's chill, they hibernate,\\nIn spring they emerge, hungry and great.\\nWith claws sharp and eyes so keen,\\nThey hunt for food, fierce and lean.\\n\\nBut beneath their tough exterior,\\nLies a gentle heart, warm and superior.\\nThey love their cubs with all their might,\\nProtecting them through day and night.\\n\\nSo let us admire these majestic creatures,\\nIn awe of their strength and features.\\nFor in the wild, they reign supreme,\\nThe mighty bears, a timeless dream.\", response_metadata={'token_usage': {'completion_tokens': 133, 'prompt_tokens': 13, 'total_tokens': 146}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': 'fp_c2295e73ad', 'finish_reason': 'stop', 'logprobs': None}, id='run-5eec0b96-d580-49fd-ac4e-e32a0803b49b-0')"
-      ]
-     },
-     "execution_count": 25,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
-    "llm = ChatAnthropic(\n",
-    "    model=\"claude-3-haiku-20240307\", temperature=0\n",
-    ").configurable_alternatives(\n",
+    "llm = ChatAnthropic(temperature=0).configurable_alternatives(\n",
     "    # This gives this field an id\n",
     "    # When configuring the end runnable, we can then use this id to configure this field\n",
     "    ConfigurableField(id=\"llm\"),\n",
@@ -510,8 +503,27 @@
     "    poem=PromptTemplate.from_template(\"Write a short poem about {topic}\"),\n",
     "    # You can add more configuration options here\n",
     ")\n",
-    "chain = prompt | llm\n",
-    "\n",
+    "chain = prompt | llm"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "id": "1dcc7ccc",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=\"In the forest, where tall trees sway,\\nA creature roams, both fierce and gray.\\nWith mighty paws and piercing eyes,\\nThe bear, a symbol of strength, defies.\\n\\nThrough snow-kissed mountains, it does roam,\\nA guardian of its woodland home.\\nWith fur so thick, a shield of might,\\nIt braves the coldest winter night.\\n\\nA gentle giant, yet wild and free,\\nThe bear commands respect, you see.\\nWith every step, it leaves a trace,\\nOf untamed power and ancient grace.\\n\\nFrom honeyed feast to salmon's leap,\\nIt takes its place, in nature's keep.\\nA symbol of untamed delight,\\nThe bear, a wonder, day and night.\\n\\nSo let us honor this noble beast,\\nIn forests where its soul finds peace.\\nFor in its presence, we come to know,\\nThe untamed spirit that in us also flows.\")"
+      ]
+     },
+     "execution_count": 29,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
     "# We can configure it write a poem with OpenAI\n",
     "chain.with_config(configurable={\"prompt\": \"poem\", \"llm\": \"openai\"}).invoke(\n",
     "    {\"topic\": \"bears\"}\n",
@@ -520,17 +532,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 26,
+   "execution_count": 30,
    "id": "e4ee9fbc",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "AIMessage(content=\"Why don't bears wear shoes?\\n\\nBecause they have bear feet!\", response_metadata={'token_usage': {'completion_tokens': 13, 'prompt_tokens': 13, 'total_tokens': 26}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': 'fp_c2295e73ad', 'finish_reason': 'stop', 'logprobs': None}, id='run-c1b14c9c-4988-49b8-9363-15bfd479973a-0')"
+       "AIMessage(content=\"Sure, here's a bear joke for you:\\n\\nWhy don't bears wear shoes?\\n\\nBecause they have bear feet!\")"
       ]
      },
-     "execution_count": 26,
+     "execution_count": 30,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -552,41 +564,35 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 27,
+   "execution_count": 31,
    "id": "5cf53202",
    "metadata": {},
+   "outputs": [],
+   "source": [
+    "openai_joke = chain.with_config(configurable={\"llm\": \"openai\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "id": "9486d701",
+   "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "AIMessage(content=\"Why did the bear break up with his girlfriend? \\nBecause he couldn't bear the relationship anymore!\", response_metadata={'token_usage': {'completion_tokens': 20, 'prompt_tokens': 13, 'total_tokens': 33}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': 'fp_c2295e73ad', 'finish_reason': 'stop', 'logprobs': None}, id='run-391ebd55-9137-458b-9a11-97acaff6a892-0')"
+       "AIMessage(content=\"Why don't bears wear shoes?\\n\\nBecause they have bear feet!\")"
       ]
      },
-     "execution_count": 27,
+     "execution_count": 32,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "openai_joke = chain.with_config(configurable={\"llm\": \"openai\"})\n",
-    "\n",
     "openai_joke.invoke({\"topic\": \"bears\"})"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "id": "76702b0e",
-   "metadata": {},
-   "source": [
-    "## Next steps\n",
-    "\n",
-    "You now know how to configure a chain's internal steps at runtime.\n",
-    "\n",
-    "To learn more, see the other how-to guides on runnables in this section, including:\n",
-    "\n",
-    "- Using [.bind()](/docs/how_to/binding) as a simpler way to set a runnable's runtime parameters"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -612,7 +618,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.11.5"
   }
  },
  "nbformat": 4,

docs/docs/expression_language/primitives/functions.ipynb

@@ -7,6 +7,7 @@
    "source": [
     "---\n",
     "sidebar_position: 3\n",
+    "title: \"Lambda: Run custom functions\"\n",
     "keywords: [RunnableLambda, LCEL]\n",
     "---"
    ]
@@ -16,64 +17,27 @@
    "id": "fbc4bf6e",
    "metadata": {},
    "source": [
-    "# How to run custom functions\n",
+    "# Run custom functions\n",
     "\n",
-    ":::info Prerequisites\n",
+    "You can use arbitrary functions in the pipeline.\n",
     "\n",
-    "This guide assumes familiarity with the following concepts:\n",
-    "- [LangChain Expression Language (LCEL)](/docs/concepts/#langchain-expression-language)\n",
-    "- [Chaining runnables](/docs/how_to/sequence/)\n",
-    "\n",
-    ":::\n",
-    "\n",
-    "You can use arbitrary functions as [Runnables](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.base.Runnable.html#langchain_core.runnables.base.Runnable). This is useful for formatting or when you need functionality not provided by other LangChain components, and custom functions used as Runnables are called [`RunnableLambdas`](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.base.RunnableLambda.html).\n",
-    "\n",
-    "Note that all inputs to these functions need to be a SINGLE argument. If you have a function that accepts multiple arguments, you should write a wrapper that accepts a single dict input and unpacks it into multiple argument.\n",
-    "\n",
-    "This guide will cover:\n",
-    "\n",
-    "- How to explicitly create a runnable from a custom function using the `RunnableLambda` constructor and the convenience `@chain` decorator\n",
-    "- Coercion of custom functions into runnables when used in chains\n",
-    "- How to accept and use run metadata in your custom function\n",
-    "- How to stream with custom functions by having them return generators\n",
-    "\n",
-    "## Using the constructor\n",
-    "\n",
-    "Below, we explicitly wrap our custom logic using the `RunnableLambda` constructor:"
+    "Note that all inputs to these functions need to be a SINGLE argument. If you have a function that accepts multiple arguments, you should write a wrapper that accepts a single input and unpacks it into multiple argument."
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "5c34d2af",
+   "cell_type": "raw",
+   "id": "9a5fe916",
    "metadata": {},
-   "outputs": [],
    "source": [
-    "%pip install -qU langchain langchain_openai\n",
-    "\n",
-    "import os\n",
-    "from getpass import getpass\n",
-    "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = getpass()"
+    "%pip install --upgrade --quiet langchain langchain-openai"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 1,
    "id": "6bb221b3",
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content='3 + 9 equals 12.', response_metadata={'token_usage': {'completion_tokens': 8, 'prompt_tokens': 14, 'total_tokens': 22}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': 'fp_c2295e73ad', 'finish_reason': 'stop', 'logprobs': None}, id='run-73728de3-e483-49e3-ad54-51bd9570e71a-0')"
-      ]
-     },
-     "execution_count": 2,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
     "from operator import itemgetter\n",
     "\n",
@@ -94,9 +58,8 @@
     "    return _multiple_length_function(_dict[\"text1\"], _dict[\"text2\"])\n",
     "\n",
     "\n",
-    "model = ChatOpenAI()\n",
-    "\n",
     "prompt = ChatPromptTemplate.from_template(\"what is {a} + {b}\")\n",
+    "model = ChatOpenAI()\n",
     "\n",
     "chain1 = prompt | model\n",
     "\n",
@@ -108,56 +71,28 @@
     "    }\n",
     "    | prompt\n",
     "    | model\n",
-    ")\n",
-    "\n",
-    "chain.invoke({\"foo\": \"bar\", \"bar\": \"gah\"})"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "b7926002",
-   "metadata": {},
-   "source": [
-    "## The convenience `@chain` decorator\n",
-    "\n",
-    "You can also turn an arbitrary function into a chain by adding a `@chain` decorator. This is functionaly equivalent to wrapping the function in a `RunnableLambda` constructor as shown above. Here's an example:"
+    ")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
-   "id": "3142a516",
+   "execution_count": 2,
+   "id": "5488ec85",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "'The subject of the joke is the bear and his girlfriend.'"
+       "AIMessage(content='3 + 9 = 12', response_metadata={'token_usage': {'completion_tokens': 7, 'prompt_tokens': 14, 'total_tokens': 21}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': 'fp_b28b39ffa8', 'finish_reason': 'stop', 'logprobs': None}, id='run-bd204541-81fd-429a-ad92-dd1913af9b1c-0')"
       ]
      },
-     "execution_count": 3,
+     "execution_count": 2,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "from langchain_core.output_parsers import StrOutputParser\n",
-    "from langchain_core.runnables import chain\n",
-    "\n",
-    "prompt1 = ChatPromptTemplate.from_template(\"Tell me a joke about {topic}\")\n",
-    "prompt2 = ChatPromptTemplate.from_template(\"What is the subject of this joke: {joke}\")\n",
-    "\n",
-    "\n",
-    "@chain\n",
-    "def custom_chain(text):\n",
-    "    prompt_val1 = prompt1.invoke({\"topic\": text})\n",
-    "    output1 = ChatOpenAI().invoke(prompt_val1)\n",
-    "    parsed_output1 = StrOutputParser().invoke(output1)\n",
-    "    chain2 = prompt2 | ChatOpenAI() | StrOutputParser()\n",
-    "    return chain2.invoke({\"joke\": parsed_output1})\n",
-    "\n",
-    "\n",
-    "custom_chain.invoke(\"bears\")"
+    "chain.invoke({\"foo\": \"bar\", \"bar\": \"gah\"})"
    ]
   },
   {
@@ -165,78 +100,31 @@
    "id": "4728ddd9-914d-42ce-ae9b-72c9ce8ec940",
    "metadata": {},
    "source": [
-    "Above, the `@chain` decorator is used to convert `custom_chain` into a runnable, which we invoke with the `.invoke()` method.\n",
+    "## Accepting a Runnable Config\n",
     "\n",
-    "If you are using a tracing with [LangSmith](/docs/langsmith/), you should see a `custom_chain` trace in there, with the calls to OpenAI nested underneath.\n",
-    "\n",
-    "## Automatic coercion in chains\n",
-    "\n",
-    "When using custom functions in chains with the pipe operator (`|`), you can omit the `RunnableLambda` or `@chain` constructor and rely on coercion. Here's a simple example with a function that takes the output from the model and returns the first five letters of it:"
+    "Runnable lambdas can optionally accept a [RunnableConfig](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.config.RunnableConfig.html#langchain_core.runnables.config.RunnableConfig), which they can use to pass callbacks, tags, and other configuration information to nested runs."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "80b3b5f6-5d58-44b9-807e-cce9a46bf49f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.output_parsers import StrOutputParser\n",
+    "from langchain_core.runnables import RunnableConfig"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 4,
-   "id": "5ab39a87",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'Once '"
-      ]
-     },
-     "execution_count": 4,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "prompt = ChatPromptTemplate.from_template(\"tell me a story about {topic}\")\n",
-    "\n",
-    "model = ChatOpenAI()\n",
-    "\n",
-    "chain_with_coerced_function = prompt | model | (lambda x: x.content[:5])\n",
-    "\n",
-    "chain_with_coerced_function.invoke({\"topic\": \"bears\"})"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "c9a481d1",
-   "metadata": {},
-   "source": [
-    "Note that we didn't need to wrap the custom function `(lambda x: x.content[:5])` in a `RunnableLambda` constructor because the `model` on the left of the pipe operator is already a Runnable. The custom function is **coerced** into a runnable. See [this section](/docs/how_to/sequence/#coercion) for more information.\n",
-    "\n",
-    "## Passing run metadata\n",
-    "\n",
-    "Runnable lambdas can optionally accept a [RunnableConfig](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.config.RunnableConfig.html#langchain_core.runnables.config.RunnableConfig) parameter, which they can use to pass callbacks, tags, and other configuration information to nested runs."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
    "id": "ff0daf0c-49dd-4d21-9772-e5fa133c5f36",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "{'foo': 'bar'}\n",
-      "Tokens Used: 62\n",
-      "\tPrompt Tokens: 56\n",
-      "\tCompletion Tokens: 6\n",
-      "Successful Requests: 1\n",
-      "Total Cost (USD): $9.6e-05\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "import json\n",
     "\n",
-    "from langchain_core.runnables import RunnableConfig\n",
-    "\n",
     "\n",
     "def parse_or_fix(text: str, config: RunnableConfig):\n",
     "    fixing_chain = (\n",
@@ -244,7 +132,7 @@
     "            \"Fix the following text:\\n\\n```text\\n{input}\\n```\\nError: {error}\"\n",
     "            \" Don't narrate, just respond with the fixed data.\"\n",
     "        )\n",
-    "        | model\n",
+    "        | ChatOpenAI()\n",
     "        | StrOutputParser()\n",
     "    )\n",
     "    for _ in range(3):\n",
@@ -252,22 +140,12 @@
     "            return json.loads(text)\n",
     "        except Exception as e:\n",
     "            text = fixing_chain.invoke({\"input\": text, \"error\": e}, config)\n",
-    "    return \"Failed to parse\"\n",
-    "\n",
-    "\n",
-    "from langchain_community.callbacks import get_openai_callback\n",
-    "\n",
-    "with get_openai_callback() as cb:\n",
-    "    output = RunnableLambda(parse_or_fix).invoke(\n",
-    "        \"{foo: bar}\", {\"tags\": [\"my-tag\"], \"callbacks\": [cb]}\n",
-    "    )\n",
-    "    print(output)\n",
-    "    print(cb)"
+    "    return \"Failed to parse\""
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 5,
    "id": "1a5e709e-9d75-48c7-bb9c-503251990505",
    "metadata": {},
    "outputs": [
@@ -302,7 +180,7 @@
    "source": [
     "# Streaming\n",
     "\n",
-    "You can use generator functions (ie. functions that use the `yield` keyword, and behave like iterators) in a chain.\n",
+    "You can use generator functions (ie. functions that use the `yield` keyword, and behave like iterators) in a LCEL pipeline.\n",
     "\n",
     "The signature of these generators should be `Iterator[Input] -> Iterator[Output]`. Or for async generators: `AsyncIterator[Input] -> AsyncIterator[Output]`.\n",
     "\n",
@@ -310,13 +188,30 @@
     "- implementing a custom output parser\n",
     "- modifying the output of a previous step, while preserving streaming capabilities\n",
     "\n",
-    "Here's an example of a custom output parser for comma-separated lists. First, we create a chain that generates such a list as text:"
+    "Here's an example of a custom output parser for comma-separated lists:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "29f55c38",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from typing import Iterator, List\n",
+    "\n",
+    "prompt = ChatPromptTemplate.from_template(\n",
+    "    \"Write a comma-separated list of 5 animals similar to: {animal}. Do not include numbers\"\n",
+    ")\n",
+    "model = ChatOpenAI(temperature=0.0)\n",
+    "\n",
+    "str_chain = prompt | model | StrOutputParser()"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 7,
-   "id": "29f55c38",
+   "id": "75aa946b",
    "metadata": {},
    "outputs": [
     {
@@ -328,44 +223,37 @@
     }
    ],
    "source": [
-    "from typing import Iterator, List\n",
-    "\n",
-    "prompt = ChatPromptTemplate.from_template(\n",
-    "    \"Write a comma-separated list of 5 animals similar to: {animal}. Do not include numbers\"\n",
-    ")\n",
-    "\n",
-    "str_chain = prompt | model | StrOutputParser()\n",
-    "\n",
     "for chunk in str_chain.stream({\"animal\": \"bear\"}):\n",
     "    print(chunk, end=\"\", flush=True)"
    ]
   },
   {
-   "cell_type": "markdown",
-   "id": "46345323",
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "d002a7fe",
    "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'lion, tiger, wolf, gorilla, panda'"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
-    "Next, we define a custom function that will aggregate the currently streamed output and yield it when the model generates the next comma in the list:"
+    "str_chain.invoke({\"animal\": \"bear\"})"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 9,
    "id": "f08b8a5b",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "['lion']\n",
-      "['tiger']\n",
-      "['wolf']\n",
-      "['gorilla']\n",
-      "['raccoon']\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "# This is a custom parser that splits an iterator of llm tokens\n",
     "# into a list of strings separated by commas\n",
@@ -384,58 +272,23 @@
     "            # save the rest for the next iteration\n",
     "            buffer = buffer[comma_index + 1 :]\n",
     "    # yield the last chunk\n",
-    "    yield [buffer.strip()]\n",
-    "\n",
-    "\n",
-    "list_chain = str_chain | split_into_list\n",
-    "\n",
-    "for chunk in list_chain.stream({\"animal\": \"bear\"}):\n",
-    "    print(chunk, flush=True)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "0a5adb69",
-   "metadata": {},
-   "source": [
-    "Invoking it gives a full array of values:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "9ea4ddc6",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "['lion', 'tiger', 'wolf', 'gorilla', 'raccoon']"
-      ]
-     },
-     "execution_count": 9,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "list_chain.invoke({\"animal\": \"bear\"})"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "96e320ed",
-   "metadata": {},
-   "source": [
-    "## Async version\n",
-    "\n",
-    "If you are working in an `async` environment, here is an `async` version of the above example:"
+    "    yield [buffer.strip()]"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 10,
-   "id": "569dbbef",
+   "id": "02e414aa",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "list_chain = str_chain | split_into_list"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "7ed8799d",
    "metadata": {},
    "outputs": [
     {
@@ -450,6 +303,46 @@
      ]
     }
    ],
+   "source": [
+    "for chunk in list_chain.stream({\"animal\": \"bear\"}):\n",
+    "    print(chunk, flush=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "9ea4ddc6",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['lion', 'tiger', 'wolf', 'gorilla', 'elephant']"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "list_chain.invoke({\"animal\": \"bear\"})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "96e320ed",
+   "metadata": {},
+   "source": [
+    "## Async version"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "569dbbef",
+   "metadata": {},
+   "outputs": [],
    "source": [
     "from typing import AsyncIterator\n",
     "\n",
@@ -469,15 +362,35 @@
     "    yield [buffer.strip()]\n",
     "\n",
     "\n",
-    "list_chain = str_chain | asplit_into_list\n",
-    "\n",
+    "list_chain = str_chain | asplit_into_list"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "7a76b713",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "['lion']\n",
+      "['tiger']\n",
+      "['wolf']\n",
+      "['gorilla']\n",
+      "['panda']\n"
+     ]
+    }
+   ],
+   "source": [
     "async for chunk in list_chain.astream({\"animal\": \"bear\"}):\n",
     "    print(chunk, flush=True)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 15,
    "id": "3a650482",
    "metadata": {},
    "outputs": [
@@ -487,7 +400,7 @@
        "['lion', 'tiger', 'wolf', 'gorilla', 'panda']"
       ]
      },
-     "execution_count": 11,
+     "execution_count": 15,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -495,18 +408,6 @@
    "source": [
     "await list_chain.ainvoke({\"animal\": \"bear\"})"
    ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "3306ac3b",
-   "metadata": {},
-   "source": [
-    "## Next steps\n",
-    "\n",
-    "Now you've learned a few different ways to use custom logic within your chains, and how to implement streaming.\n",
-    "\n",
-    "To learn more, see the other how-to guides on runnables in this section."
-   ]
   }
  ],
  "metadata": {
@@ -525,7 +426,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.10.5"
   }
  },
  "nbformat": 4,

docs/docs/expression_language/primitives/index.mdx

@@ -0,0 +1,15 @@
+---
+sidebar_class_name: hidden
+---
+
+# Primitives
+
+In addition to various [components](/docs/modules) that are usable with LCEL, LangChain also includes various primitives
+that help pass around and format data, bind arguments, invoke custom logic, and more.
+
+This section goes into greater depth on where and how some of these components are useful.
+
+import DocCardList from "@theme/DocCardList";
+import { useCurrentSidebarCategory } from '@docusaurus/theme-common';
+
+<DocCardList items={useCurrentSidebarCategory().items.filter((item) => item.href !== "/docs/expression_language/primitives/")} />

docs/docs/expression_language/primitives/parallel.ipynb

@@ -7,6 +7,7 @@
    "source": [
     "---\n",
     "sidebar_position: 1\n",
+    "title: \"Parallel: Format data\"\n",
     "keywords: [RunnableParallel, RunnableMap, LCEL]\n",
     "---"
    ]
@@ -16,33 +17,13 @@
    "id": "b022ab74-794d-4c54-ad47-ff9549ddb9d2",
    "metadata": {},
    "source": [
-    "# How to invoke runnables in parallel\n",
+    "# Formatting inputs & output\n",
     "\n",
-    ":::info Prerequisites\n",
+    "The `RunnableParallel` primitive is essentially a dict whose values are runnables (or things that can be coerced to runnables, like functions). It runs all of its values in parallel, and each value is called with the overall input of the `RunnableParallel`. The final return value is a dict with the results of each value under its appropriate key.\n",
     "\n",
-    "This guide assumes familiarity with the following concepts:\n",
-    "- [LangChain Expression Language (LCEL)](/docs/concepts/#langchain-expression-language)\n",
-    "- [Chaining runnables](/docs/how_to/sequence)\n",
+    "It is useful for parallelizing operations, but can also be useful for manipulating the output of one Runnable to match the input format of the next Runnable in a sequence.\n",
     "\n",
-    ":::\n",
-    "\n",
-    "The [`RunnableParallel`](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.base.RunnableParallel.html) primitive is essentially a dict whose values are runnables (or things that can be coerced to runnables, like functions). It runs all of its values in parallel, and each value is called with the overall input of the `RunnableParallel`. The final return value is a dict with the results of each value under its appropriate key.\n",
-    "\n",
-    "## Formatting with `RunnableParallels`\n",
-    "\n",
-    "`RunnableParallels` are useful for parallelizing operations, but can also be useful for manipulating the output of one Runnable to match the input format of the next Runnable in a sequence. You can use them to split or fork the chain so that multiple components can process the input in parallel. Later, other components can join or merge the results to synthesize a final response. This type of chain creates a computation graph that looks like the following:\n",
-    "\n",
-    "```text\n",
-    "     Input\n",
-    "      / \\\n",
-    "     /   \\\n",
-    " Branch1 Branch2\n",
-    "     \\   /\n",
-    "      \\ /\n",
-    "      Combine\n",
-    "```\n",
-    "\n",
-    "Below, the input to prompt is expected to be a map with keys `\"context\"` and `\"question\"`. The user input is just the question. So we need to get the context using our retriever and passthrough the user input under the `\"question\"` key.\n"
+    "Here the input to prompt is expected to be a map with keys \"context\" and \"question\". The user input is just the question. So we need to get the context using our retriever and passthrough the user input under the \"question\" key.\n"
    ]
   },
   {
@@ -52,20 +33,12 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# | output: false\n",
-    "# | echo: false\n",
-    "\n",
-    "%pip install -qU langchain langchain_openai\n",
-    "\n",
-    "import os\n",
-    "from getpass import getpass\n",
-    "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = getpass()"
+    "%pip install --upgrade --quiet  langchain langchain-openai"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 3,
    "id": "267d1460-53c1-4fdb-b2c3-b6a1eb7fccff",
    "metadata": {},
    "outputs": [
@@ -75,7 +48,7 @@
        "'Harrison worked at Kensho.'"
       ]
      },
-     "execution_count": 2,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -96,10 +69,7 @@
     "\n",
     "Question: {question}\n",
     "\"\"\"\n",
-    "\n",
-    "# The prompt expects input with keys for \"context\" and \"question\"\n",
     "prompt = ChatPromptTemplate.from_template(template)\n",
-    "\n",
     "model = ChatOpenAI()\n",
     "\n",
     "retrieval_chain = (\n",
@@ -132,8 +102,7 @@
     "```\n",
     "RunnableParallel(context=retriever, question=RunnablePassthrough())\n",
     "```\n",
-    "\n",
-    "See the section on [coercion for more](/docs/how_to/sequence/#coercion)."
+    "\n"
    ]
   },
   {
@@ -150,7 +119,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 6,
    "id": "84fc49e1-2daf-4700-ae33-a0a6ed47d5f6",
    "metadata": {},
    "outputs": [
@@ -160,7 +129,7 @@
        "'Harrison ha lavorato a Kensho.'"
       ]
      },
-     "execution_count": 3,
+     "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -209,23 +178,23 @@
    "source": [
     "## Parallelize steps\n",
     "\n",
-    "RunnableParallels make it easy to execute multiple Runnables in parallel, and to return the output of these Runnables as a map."
+    "RunnableParallel (aka. RunnableMap) makes it easy to execute multiple Runnables in parallel, and to return the output of these Runnables as a map."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 1,
    "id": "31f18442-f837-463f-bef4-8729368f5f8b",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "{'joke': AIMessage(content=\"Why don't bears like fast food? Because they can't catch it!\", response_metadata={'token_usage': {'completion_tokens': 15, 'prompt_tokens': 13, 'total_tokens': 28}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': 'fp_d9767fc5b9', 'finish_reason': 'stop', 'logprobs': None}, id='run-fe024170-c251-4b7a-bfd4-64a3737c67f2-0'),\n",
-       " 'poem': AIMessage(content='In the quiet of the forest, the bear roams free\\nMajestic and wild, a sight to see.', response_metadata={'token_usage': {'completion_tokens': 24, 'prompt_tokens': 15, 'total_tokens': 39}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': 'fp_c2295e73ad', 'finish_reason': 'stop', 'logprobs': None}, id='run-2707913e-a743-4101-b6ec-840df4568a76-0')}"
+       "{'joke': AIMessage(content=\"Why don't bears wear shoes?\\n\\nBecause they have bear feet!\"),\n",
+       " 'poem': AIMessage(content=\"In the wild's embrace, bear roams free,\\nStrength and grace, a majestic decree.\")}"
       ]
      },
-     "execution_count": 4,
+     "execution_count": 1,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -258,7 +227,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 6,
    "id": "38e47834-45af-4281-991f-86f150001510",
    "metadata": {},
    "outputs": [
@@ -266,7 +235,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "610 ms ± 64 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)\n"
+      "958 ms ± 402 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)\n"
      ]
     }
    ],
@@ -278,7 +247,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 7,
    "id": "d0cd40de-b37e-41fa-a2f6-8aaa49f368d6",
    "metadata": {},
    "outputs": [
@@ -286,7 +255,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "599 ms ± 73.3 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)\n"
+      "1.22 s ± 508 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)\n"
      ]
     }
    ],
@@ -298,7 +267,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 8,
    "id": "799894e1-8e18-4a73-b466-f6aea6af3920",
    "metadata": {},
    "outputs": [
@@ -306,7 +275,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "643 ms ± 77.8 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)\n"
+      "1.15 s ± 119 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)\n"
      ]
     }
    ],
@@ -315,26 +284,6 @@
     "\n",
     "map_chain.invoke({\"topic\": \"bear\"})"
    ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "7d4492e1",
-   "metadata": {},
-   "source": [
-    "## Next steps\n",
-    "\n",
-    "You now know some ways to format and parallelize chain steps with `RunnableParallel`.\n",
-    "\n",
-    "To learn more, see the other how-to guides on runnables in this section."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "4af8bebd",
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {
@@ -353,7 +302,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.11.6"
   }
  },
  "nbformat": 4,

docs/docs/expression_language/primitives/passthrough.ipynb

@@ -7,6 +7,7 @@
    "source": [
     "---\n",
     "sidebar_position: 5\n",
+    "title: \"Passthrough: Pass through inputs\"\n",
     "keywords: [RunnablePassthrough, LCEL]\n",
     "---"
    ]
@@ -16,20 +17,9 @@
    "id": "b022ab74-794d-4c54-ad47-ff9549ddb9d2",
    "metadata": {},
    "source": [
-    "# How to pass through arguments from one step to the next\n",
+    "# Passing data through\n",
     "\n",
-    ":::info Prerequisites\n",
-    "\n",
-    "This guide assumes familiarity with the following concepts:\n",
-    "- [LangChain Expression Language (LCEL)](/docs/concepts/#langchain-expression-language)\n",
-    "- [Chaining runnables](/docs/how_to/sequence/)\n",
-    "- [Calling runnables in parallel](/docs/how_to/parallel/)\n",
-    "- [Custom functions](/docs/how_to/functions/)\n",
-    "\n",
-    ":::\n",
-    "\n",
-    "\n",
-    "When composing chains with several steps, sometimes you will want to pass data from previous steps unchanged for use as input to a later step. The [`RunnablePassthrough`](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.passthrough.RunnablePassthrough.html) class allows you to do just this, and is typically is used in conjuction with a [RunnableParallel](/docs/how_to/parallel/) to pass data through to a later step in your constructed chains.\n",
+    "RunnablePassthrough on its own allows you to pass inputs unchanged. This typically is used in conjuction with RunnableParallel to pass data through to a new key in the map. \n",
     "\n",
     "See the example below:"
    ]
@@ -41,27 +31,22 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install -qU langchain langchain-openai\n",
-    "\n",
-    "import os\n",
-    "from getpass import getpass\n",
-    "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = getpass()"
+    "%pip install --upgrade --quiet  langchain langchain-openai"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 11,
    "id": "03988b8d-d54c-4492-8707-1594372cf093",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "{'passed': {'num': 1}, 'modified': 2}"
+       "{'passed': {'num': 1}, 'extra': {'num': 1, 'mult': 3}, 'modified': 2}"
       ]
      },
-     "execution_count": 2,
+     "execution_count": 11,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -94,12 +79,12 @@
    "source": [
     "## Retrieval Example\n",
     "\n",
-    "In the example below, we see a more real-world use case where we use `RunnablePassthrough` along with `RunnableParallel` in a chain to properly format inputs to a prompt:"
+    "In the example below, we see a use case where we use `RunnablePassthrough` along with `RunnableParallel`. "
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 17,
    "id": "267d1460-53c1-4fdb-b2c3-b6a1eb7fccff",
    "metadata": {},
    "outputs": [
@@ -109,7 +94,7 @@
        "'Harrison worked at Kensho.'"
       ]
      },
-     "execution_count": 3,
+     "execution_count": 17,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -148,13 +133,7 @@
    "id": "392cd4c4-e7ed-4ab8-934d-f7a4eca55ee1",
    "metadata": {},
    "source": [
-    "Here the input to prompt is expected to be a map with keys \"context\" and \"question\". The user input is just the question. So we need to get the context using our retriever and passthrough the user input under the \"question\" key. The `RunnablePassthrough` allows us to pass on the user's question to the prompt and model. \n",
-    "\n",
-    "## Next steps\n",
-    "\n",
-    "Now you've learned how to pass data through your chains to help to help format the data flowing through your chains.\n",
-    "\n",
-    "To learn more, see the other how-to guides on runnables in this section."
+    "Here the input to prompt is expected to be a map with keys \"context\" and \"question\". The user input is just the question. So we need to get the context using our retriever and passthrough the user input under the \"question\" key. In this case, the RunnablePassthrough allows us to pass on the user's question to the prompt and model. \n"
    ]
   }
  ],
@@ -174,7 +153,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.11.6"
   }
  },
  "nbformat": 4,

docs/docs/expression_language/primitives/sequence.ipynb

@@ -6,6 +6,7 @@
    "source": [
     "---\n",
     "sidebar_position: 0\n",
+    "title: \"Sequences: Chaining runnables\"\n",
     "keywords: [Runnable, Runnables, LCEL]\n",
     "---"
    ]
@@ -14,54 +15,22 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# How to chain runnables\n",
+    "# Chaining runnables\n",
     "\n",
-    ":::info Prerequisites\n",
-    "\n",
-    "This guide assumes familiarity with the following concepts:\n",
-    "- [LangChain Expression Language (LCEL)](/docs/concepts/#langchain-expression-language)\n",
-    "- [Prompt templates](/docs/concepts/#prompt-templates)\n",
-    "- [Chat models](/docs/concepts/#chat-models)\n",
-    "- [Output parser](/docs/concepts/#output-parsers)\n",
-    "\n",
-    ":::\n",
-    "\n",
-    "One point about [LangChain Expression Language](/docs/concepts/#langchain-expression-language) is that any two runnables can be \"chained\" together into sequences. The output of the previous runnable's `.invoke()` call is passed as input to the next runnable. This can be done using the pipe operator (`|`), or the more explicit `.pipe()` method, which does the same thing.\n",
-    "\n",
-    "The resulting [`RunnableSequence`](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.base.RunnableSequence.html) is itself a runnable, which means it can be invoked, streamed, or further chained just like any other runnable. Advantages of chaining runnables in this way are efficient streaming (the sequence will stream output as soon as it is available), and debugging and tracing with tools like [LangSmith](/docs/how_to/debugging).\n",
+    "One key advantage of the `Runnable` interface is that any two runnables can be \"chained\" together into sequences. The output of the previous runnable's `.invoke()` call is passed as input to the next runnable. This can be done using the pipe operator (`|`), or the more explicit `.pipe()` method, which does the same thing. The resulting `RunnableSequence` is itself a runnable, which means it can be invoked, streamed, or piped just like any other runnable.\n",
     "\n",
     "## The pipe operator\n",
     "\n",
-    "To show off how this works, let's go through an example. We'll walk through a common pattern in LangChain: using a [prompt template](/docs/how_to#prompt-templates) to format input into a [chat model](/docs/how_to#chat-models), and finally converting the chat message output into a string with an [output parser](/docs/how_to#output-parsers).\n",
-    "\n",
-    "```{=mdx}\n",
-    "import ChatModelTabs from \"@theme/ChatModelTabs\";\n",
-    "\n",
-    "<ChatModelTabs\n",
-    "  customVarName=\"model\"\n",
-    "/>\n",
-    "```"
+    "To show off how this works, let's go through an example. We'll walk through a common pattern in LangChain: using a [prompt template](/docs/modules/model_io/prompts/) to format input into a [chat model](/docs/modules/model_io/chat/), and finally converting the chat message output into a string with an [output parser](/docs/modules/model_io/output_parsers/)."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
-    "# | output: false\n",
-    "# | echo: false\n",
-    "\n",
-    "%pip install -qU langchain langchain_anthropic\n",
-    "\n",
-    "import os\n",
-    "from getpass import getpass\n",
-    "\n",
-    "from langchain_anthropic import ChatAnthropic\n",
-    "\n",
-    "os.environ[\"ANTHROPIC_API_KEY\"] = getpass()\n",
-    "\n",
-    "model = ChatAnthropic(model=\"claude-3-sonnet-20240229\", temperature=0)"
+    "%pip install --upgrade --quiet langchain langchain-anthropic"
    ]
   },
   {
@@ -70,10 +39,12 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "from langchain_anthropic import ChatAnthropic\n",
     "from langchain_core.output_parsers import StrOutputParser\n",
     "from langchain_core.prompts import ChatPromptTemplate\n",
     "\n",
     "prompt = ChatPromptTemplate.from_template(\"tell me a joke about {topic}\")\n",
+    "model = ChatAnthropic(model_name=\"claude-3-haiku-20240307\")\n",
     "\n",
     "chain = prompt | model | StrOutputParser()"
    ]
@@ -93,7 +64,7 @@
     {
      "data": {
       "text/plain": [
-       "\"Here's a bear joke for you:\\n\\nWhy did the bear dissolve in water?\\nBecause it was a polar bear!\""
+       "\"Here's a bear joke for you:\\n\\nWhy don't bears wear socks? \\nBecause they have bear feet!\\n\\nHow's that? I tried to keep it light and silly. Bears can make for some fun puns and jokes. Let me know if you'd like to hear another one!\""
       ]
      },
      "execution_count": 3,
@@ -115,7 +86,7 @@
     "\n",
     "For example, let's say we wanted to compose the joke generating chain with another chain that evaluates whether or not the generated joke was funny.\n",
     "\n",
-    "We would need to be careful with how we format the input into the next chain. In the below example, the dict in the chain is automatically parsed and converted into a [`RunnableParallel`](/docs/how_to/parallel), which runs all of its values in parallel and returns a dict with the results.\n",
+    "We would need to be careful with how we format the input into the next chain. In the below example, the dict in the chain is automatically parsed and converted into a [`RunnableParallel`](/docs/expression_language/primitives/parallel), which runs all of its values in parallel and returns a dict with the results.\n",
     "\n",
     "This happens to be the same format the next prompt template expects. Here it is in action:"
    ]
@@ -124,25 +95,32 @@
    "cell_type": "code",
    "execution_count": 4,
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'Haha, that\\'s a clever play on words! Using \"polar\" to imply the bear dissolved or became polar/polarized when put in water. Not the most hilarious joke ever, but it has a cute, groan-worthy pun that makes it mildly amusing. I appreciate a good pun or wordplay joke.'"
-      ]
-     },
-     "execution_count": 4,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
     "from langchain_core.output_parsers import StrOutputParser\n",
     "\n",
     "analysis_prompt = ChatPromptTemplate.from_template(\"is this a funny joke? {joke}\")\n",
     "\n",
-    "composed_chain = {\"joke\": chain} | analysis_prompt | model | StrOutputParser()\n",
-    "\n",
+    "composed_chain = {\"joke\": chain} | analysis_prompt | model | StrOutputParser()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "\"That's a pretty classic and well-known bear pun joke. Whether it's considered funny is quite subjective, as humor is very personal. Some people may find that type of pun-based joke amusing, while others may not find it that humorous. Ultimately, the funniness of a joke is in the eye (or ear) of the beholder. If you enjoyed the joke and got a chuckle out of it, then that's what matters most.\""
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
     "composed_chain.invoke({\"topic\": \"bears\"})"
    ]
   },
@@ -155,20 +133,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 6,
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "\"Haha, that's a cute and punny joke! I like how it plays on the idea of beets blushing or turning red like someone blushing. Food puns can be quite amusing. While not a total knee-slapper, it's a light-hearted, groan-worthy dad joke that would make me chuckle and shake my head. Simple vegetable humor!\""
-      ]
-     },
-     "execution_count": 5,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
     "composed_chain_with_lambda = (\n",
     "    chain\n",
@@ -176,8 +143,26 @@
     "    | analysis_prompt\n",
     "    | model\n",
     "    | StrOutputParser()\n",
-    ")\n",
-    "\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'I appreciate the effort, but I have to be honest - I didn\\'t find that joke particularly funny. Beet-themed puns can be quite hit-or-miss, and this one falls more on the \"miss\" side for me. The premise is a bit too straightforward and predictable. While I can see the logic behind it, the punchline just doesn\\'t pack much of a comedic punch. \\n\\nThat said, I do admire your willingness to explore puns and wordplay around vegetables. Cultivating a good sense of humor takes practice, and not every joke is going to land. The important thing is to keep experimenting and finding what works. Maybe try for a more unexpected or creative twist on beet-related humor next time. But thanks for sharing - I always appreciate when humans test out jokes on me, even if they don\\'t always make me laugh out loud.'"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
     "composed_chain_with_lambda.invoke({\"topic\": \"beets\"})"
    ]
   },
@@ -185,7 +170,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "However, keep in mind that using functions like this may interfere with operations like streaming. See [this section](/docs/how_to/functions) for more information."
+    "However, keep in mind that using functions like this may interfere with operations like streaming. See [this section](/docs/expression_language/primitives/functions) for more information."
    ]
   },
   {
@@ -199,20 +184,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 8,
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "\"I cannot reproduce any copyrighted material verbatim, but I can try to analyze the humor in the joke you provided without quoting it directly.\\n\\nThe joke plays on the idea that the Cylon raiders, who are the antagonists in the Battlestar Galactica universe, failed to locate the human survivors after attacking their home planets (the Twelve Colonies) due to using an outdated and poorly performing operating system (Windows Vista) for their targeting systems.\\n\\nThe humor stems from the juxtaposition of a futuristic science fiction setting with a relatable real-world frustration – the use of buggy, slow, or unreliable software or technology. It pokes fun at the perceived inadequacies of Windows Vista, which was widely criticized for its performance issues and other problems when it was released.\\n\\nBy attributing the Cylons' failure to locate the humans to their use of Vista, the joke creates an amusing and unexpected connection between a fictional advanced race of robots and a familiar technological annoyance experienced by many people in the real world.\\n\\nOverall, the joke relies on incongruity and relatability to generate humor, but without reproducing any copyrighted material directly.\""
-      ]
-     },
-     "execution_count": 6,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
     "from langchain_core.runnables import RunnableParallel\n",
     "\n",
@@ -221,26 +195,33 @@
     "    .pipe(analysis_prompt)\n",
     "    .pipe(model)\n",
     "    .pipe(StrOutputParser())\n",
-    ")\n",
-    "\n",
-    "composed_chain_with_pipe.invoke({\"topic\": \"battlestar galactica\"})"
+    ")"
    ]
   },
   {
-   "cell_type": "markdown",
+   "cell_type": "code",
+   "execution_count": 9,
    "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'That\\'s a pretty good Battlestar Galactica-themed pun! I appreciated the clever play on words with \"Centurion\" and \"center on.\" It\\'s the kind of nerdy, science fiction-inspired humor that fans of the show would likely enjoy. The joke is clever and demonstrates a good understanding of the Battlestar Galactica universe. I\\'d be curious to hear any other Battlestar-related jokes you might have up your sleeve. As long as they don\\'t reproduce copyrighted material, I\\'m happy to provide my thoughts on the humor and appeal for fans of the show.'"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
-    "## Next steps\n",
-    "\n",
-    "You now know some ways to chain two runnables together.\n",
-    "\n",
-    "To learn more, see the other how-to guides on runnables in this section."
+    "composed_chain_with_pipe.invoke({\"topic\": \"battlestar galactica\"})"
    ]
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": "Python 3",
    "language": "python",
    "name": "python3"
   },
@@ -254,9 +235,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.10.5"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 4
+ "nbformat_minor": 2
 }

docs/docs/get_started/introduction.mdx

@@ -8,18 +8,17 @@ sidebar_class_name: hidden
 **LangChain** is a framework for developing applications powered by large language models (LLMs).
 
 LangChain simplifies every stage of the LLM application lifecycle:
-- **Development**: Build your applications using LangChain's open-source [building blocks](/docs/concepts#langchain-expression-language) and [components](/docs/concepts). Hit the ground running using [third-party integrations](/docs/integrations/platforms/) and [Templates](/docs/templates).
+- **Development**: Build your applications using LangChain's open-source [building blocks](/docs/expression_language/) and [components](/docs/modules/). Hit the ground running using [third-party integrations](/docs/integrations/platforms/) and [Templates](/docs/templates).
 - **Productionization**: Use [LangSmith](/docs/langsmith/) to inspect, monitor and evaluate your chains, so that you can continuously optimize and deploy with confidence.
 - **Deployment**: Turn any chain into an API with [LangServe](/docs/langserve).
 
 import ThemedImage from '@theme/ThemedImage';
-import useBaseUrl from '@docusaurus/useBaseUrl';
 
 <ThemedImage
   alt="Diagram outlining the hierarchical organization of the LangChain framework, displaying the interconnected parts across multiple layers."
   sources={{
-    light: useBaseUrl('/svg/langchain_stack.svg'),
-    dark: useBaseUrl('/svg/langchain_stack_dark.svg'),
+    light: '/svg/langchain_stack.svg',
+    dark: '/svg/langchain_stack_dark.svg',
   }}
   title="LangChain Framework Overview"
 />
@@ -32,8 +31,16 @@ Concretely, the framework consists of the following open-source libraries:
 - **`langchain`**: Chains, agents, and retrieval strategies that make up an application's cognitive architecture.
 - **[langgraph](/docs/langgraph)**: Build robust and stateful multi-actor applications with LLMs by modeling steps as edges and nodes in a graph.
 - **[langserve](/docs/langserve)**: Deploy LangChain chains as REST APIs.
-- **[LangSmith](/docs/langsmith)**: A developer platform that lets you debug, test, evaluate, and monitor LLM applications.
 
+The broader ecosystem includes:
+
+- **[LangSmith](/docs/langsmith)**: A developer platform that lets you debug, test, evaluate, and monitor LLM applications and seamlessly integrates with LangChain.
+
+## Get started
+
+We recommend following our [Quickstart](/docs/get_started/quickstart) guide to familiarize yourself with the framework by building your first LangChain application.
+
+[See here](/docs/get_started/installation) for instructions on how to install LangChain, set up your environment, and start building.
 
 :::note
 
@@ -41,31 +48,25 @@ These docs focus on the Python LangChain library. [Head here](https://js.langcha
 
 :::
 
-## [Tutorials](/docs/tutorials)
+## Use cases
 
-If you're looking to build something specific or are more of a hands-on learner, check out our [tutorials](/docs/tutorials).
-This is the best place to get started.
+If you're looking to build something specific or are more of a hands-on learner, check out our [use-cases](/docs/use_cases).
+They're walkthroughs and techniques for common end-to-end tasks, such as:
 
-These are the best ones to get started with:
-- [Build a Simple LLM Application](/docs/tutorials/llm_chain)
-- [Build a Chatbot](/docs/tutorials/chatbot)
-- [Build an Agent](/docs/tutorials/agents)
-
-Explore the full list of tutorials [here](/docs/tutorials).
+- [Question answering with RAG](/docs/use_cases/question_answering/)
+- [Extracting structured output](/docs/use_cases/extraction/)
+- [Chatbots](/docs/use_cases/chatbots/)
+- and more!
 
 
-## [How-to guides](/docs/how_to)
+## Expression Language
 
-[Here](/docs/how_to) you’ll find short answers to “How do I….?” types of questions.
-These how-to guides don’t cover topics in depth – you’ll find that material in the [Tutorials](/docs/tutorials) and the [API Reference](https://api.python.langchain.com/en/latest/).
-However, these guides will help you quickly accomplish common tasks.
+LangChain Expression Language (LCEL) is the foundation of many of LangChain's components, and is a declarative way to compose chains. LCEL was designed from day 1 to support putting prototypes in production, with no code changes, from the simplest “prompt + LLM” chain to the most complex chains.
 
-## [Conceptual guide](/docs/concepts)
-
-Introductions to all the key parts of LangChain you’ll need to know! [Here](/docs/concepts) you'll find high level explanations of all LangChain concepts.
-
-## [API reference](https://api.python.langchain.com)
-Head to the reference section for full documentation of all classes and methods in the LangChain Python packages.
+- **[Get started](/docs/expression_language/)**: LCEL and its benefits
+- **[Runnable interface](/docs/expression_language/interface)**: The standard interface for LCEL objects
+- **[Primitives](/docs/expression_language/primitives)**: More on the primitives LCEL includes
+- and more!
 
 ## Ecosystem
 
@@ -78,14 +79,22 @@ Build stateful, multi-actor applications with LLMs, built on top of (and intende
 ### [🦜🏓 LangServe](/docs/langserve)
 Deploy LangChain runnables and chains as REST APIs.
 
+## [Security](/docs/security)
+Read up on our [Security](/docs/security) best practices to make sure you're developing safely with LangChain.
 
 ## Additional resources
 
-### [Security](/docs/security)
-Read up on our [Security](/docs/security) best practices to make sure you're developing safely with LangChain.
+### [Components](/docs/modules/)
+LangChain provides standard, extendable interfaces and integrations for many different components, including:
 
 ### [Integrations](/docs/integrations/providers/)
 LangChain is part of a rich ecosystem of tools that integrate with our framework and build on top of it. Check out our growing list of [integrations](/docs/integrations/providers/).
 
+### [Guides](/docs/guides/)
+Best practices for developing with LangChain.
+
+### [API reference](https://api.python.langchain.com)
+Head to the reference section for full documentation of all classes and methods in the LangChain and LangChain Experimental Python packages.
+
 ### [Contributing](/docs/contributing)
 Check out the developer's guide for guidelines on contributing and help getting your dev environment set up.

docs/docs/get_started/quickstart.mdx

@@ -0,0 +1,685 @@
+---
+sidebar_position: 1
+---
+
+# Quickstart
+
+In this quickstart we'll show you how to:
+- Get setup with LangChain, LangSmith and LangServe
+- Use the most basic and common components of LangChain: prompt templates, models, and output parsers
+- Use LangChain Expression Language, the protocol that LangChain is built on and which facilitates component chaining
+- Build a simple application with LangChain
+- Trace your application with LangSmith
+- Serve your application with LangServe
+
+That's a fair amount to cover! Let's dive in.
+
+## Setup
+
+### Jupyter Notebook
+
+This guide (and most of the other guides in the documentation) uses [Jupyter notebooks](https://jupyter.org/) and assumes the reader is as well. Jupyter notebooks are perfect for learning how to work with LLM systems because oftentimes things can go wrong (unexpected output, API down, etc) and going through guides in an interactive environment is a great way to better understand them.
+
+You do not NEED to go through the guide in a Jupyter Notebook, but it is recommended. See [here](https://jupyter.org/install) for instructions on how to install.
+
+### Installation
+
+To install LangChain run:
+
+import Tabs from '@theme/Tabs';
+import TabItem from '@theme/TabItem';
+import CodeBlock from "@theme/CodeBlock";
+
+<Tabs>
+  <TabItem value="pip" label="Pip" default>
+    <CodeBlock language="bash">pip install langchain</CodeBlock>
+  </TabItem>
+  <TabItem value="conda" label="Conda">
+    <CodeBlock language="bash">conda install langchain -c conda-forge</CodeBlock>
+  </TabItem>
+</Tabs>
+
+
+For more details, see our [Installation guide](/docs/get_started/installation).
+
+### LangSmith
+
+Many of the applications you build with LangChain will contain multiple steps with multiple invocations of LLM calls.
+As these applications get more and more complex, it becomes crucial to be able to inspect what exactly is going on inside your chain or agent.
+The best way to do this is with [LangSmith](https://smith.langchain.com).
+
+Note that LangSmith is not needed, but it is helpful.
+If you do want to use LangSmith, after you sign up at the link above, make sure to set your environment variables to start logging traces:
+
+```shell
+export LANGCHAIN_TRACING_V2="true"
+export LANGCHAIN_API_KEY="..."
+```
+
+## Building with LangChain
+
+LangChain enables building application that connect external sources of data and computation to LLMs.
+In this quickstart, we will walk through a few different ways of doing that.
+We will start with a simple LLM chain, which just relies on information in the prompt template to respond.
+Next, we will build a retrieval chain, which fetches data from a separate database and passes that into the prompt template.
+We will then add in chat history, to create a conversation retrieval chain. This allows you to interact in a chat manner with this LLM, so it remembers previous questions.
+Finally, we will build an agent - which utilizes an LLM to determine whether or not it needs to fetch data to answer questions.
+We will cover these at a high level, but there are lot of details to all of these!
+We will link to relevant docs.
+
+## LLM Chain
+
+We'll show how to use models available via API, like OpenAI, and local open source models, using integrations like Ollama.
+
+<Tabs>
+  <TabItem value="openai" label="OpenAI" default>
+
+First we'll need to import the LangChain x OpenAI integration package.
+
+```shell
+pip install langchain-openai
+```
+
+Accessing the API requires an API key, which you can get by creating an account and heading [here](https://platform.openai.com/account/api-keys). Once we have a key we'll want to set it as an environment variable by running:
+
+```shell
+export OPENAI_API_KEY="..."
+```
+
+We can then initialize the model:
+
+```python
+from langchain_openai import ChatOpenAI
+
+llm = ChatOpenAI()
+```
+
+If you'd prefer not to set an environment variable you can pass the key in directly via the `api_key` named parameter when initiating the OpenAI LLM class:
+
+```python
+from langchain_openai import ChatOpenAI
+
+llm = ChatOpenAI(api_key="...")
+```
+
+  </TabItem>
+  <TabItem value="local" label="Local (using Ollama)">
+
+[Ollama](https://ollama.ai/) allows you to run open-source large language models, such as Llama 2, locally.
+
+First, follow [these instructions](https://github.com/jmorganca/ollama) to set up and run a local Ollama instance:
+
+* [Download](https://ollama.ai/download)
+* Fetch a model via `ollama pull llama2`
+
+Then, make sure the Ollama server is running. After that, you can do:
+```python
+from langchain_community.llms import Ollama
+llm = Ollama(model="llama2")
+```
+
+  </TabItem>
+  <TabItem value="anthropic" label="Anthropic">
+
+First we'll need to import the LangChain x Anthropic package.
+
+```shell
+pip install langchain-anthropic
+```
+
+Accessing the API requires an API key, which you can get by creating an account [here](https://claude.ai/login). Once we have a key we'll want to set it as an environment variable by running:
+
+```shell
+export ANTHROPIC_API_KEY="..."
+```
+
+We can then initialize the model:
+
+```python
+from langchain_anthropic import ChatAnthropic
+
+llm = ChatAnthropic(model="claude-3-sonnet-20240229", temperature=0.2, max_tokens=1024)
+```
+
+If you'd prefer not to set an environment variable you can pass the key in directly via the `api_key` named parameter when initiating the Anthropic Chat Model class:
+
+```python
+llm = ChatAnthropic(api_key="...")
+```
+
+  </TabItem>
+  <TabItem value="cohere" label="Cohere">
+
+First we'll need to import the Cohere SDK package.
+
+```shell
+pip install langchain-cohere
+```
+
+Accessing the API requires an API key, which you can get by creating an account and heading [here](https://dashboard.cohere.com/api-keys). Once we have a key we'll want to set it as an environment variable by running:
+
+```shell
+export COHERE_API_KEY="..."
+```
+
+We can then initialize the model:
+
+```python
+from langchain_cohere import ChatCohere
+
+llm = ChatCohere()
+```
+
+If you'd prefer not to set an environment variable you can pass the key in directly via the `cohere_api_key` named parameter when initiating the Cohere LLM class:
+
+```python
+from langchain_cohere import ChatCohere
+
+llm = ChatCohere(cohere_api_key="...")
+```
+
+  </TabItem>
+</Tabs>
+
+Once you've installed and initialized the LLM of your choice, we can try using it!
+Let's ask it what LangSmith is - this is something that wasn't present in the training data so it shouldn't have a very good response.
+
+```python
+llm.invoke("how can langsmith help with testing?")
+```
+
+We can also guide its response with a prompt template.
+Prompt templates convert raw user input to better input to the LLM.
+
+```python
+from langchain_core.prompts import ChatPromptTemplate
+prompt = ChatPromptTemplate.from_messages([
+    ("system", "You are world class technical documentation writer."),
+    ("user", "{input}")
+])
+```
+
+We can now combine these into a simple LLM chain:
+
+```python
+chain = prompt | llm 
+```
+
+We can now invoke it and ask the same question. It still won't know the answer, but it should respond in a more proper tone for a technical writer!
+
+```python
+chain.invoke({"input": "how can langsmith help with testing?"})
+```
+
+The output of a ChatModel (and therefore, of this chain) is a message. However, it's often much more convenient to work with strings. Let's add a simple output parser to convert the chat message to a string.
+
+```python
+from langchain_core.output_parsers import StrOutputParser
+
+output_parser = StrOutputParser()
+```
+
+We can now add this to the previous chain:
+
+```python
+chain = prompt | llm | output_parser
+```
+
+We can now invoke it and ask the same question. The answer will now be a string (rather than a ChatMessage).
+
+```python
+chain.invoke({"input": "how can langsmith help with testing?"})
+```
+
+### Diving Deeper
+
+We've now successfully set up a basic LLM chain. We only touched on the basics of prompts, models, and output parsers - for a deeper dive into everything mentioned here, see [this section of documentation](/docs/modules/model_io).
+
+
+## Retrieval Chain
+
+To properly answer the original question ("how can langsmith help with testing?"), we need to provide additional context to the LLM.
+We can do this via *retrieval*.
+Retrieval is useful when you have **too much data** to pass to the LLM directly.
+You can then use a retriever to fetch only the most relevant pieces and pass those in.
+
+In this process, we will look up relevant documents from a *Retriever* and then pass them into the prompt.
+A Retriever can be backed by anything - a SQL table, the internet, etc - but in this instance we will populate a vector store and use that as a retriever. For more information on vectorstores, see [this documentation](/docs/modules/data_connection/vectorstores).
+
+First, we need to load the data that we want to index. To do this, we will use the WebBaseLoader. This requires installing [BeautifulSoup](https://beautiful-soup-4.readthedocs.io/en/latest/):
+
+```shell
+pip install beautifulsoup4
+```
+
+After that, we can import and use WebBaseLoader.
+
+
+```python
+from langchain_community.document_loaders import WebBaseLoader
+loader = WebBaseLoader("https://docs.smith.langchain.com/user_guide")
+
+docs = loader.load()
+```
+
+Next, we need to index it into a vectorstore. This requires a few components, namely an [embedding model](/docs/modules/data_connection/text_embedding) and a [vectorstore](/docs/modules/data_connection/vectorstores).
+
+For embedding models, we once again provide examples for accessing via API or by running local models.
+
+<Tabs>
+  <TabItem value="openai" label="OpenAI (API)" default>
+  
+Make sure you have the `langchain_openai` package installed an the appropriate environment variables set (these are the same as needed for the LLM).
+
+```python
+from langchain_openai import OpenAIEmbeddings
+
+embeddings = OpenAIEmbeddings()
+```
+
+</TabItem>
+<TabItem value="local" label="Local (using Ollama)">
+
+Make sure you have Ollama running (same set up as with the LLM).
+
+```python
+from langchain_community.embeddings import OllamaEmbeddings
+
+embeddings = OllamaEmbeddings()
+```
+  </TabItem>
+<TabItem value="cohere" label="Cohere (API)" default>
+
+Make sure you have the `cohere` package installed and the appropriate environment variables set (these are the same as needed for the LLM).
+
+```python
+from langchain_community.embeddings import CohereEmbeddings
+
+embeddings = CohereEmbeddings()
+```
+
+</TabItem>
+</Tabs>
+
+Now, we can use this embedding model to ingest documents into a vectorstore.
+We will use a simple local vectorstore, [FAISS](/docs/integrations/vectorstores/faiss), for simplicity's sake.
+
+First we need to install the required packages for that:
+
+```shell
+pip install faiss-cpu
+```
+
+Then we can build our index:
+
+```python
+from langchain_community.vectorstores import FAISS
+from langchain_text_splitters import RecursiveCharacterTextSplitter
+
+
+text_splitter = RecursiveCharacterTextSplitter()
+documents = text_splitter.split_documents(docs)
+vector = FAISS.from_documents(documents, embeddings)
+```
+
+Now that we have this data indexed in a vectorstore, we will create a retrieval chain.
+This chain will take an incoming question, look up relevant documents, then pass those documents along with the original question into an LLM and ask it to answer the original question.
+
+First, let's set up the chain that takes a question and the retrieved documents and generates an answer.
+
+```python
+from langchain.chains.combine_documents import create_stuff_documents_chain
+
+prompt = ChatPromptTemplate.from_template("""Answer the following question based only on the provided context:
+
+<context>
+{context}
+</context>
+
+Question: {input}""")
+
+document_chain = create_stuff_documents_chain(llm, prompt)
+```
+
+If we wanted to, we could run this ourselves by passing in documents directly:
+
+```python
+from langchain_core.documents import Document
+
+document_chain.invoke({
+    "input": "how can langsmith help with testing?",
+    "context": [Document(page_content="langsmith can let you visualize test results")]
+})
+```
+
+However, we want the documents to first come from the retriever we just set up.
+That way, we can use the retriever to dynamically select the most relevant documents and pass those in for a given question.
+
+```python
+from langchain.chains import create_retrieval_chain
+
+retriever = vector.as_retriever()
+retrieval_chain = create_retrieval_chain(retriever, document_chain)
+```
+
+We can now invoke this chain. This returns a dictionary - the response from the LLM is in the `answer` key
+
+```python
+response = retrieval_chain.invoke({"input": "how can langsmith help with testing?"})
+print(response["answer"])
+
+# LangSmith offers several features that can help with testing:...
+```
+
+This answer should be much more accurate!
+
+### Diving Deeper
+
+We've now successfully set up a basic retrieval chain. We only touched on the basics of retrieval - for a deeper dive into everything mentioned here, see [this section of documentation](/docs/modules/data_connection).
+
+## Conversation Retrieval Chain
+
+The chain we've created so far can only answer single questions. One of the main types of LLM applications that people are building are chat bots. So how do we turn this chain into one that can answer follow up questions?
+
+We can still use the `create_retrieval_chain` function, but we need to change two things:
+
+1. The retrieval method should now not just work on the most recent input, but rather should take the whole history into account.
+2. The final LLM chain should likewise take the whole history into account
+
+**Updating Retrieval**
+
+In order to update retrieval, we will create a new chain. This chain will take in the most recent input (`input`) and the conversation history (`chat_history`) and use an LLM to generate a search query.
+
+```python
+from langchain.chains import create_history_aware_retriever
+from langchain_core.prompts import MessagesPlaceholder
+
+# First we need a prompt that we can pass into an LLM to generate this search query
+
+prompt = ChatPromptTemplate.from_messages([
+    MessagesPlaceholder(variable_name="chat_history"),
+    ("user", "{input}"),
+    ("user", "Given the above conversation, generate a search query to look up to get information relevant to the conversation")
+])
+retriever_chain = create_history_aware_retriever(llm, retriever, prompt)
+```
+
+We can test this out by passing in an instance where the user asks a follow-up question.
+
+```python
+from langchain_core.messages import HumanMessage, AIMessage
+
+chat_history = [HumanMessage(content="Can LangSmith help test my LLM applications?"), AIMessage(content="Yes!")]
+retriever_chain.invoke({
+    "chat_history": chat_history,
+    "input": "Tell me how"
+})
+```
+You should see that this returns documents about testing in LangSmith. This is because the LLM generated a new query, combining the chat history with the follow-up question.
+
+Now that we have this new retriever, we can create a new chain to continue the conversation with these retrieved documents in mind.
+
+```python
+prompt = ChatPromptTemplate.from_messages([
+    ("system", "Answer the user's questions based on the below context:\n\n{context}"),
+    MessagesPlaceholder(variable_name="chat_history"),
+    ("user", "{input}"),
+])
+document_chain = create_stuff_documents_chain(llm, prompt)
+
+retrieval_chain = create_retrieval_chain(retriever_chain, document_chain)
+```
+
+We can now test this out end-to-end:
+
+```python
+chat_history = [HumanMessage(content="Can LangSmith help test my LLM applications?"), AIMessage(content="Yes!")]
+retrieval_chain.invoke({
+    "chat_history": chat_history,
+    "input": "Tell me how"
+})
+```
+We can see that this gives a coherent answer - we've successfully turned our retrieval chain into a chatbot!
+
+## Agent
+
+We've so far created examples of chains - where each step is known ahead of time.
+The final thing we will create is an agent - where the LLM decides what steps to take.
+
+**NOTE: for this example we will only show how to create an agent using OpenAI models, as local models are not reliable enough yet.**
+
+One of the first things to do when building an agent is to decide what tools it should have access to.
+For this example, we will give the agent access to two tools:
+
+1. The retriever we just created. This will let it easily answer questions about LangSmith
+2. A search tool. This will let it easily answer questions that require up-to-date information.
+
+First, let's set up a tool for the retriever we just created:
+
+```python
+from langchain.tools.retriever import create_retriever_tool
+
+retriever_tool = create_retriever_tool(
+    retriever,
+    "langsmith_search",
+    "Search for information about LangSmith. For any questions about LangSmith, you must use this tool!",
+)
+```
+
+
+The search tool that we will use is [Tavily](/docs/integrations/retrievers/tavily). This will require an API key (they have generous free tier). After creating it on their platform, you need to set it as an environment variable:
+
+```shell
+export TAVILY_API_KEY=...
+```
+If you do not want to set up an API key, you can skip creating this tool.
+
+```python
+from langchain_community.tools.tavily_search import TavilySearchResults
+
+search = TavilySearchResults()
+```
+
+We can now create a list of the tools we want to work with:
+
+```python
+tools = [retriever_tool, search]
+```
+
+Now that we have the tools, we can create an agent to use them. We will go over this pretty quickly - for a deeper dive into what exactly is going on, check out the [Agent's Getting Started documentation](/docs/modules/agents)
+
+Install langchain hub first
+```bash
+pip install langchainhub
+```
+Install the langchain-openai package
+To interact with OpenAI we need to use langchain-openai which connects with OpenAI SDK[https://github.com/langchain-ai/langchain/tree/master/libs/partners/openai].  
+```bash
+pip install langchain-openai
+```
+
+Now we can use it to get a predefined prompt
+
+```python
+from langchain_openai import ChatOpenAI
+from langchain import hub
+from langchain.agents import create_openai_functions_agent
+from langchain.agents import AgentExecutor
+
+# Get the prompt to use - you can modify this!
+prompt = hub.pull("hwchase17/openai-functions-agent")
+
+# You need to set OPENAI_API_KEY environment variable or pass it as argument `api_key`.
+llm = ChatOpenAI(model="gpt-3.5-turbo", temperature=0)
+agent = create_openai_functions_agent(llm, tools, prompt)
+agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)
+```
+
+We can now invoke the agent and see how it responds! We can ask it questions about LangSmith:
+
+```python
+agent_executor.invoke({"input": "how can langsmith help with testing?"})
+```
+
+We can ask it about the weather:
+
+```python
+agent_executor.invoke({"input": "what is the weather in SF?"})
+```
+
+We can have conversations with it:
+
+```python
+chat_history = [HumanMessage(content="Can LangSmith help test my LLM applications?"), AIMessage(content="Yes!")]
+agent_executor.invoke({
+    "chat_history": chat_history,
+    "input": "Tell me how"
+})
+```
+
+### Diving Deeper
+
+We've now successfully set up a basic agent. We only touched on the basics of agents - for a deeper dive into everything mentioned here, see [this section of documentation](/docs/modules/agents).
+
+
+## Serving with LangServe
+
+Now that we've built an application, we need to serve it. That's where LangServe comes in.
+LangServe helps developers deploy LangChain chains as a REST API. You do not need to use LangServe to use LangChain, but in this guide we'll show how you can deploy your app with LangServe.
+
+While the first part of this guide was intended to be run in a Jupyter Notebook, we will now move out of that. We will be creating a Python file and then interacting with it from the command line.
+
+Install with:
+```bash
+pip install "langserve[all]"
+```
+
+### Server
+
+To create a server for our application we'll make a `serve.py` file. This will contain our logic for serving our application. It consists of three things:
+1. The definition of our chain that we just built above
+2. Our FastAPI app
+3. A definition of a route from which to serve the chain, which is done with `langserve.add_routes`
+
+```python
+#!/usr/bin/env python
+from typing import List
+
+from fastapi import FastAPI
+from langchain_core.prompts import ChatPromptTemplate
+from langchain_openai import ChatOpenAI
+from langchain_community.document_loaders import WebBaseLoader
+from langchain_openai import OpenAIEmbeddings
+from langchain_community.vectorstores import FAISS
+from langchain_text_splitters import RecursiveCharacterTextSplitter
+from langchain.tools.retriever import create_retriever_tool
+from langchain_community.tools.tavily_search import TavilySearchResults
+from langchain import hub
+from langchain.agents import create_openai_functions_agent
+from langchain.agents import AgentExecutor
+from langchain.pydantic_v1 import BaseModel, Field
+from langchain_core.messages import BaseMessage
+from langserve import add_routes
+
+# 1. Load Retriever
+loader = WebBaseLoader("https://docs.smith.langchain.com/user_guide")
+docs = loader.load()
+text_splitter = RecursiveCharacterTextSplitter()
+documents = text_splitter.split_documents(docs)
+embeddings = OpenAIEmbeddings()
+vector = FAISS.from_documents(documents, embeddings)
+retriever = vector.as_retriever()
+
+# 2. Create Tools
+retriever_tool = create_retriever_tool(
+    retriever,
+    "langsmith_search",
+    "Search for information about LangSmith. For any questions about LangSmith, you must use this tool!",
+)
+search = TavilySearchResults()
+tools = [retriever_tool, search]
+
+
+# 3. Create Agent
+prompt = hub.pull("hwchase17/openai-functions-agent")
+llm = ChatOpenAI(model="gpt-3.5-turbo", temperature=0)
+agent = create_openai_functions_agent(llm, tools, prompt)
+agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)
+
+
+# 4. App definition
+app = FastAPI(
+  title="LangChain Server",
+  version="1.0",
+  description="A simple API server using LangChain's Runnable interfaces",
+)
+
+# 5. Adding chain route
+
+# We need to add these input/output schemas because the current AgentExecutor
+# is lacking in schemas.
+
+class Input(BaseModel):
+    input: str
+    chat_history: List[BaseMessage] = Field(
+        ...,
+        extra={"widget": {"type": "chat", "input": "location"}},
+    )
+
+
+class Output(BaseModel):
+    output: str
+
+add_routes(
+    app,
+    agent_executor.with_types(input_type=Input, output_type=Output),
+    path="/agent",
+)
+
+if __name__ == "__main__":
+    import uvicorn
+
+    uvicorn.run(app, host="localhost", port=8000)
+```
+
+And that's it! If we execute this file:
+```bash
+python serve.py
+```
+we should see our chain being served at localhost:8000.
+
+### Playground
+
+Every LangServe service comes with a simple built-in UI for configuring and invoking the application with streaming output and visibility into intermediate steps.
+Head to http://localhost:8000/agent/playground/ to try it out! Pass in the same question as before - "how can langsmith help with testing?" - and it should respond same as before.
+
+### Client
+
+Now let's set up a client for programmatically interacting with our service. We can easily do this with the `[langserve.RemoteRunnable](/docs/langserve#client)`.
+Using this, we can interact with the served chain as if it were running client-side.
+
+```python
+from langserve import RemoteRunnable
+
+remote_chain = RemoteRunnable("http://localhost:8000/agent/")
+remote_chain.invoke({
+    "input": "how can langsmith help with testing?",
+    "chat_history": []  # Providing an empty list as this is the first call
+})
+```
+
+To learn more about the many other features of LangServe [head here](/docs/langserve).
+
+## Next steps
+
+We've touched on how to build an application with LangChain, how to trace it with LangSmith, and how to serve it with LangServe.
+There are a lot more features in all three of these than we can cover here.
+To continue on your journey, we recommend you read the following (in order):
+
+- All of these features are backed by [LangChain Expression Language (LCEL)](/docs/expression_language) - a way to chain these components together. Check out that documentation to better understand how to create custom chains.
+- [Model IO](/docs/modules/model_io) covers more details of prompts, LLMs, and output parsers.
+- [Retrieval](/docs/modules/data_connection) covers more details of everything related to retrieval
+- [Agents](/docs/modules/agents) covers details of everything related to agents
+- Explore common [end-to-end use cases](/docs/use_cases/) and [template applications](/docs/templates)
+- [Read up on LangSmith](/docs/langsmith/), the platform for debugging, testing, monitoring and more
+- Learn more about serving your applications with [LangServe](/docs/langserve)

docs/docs/guides/development/debugging.md

@@ -0,0 +1,661 @@
+# Debugging
+
+If you're building with LLMs, at some point something will break, and you'll need to debug. A model call will fail, or the model output will be misformatted, or there will be some nested model calls and it won't be clear where along the way an incorrect output was created.
+
+Here are a few different tools and functionalities to aid in debugging.
+
+
+
+## Tracing
+
+Platforms with tracing capabilities like [LangSmith](/docs/langsmith/) are the most comprehensive solutions for debugging. These platforms make it easy to not only log and visualize LLM apps, but also to actively debug, test and refine them.
+
+When building production-grade LLM applications, platforms like this are essential.
+
+![Screenshot of the LangSmith debugging interface showing an AgentExecutor run with input and output details, and a run tree visualization.](../../../static/img/run_details.png "LangSmith Debugging Interface")
+
+## `set_debug` and `set_verbose`
+
+If you're prototyping in Jupyter Notebooks or running Python scripts, it can be helpful to print out the intermediate steps of a Chain run. 
+
+There are a number of ways to enable printing at varying degrees of verbosity.
+
+Let's suppose we have a simple agent, and want to visualize the actions it takes and tool outputs it receives. Without any debugging, here's what we see:
+
+
+```python
+from langchain.agents import AgentType, initialize_agent, load_tools
+from langchain_openai import ChatOpenAI
+
+llm = ChatOpenAI(model="gpt-4", temperature=0)
+tools = load_tools(["ddg-search", "llm-math"], llm=llm)
+agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION)
+```
+
+
+```python
+agent.run("Who directed the 2023 film Oppenheimer and what is their age? What is their age in days (assume 365 days per year)?")
+```
+
+<CodeOutputBlock lang="python">
+
+```
+    'The director of the 2023 film Oppenheimer is Christopher Nolan and he is approximately 19345 days old in 2023.'
+```
+
+</CodeOutputBlock>
+
+### `set_debug(True)`
+
+Setting the global `debug` flag will cause all LangChain components with callback support (chains, models, agents, tools, retrievers) to print the inputs they receive and outputs they generate. This is the most verbose setting and will fully log raw inputs and outputs.
+
+
+```python
+from langchain.globals import set_debug
+
+set_debug(True)
+
+agent.run("Who directed the 2023 film Oppenheimer and what is their age? What is their age in days (assume 365 days per year)?")
+```
+
+<details> <summary>Console output</summary>
+
+<CodeOutputBlock lang="python">
+
+```
+    [chain/start] [1:RunTypeEnum.chain:AgentExecutor] Entering Chain run with input:
+    {
+      "input": "Who directed the 2023 film Oppenheimer and what is their age? What is their age in days (assume 365 days per year)?"
+    }
+    [chain/start] [1:RunTypeEnum.chain:AgentExecutor > 2:RunTypeEnum.chain:LLMChain] Entering Chain run with input:
+    {
+      "input": "Who directed the 2023 film Oppenheimer and what is their age? What is their age in days (assume 365 days per year)?",
+      "agent_scratchpad": "",
+      "stop": [
+        "\nObservation:",
+        "\n\tObservation:"
+      ]
+    }
+    [llm/start] [1:RunTypeEnum.chain:AgentExecutor > 2:RunTypeEnum.chain:LLMChain > 3:RunTypeEnum.llm:ChatOpenAI] Entering LLM run with input:
+    {
+      "prompts": [
+        "Human: Answer the following questions as best you can. You have access to the following tools:\n\nduckduckgo_search: A wrapper around DuckDuckGo Search. Useful for when you need to answer questions about current events. Input should be a search query.\nCalculator: Useful for when you need to answer questions about math.\n\nUse the following format:\n\nQuestion: the input question you must answer\nThought: you should always think about what to do\nAction: the action to take, should be one of [duckduckgo_search, Calculator]\nAction Input: the input to the action\nObservation: the result of the action\n... (this Thought/Action/Action Input/Observation can repeat N times)\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question\n\nBegin!\n\nQuestion: Who directed the 2023 film Oppenheimer and what is their age? What is their age in days (assume 365 days per year)?\nThought:"
+      ]
+    }
+    [llm/end] [1:RunTypeEnum.chain:AgentExecutor > 2:RunTypeEnum.chain:LLMChain > 3:RunTypeEnum.llm:ChatOpenAI] [5.53s] Exiting LLM run with output:
+    {
+      "generations": [
+        [
+          {
+            "text": "I need to find out who directed the 2023 film Oppenheimer and their age. Then, I need to calculate their age in days. I will use DuckDuckGo to find out the director and their age.\nAction: duckduckgo_search\nAction Input: \"Director of the 2023 film Oppenheimer and their age\"",
+            "generation_info": {
+              "finish_reason": "stop"
+            },
+            "message": {
+              "lc": 1,
+              "type": "constructor",
+              "id": [
+                "langchain",
+                "schema",
+                "messages",
+                "AIMessage"
+              ],
+              "kwargs": {
+                "content": "I need to find out who directed the 2023 film Oppenheimer and their age. Then, I need to calculate their age in days. I will use DuckDuckGo to find out the director and their age.\nAction: duckduckgo_search\nAction Input: \"Director of the 2023 film Oppenheimer and their age\"",
+                "additional_kwargs": {}
+              }
+            }
+          }
+        ]
+      ],
+      "llm_output": {
+        "token_usage": {
+          "prompt_tokens": 206,
+          "completion_tokens": 71,
+          "total_tokens": 277
+        },
+        "model_name": "gpt-4"
+      },
+      "run": null
+    }
+    [chain/end] [1:RunTypeEnum.chain:AgentExecutor > 2:RunTypeEnum.chain:LLMChain] [5.53s] Exiting Chain run with output:
+    {
+      "text": "I need to find out who directed the 2023 film Oppenheimer and their age. Then, I need to calculate their age in days. I will use DuckDuckGo to find out the director and their age.\nAction: duckduckgo_search\nAction Input: \"Director of the 2023 film Oppenheimer and their age\""
+    }
+    [tool/start] [1:RunTypeEnum.chain:AgentExecutor > 4:RunTypeEnum.tool:duckduckgo_search] Entering Tool run with input:
+    "Director of the 2023 film Oppenheimer and their age"
+    [tool/end] [1:RunTypeEnum.chain:AgentExecutor > 4:RunTypeEnum.tool:duckduckgo_search] [1.51s] Exiting Tool run with output:
+    "Capturing the mad scramble to build the first atomic bomb required rapid-fire filming, strict set rules and the construction of an entire 1940s western town. By Jada Yuan. July 19, 2023 at 5:00 a ... In Christopher Nolan's new film, "Oppenheimer," Cillian Murphy stars as J. Robert Oppenheimer, the American physicist who oversaw the Manhattan Project in Los Alamos, N.M. Universal Pictures... Oppenheimer: Directed by Christopher Nolan. With Cillian Murphy, Emily Blunt, Robert Downey Jr., Alden Ehrenreich. The story of American scientist J. Robert Oppenheimer and his role in the development of the atomic bomb. Christopher Nolan goes deep on 'Oppenheimer,' his most 'extreme' film to date. By Kenneth Turan. July 11, 2023 5 AM PT. For Subscribers. Christopher Nolan is photographed in Los Angeles ... Oppenheimer is a 2023 epic biographical thriller film written and directed by Christopher Nolan.It is based on the 2005 biography American Prometheus by Kai Bird and Martin J. Sherwin about J. Robert Oppenheimer, a theoretical physicist who was pivotal in developing the first nuclear weapons as part of the Manhattan Project and thereby ushering in the Atomic Age."
+    [chain/start] [1:RunTypeEnum.chain:AgentExecutor > 5:RunTypeEnum.chain:LLMChain] Entering Chain run with input:
+    {
+      "input": "Who directed the 2023 film Oppenheimer and what is their age? What is their age in days (assume 365 days per year)?",
+      "agent_scratchpad": "I need to find out who directed the 2023 film Oppenheimer and their age. Then, I need to calculate their age in days. I will use DuckDuckGo to find out the director and their age.\nAction: duckduckgo_search\nAction Input: \"Director of the 2023 film Oppenheimer and their age\"\nObservation: Capturing the mad scramble to build the first atomic bomb required rapid-fire filming, strict set rules and the construction of an entire 1940s western town. By Jada Yuan. July 19, 2023 at 5:00 a ... In Christopher Nolan's new film, \"Oppenheimer,\" Cillian Murphy stars as J. Robert Oppenheimer, the American physicist who oversaw the Manhattan Project in Los Alamos, N.M. Universal Pictures... Oppenheimer: Directed by Christopher Nolan. With Cillian Murphy, Emily Blunt, Robert Downey Jr., Alden Ehrenreich. The story of American scientist J. Robert Oppenheimer and his role in the development of the atomic bomb. Christopher Nolan goes deep on 'Oppenheimer,' his most 'extreme' film to date. By Kenneth Turan. July 11, 2023 5 AM PT. For Subscribers. Christopher Nolan is photographed in Los Angeles ... Oppenheimer is a 2023 epic biographical thriller film written and directed by Christopher Nolan.It is based on the 2005 biography American Prometheus by Kai Bird and Martin J. Sherwin about J. Robert Oppenheimer, a theoretical physicist who was pivotal in developing the first nuclear weapons as part of the Manhattan Project and thereby ushering in the Atomic Age.\nThought:",
+      "stop": [
+        "\nObservation:",
+        "\n\tObservation:"
+      ]
+    }
+    [llm/start] [1:RunTypeEnum.chain:AgentExecutor > 5:RunTypeEnum.chain:LLMChain > 6:RunTypeEnum.llm:ChatOpenAI] Entering LLM run with input:
+    {
+      "prompts": [
+        "Human: Answer the following questions as best you can. You have access to the following tools:\n\nduckduckgo_search: A wrapper around DuckDuckGo Search. Useful for when you need to answer questions about current events. Input should be a search query.\nCalculator: Useful for when you need to answer questions about math.\n\nUse the following format:\n\nQuestion: the input question you must answer\nThought: you should always think about what to do\nAction: the action to take, should be one of [duckduckgo_search, Calculator]\nAction Input: the input to the action\nObservation: the result of the action\n... (this Thought/Action/Action Input/Observation can repeat N times)\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question\n\nBegin!\n\nQuestion: Who directed the 2023 film Oppenheimer and what is their age? What is their age in days (assume 365 days per year)?\nThought:I need to find out who directed the 2023 film Oppenheimer and their age. Then, I need to calculate their age in days. I will use DuckDuckGo to find out the director and their age.\nAction: duckduckgo_search\nAction Input: \"Director of the 2023 film Oppenheimer and their age\"\nObservation: Capturing the mad scramble to build the first atomic bomb required rapid-fire filming, strict set rules and the construction of an entire 1940s western town. By Jada Yuan. July 19, 2023 at 5:00 a ... In Christopher Nolan's new film, \"Oppenheimer,\" Cillian Murphy stars as J. Robert Oppenheimer, the American physicist who oversaw the Manhattan Project in Los Alamos, N.M. Universal Pictures... Oppenheimer: Directed by Christopher Nolan. With Cillian Murphy, Emily Blunt, Robert Downey Jr., Alden Ehrenreich. The story of American scientist J. Robert Oppenheimer and his role in the development of the atomic bomb. Christopher Nolan goes deep on 'Oppenheimer,' his most 'extreme' film to date. By Kenneth Turan. July 11, 2023 5 AM PT. For Subscribers. Christopher Nolan is photographed in Los Angeles ... Oppenheimer is a 2023 epic biographical thriller film written and directed by Christopher Nolan.It is based on the 2005 biography American Prometheus by Kai Bird and Martin J. Sherwin about J. Robert Oppenheimer, a theoretical physicist who was pivotal in developing the first nuclear weapons as part of the Manhattan Project and thereby ushering in the Atomic Age.\nThought:"
+      ]
+    }
+    [llm/end] [1:RunTypeEnum.chain:AgentExecutor > 5:RunTypeEnum.chain:LLMChain > 6:RunTypeEnum.llm:ChatOpenAI] [4.46s] Exiting LLM run with output:
+    {
+      "generations": [
+        [
+          {
+            "text": "The director of the 2023 film Oppenheimer is Christopher Nolan. Now I need to find out his age.\nAction: duckduckgo_search\nAction Input: \"Christopher Nolan age\"",
+            "generation_info": {
+              "finish_reason": "stop"
+            },
+            "message": {
+              "lc": 1,
+              "type": "constructor",
+              "id": [
+                "langchain",
+                "schema",
+                "messages",
+                "AIMessage"
+              ],
+              "kwargs": {
+                "content": "The director of the 2023 film Oppenheimer is Christopher Nolan. Now I need to find out his age.\nAction: duckduckgo_search\nAction Input: \"Christopher Nolan age\"",
+                "additional_kwargs": {}
+              }
+            }
+          }
+        ]
+      ],
+      "llm_output": {
+        "token_usage": {
+          "prompt_tokens": 550,
+          "completion_tokens": 39,
+          "total_tokens": 589
+        },
+        "model_name": "gpt-4"
+      },
+      "run": null
+    }
+    [chain/end] [1:RunTypeEnum.chain:AgentExecutor > 5:RunTypeEnum.chain:LLMChain] [4.46s] Exiting Chain run with output:
+    {
+      "text": "The director of the 2023 film Oppenheimer is Christopher Nolan. Now I need to find out his age.\nAction: duckduckgo_search\nAction Input: \"Christopher Nolan age\""
+    }
+    [tool/start] [1:RunTypeEnum.chain:AgentExecutor > 7:RunTypeEnum.tool:duckduckgo_search] Entering Tool run with input:
+    "Christopher Nolan age"
+    [tool/end] [1:RunTypeEnum.chain:AgentExecutor > 7:RunTypeEnum.tool:duckduckgo_search] [1.33s] Exiting Tool run with output:
+    "Christopher Edward Nolan CBE (born 30 July 1970) is a British and American filmmaker. Known for his Hollywood blockbusters with complex storytelling, Nolan is considered a leading filmmaker of the 21st century. His films have grossed $5 billion worldwide. The recipient of many accolades, he has been nominated for five Academy Awards, five BAFTA Awards and six Golden Globe Awards. July 30, 1970 (age 52) London England Notable Works: "Dunkirk" "Tenet" "The Prestige" See all related content → Recent News Jul. 13, 2023, 11:11 AM ET (AP) Cillian Murphy, playing Oppenheimer, finally gets to lead a Christopher Nolan film July 11, 2023 5 AM PT For Subscribers Christopher Nolan is photographed in Los Angeles. (Joe Pugliese / For The Times) This is not the story I was supposed to write. Oppenheimer director Christopher Nolan, Cillian Murphy, Emily Blunt and Matt Damon on the stakes of making a three-hour, CGI-free summer film. Christopher Nolan, the director behind such films as "Dunkirk," "Inception," "Interstellar," and the "Dark Knight" trilogy, has spent the last three years living in Oppenheimer's world, writing ..."
+    [chain/start] [1:RunTypeEnum.chain:AgentExecutor > 8:RunTypeEnum.chain:LLMChain] Entering Chain run with input:
+    {
+      "input": "Who directed the 2023 film Oppenheimer and what is their age? What is their age in days (assume 365 days per year)?",
+      "agent_scratchpad": "I need to find out who directed the 2023 film Oppenheimer and their age. Then, I need to calculate their age in days. I will use DuckDuckGo to find out the director and their age.\nAction: duckduckgo_search\nAction Input: \"Director of the 2023 film Oppenheimer and their age\"\nObservation: Capturing the mad scramble to build the first atomic bomb required rapid-fire filming, strict set rules and the construction of an entire 1940s western town. By Jada Yuan. July 19, 2023 at 5:00 a ... In Christopher Nolan's new film, \"Oppenheimer,\" Cillian Murphy stars as J. Robert Oppenheimer, the American physicist who oversaw the Manhattan Project in Los Alamos, N.M. Universal Pictures... Oppenheimer: Directed by Christopher Nolan. With Cillian Murphy, Emily Blunt, Robert Downey Jr., Alden Ehrenreich. The story of American scientist J. Robert Oppenheimer and his role in the development of the atomic bomb. Christopher Nolan goes deep on 'Oppenheimer,' his most 'extreme' film to date. By Kenneth Turan. July 11, 2023 5 AM PT. For Subscribers. Christopher Nolan is photographed in Los Angeles ... Oppenheimer is a 2023 epic biographical thriller film written and directed by Christopher Nolan.It is based on the 2005 biography American Prometheus by Kai Bird and Martin J. Sherwin about J. Robert Oppenheimer, a theoretical physicist who was pivotal in developing the first nuclear weapons as part of the Manhattan Project and thereby ushering in the Atomic Age.\nThought:The director of the 2023 film Oppenheimer is Christopher Nolan. Now I need to find out his age.\nAction: duckduckgo_search\nAction Input: \"Christopher Nolan age\"\nObservation: Christopher Edward Nolan CBE (born 30 July 1970) is a British and American filmmaker. Known for his Hollywood blockbusters with complex storytelling, Nolan is considered a leading filmmaker of the 21st century. His films have grossed $5 billion worldwide. The recipient of many accolades, he has been nominated for five Academy Awards, five BAFTA Awards and six Golden Globe Awards. July 30, 1970 (age 52) London England Notable Works: \"Dunkirk\" \"Tenet\" \"The Prestige\" See all related content → Recent News Jul. 13, 2023, 11:11 AM ET (AP) Cillian Murphy, playing Oppenheimer, finally gets to lead a Christopher Nolan film July 11, 2023 5 AM PT For Subscribers Christopher Nolan is photographed in Los Angeles. (Joe Pugliese / For The Times) This is not the story I was supposed to write. Oppenheimer director Christopher Nolan, Cillian Murphy, Emily Blunt and Matt Damon on the stakes of making a three-hour, CGI-free summer film. Christopher Nolan, the director behind such films as \"Dunkirk,\" \"Inception,\" \"Interstellar,\" and the \"Dark Knight\" trilogy, has spent the last three years living in Oppenheimer's world, writing ...\nThought:",
+      "stop": [
+        "\nObservation:",
+        "\n\tObservation:"
+      ]
+    }
+    [llm/start] [1:RunTypeEnum.chain:AgentExecutor > 8:RunTypeEnum.chain:LLMChain > 9:RunTypeEnum.llm:ChatOpenAI] Entering LLM run with input:
+    {
+      "prompts": [
+        "Human: Answer the following questions as best you can. You have access to the following tools:\n\nduckduckgo_search: A wrapper around DuckDuckGo Search. Useful for when you need to answer questions about current events. Input should be a search query.\nCalculator: Useful for when you need to answer questions about math.\n\nUse the following format:\n\nQuestion: the input question you must answer\nThought: you should always think about what to do\nAction: the action to take, should be one of [duckduckgo_search, Calculator]\nAction Input: the input to the action\nObservation: the result of the action\n... (this Thought/Action/Action Input/Observation can repeat N times)\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question\n\nBegin!\n\nQuestion: Who directed the 2023 film Oppenheimer and what is their age? What is their age in days (assume 365 days per year)?\nThought:I need to find out who directed the 2023 film Oppenheimer and their age. Then, I need to calculate their age in days. I will use DuckDuckGo to find out the director and their age.\nAction: duckduckgo_search\nAction Input: \"Director of the 2023 film Oppenheimer and their age\"\nObservation: Capturing the mad scramble to build the first atomic bomb required rapid-fire filming, strict set rules and the construction of an entire 1940s western town. By Jada Yuan. July 19, 2023 at 5:00 a ... In Christopher Nolan's new film, \"Oppenheimer,\" Cillian Murphy stars as J. Robert Oppenheimer, the American physicist who oversaw the Manhattan Project in Los Alamos, N.M. Universal Pictures... Oppenheimer: Directed by Christopher Nolan. With Cillian Murphy, Emily Blunt, Robert Downey Jr., Alden Ehrenreich. The story of American scientist J. Robert Oppenheimer and his role in the development of the atomic bomb. Christopher Nolan goes deep on 'Oppenheimer,' his most 'extreme' film to date. By Kenneth Turan. July 11, 2023 5 AM PT. For Subscribers. Christopher Nolan is photographed in Los Angeles ... Oppenheimer is a 2023 epic biographical thriller film written and directed by Christopher Nolan.It is based on the 2005 biography American Prometheus by Kai Bird and Martin J. Sherwin about J. Robert Oppenheimer, a theoretical physicist who was pivotal in developing the first nuclear weapons as part of the Manhattan Project and thereby ushering in the Atomic Age.\nThought:The director of the 2023 film Oppenheimer is Christopher Nolan. Now I need to find out his age.\nAction: duckduckgo_search\nAction Input: \"Christopher Nolan age\"\nObservation: Christopher Edward Nolan CBE (born 30 July 1970) is a British and American filmmaker. Known for his Hollywood blockbusters with complex storytelling, Nolan is considered a leading filmmaker of the 21st century. His films have grossed $5 billion worldwide. The recipient of many accolades, he has been nominated for five Academy Awards, five BAFTA Awards and six Golden Globe Awards. July 30, 1970 (age 52) London England Notable Works: \"Dunkirk\" \"Tenet\" \"The Prestige\" See all related content → Recent News Jul. 13, 2023, 11:11 AM ET (AP) Cillian Murphy, playing Oppenheimer, finally gets to lead a Christopher Nolan film July 11, 2023 5 AM PT For Subscribers Christopher Nolan is photographed in Los Angeles. (Joe Pugliese / For The Times) This is not the story I was supposed to write. Oppenheimer director Christopher Nolan, Cillian Murphy, Emily Blunt and Matt Damon on the stakes of making a three-hour, CGI-free summer film. Christopher Nolan, the director behind such films as \"Dunkirk,\" \"Inception,\" \"Interstellar,\" and the \"Dark Knight\" trilogy, has spent the last three years living in Oppenheimer's world, writing ...\nThought:"
+      ]
+    }
+    [llm/end] [1:RunTypeEnum.chain:AgentExecutor > 8:RunTypeEnum.chain:LLMChain > 9:RunTypeEnum.llm:ChatOpenAI] [2.69s] Exiting LLM run with output:
+    {
+      "generations": [
+        [
+          {
+            "text": "Christopher Nolan was born on July 30, 1970, which makes him 52 years old in 2023. Now I need to calculate his age in days.\nAction: Calculator\nAction Input: 52*365",
+            "generation_info": {
+              "finish_reason": "stop"
+            },
+            "message": {
+              "lc": 1,
+              "type": "constructor",
+              "id": [
+                "langchain",
+                "schema",
+                "messages",
+                "AIMessage"
+              ],
+              "kwargs": {
+                "content": "Christopher Nolan was born on July 30, 1970, which makes him 52 years old in 2023. Now I need to calculate his age in days.\nAction: Calculator\nAction Input: 52*365",
+                "additional_kwargs": {}
+              }
+            }
+          }
+        ]
+      ],
+      "llm_output": {
+        "token_usage": {
+          "prompt_tokens": 868,
+          "completion_tokens": 46,
+          "total_tokens": 914
+        },
+        "model_name": "gpt-4"
+      },
+      "run": null
+    }
+    [chain/end] [1:RunTypeEnum.chain:AgentExecutor > 8:RunTypeEnum.chain:LLMChain] [2.69s] Exiting Chain run with output:
+    {
+      "text": "Christopher Nolan was born on July 30, 1970, which makes him 52 years old in 2023. Now I need to calculate his age in days.\nAction: Calculator\nAction Input: 52*365"
+    }
+    [tool/start] [1:RunTypeEnum.chain:AgentExecutor > 10:RunTypeEnum.tool:Calculator] Entering Tool run with input:
+    "52*365"
+    [chain/start] [1:RunTypeEnum.chain:AgentExecutor > 10:RunTypeEnum.tool:Calculator > 11:RunTypeEnum.chain:LLMMathChain] Entering Chain run with input:
+    {
+      "question": "52*365"
+    }
+    [chain/start] [1:RunTypeEnum.chain:AgentExecutor > 10:RunTypeEnum.tool:Calculator > 11:RunTypeEnum.chain:LLMMathChain > 12:RunTypeEnum.chain:LLMChain] Entering Chain run with input:
+    {
+      "question": "52*365",
+      "stop": [
+        "```output"
+      ]
+    }
+    [llm/start] [1:RunTypeEnum.chain:AgentExecutor > 10:RunTypeEnum.tool:Calculator > 11:RunTypeEnum.chain:LLMMathChain > 12:RunTypeEnum.chain:LLMChain > 13:RunTypeEnum.llm:ChatOpenAI] Entering LLM run with input:
+    {
+      "prompts": [
+        "Human: Translate a math problem into a expression that can be executed using Python's numexpr library. Use the output of running this code to answer the question.\n\nQuestion: ${Question with math problem.}\n```text\n${single line mathematical expression that solves the problem}\n```\n...numexpr.evaluate(text)...\n```output\n${Output of running the code}\n```\nAnswer: ${Answer}\n\nBegin.\n\nQuestion: What is 37593 * 67?\n```text\n37593 * 67\n```\n...numexpr.evaluate(\"37593 * 67\")...\n```output\n2518731\n```\nAnswer: 2518731\n\nQuestion: 37593^(1/5)\n```text\n37593**(1/5)\n```\n...numexpr.evaluate(\"37593**(1/5)\")...\n```output\n8.222831614237718\n```\nAnswer: 8.222831614237718\n\nQuestion: 52*365"
+      ]
+    }
+    [llm/end] [1:RunTypeEnum.chain:AgentExecutor > 10:RunTypeEnum.tool:Calculator > 11:RunTypeEnum.chain:LLMMathChain > 12:RunTypeEnum.chain:LLMChain > 13:RunTypeEnum.llm:ChatOpenAI] [2.89s] Exiting LLM run with output:
+    {
+      "generations": [
+        [
+          {
+            "text": "```text\n52*365\n```\n...numexpr.evaluate(\"52*365\")...\n",
+            "generation_info": {
+              "finish_reason": "stop"
+            },
+            "message": {
+              "lc": 1,
+              "type": "constructor",
+              "id": [
+                "langchain",
+                "schema",
+                "messages",
+                "AIMessage"
+              ],
+              "kwargs": {
+                "content": "```text\n52*365\n```\n...numexpr.evaluate(\"52*365\")...\n",
+                "additional_kwargs": {}
+              }
+            }
+          }
+        ]
+      ],
+      "llm_output": {
+        "token_usage": {
+          "prompt_tokens": 203,
+          "completion_tokens": 19,
+          "total_tokens": 222
+        },
+        "model_name": "gpt-4"
+      },
+      "run": null
+    }
+    [chain/end] [1:RunTypeEnum.chain:AgentExecutor > 10:RunTypeEnum.tool:Calculator > 11:RunTypeEnum.chain:LLMMathChain > 12:RunTypeEnum.chain:LLMChain] [2.89s] Exiting Chain run with output:
+    {
+      "text": "```text\n52*365\n```\n...numexpr.evaluate(\"52*365\")...\n"
+    }
+    [chain/end] [1:RunTypeEnum.chain:AgentExecutor > 10:RunTypeEnum.tool:Calculator > 11:RunTypeEnum.chain:LLMMathChain] [2.90s] Exiting Chain run with output:
+    {
+      "answer": "Answer: 18980"
+    }
+    [tool/end] [1:RunTypeEnum.chain:AgentExecutor > 10:RunTypeEnum.tool:Calculator] [2.90s] Exiting Tool run with output:
+    "Answer: 18980"
+    [chain/start] [1:RunTypeEnum.chain:AgentExecutor > 14:RunTypeEnum.chain:LLMChain] Entering Chain run with input:
+    {
+      "input": "Who directed the 2023 film Oppenheimer and what is their age? What is their age in days (assume 365 days per year)?",
+      "agent_scratchpad": "I need to find out who directed the 2023 film Oppenheimer and their age. Then, I need to calculate their age in days. I will use DuckDuckGo to find out the director and their age.\nAction: duckduckgo_search\nAction Input: \"Director of the 2023 film Oppenheimer and their age\"\nObservation: Capturing the mad scramble to build the first atomic bomb required rapid-fire filming, strict set rules and the construction of an entire 1940s western town. By Jada Yuan. July 19, 2023 at 5:00 a ... In Christopher Nolan's new film, \"Oppenheimer,\" Cillian Murphy stars as J. Robert Oppenheimer, the American physicist who oversaw the Manhattan Project in Los Alamos, N.M. Universal Pictures... Oppenheimer: Directed by Christopher Nolan. With Cillian Murphy, Emily Blunt, Robert Downey Jr., Alden Ehrenreich. The story of American scientist J. Robert Oppenheimer and his role in the development of the atomic bomb. Christopher Nolan goes deep on 'Oppenheimer,' his most 'extreme' film to date. By Kenneth Turan. July 11, 2023 5 AM PT. For Subscribers. Christopher Nolan is photographed in Los Angeles ... Oppenheimer is a 2023 epic biographical thriller film written and directed by Christopher Nolan.It is based on the 2005 biography American Prometheus by Kai Bird and Martin J. Sherwin about J. Robert Oppenheimer, a theoretical physicist who was pivotal in developing the first nuclear weapons as part of the Manhattan Project and thereby ushering in the Atomic Age.\nThought:The director of the 2023 film Oppenheimer is Christopher Nolan. Now I need to find out his age.\nAction: duckduckgo_search\nAction Input: \"Christopher Nolan age\"\nObservation: Christopher Edward Nolan CBE (born 30 July 1970) is a British and American filmmaker. Known for his Hollywood blockbusters with complex storytelling, Nolan is considered a leading filmmaker of the 21st century. His films have grossed $5 billion worldwide. The recipient of many accolades, he has been nominated for five Academy Awards, five BAFTA Awards and six Golden Globe Awards. July 30, 1970 (age 52) London England Notable Works: \"Dunkirk\" \"Tenet\" \"The Prestige\" See all related content → Recent News Jul. 13, 2023, 11:11 AM ET (AP) Cillian Murphy, playing Oppenheimer, finally gets to lead a Christopher Nolan film July 11, 2023 5 AM PT For Subscribers Christopher Nolan is photographed in Los Angeles. (Joe Pugliese / For The Times) This is not the story I was supposed to write. Oppenheimer director Christopher Nolan, Cillian Murphy, Emily Blunt and Matt Damon on the stakes of making a three-hour, CGI-free summer film. Christopher Nolan, the director behind such films as \"Dunkirk,\" \"Inception,\" \"Interstellar,\" and the \"Dark Knight\" trilogy, has spent the last three years living in Oppenheimer's world, writing ...\nThought:Christopher Nolan was born on July 30, 1970, which makes him 52 years old in 2023. Now I need to calculate his age in days.\nAction: Calculator\nAction Input: 52*365\nObservation: Answer: 18980\nThought:",
+      "stop": [
+        "\nObservation:",
+        "\n\tObservation:"
+      ]
+    }
+    [llm/start] [1:RunTypeEnum.chain:AgentExecutor > 14:RunTypeEnum.chain:LLMChain > 15:RunTypeEnum.llm:ChatOpenAI] Entering LLM run with input:
+    {
+      "prompts": [
+        "Human: Answer the following questions as best you can. You have access to the following tools:\n\nduckduckgo_search: A wrapper around DuckDuckGo Search. Useful for when you need to answer questions about current events. Input should be a search query.\nCalculator: Useful for when you need to answer questions about math.\n\nUse the following format:\n\nQuestion: the input question you must answer\nThought: you should always think about what to do\nAction: the action to take, should be one of [duckduckgo_search, Calculator]\nAction Input: the input to the action\nObservation: the result of the action\n... (this Thought/Action/Action Input/Observation can repeat N times)\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question\n\nBegin!\n\nQuestion: Who directed the 2023 film Oppenheimer and what is their age? What is their age in days (assume 365 days per year)?\nThought:I need to find out who directed the 2023 film Oppenheimer and their age. Then, I need to calculate their age in days. I will use DuckDuckGo to find out the director and their age.\nAction: duckduckgo_search\nAction Input: \"Director of the 2023 film Oppenheimer and their age\"\nObservation: Capturing the mad scramble to build the first atomic bomb required rapid-fire filming, strict set rules and the construction of an entire 1940s western town. By Jada Yuan. July 19, 2023 at 5:00 a ... In Christopher Nolan's new film, \"Oppenheimer,\" Cillian Murphy stars as J. Robert Oppenheimer, the American physicist who oversaw the Manhattan Project in Los Alamos, N.M. Universal Pictures... Oppenheimer: Directed by Christopher Nolan. With Cillian Murphy, Emily Blunt, Robert Downey Jr., Alden Ehrenreich. The story of American scientist J. Robert Oppenheimer and his role in the development of the atomic bomb. Christopher Nolan goes deep on 'Oppenheimer,' his most 'extreme' film to date. By Kenneth Turan. July 11, 2023 5 AM PT. For Subscribers. Christopher Nolan is photographed in Los Angeles ... Oppenheimer is a 2023 epic biographical thriller film written and directed by Christopher Nolan.It is based on the 2005 biography American Prometheus by Kai Bird and Martin J. Sherwin about J. Robert Oppenheimer, a theoretical physicist who was pivotal in developing the first nuclear weapons as part of the Manhattan Project and thereby ushering in the Atomic Age.\nThought:The director of the 2023 film Oppenheimer is Christopher Nolan. Now I need to find out his age.\nAction: duckduckgo_search\nAction Input: \"Christopher Nolan age\"\nObservation: Christopher Edward Nolan CBE (born 30 July 1970) is a British and American filmmaker. Known for his Hollywood blockbusters with complex storytelling, Nolan is considered a leading filmmaker of the 21st century. His films have grossed $5 billion worldwide. The recipient of many accolades, he has been nominated for five Academy Awards, five BAFTA Awards and six Golden Globe Awards. July 30, 1970 (age 52) London England Notable Works: \"Dunkirk\" \"Tenet\" \"The Prestige\" See all related content → Recent News Jul. 13, 2023, 11:11 AM ET (AP) Cillian Murphy, playing Oppenheimer, finally gets to lead a Christopher Nolan film July 11, 2023 5 AM PT For Subscribers Christopher Nolan is photographed in Los Angeles. (Joe Pugliese / For The Times) This is not the story I was supposed to write. Oppenheimer director Christopher Nolan, Cillian Murphy, Emily Blunt and Matt Damon on the stakes of making a three-hour, CGI-free summer film. Christopher Nolan, the director behind such films as \"Dunkirk,\" \"Inception,\" \"Interstellar,\" and the \"Dark Knight\" trilogy, has spent the last three years living in Oppenheimer's world, writing ...\nThought:Christopher Nolan was born on July 30, 1970, which makes him 52 years old in 2023. Now I need to calculate his age in days.\nAction: Calculator\nAction Input: 52*365\nObservation: Answer: 18980\nThought:"
+      ]
+    }
+    [llm/end] [1:RunTypeEnum.chain:AgentExecutor > 14:RunTypeEnum.chain:LLMChain > 15:RunTypeEnum.llm:ChatOpenAI] [3.52s] Exiting LLM run with output:
+    {
+      "generations": [
+        [
+          {
+            "text": "I now know the final answer\nFinal Answer: The director of the 2023 film Oppenheimer is Christopher Nolan and he is 52 years old. His age in days is approximately 18980 days.",
+            "generation_info": {
+              "finish_reason": "stop"
+            },
+            "message": {
+              "lc": 1,
+              "type": "constructor",
+              "id": [
+                "langchain",
+                "schema",
+                "messages",
+                "AIMessage"
+              ],
+              "kwargs": {
+                "content": "I now know the final answer\nFinal Answer: The director of the 2023 film Oppenheimer is Christopher Nolan and he is 52 years old. His age in days is approximately 18980 days.",
+                "additional_kwargs": {}
+              }
+            }
+          }
+        ]
+      ],
+      "llm_output": {
+        "token_usage": {
+          "prompt_tokens": 926,
+          "completion_tokens": 43,
+          "total_tokens": 969
+        },
+        "model_name": "gpt-4"
+      },
+      "run": null
+    }
+    [chain/end] [1:RunTypeEnum.chain:AgentExecutor > 14:RunTypeEnum.chain:LLMChain] [3.52s] Exiting Chain run with output:
+    {
+      "text": "I now know the final answer\nFinal Answer: The director of the 2023 film Oppenheimer is Christopher Nolan and he is 52 years old. His age in days is approximately 18980 days."
+    }
+    [chain/end] [1:RunTypeEnum.chain:AgentExecutor] [21.96s] Exiting Chain run with output:
+    {
+      "output": "The director of the 2023 film Oppenheimer is Christopher Nolan and he is 52 years old. His age in days is approximately 18980 days."
+    }
+
+
+
+
+
+    'The director of the 2023 film Oppenheimer is Christopher Nolan and he is 52 years old. His age in days is approximately 18980 days.'
+```
+
+</CodeOutputBlock>
+
+</details>
+
+### `set_verbose(True)`
+
+Setting the `verbose` flag will print out inputs and outputs in a slightly more readable format and will skip logging certain raw outputs (like the token usage stats for an LLM call) so that you can focus on application logic.
+
+
+```python
+from langchain.globals import set_verbose
+
+set_verbose(True)
+
+agent.run("Who directed the 2023 film Oppenheimer and what is their age? What is their age in days (assume 365 days per year)?")
+```
+
+<details> <summary>Console output</summary>
+
+<CodeOutputBlock lang="python">
+
+```
+    
+    
+    > Entering new AgentExecutor chain...
+    
+    
+    > Entering new LLMChain chain...
+    Prompt after formatting:
+    Answer the following questions as best you can. You have access to the following tools:
+    
+    duckduckgo_search: A wrapper around DuckDuckGo Search. Useful for when you need to answer questions about current events. Input should be a search query.
+    Calculator: Useful for when you need to answer questions about math.
+    
+    Use the following format:
+    
+    Question: the input question you must answer
+    Thought: you should always think about what to do
+    Action: the action to take, should be one of [duckduckgo_search, Calculator]
+    Action Input: the input to the action
+    Observation: the result of the action
+    ... (this Thought/Action/Action Input/Observation can repeat N times)
+    Thought: I now know the final answer
+    Final Answer: the final answer to the original input question
+    
+    Begin!
+    
+    Question: Who directed the 2023 film Oppenheimer and what is their age? What is their age in days (assume 365 days per year)?
+    Thought:
+    
+    > Finished chain.
+    First, I need to find out who directed the film Oppenheimer in 2023 and their birth date to calculate their age.
+    Action: duckduckgo_search
+    Action Input: "Director of the 2023 film Oppenheimer"
+    Observation: Oppenheimer: Directed by Christopher Nolan. With Cillian Murphy, Emily Blunt, Robert Downey Jr., Alden Ehrenreich. The story of American scientist J. Robert Oppenheimer and his role in the development of the atomic bomb. In Christopher Nolan's new film, "Oppenheimer," Cillian Murphy stars as J. Robert ... 2023, 12:16 p.m. ET. ... including his role as the director of the Manhattan Engineer District, better ... J Robert Oppenheimer was the director of the secret Los Alamos Laboratory. It was established under US president Franklin D Roosevelt as part of the Manhattan Project to build the first atomic bomb. He oversaw the first atomic bomb detonation in the New Mexico desert in July 1945, code-named "Trinity". In this opening salvo of 2023's Oscar battle, Nolan has enjoined a star-studded cast for a retelling of the brilliant and haunted life of J. Robert Oppenheimer, the American physicist whose... Oppenheimer is a 2023 epic biographical thriller film written and directed by Christopher Nolan.It is based on the 2005 biography American Prometheus by Kai Bird and Martin J. Sherwin about J. Robert Oppenheimer, a theoretical physicist who was pivotal in developing the first nuclear weapons as part of the Manhattan Project and thereby ushering in the Atomic Age.
+    Thought:
+    
+    > Entering new LLMChain chain...
+    Prompt after formatting:
+    Answer the following questions as best you can. You have access to the following tools:
+    
+    duckduckgo_search: A wrapper around DuckDuckGo Search. Useful for when you need to answer questions about current events. Input should be a search query.
+    Calculator: Useful for when you need to answer questions about math.
+    
+    Use the following format:
+    
+    Question: the input question you must answer
+    Thought: you should always think about what to do
+    Action: the action to take, should be one of [duckduckgo_search, Calculator]
+    Action Input: the input to the action
+    Observation: the result of the action
+    ... (this Thought/Action/Action Input/Observation can repeat N times)
+    Thought: I now know the final answer
+    Final Answer: the final answer to the original input question
+    
+    Begin!
+    
+    Question: Who directed the 2023 film Oppenheimer and what is their age? What is their age in days (assume 365 days per year)?
+    Thought:First, I need to find out who directed the film Oppenheimer in 2023 and their birth date to calculate their age.
+    Action: duckduckgo_search
+    Action Input: "Director of the 2023 film Oppenheimer"
+    Observation: Oppenheimer: Directed by Christopher Nolan. With Cillian Murphy, Emily Blunt, Robert Downey Jr., Alden Ehrenreich. The story of American scientist J. Robert Oppenheimer and his role in the development of the atomic bomb. In Christopher Nolan's new film, "Oppenheimer," Cillian Murphy stars as J. Robert ... 2023, 12:16 p.m. ET. ... including his role as the director of the Manhattan Engineer District, better ... J Robert Oppenheimer was the director of the secret Los Alamos Laboratory. It was established under US president Franklin D Roosevelt as part of the Manhattan Project to build the first atomic bomb. He oversaw the first atomic bomb detonation in the New Mexico desert in July 1945, code-named "Trinity". In this opening salvo of 2023's Oscar battle, Nolan has enjoined a star-studded cast for a retelling of the brilliant and haunted life of J. Robert Oppenheimer, the American physicist whose... Oppenheimer is a 2023 epic biographical thriller film written and directed by Christopher Nolan.It is based on the 2005 biography American Prometheus by Kai Bird and Martin J. Sherwin about J. Robert Oppenheimer, a theoretical physicist who was pivotal in developing the first nuclear weapons as part of the Manhattan Project and thereby ushering in the Atomic Age.
+    Thought:
+    
+    > Finished chain.
+    The director of the 2023 film Oppenheimer is Christopher Nolan. Now I need to find out his birth date to calculate his age.
+    Action: duckduckgo_search
+    Action Input: "Christopher Nolan birth date"
+    Observation: July 30, 1970 (age 52) London England Notable Works: "Dunkirk" "Tenet" "The Prestige" See all related content → Recent News Jul. 13, 2023, 11:11 AM ET (AP) Cillian Murphy, playing Oppenheimer, finally gets to lead a Christopher Nolan film Christopher Edward Nolan CBE (born 30 July 1970) is a British and American filmmaker. Known for his Hollywood blockbusters with complex storytelling, Nolan is considered a leading filmmaker of the 21st century. His films have grossed $5 billion worldwide. The recipient of many accolades, he has been nominated for five Academy Awards, five BAFTA Awards and six Golden Globe Awards. Christopher Nolan is currently 52 according to his birthdate July 30, 1970 Sun Sign Leo Born Place Westminster, London, England, United Kingdom Residence Los Angeles, California, United States Nationality Education Chris attended Haileybury and Imperial Service College, in Hertford Heath, Hertfordshire. Christopher Nolan's next movie will study the man who developed the atomic bomb, J. Robert Oppenheimer. Here's the release date, plot, trailers & more. July 2023 sees the release of Christopher Nolan's new film, Oppenheimer, his first movie since 2020's Tenet and his split from Warner Bros. Billed as an epic thriller about "the man who ...
+    Thought:
+    
+    > Entering new LLMChain chain...
+    Prompt after formatting:
+    Answer the following questions as best you can. You have access to the following tools:
+    
+    duckduckgo_search: A wrapper around DuckDuckGo Search. Useful for when you need to answer questions about current events. Input should be a search query.
+    Calculator: Useful for when you need to answer questions about math.
+    
+    Use the following format:
+    
+    Question: the input question you must answer
+    Thought: you should always think about what to do
+    Action: the action to take, should be one of [duckduckgo_search, Calculator]
+    Action Input: the input to the action
+    Observation: the result of the action
+    ... (this Thought/Action/Action Input/Observation can repeat N times)
+    Thought: I now know the final answer
+    Final Answer: the final answer to the original input question
+    
+    Begin!
+    
+    Question: Who directed the 2023 film Oppenheimer and what is their age? What is their age in days (assume 365 days per year)?
+    Thought:First, I need to find out who directed the film Oppenheimer in 2023 and their birth date to calculate their age.
+    Action: duckduckgo_search
+    Action Input: "Director of the 2023 film Oppenheimer"
+    Observation: Oppenheimer: Directed by Christopher Nolan. With Cillian Murphy, Emily Blunt, Robert Downey Jr., Alden Ehrenreich. The story of American scientist J. Robert Oppenheimer and his role in the development of the atomic bomb. In Christopher Nolan's new film, "Oppenheimer," Cillian Murphy stars as J. Robert ... 2023, 12:16 p.m. ET. ... including his role as the director of the Manhattan Engineer District, better ... J Robert Oppenheimer was the director of the secret Los Alamos Laboratory. It was established under US president Franklin D Roosevelt as part of the Manhattan Project to build the first atomic bomb. He oversaw the first atomic bomb detonation in the New Mexico desert in July 1945, code-named "Trinity". In this opening salvo of 2023's Oscar battle, Nolan has enjoined a star-studded cast for a retelling of the brilliant and haunted life of J. Robert Oppenheimer, the American physicist whose... Oppenheimer is a 2023 epic biographical thriller film written and directed by Christopher Nolan.It is based on the 2005 biography American Prometheus by Kai Bird and Martin J. Sherwin about J. Robert Oppenheimer, a theoretical physicist who was pivotal in developing the first nuclear weapons as part of the Manhattan Project and thereby ushering in the Atomic Age.
+    Thought:The director of the 2023 film Oppenheimer is Christopher Nolan. Now I need to find out his birth date to calculate his age.
+    Action: duckduckgo_search
+    Action Input: "Christopher Nolan birth date"
+    Observation: July 30, 1970 (age 52) London England Notable Works: "Dunkirk" "Tenet" "The Prestige" See all related content → Recent News Jul. 13, 2023, 11:11 AM ET (AP) Cillian Murphy, playing Oppenheimer, finally gets to lead a Christopher Nolan film Christopher Edward Nolan CBE (born 30 July 1970) is a British and American filmmaker. Known for his Hollywood blockbusters with complex storytelling, Nolan is considered a leading filmmaker of the 21st century. His films have grossed $5 billion worldwide. The recipient of many accolades, he has been nominated for five Academy Awards, five BAFTA Awards and six Golden Globe Awards. Christopher Nolan is currently 52 according to his birthdate July 30, 1970 Sun Sign Leo Born Place Westminster, London, England, United Kingdom Residence Los Angeles, California, United States Nationality Education Chris attended Haileybury and Imperial Service College, in Hertford Heath, Hertfordshire. Christopher Nolan's next movie will study the man who developed the atomic bomb, J. Robert Oppenheimer. Here's the release date, plot, trailers & more. July 2023 sees the release of Christopher Nolan's new film, Oppenheimer, his first movie since 2020's Tenet and his split from Warner Bros. Billed as an epic thriller about "the man who ...
+    Thought:
+    
+    > Finished chain.
+    Christopher Nolan was born on July 30, 1970. Now I need to calculate his age in 2023 and then convert it into days.
+    Action: Calculator
+    Action Input: (2023 - 1970) * 365
+    
+    > Entering new LLMMathChain chain...
+    (2023 - 1970) * 365
+    
+    > Entering new LLMChain chain...
+    Prompt after formatting:
+    Translate a math problem into a expression that can be executed using Python's numexpr library. Use the output of running this code to answer the question.
+    
+    Question: ${Question with math problem.}
+    ```text
+    ${single line mathematical expression that solves the problem}
+    ```
+    ...numexpr.evaluate(text)...
+    ```output
+    ${Output of running the code}
+    ```
+    Answer: ${Answer}
+    
+    Begin.
+    
+    Question: What is 37593 * 67?
+    ```text
+    37593 * 67
+    ```
+    ...numexpr.evaluate("37593 * 67")...
+    ```output
+    2518731
+    ```
+    Answer: 2518731
+    
+    Question: 37593^(1/5)
+    ```text
+    37593**(1/5)
+    ```
+    ...numexpr.evaluate("37593**(1/5)")...
+    ```output
+    8.222831614237718
+    ```
+    Answer: 8.222831614237718
+    
+    Question: (2023 - 1970) * 365
+    
+    
+    > Finished chain.
+    ```text
+    (2023 - 1970) * 365
+    ```
+    ...numexpr.evaluate("(2023 - 1970) * 365")...
+    
+    Answer: 19345
+    > Finished chain.
+    
+    Observation: Answer: 19345
+    Thought:
+    
+    > Entering new LLMChain chain...
+    Prompt after formatting:
+    Answer the following questions as best you can. You have access to the following tools:
+    
+    duckduckgo_search: A wrapper around DuckDuckGo Search. Useful for when you need to answer questions about current events. Input should be a search query.
+    Calculator: Useful for when you need to answer questions about math.
+    
+    Use the following format:
+    
+    Question: the input question you must answer
+    Thought: you should always think about what to do
+    Action: the action to take, should be one of [duckduckgo_search, Calculator]
+    Action Input: the input to the action
+    Observation: the result of the action
+    ... (this Thought/Action/Action Input/Observation can repeat N times)
+    Thought: I now know the final answer
+    Final Answer: the final answer to the original input question
+    
+    Begin!
+    
+    Question: Who directed the 2023 film Oppenheimer and what is their age? What is their age in days (assume 365 days per year)?
+    Thought:First, I need to find out who directed the film Oppenheimer in 2023 and their birth date to calculate their age.
+    Action: duckduckgo_search
+    Action Input: "Director of the 2023 film Oppenheimer"
+    Observation: Oppenheimer: Directed by Christopher Nolan. With Cillian Murphy, Emily Blunt, Robert Downey Jr., Alden Ehrenreich. The story of American scientist J. Robert Oppenheimer and his role in the development of the atomic bomb. In Christopher Nolan's new film, "Oppenheimer," Cillian Murphy stars as J. Robert ... 2023, 12:16 p.m. ET. ... including his role as the director of the Manhattan Engineer District, better ... J Robert Oppenheimer was the director of the secret Los Alamos Laboratory. It was established under US president Franklin D Roosevelt as part of the Manhattan Project to build the first atomic bomb. He oversaw the first atomic bomb detonation in the New Mexico desert in July 1945, code-named "Trinity". In this opening salvo of 2023's Oscar battle, Nolan has enjoined a star-studded cast for a retelling of the brilliant and haunted life of J. Robert Oppenheimer, the American physicist whose... Oppenheimer is a 2023 epic biographical thriller film written and directed by Christopher Nolan.It is based on the 2005 biography American Prometheus by Kai Bird and Martin J. Sherwin about J. Robert Oppenheimer, a theoretical physicist who was pivotal in developing the first nuclear weapons as part of the Manhattan Project and thereby ushering in the Atomic Age.
+    Thought:The director of the 2023 film Oppenheimer is Christopher Nolan. Now I need to find out his birth date to calculate his age.
+    Action: duckduckgo_search
+    Action Input: "Christopher Nolan birth date"
+    Observation: July 30, 1970 (age 52) London England Notable Works: "Dunkirk" "Tenet" "The Prestige" See all related content → Recent News Jul. 13, 2023, 11:11 AM ET (AP) Cillian Murphy, playing Oppenheimer, finally gets to lead a Christopher Nolan film Christopher Edward Nolan CBE (born 30 July 1970) is a British and American filmmaker. Known for his Hollywood blockbusters with complex storytelling, Nolan is considered a leading filmmaker of the 21st century. His films have grossed $5 billion worldwide. The recipient of many accolades, he has been nominated for five Academy Awards, five BAFTA Awards and six Golden Globe Awards. Christopher Nolan is currently 52 according to his birthdate July 30, 1970 Sun Sign Leo Born Place Westminster, London, England, United Kingdom Residence Los Angeles, California, United States Nationality Education Chris attended Haileybury and Imperial Service College, in Hertford Heath, Hertfordshire. Christopher Nolan's next movie will study the man who developed the atomic bomb, J. Robert Oppenheimer. Here's the release date, plot, trailers & more. July 2023 sees the release of Christopher Nolan's new film, Oppenheimer, his first movie since 2020's Tenet and his split from Warner Bros. Billed as an epic thriller about "the man who ...
+    Thought:Christopher Nolan was born on July 30, 1970. Now I need to calculate his age in 2023 and then convert it into days.
+    Action: Calculator
+    Action Input: (2023 - 1970) * 365
+    Observation: Answer: 19345
+    Thought:
+    
+    > Finished chain.
+    I now know the final answer
+    Final Answer: The director of the 2023 film Oppenheimer is Christopher Nolan and he is 53 years old in 2023. His age in days is 19345 days.
+    
+    > Finished chain.
+
+
+    'The director of the 2023 film Oppenheimer is Christopher Nolan and he is 53 years old in 2023. His age in days is 19345 days.'
+```
+
+</CodeOutputBlock>
+
+</details>
+
+### `Chain(..., verbose=True)`
+
+You can also scope verbosity down to a single object, in which case only the inputs and outputs to that object are printed (along with any additional callbacks calls made specifically by that object).
+
+
+```python
+# Passing verbose=True to initialize_agent will pass that along to the AgentExecutor (which is a Chain).
+agent = initialize_agent(
+    tools, 
+    llm, 
+    agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,
+    verbose=True,
+)
+
+agent.run("Who directed the 2023 film Oppenheimer and what is their age? What is their age in days (assume 365 days per year)?")
+```
+
+<details> <summary>Console output</summary>
+
+<CodeOutputBlock lang="python">
+
+```
+    > Entering new AgentExecutor chain...
+    First, I need to find out who directed the film Oppenheimer in 2023 and their birth date. Then, I can calculate their age in years and days.
+    Action: duckduckgo_search
+    Action Input: "Director of 2023 film Oppenheimer"
+    Observation: Oppenheimer: Directed by Christopher Nolan. With Cillian Murphy, Emily Blunt, Robert Downey Jr., Alden Ehrenreich. The story of American scientist J. Robert Oppenheimer and his role in the development of the atomic bomb. In Christopher Nolan's new film, "Oppenheimer," Cillian Murphy stars as J. Robert Oppenheimer, the American physicist who oversaw the Manhattan Project in Los Alamos, N.M. Universal Pictures... J Robert Oppenheimer was the director of the secret Los Alamos Laboratory. It was established under US president Franklin D Roosevelt as part of the Manhattan Project to build the first atomic bomb. He oversaw the first atomic bomb detonation in the New Mexico desert in July 1945, code-named "Trinity". A Review of Christopher Nolan's new film 'Oppenheimer' , the story of the man who fathered the Atomic Bomb. Cillian Murphy leads an all star cast ... Release Date: July 21, 2023. Director ... For his new film, "Oppenheimer," starring Cillian Murphy and Emily Blunt, director Christopher Nolan set out to build an entire 1940s western town.
+    Thought:The director of the 2023 film Oppenheimer is Christopher Nolan. Now I need to find out his birth date to calculate his age.
+    Action: duckduckgo_search
+    Action Input: "Christopher Nolan birth date"
+    Observation: July 30, 1970 (age 52) London England Notable Works: "Dunkirk" "Tenet" "The Prestige" See all related content → Recent News Jul. 13, 2023, 11:11 AM ET (AP) Cillian Murphy, playing Oppenheimer, finally gets to lead a Christopher Nolan film Christopher Edward Nolan CBE (born 30 July 1970) is a British and American filmmaker. Known for his Hollywood blockbusters with complex storytelling, Nolan is considered a leading filmmaker of the 21st century. His films have grossed $5 billion worldwide. The recipient of many accolades, he has been nominated for five Academy Awards, five BAFTA Awards and six Golden Globe Awards. Christopher Nolan is currently 52 according to his birthdate July 30, 1970 Sun Sign Leo Born Place Westminster, London, England, United Kingdom Residence Los Angeles, California, United States Nationality Education Chris attended Haileybury and Imperial Service College, in Hertford Heath, Hertfordshire. Christopher Nolan's next movie will study the man who developed the atomic bomb, J. Robert Oppenheimer. Here's the release date, plot, trailers & more. Date of Birth: 30 July 1970 . ... Christopher Nolan is a British-American film director, producer, and screenwriter. His films have grossed more than US$5 billion worldwide, and have garnered 11 Academy Awards from 36 nominations. ...
+    Thought:Christopher Nolan was born on July 30, 1970. Now I can calculate his age in years and then in days.
+    Action: Calculator
+    Action Input: {"operation": "subtract", "operands": [2023, 1970]}
+    Observation: Answer: 53
+    Thought:Christopher Nolan is 53 years old in 2023. Now I need to calculate his age in days.
+    Action: Calculator
+    Action Input: {"operation": "multiply", "operands": [53, 365]}
+    Observation: Answer: 19345
+    Thought:I now know the final answer
+    Final Answer: The director of the 2023 film Oppenheimer is Christopher Nolan. He is 53 years old in 2023, which is approximately 19345 days.
+    
+    > Finished chain.
+
+
+    'The director of the 2023 film Oppenheimer is Christopher Nolan. He is 53 years old in 2023, which is approximately 19345 days.'
+```
+
+</CodeOutputBlock>
+
+</details>
+
+## Other callbacks
+
+`Callbacks` are what we use to execute any functionality within a component outside the primary component logic. All of the above solutions use `Callbacks` under the hood to log intermediate steps of components. There are a number of `Callbacks` relevant for debugging that come with LangChain out of the box, like the [FileCallbackHandler](/docs/modules/callbacks/filecallbackhandler). You can also implement your own callbacks to execute custom functionality.
+
+See here for more info on [Callbacks](/docs/modules/callbacks/), how to use them, and customize them.

docs/docs/guides/development/extending_langchain.mdx

@@ -0,0 +1,13 @@
+---
+hide_table_of_contents: true
+---
+
+# Extending LangChain
+
+Extending LangChain's base abstractions, whether you're planning to contribute back to the open-source repo or build a bespoke internal integration, is encouraged.
+
+Check out these guides for building your own custom classes for the following modules:
+
+- [Chat models](/docs/modules/model_io/chat/custom_chat_model) for interfacing with chat-tuned language models.
+- [LLMs](/docs/modules/model_io/llms/custom_llm) for interfacing with text language models.
+- [Output parsers](/docs/modules/model_io/output_parsers/custom) for handling language model outputs.

docs/docs/guides/development/index.mdx

@@ -0,0 +1,13 @@
+---
+sidebar_position: 1
+sidebar_class_name: hidden
+---
+
+# Development
+
+This section contains guides with general information around building apps with LangChain.
+
+import DocCardList from "@theme/DocCardList";
+import { useCurrentSidebarCategory } from '@docusaurus/theme-common';
+
+<DocCardList items={useCurrentSidebarCategory().items.filter((item) => item.href !== "/docs/guides/development/")} />

docs/docs/guides/development/local_llms.ipynb

@@ -32,7 +32,7 @@
     "1. `Base model`: What is the base-model and how was it trained?\n",
     "2. `Fine-tuning approach`: Was the base-model fine-tuned and, if so, what [set of instructions](https://cameronrwolfe.substack.com/p/beyond-llama-the-power-of-open-llms#%C2%A7alpaca-an-instruction-following-llama-model) was used?\n",
     "\n",
-    "![Image description](../../static/img/OSS_LLM_overview.png)\n",
+    "![Image description](../../../static/img/OSS_LLM_overview.png)\n",
     "\n",
     "The relative performance of these models can be assessed using several leaderboards, including:\n",
     "\n",
@@ -56,7 +56,7 @@
     "\n",
     "In particular, see [this excellent post](https://finbarr.ca/how-is-llama-cpp-possible/) on the importance of quantization.\n",
     "\n",
-    "![Image description](../../static/img/llama-memory-weights.png)\n",
+    "![Image description](../../../static/img/llama-memory-weights.png)\n",
     "\n",
     "With less precision, we radically decrease the memory needed to store the LLM in memory.\n",
     "\n",
@@ -64,7 +64,7 @@
     "\n",
     "A Mac M2 Max is 5-6x faster than a M1 for inference due to the larger GPU memory bandwidth.\n",
     "\n",
-    "![Image description](../../static/img/llama_t_put.png)\n",
+    "![Image description](../../../static/img/llama_t_put.png)\n",
     "\n",
     "## Quickstart\n",
     "\n",
@@ -639,9 +639,9 @@
    "source": [
     "## Use cases\n",
     "\n",
-    "Given an `llm` created from one of the models above, you can use it for [many use cases](/docs/how_to#use-cases).\n",
+    "Given an `llm` created from one of the models above, you can use it for [many use cases](/docs/use_cases/).\n",
     "\n",
-    "For example, here is a guide to [RAG](/docs/tutorials/local_rag) with local LLMs.\n",
+    "For example, here is a guide to [RAG](/docs/use_cases/question_answering/local_retrieval_qa) with local LLMs.\n",
     "\n",
     "In general, use cases for local LLMs can be driven by at least two factors:\n",
     "\n",

docs/docs/guides/development/pydantic_compatibility.md

@@ -0,0 +1,105 @@
+# Pydantic compatibility
+
+- Pydantic v2 was released in June, 2023 (https://docs.pydantic.dev/2.0/blog/pydantic-v2-final/)
+- v2 contains has a number of breaking changes (https://docs.pydantic.dev/2.0/migration/)
+- Pydantic v2 and v1 are under the same package name, so both versions cannot be installed at the same time
+
+## LangChain Pydantic migration plan
+
+As of `langchain>=0.0.267`, LangChain will allow users to install either Pydantic V1 or V2. 
+   * Internally LangChain will continue to [use V1](https://docs.pydantic.dev/latest/migration/#continue-using-pydantic-v1-features).
+   * During this time, users can pin their pydantic version to v1 to avoid breaking changes, or start a partial
+   migration using pydantic v2 throughout their code, but avoiding mixing v1 and v2 code for LangChain (see below).
+
+User can either pin to pydantic v1, and upgrade their code in one go once LangChain has migrated to v2 internally, or they can start a partial migration to v2, but must avoid mixing v1 and v2 code for LangChain.
+
+Below are two examples of showing how to avoid mixing pydantic v1 and v2 code in
+the case of inheritance and in the case of passing objects to LangChain.
+
+**Example 1: Extending via inheritance**
+
+**YES** 
+
+```python
+from pydantic.v1 import root_validator, validator
+
+class CustomTool(BaseTool): # BaseTool is v1 code
+    x: int = Field(default=1)
+
+    def _run(*args, **kwargs):
+        return "hello"
+
+    @validator('x') # v1 code
+    @classmethod
+    def validate_x(cls, x: int) -> int:
+        return 1
+    
+
+CustomTool(
+    name='custom_tool',
+    description="hello",
+    x=1,
+)
+```
+
+Mixing Pydantic v2 primitives with Pydantic v1 primitives can raise cryptic errors
+
+**NO** 
+
+```python
+from pydantic import Field, field_validator # pydantic v2
+
+class CustomTool(BaseTool): # BaseTool is v1 code
+    x: int = Field(default=1)
+
+    def _run(*args, **kwargs):
+        return "hello"
+
+    @field_validator('x') # v2 code
+    @classmethod
+    def validate_x(cls, x: int) -> int:
+        return 1
+    
+
+CustomTool( 
+    name='custom_tool',
+    description="hello",
+    x=1,
+)
+```
+
+**Example 2: Passing objects to LangChain**
+
+**YES**
+
+```python
+from langchain_core.tools import Tool
+from pydantic.v1 import BaseModel, Field # <-- Uses v1 namespace
+
+class CalculatorInput(BaseModel):
+    question: str = Field()
+
+Tool.from_function( # <-- tool uses v1 namespace
+    func=lambda question: 'hello',
+    name="Calculator",
+    description="useful for when you need to answer questions about math",
+    args_schema=CalculatorInput
+)
+```
+
+**NO**
+
+```python
+from langchain_core.tools import Tool
+from pydantic import BaseModel, Field # <-- Uses v2 namespace
+
+class CalculatorInput(BaseModel):
+    question: str = Field()
+
+Tool.from_function( # <-- tool uses v1 namespace
+    func=lambda question: 'hello',
+    name="Calculator",
+    description="useful for when you need to answer questions about math",
+    args_schema=CalculatorInput
+)
+```

docs/docs/guides/index.mdx

@@ -0,0 +1,3 @@
+# Guides
+
+This section contains deeper dives into the LangChain framework and how to apply it.

docs/docs/guides/productionization/deployments/index.mdx

@@ -0,0 +1,115 @@
+# Deployment
+
+In today's fast-paced technological landscape, the use of Large Language Models (LLMs) is rapidly expanding. As a result, it is crucial for developers to understand how to effectively deploy these models in production environments. LLM interfaces typically fall into two categories:
+
+- **Case 1: Utilizing External LLM Providers (OpenAI, Anthropic, etc.)**
+    In this scenario, most of the computational burden is handled by the LLM providers, while LangChain simplifies the implementation of business logic around these services. This approach includes features such as prompt templating, chat message generation, caching, vector embedding database creation, preprocessing, etc.
+
+- **Case 2: Self-hosted Open-Source Models**
+    Alternatively, developers can opt to use smaller, yet comparably capable, self-hosted open-source LLM models. This approach can significantly decrease costs, latency, and privacy concerns associated with transferring data to external LLM providers.
+
+Regardless of the framework that forms the backbone of your product, deploying LLM applications comes with its own set of challenges. It's vital to understand the trade-offs and key considerations when evaluating serving frameworks.
+
+## Outline
+
+This guide aims to provide a comprehensive overview of the requirements for deploying LLMs in a production setting, focusing on:
+
+- **Designing a Robust LLM Application Service**
+- **Maintaining Cost-Efficiency**
+- **Ensuring Rapid Iteration**
+
+Understanding these components is crucial when assessing serving systems. LangChain integrates with several open-source projects designed to tackle these issues, providing a robust framework for productionizing your LLM applications. Some notable frameworks include:
+
+- [Ray Serve](/docs/integrations/providers/ray_serve)
+- [BentoML](https://github.com/bentoml/BentoML)
+- [OpenLLM](/docs/integrations/providers/openllm)
+- [Modal](/docs/integrations/providers/modal)
+- [Jina](/docs/integrations/providers/jina)
+
+These links will provide further information on each ecosystem, assisting you in finding the best fit for your LLM deployment needs.
+
+## Designing a Robust LLM Application Service
+
+When deploying an LLM service in production, it's imperative to provide a seamless user experience free from outages. Achieving 24/7 service availability involves creating and maintaining several sub-systems surrounding your application.
+
+### Monitoring
+
+Monitoring forms an integral part of any system running in a production environment. In the context of LLMs, it is essential to monitor both performance and quality metrics.
+
+**Performance Metrics:** These metrics provide insights into the efficiency and capacity of your model. Here are some key examples:
+
+- Query per second (QPS): This measures the number of queries your model processes in a second, offering insights into its utilization.
+- Latency: This metric quantifies the delay from when your client sends a request to when they receive a response.
+- Tokens Per Second (TPS): This represents the number of tokens your model can generate in a second.
+
+**Quality Metrics:** These metrics are typically customized according to the business use-case. For instance, how does the output of your system compare to a baseline, such as a previous version? Although these metrics can be calculated offline, you need to log the necessary data to use them later.
+
+### Fault tolerance
+
+Your application may encounter errors such as exceptions in your model inference or business logic code, causing failures and disrupting traffic. Other potential issues could arise from the machine running your application, such as unexpected hardware breakdowns or loss of spot-instances during high-demand periods. One way to mitigate these risks is by increasing redundancy through replica scaling and implementing recovery mechanisms for failed replicas. However, model replicas aren't the only potential points of failure. It's essential to build resilience against various failures that could occur at any point in your stack.
+
+
+### Zero down time upgrade
+
+System upgrades are often necessary but can result in service disruptions if not handled correctly. One way to prevent downtime during upgrades is by implementing a smooth transition process from the old version to the new one. Ideally, the new version of your LLM service is deployed, and traffic gradually shifts from the old to the new version, maintaining a constant QPS throughout the process.
+
+
+### Load balancing
+
+Load balancing, in simple terms, is a technique to distribute work evenly across multiple computers, servers, or other resources to optimize the utilization of the system, maximize throughput, minimize response time, and avoid overload of any single resource. Think of it as a traffic officer directing cars (requests) to different roads (servers) so that no single road becomes too congested.
+
+There are several strategies for load balancing. For example, one common method is the *Round Robin* strategy, where each request is sent to the next server in line, cycling back to the first when all servers have received a request. This works well when all servers are equally capable. However, if some servers are more powerful than others, you might use a *Weighted Round Robin* or *Least Connections* strategy, where more requests are sent to the more powerful servers, or to those currently handling the fewest active requests. Let's imagine you're running a LLM chain. If your application becomes popular, you could have hundreds or even thousands of users asking questions at the same time. If one server gets too busy (high load), the load balancer would direct new requests to another server that is less busy. This way, all your users get a timely response and the system remains stable.
+
+
+
+## Maintaining Cost-Efficiency and Scalability
+
+Deploying LLM services can be costly, especially when you're handling a large volume of user interactions. Charges by LLM providers are usually based on tokens used, making a chat system inference on these models potentially expensive. However, several strategies can help manage these costs without compromising the quality of the service.
+
+
+### Self-hosting models
+
+Several smaller and open-source LLMs are emerging to tackle the issue of reliance on LLM providers. Self-hosting allows you to maintain similar quality to LLM provider models while managing costs. The challenge lies in building a reliable, high-performing LLM serving system on your own machines. 
+
+### Resource Management and Auto-Scaling
+
+Computational logic within your application requires precise resource allocation. For instance, if part of your traffic is served by an OpenAI endpoint and another part by a self-hosted model, it's crucial to allocate suitable resources for each. Auto-scaling—adjusting resource allocation based on traffic—can significantly impact the cost of running your application. This strategy requires a balance between cost and responsiveness, ensuring neither resource over-provisioning nor compromised application responsiveness.
+
+### Utilizing Spot Instances
+
+On platforms like AWS, spot instances offer substantial cost savings, typically priced at about a third of on-demand instances. The trade-off is a higher crash rate, necessitating a robust fault-tolerance mechanism for effective use.
+
+### Independent Scaling
+
+When self-hosting your models, you should consider independent scaling. For example, if you have two translation models, one fine-tuned for French and another for Spanish, incoming requests might necessitate different scaling requirements for each.
+
+### Batching requests
+
+In the context of Large Language Models, batching requests can enhance efficiency by better utilizing your GPU resources. GPUs are inherently parallel processors, designed to handle multiple tasks simultaneously. If you send individual requests to the model, the GPU might not be fully utilized as it's only working on a single task at a time. On the other hand, by batching requests together, you're allowing the GPU to work on multiple tasks at once, maximizing its utilization and improving inference speed. This not only leads to cost savings but can also improve the overall latency of your LLM service.
+
+
+In summary, managing costs while scaling your LLM services requires a strategic approach. Utilizing self-hosting models, managing resources effectively, employing auto-scaling, using spot instances, independently scaling models, and batching requests are key strategies to consider. Open-source libraries such as Ray Serve and BentoML are designed to deal with these complexities. 
+
+
+
+## Ensuring Rapid Iteration
+
+The LLM landscape is evolving at an unprecedented pace, with new libraries and model architectures being introduced constantly. Consequently, it's crucial to avoid tying yourself to a solution specific to one particular framework. This is especially relevant in serving, where changes to your infrastructure can be time-consuming, expensive, and risky. Strive for infrastructure that is not locked into any specific machine learning library or framework, but instead offers a general-purpose, scalable serving layer. Here are some aspects where flexibility plays a key role:
+
+### Model composition
+
+Deploying systems like LangChain demands the ability to piece together different models and connect them via logic. Take the example of building a natural language input SQL query engine. Querying an LLM and obtaining the SQL command is only part of the system. You need to extract metadata from the connected database, construct a prompt for the LLM, run the SQL query on an engine, collect and feedback the response to the LLM as the query runs, and present the results to the user. This demonstrates the need to seamlessly integrate various complex components built in Python into a dynamic chain of logical blocks that can be served together.
+
+## Cloud providers
+
+Many hosted solutions are restricted to a single cloud provider, which can limit your options in today's multi-cloud world. Depending on where your other infrastructure components are built, you might prefer to stick with your chosen cloud provider.
+
+
+## Infrastructure as Code (IaC)
+
+Rapid iteration also involves the ability to recreate your infrastructure quickly and reliably. This is where Infrastructure as Code (IaC) tools like Terraform, CloudFormation, or Kubernetes YAML files come into play. They allow you to define your infrastructure in code files, which can be version controlled and quickly deployed, enabling faster and more reliable iterations.
+
+
+## CI/CD
+
+In a fast-paced environment, implementing CI/CD pipelines can significantly speed up the iteration process. They help automate the testing and deployment of your LLM applications, reducing the risk of errors and enabling faster feedback and iteration.

docs/docs/guides/productionization/deployments/template_repos.mdx

@@ -0,0 +1,7 @@
+# LangChain Templates
+
+For more information on LangChain Templates, visit 
+
+- [LangChain Templates Quickstart](https://github.com/langchain-ai/langchain/blob/master/templates/README.md)
+- [LangChain Templates Index](https://github.com/langchain-ai/langchain/blob/master/templates/docs/INDEX.md)
+- [Full List of Templates](https://github.com/langchain-ai/langchain/blob/master/templates/)

docs/docs/guides/productionization/evaluation/comparison/custom.ipynb

@@ -0,0 +1,293 @@
+{
+ "cells": [
+  {
+   "cell_type": "raw",
+   "id": "5046d96f-d578-4d5b-9a7e-43b28cafe61d",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "sidebar_position: 2\n",
+    "title: Custom pairwise evaluator\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "657d2c8c-54b4-42a3-9f02-bdefa0ed6728",
+   "metadata": {},
+   "source": [
+    "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/langchain-ai/langchain/blob/master/docs/docs/guides/evaluation/comparison/custom.ipynb)\n",
+    "\n",
+    "You can make your own pairwise string evaluators by inheriting from `PairwiseStringEvaluator` class and overwriting the `_evaluate_string_pairs` method (and the `_aevaluate_string_pairs` method if you want to use the evaluator asynchronously).\n",
+    "\n",
+    "In this example, you will make a simple custom evaluator that just returns whether the first prediction has more whitespace tokenized 'words' than the second.\n",
+    "\n",
+    "You can check out the reference docs for the [PairwiseStringEvaluator interface](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.schema.PairwiseStringEvaluator.html#langchain.evaluation.schema.PairwiseStringEvaluator) for more info.\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "93f3a653-d198-4291-973c-8d1adba338b2",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from typing import Any, Optional\n",
+    "\n",
+    "from langchain.evaluation import PairwiseStringEvaluator\n",
+    "\n",
+    "\n",
+    "class LengthComparisonPairwiseEvaluator(PairwiseStringEvaluator):\n",
+    "    \"\"\"\n",
+    "    Custom evaluator to compare two strings.\n",
+    "    \"\"\"\n",
+    "\n",
+    "    def _evaluate_string_pairs(\n",
+    "        self,\n",
+    "        *,\n",
+    "        prediction: str,\n",
+    "        prediction_b: str,\n",
+    "        reference: Optional[str] = None,\n",
+    "        input: Optional[str] = None,\n",
+    "        **kwargs: Any,\n",
+    "    ) -> dict:\n",
+    "        score = int(len(prediction.split()) > len(prediction_b.split()))\n",
+    "        return {\"score\": score}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "7d4a77c3-07a7-4076-8e7f-f9bca0d6c290",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'score': 1}"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "evaluator = LengthComparisonPairwiseEvaluator()\n",
+    "\n",
+    "evaluator.evaluate_string_pairs(\n",
+    "    prediction=\"The quick brown fox jumped over the lazy dog.\",\n",
+    "    prediction_b=\"The quick brown fox jumped over the dog.\",\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d90f128f-6f49-42a1-b05a-3aea568ee03b",
+   "metadata": {},
+   "source": [
+    "## LLM-Based Example\n",
+    "\n",
+    "That example was simple to illustrate the API, but it wasn't very useful in practice. Below, use an LLM with some custom instructions to form a simple preference scorer similar to the built-in [PairwiseStringEvalChain](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.comparison.eval_chain.PairwiseStringEvalChain.html#langchain.evaluation.comparison.eval_chain.PairwiseStringEvalChain). We will use `ChatAnthropic` for the evaluator chain."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "b4b43098-4d96-417b-a8a9-b3e75779cfe8",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "%pip install --upgrade --quiet  anthropic\n",
+    "# %env ANTHROPIC_API_KEY=YOUR_API_KEY"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "b6e978ab-48f1-47ff-9506-e13b1a50be6e",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from typing import Any, Optional\n",
+    "\n",
+    "from langchain.chains import LLMChain\n",
+    "from langchain.evaluation import PairwiseStringEvaluator\n",
+    "from langchain_community.chat_models import ChatAnthropic\n",
+    "\n",
+    "\n",
+    "class CustomPreferenceEvaluator(PairwiseStringEvaluator):\n",
+    "    \"\"\"\n",
+    "    Custom evaluator to compare two strings using a custom LLMChain.\n",
+    "    \"\"\"\n",
+    "\n",
+    "    def __init__(self) -> None:\n",
+    "        llm = ChatAnthropic(model=\"claude-2\", temperature=0)\n",
+    "        self.eval_chain = LLMChain.from_string(\n",
+    "            llm,\n",
+    "            \"\"\"Which option is preferred? Do not take order into account. Evaluate based on accuracy and helpfulness. If neither is preferred, respond with C. Provide your reasoning, then finish with Preference: A/B/C\n",
+    "\n",
+    "Input: How do I get the path of the parent directory in python 3.8?\n",
+    "Option A: You can use the following code:\n",
+    "```python\n",
+    "import os\n",
+    "\n",
+    "os.path.dirname(os.path.dirname(os.path.abspath(__file__)))\n",
+    "```\n",
+    "Option B: You can use the following code:\n",
+    "```python\n",
+    "from pathlib import Path\n",
+    "Path(__file__).absolute().parent\n",
+    "```\n",
+    "Reasoning: Both options return the same result. However, since option B is more concise and easily understand, it is preferred.\n",
+    "Preference: B\n",
+    "\n",
+    "Which option is preferred? Do not take order into account. Evaluate based on accuracy and helpfulness. If neither is preferred, respond with C. Provide your reasoning, then finish with Preference: A/B/C\n",
+    "Input: {input}\n",
+    "Option A: {prediction}\n",
+    "Option B: {prediction_b}\n",
+    "Reasoning:\"\"\",\n",
+    "        )\n",
+    "\n",
+    "    @property\n",
+    "    def requires_input(self) -> bool:\n",
+    "        return True\n",
+    "\n",
+    "    @property\n",
+    "    def requires_reference(self) -> bool:\n",
+    "        return False\n",
+    "\n",
+    "    def _evaluate_string_pairs(\n",
+    "        self,\n",
+    "        *,\n",
+    "        prediction: str,\n",
+    "        prediction_b: str,\n",
+    "        reference: Optional[str] = None,\n",
+    "        input: Optional[str] = None,\n",
+    "        **kwargs: Any,\n",
+    "    ) -> dict:\n",
+    "        result = self.eval_chain(\n",
+    "            {\n",
+    "                \"input\": input,\n",
+    "                \"prediction\": prediction,\n",
+    "                \"prediction_b\": prediction_b,\n",
+    "                \"stop\": [\"Which option is preferred?\"],\n",
+    "            },\n",
+    "            **kwargs,\n",
+    "        )\n",
+    "\n",
+    "        response_text = result[\"text\"]\n",
+    "        reasoning, preference = response_text.split(\"Preference:\", maxsplit=1)\n",
+    "        preference = preference.strip()\n",
+    "        score = 1.0 if preference == \"A\" else (0.0 if preference == \"B\" else None)\n",
+    "        return {\"reasoning\": reasoning.strip(), \"value\": preference, \"score\": score}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "5cbd8b1d-2cb0-4f05-b435-a1a00074d94a",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "evaluator = CustomPreferenceEvaluator()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "2c0a7fb7-b976-4443-9f0e-e707a6dfbdf7",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'reasoning': 'Option B is preferred over option A for importing from a relative directory, because it is more straightforward and concise.\\n\\nOption A uses the importlib module, which allows importing a module by specifying the full name as a string. While this works, it is less clear compared to option B.\\n\\nOption B directly imports from the relative path using dot notation, which clearly shows that it is a relative import. This is the recommended way to do relative imports in Python.\\n\\nIn summary, option B is more accurate and helpful as it uses the standard Python relative import syntax.',\n",
+       " 'value': 'B',\n",
+       " 'score': 0.0}"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "evaluator.evaluate_string_pairs(\n",
+    "    input=\"How do I import from a relative directory?\",\n",
+    "    prediction=\"use importlib! importlib.import_module('.my_package', '.')\",\n",
+    "    prediction_b=\"from .sibling import foo\",\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "f13a1346-7dbe-451d-b3a3-99e8fc7b753b",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CustomPreferenceEvaluator requires an input string.\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Setting requires_input to return True adds additional validation to avoid returning a grade when insufficient data is provided to the chain.\n",
+    "\n",
+    "try:\n",
+    "    evaluator.evaluate_string_pairs(\n",
+    "        prediction=\"use importlib! importlib.import_module('.my_package', '.')\",\n",
+    "        prediction_b=\"from .sibling import foo\",\n",
+    "    )\n",
+    "except ValueError as e:\n",
+    "    print(e)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e7829cc3-ebd1-4628-ae97-15166202e9cc",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/guides/productionization/evaluation/comparison/index.mdx

@@ -0,0 +1,28 @@
+---
+sidebar_position: 3 
+---
+# Comparison Evaluators
+
+Comparison evaluators in LangChain help measure two different chains or LLM outputs. These evaluators are helpful for comparative analyses, such as A/B testing between two language models, or comparing different versions of the same model. They can also be useful for things like generating preference scores for ai-assisted reinforcement learning.
+
+These evaluators inherit from the `PairwiseStringEvaluator` class, providing a comparison interface for two strings - typically, the outputs from two different prompts or models, or two versions of the same model. In essence, a comparison evaluator performs an evaluation on a pair of strings and returns a dictionary containing the evaluation score and other relevant details.
+
+To create a custom comparison evaluator, inherit from the `PairwiseStringEvaluator` class and overwrite the `_evaluate_string_pairs` method. If you require asynchronous evaluation, also overwrite the `_aevaluate_string_pairs` method.
+
+Here's a summary of the key methods and properties of a comparison evaluator:
+
+- `evaluate_string_pairs`: Evaluate the output string pairs. This function should be overwritten when creating custom evaluators.
+- `aevaluate_string_pairs`: Asynchronously evaluate the output string pairs. This function should be overwritten for asynchronous evaluation.
+- `requires_input`: This property indicates whether this evaluator requires an input string.
+- `requires_reference`: This property specifies whether this evaluator requires a reference label.
+
+:::note LangSmith Support
+The [run_on_dataset](https://api.python.langchain.com/en/latest/langchain_api_reference.html#module-langchain.smith) evaluation method is designed to evaluate only a single model at a time, and thus, doesn't support these evaluators.
+:::
+
+Detailed information about creating custom evaluators and the available built-in comparison evaluators is provided in the following sections.
+
+import DocCardList from "@theme/DocCardList";
+
+<DocCardList />
+

docs/docs/guides/productionization/evaluation/comparison/pairwise_embedding_distance.ipynb

@@ -0,0 +1,242 @@
+{
+ "cells": [
+  {
+   "cell_type": "raw",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "sidebar_position: 1\n",
+    "title: Pairwise embedding distance\n",
+    "---"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/langchain-ai/langchain/blob/master/docs/docs/guides/evaluation/comparison/pairwise_embedding_distance.ipynb)\n",
+    "\n",
+    "One way to measure the similarity (or dissimilarity) between two predictions on a shared or similar input is to embed the predictions and compute a vector distance between the two embeddings.<a name=\"cite_ref-1\"></a>[<sup>[1]</sup>](#cite_note-1)\n",
+    "\n",
+    "You can load the `pairwise_embedding_distance` evaluator to do this.\n",
+    "\n",
+    "**Note:** This returns a **distance** score, meaning that the lower the number, the **more** similar the outputs are, according to their embedded representation.\n",
+    "\n",
+    "Check out the reference docs for the [PairwiseEmbeddingDistanceEvalChain](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.embedding_distance.base.PairwiseEmbeddingDistanceEvalChain.html#langchain.evaluation.embedding_distance.base.PairwiseEmbeddingDistanceEvalChain) for more info."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from langchain.evaluation import load_evaluator\n",
+    "\n",
+    "evaluator = load_evaluator(\"pairwise_embedding_distance\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'score': 0.0966466944859925}"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "evaluator.evaluate_string_pairs(\n",
+    "    prediction=\"Seattle is hot in June\", prediction_b=\"Seattle is cool in June.\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'score': 0.03761174337464557}"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "evaluator.evaluate_string_pairs(\n",
+    "    prediction=\"Seattle is warm in June\", prediction_b=\"Seattle is cool in June.\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Select the Distance Metric\n",
+    "\n",
+    "By default, the evaluator uses cosine distance. You can choose a different distance metric if you'd like. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[<EmbeddingDistance.COSINE: 'cosine'>,\n",
+       " <EmbeddingDistance.EUCLIDEAN: 'euclidean'>,\n",
+       " <EmbeddingDistance.MANHATTAN: 'manhattan'>,\n",
+       " <EmbeddingDistance.CHEBYSHEV: 'chebyshev'>,\n",
+       " <EmbeddingDistance.HAMMING: 'hamming'>]"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain.evaluation import EmbeddingDistance\n",
+    "\n",
+    "list(EmbeddingDistance)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "evaluator = load_evaluator(\n",
+    "    \"pairwise_embedding_distance\", distance_metric=EmbeddingDistance.EUCLIDEAN\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Select Embeddings to Use\n",
+    "\n",
+    "The constructor uses `OpenAI` embeddings by default, but you can configure this however you want. Below, use huggingface local embeddings"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from langchain_community.embeddings import HuggingFaceEmbeddings\n",
+    "\n",
+    "embedding_model = HuggingFaceEmbeddings()\n",
+    "hf_evaluator = load_evaluator(\"pairwise_embedding_distance\", embeddings=embedding_model)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'score': 0.5486443280477362}"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "hf_evaluator.evaluate_string_pairs(\n",
+    "    prediction=\"Seattle is hot in June\", prediction_b=\"Seattle is cool in June.\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'score': 0.21018880025138598}"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "hf_evaluator.evaluate_string_pairs(\n",
+    "    prediction=\"Seattle is warm in June\", prediction_b=\"Seattle is cool in June.\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<a name=\"cite_note-1\"></a><i>1. Note: When it comes to semantic similarity, this often gives better results than older string distance metrics (such as those in the `PairwiseStringDistanceEvalChain`), though it tends to be less reliable than evaluators that use the LLM directly (such as the `PairwiseStringEvalChain`) </i>"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

docs/docs/guides/productionization/evaluation/comparison/pairwise_string.ipynb

@@ -0,0 +1,392 @@
+{
+ "cells": [
+  {
+   "cell_type": "raw",
+   "id": "dcfcf124-78fe-4d67-85a4-cfd3409a1ff6",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "sidebar_position: 0\n",
+    "title: Pairwise string comparison\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2da95378",
+   "metadata": {},
+   "source": [
+    "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/langchain-ai/langchain/blob/master/docs/docs/guides/evaluation/comparison/pairwise_string.ipynb)\n",
+    "\n",
+    "Often you will want to compare predictions of an LLM, Chain, or Agent for a given input. The `StringComparison` evaluators facilitate this so you can answer questions like:\n",
+    "\n",
+    "- Which LLM or prompt produces a preferred output for a given question?\n",
+    "- Which examples should I include for few-shot example selection?\n",
+    "- Which output is better to include for fine-tuning?\n",
+    "\n",
+    "The simplest and often most reliable automated way to choose a preferred prediction for a given input is to use the `pairwise_string` evaluator.\n",
+    "\n",
+    "Check out the reference docs for the [PairwiseStringEvalChain](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.comparison.eval_chain.PairwiseStringEvalChain.html#langchain.evaluation.comparison.eval_chain.PairwiseStringEvalChain) for more info."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "f6790c46",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from langchain.evaluation import load_evaluator\n",
+    "\n",
+    "evaluator = load_evaluator(\"labeled_pairwise_string\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "49ad9139",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'reasoning': 'Both responses are relevant to the question asked, as they both provide a numerical answer to the question about the number of dogs in the park. However, Response A is incorrect according to the reference answer, which states that there are four dogs. Response B, on the other hand, is correct as it matches the reference answer. Neither response demonstrates depth of thought, as they both simply provide a numerical answer without any additional information or context. \\n\\nBased on these criteria, Response B is the better response.\\n',\n",
+       " 'value': 'B',\n",
+       " 'score': 0}"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "evaluator.evaluate_string_pairs(\n",
+    "    prediction=\"there are three dogs\",\n",
+    "    prediction_b=\"4\",\n",
+    "    input=\"how many dogs are in the park?\",\n",
+    "    reference=\"four\",\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7491d2e6-4e77-4b17-be6b-7da966785c1d",
+   "metadata": {},
+   "source": [
+    "## Methods\n",
+    "\n",
+    "\n",
+    "The pairwise string evaluator can be called using [evaluate_string_pairs](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.comparison.eval_chain.PairwiseStringEvalChain.html#langchain.evaluation.comparison.eval_chain.PairwiseStringEvalChain.evaluate_string_pairs) (or async [aevaluate_string_pairs](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.comparison.eval_chain.PairwiseStringEvalChain.html#langchain.evaluation.comparison.eval_chain.PairwiseStringEvalChain.aevaluate_string_pairs)) methods, which accept:\n",
+    "\n",
+    "- prediction (str) – The predicted response of the first model, chain, or prompt.\n",
+    "- prediction_b (str) – The predicted response of the second model, chain, or prompt.\n",
+    "- input (str) – The input question, prompt, or other text.\n",
+    "- reference (str) – (Only for the labeled_pairwise_string variant) The reference response.\n",
+    "\n",
+    "They return a dictionary with the following values:\n",
+    "\n",
+    "- value: 'A' or 'B', indicating whether `prediction` or `prediction_b` is preferred, respectively\n",
+    "- score: Integer 0 or 1 mapped from the 'value', where a score of 1 would mean that the first `prediction` is preferred, and a score of 0 would mean `prediction_b` is preferred.\n",
+    "- reasoning: String \"chain of thought reasoning\" from the LLM generated prior to creating the score"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ed353b93-be71-4479-b9c0-8c97814c2e58",
+   "metadata": {},
+   "source": [
+    "## Without References\n",
+    "\n",
+    "When references aren't available, you can still predict the preferred response.\n",
+    "The results will reflect the evaluation model's preference, which is less reliable and may result\n",
+    "in preferences that are factually incorrect."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "586320da",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from langchain.evaluation import load_evaluator\n",
+    "\n",
+    "evaluator = load_evaluator(\"pairwise_string\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "7f56c76e-a39b-4509-8b8a-8a2afe6c3da1",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'reasoning': 'Both responses are correct and relevant to the question. However, Response B is more helpful and insightful as it provides a more detailed explanation of what addition is. Response A is correct but lacks depth as it does not explain what the operation of addition entails. \\n\\nFinal Decision: [[B]]',\n",
+       " 'value': 'B',\n",
+       " 'score': 0}"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "evaluator.evaluate_string_pairs(\n",
+    "    prediction=\"Addition is a mathematical operation.\",\n",
+    "    prediction_b=\"Addition is a mathematical operation that adds two numbers to create a third number, the 'sum'.\",\n",
+    "    input=\"What is addition?\",\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4a09b21d-9851-47e8-93d3-90044b2945b0",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "## Defining the Criteria\n",
+    "\n",
+    "By default, the LLM is instructed to select the 'preferred' response based on helpfulness, relevance, correctness, and depth of thought. You can customize the criteria by passing in a `criteria` argument, where the criteria could take any of the following forms:\n",
+    "\n",
+    "- [`Criteria`](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.criteria.eval_chain.Criteria.html#langchain.evaluation.criteria.eval_chain.Criteria) enum or its string value - to use one of the default criteria and their descriptions\n",
+    "- [Constitutional principal](https://api.python.langchain.com/en/latest/chains/langchain.chains.constitutional_ai.models.ConstitutionalPrinciple.html#langchain.chains.constitutional_ai.models.ConstitutionalPrinciple) - use one any of the constitutional principles defined in langchain\n",
+    "- Dictionary: a list of custom criteria, where the key is the name of the criteria, and the value is the description.\n",
+    "- A list of criteria or constitutional principles - to combine multiple criteria in one.\n",
+    "\n",
+    "Below is an example for determining preferred writing responses based on a custom style."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "8539e7d9-f7b0-4d32-9c45-593a7915c093",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "custom_criteria = {\n",
+    "    \"simplicity\": \"Is the language straightforward and unpretentious?\",\n",
+    "    \"clarity\": \"Are the sentences clear and easy to understand?\",\n",
+    "    \"precision\": \"Is the writing precise, with no unnecessary words or details?\",\n",
+    "    \"truthfulness\": \"Does the writing feel honest and sincere?\",\n",
+    "    \"subtext\": \"Does the writing suggest deeper meanings or themes?\",\n",
+    "}\n",
+    "evaluator = load_evaluator(\"pairwise_string\", criteria=custom_criteria)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "fec7bde8-fbdc-4730-8366-9d90d033c181",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'reasoning': 'Response A is simple, clear, and precise. It uses straightforward language to convey a deep and sincere message about families. The metaphor of joy and sorrow as music is effective and easy to understand.\\n\\nResponse B, on the other hand, is more complex and less clear. The language is more pretentious, with words like \"domicile,\" \"resounds,\" \"abode,\" \"dissonant,\" and \"elegy.\" While it conveys a similar message to Response A, it does so in a more convoluted way. The precision is also lacking due to the use of unnecessary words and details.\\n\\nBoth responses suggest deeper meanings or themes about the shared joy and unique sorrow in families. However, Response A does so in a more effective and accessible way.\\n\\nTherefore, the better response is [[A]].',\n",
+       " 'value': 'A',\n",
+       " 'score': 1}"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "evaluator.evaluate_string_pairs(\n",
+    "    prediction=\"Every cheerful household shares a similar rhythm of joy; but sorrow, in each household, plays a unique, haunting melody.\",\n",
+    "    prediction_b=\"Where one finds a symphony of joy, every domicile of happiness resounds in harmonious,\"\n",
+    "    \" identical notes; yet, every abode of despair conducts a dissonant orchestra, each\"\n",
+    "    \" playing an elegy of grief that is peculiar and profound to its own existence.\",\n",
+    "    input=\"Write some prose about families.\",\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a25b60b2-627c-408a-be4b-a2e5cbc10726",
+   "metadata": {},
+   "source": [
+    "## Customize the LLM\n",
+    "\n",
+    "By default, the loader uses `gpt-4` in the evaluation chain. You can customize this when loading."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "de84a958-1330-482b-b950-68bcf23f9e35",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_community.chat_models import ChatAnthropic\n",
+    "\n",
+    "llm = ChatAnthropic(temperature=0)\n",
+    "\n",
+    "evaluator = load_evaluator(\"labeled_pairwise_string\", llm=llm)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "e162153f-d50a-4a7c-a033-019dabbc954c",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'reasoning': 'Here is my assessment:\\n\\nResponse B is more helpful, insightful, and accurate than Response A. Response B simply states \"4\", which directly answers the question by providing the exact number of dogs mentioned in the reference answer. In contrast, Response A states \"there are three dogs\", which is incorrect according to the reference answer. \\n\\nIn terms of helpfulness, Response B gives the precise number while Response A provides an inaccurate guess. For relevance, both refer to dogs in the park from the question. However, Response B is more correct and factual based on the reference answer. Response A shows some attempt at reasoning but is ultimately incorrect. Response B requires less depth of thought to simply state the factual number.\\n\\nIn summary, Response B is superior in terms of helpfulness, relevance, correctness, and depth. My final decision is: [[B]]\\n',\n",
+       " 'value': 'B',\n",
+       " 'score': 0}"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "evaluator.evaluate_string_pairs(\n",
+    "    prediction=\"there are three dogs\",\n",
+    "    prediction_b=\"4\",\n",
+    "    input=\"how many dogs are in the park?\",\n",
+    "    reference=\"four\",\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e0e89c13-d0ad-4f87-8fcb-814399bafa2a",
+   "metadata": {},
+   "source": [
+    "## Customize the Evaluation Prompt\n",
+    "\n",
+    "You can use your own custom evaluation prompt to add more task-specific instructions or to instruct the evaluator to score the output.\n",
+    "\n",
+    "*Note: If you use a prompt that expects generates a result in a unique format, you may also have to pass in a custom output parser (`output_parser=your_parser()`) instead of the default `PairwiseStringResultOutputParser`"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "fb817efa-3a4d-439d-af8c-773b89d97ec9",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from langchain_core.prompts import PromptTemplate\n",
+    "\n",
+    "prompt_template = PromptTemplate.from_template(\n",
+    "    \"\"\"Given the input context, which do you prefer: A or B?\n",
+    "Evaluate based on the following criteria:\n",
+    "{criteria}\n",
+    "Reason step by step and finally, respond with either [[A]] or [[B]] on its own line.\n",
+    "\n",
+    "DATA\n",
+    "----\n",
+    "input: {input}\n",
+    "reference: {reference}\n",
+    "A: {prediction}\n",
+    "B: {prediction_b}\n",
+    "---\n",
+    "Reasoning:\n",
+    "\n",
+    "\"\"\"\n",
+    ")\n",
+    "evaluator = load_evaluator(\"labeled_pairwise_string\", prompt=prompt_template)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "d40aa4f0-cfd5-4cb4-83c8-8d2300a04c2f",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "input_variables=['prediction', 'reference', 'prediction_b', 'input'] output_parser=None partial_variables={'criteria': 'helpfulness: Is the submission helpful, insightful, and appropriate?\\nrelevance: Is the submission referring to a real quote from the text?\\ncorrectness: Is the submission correct, accurate, and factual?\\ndepth: Does the submission demonstrate depth of thought?'} template='Given the input context, which do you prefer: A or B?\\nEvaluate based on the following criteria:\\n{criteria}\\nReason step by step and finally, respond with either [[A]] or [[B]] on its own line.\\n\\nDATA\\n----\\ninput: {input}\\nreference: {reference}\\nA: {prediction}\\nB: {prediction_b}\\n---\\nReasoning:\\n\\n' template_format='f-string' validate_template=True\n"
+     ]
+    }
+   ],
+   "source": [
+    "# The prompt was assigned to the evaluator\n",
+    "print(evaluator.prompt)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "9467bb42-7a31-4071-8f66-9ed2c6f06dcd",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'reasoning': 'Helpfulness: Both A and B are helpful as they provide a direct answer to the question.\\nRelevance: A is relevant as it refers to the correct name of the dog from the text. B is not relevant as it provides a different name.\\nCorrectness: A is correct as it accurately states the name of the dog. B is incorrect as it provides a different name.\\nDepth: Both A and B demonstrate a similar level of depth as they both provide a straightforward answer to the question.\\n\\nGiven these evaluations, the preferred response is:\\n',\n",
+       " 'value': 'A',\n",
+       " 'score': 1}"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "evaluator.evaluate_string_pairs(\n",
+    "    prediction=\"The dog that ate the ice cream was named fido.\",\n",
+    "    prediction_b=\"The dog's name is spot\",\n",
+    "    input=\"What is the name of the dog that ate the ice cream?\",\n",
+    "    reference=\"The dog's name is fido\",\n",
+    ")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/guides/productionization/evaluation/examples/comparisons.ipynb

@@ -0,0 +1,456 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Comparing Chain Outputs\n",
+    "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/langchain-ai/langchain/blob/master/docs/docs/guides/evaluation/examples/comparisons.ipynb)\n",
+    "\n",
+    "Suppose you have two different prompts (or LLMs). How do you know which will generate \"better\" results?\n",
+    "\n",
+    "One automated way to predict the preferred configuration is to use a `PairwiseStringEvaluator` like the `PairwiseStringEvalChain`<a name=\"cite_ref-1\"></a>[<sup>[1]</sup>](#cite_note-1). This chain prompts an LLM to select which output is preferred, given a specific input.\n",
+    "\n",
+    "For this evaluation, we will need 3 things:\n",
+    "1. An evaluator\n",
+    "2. A dataset of inputs\n",
+    "3. 2 (or more) LLMs, Chains, or Agents to compare\n",
+    "\n",
+    "Then we will aggregate the results to determine the preferred model.\n",
+    "\n",
+    "### Step 1. Create the Evaluator\n",
+    "\n",
+    "In this example, you will use gpt-4 to select which output is preferred."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install --upgrade --quiet  langchain langchain-openai"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from langchain.evaluation import load_evaluator\n",
+    "\n",
+    "eval_chain = load_evaluator(\"pairwise_string\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Step 2. Select Dataset\n",
+    "\n",
+    "If you already have real usage data for your LLM, you can use a representative sample. More examples\n",
+    "provide more reliable results. We will use some example queries someone might have about how to use langchain here."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Found cached dataset parquet (/Users/wfh/.cache/huggingface/datasets/LangChainDatasets___parquet/LangChainDatasets--langchain-howto-queries-bbb748bbee7e77aa/0.0.0/14a00e99c0d15a23649d0db8944380ac81082d4b021f398733dd84f3a6c569a7)\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "a2358d37246640ce95e0f9940194590a",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "  0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "from langchain.evaluation.loading import load_dataset\n",
+    "\n",
+    "dataset = load_dataset(\"langchain-howto-queries\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Step 3. Define Models to Compare\n",
+    "\n",
+    "We will be comparing two agents in this case."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from langchain.agents import AgentType, Tool, initialize_agent\n",
+    "from langchain_community.utilities import SerpAPIWrapper\n",
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "# Initialize the language model\n",
+    "# You can add your own OpenAI API key by adding openai_api_key=\"<your_api_key>\"\n",
+    "llm = ChatOpenAI(temperature=0, model=\"gpt-3.5-turbo-0613\")\n",
+    "\n",
+    "# Initialize the SerpAPIWrapper for search functionality\n",
+    "# Replace <your_api_key> in openai_api_key=\"<your_api_key>\" with your actual SerpAPI key.\n",
+    "search = SerpAPIWrapper()\n",
+    "\n",
+    "# Define a list of tools offered by the agent\n",
+    "tools = [\n",
+    "    Tool(\n",
+    "        name=\"Search\",\n",
+    "        func=search.run,\n",
+    "        coroutine=search.arun,\n",
+    "        description=\"Useful when you need to answer questions about current events. You should ask targeted questions.\",\n",
+    "    ),\n",
+    "]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "functions_agent = initialize_agent(\n",
+    "    tools, llm, agent=AgentType.OPENAI_MULTI_FUNCTIONS, verbose=False\n",
+    ")\n",
+    "conversations_agent = initialize_agent(\n",
+    "    tools, llm, agent=AgentType.CHAT_ZERO_SHOT_REACT_DESCRIPTION, verbose=False\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Step 4. Generate Responses\n",
+    "\n",
+    "We will generate outputs for each of the models before evaluating them."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "87277cb39a1a4726bb7cc533a24e2ea4",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "  0%|          | 0/20 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "import asyncio\n",
+    "\n",
+    "from tqdm.notebook import tqdm\n",
+    "\n",
+    "results = []\n",
+    "agents = [functions_agent, conversations_agent]\n",
+    "concurrency_level = 6  # How many concurrent agents to run. May need to decrease if OpenAI is rate limiting.\n",
+    "\n",
+    "# We will only run the first 20 examples of this dataset to speed things up\n",
+    "# This will lead to larger confidence intervals downstream.\n",
+    "batch = []\n",
+    "for example in tqdm(dataset[:20]):\n",
+    "    batch.extend([agent.acall(example[\"inputs\"]) for agent in agents])\n",
+    "    if len(batch) >= concurrency_level:\n",
+    "        batch_results = await asyncio.gather(*batch, return_exceptions=True)\n",
+    "        results.extend(list(zip(*[iter(batch_results)] * 2)))\n",
+    "        batch = []\n",
+    "if batch:\n",
+    "    batch_results = await asyncio.gather(*batch, return_exceptions=True)\n",
+    "    results.extend(list(zip(*[iter(batch_results)] * 2)))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Step 5. Evaluate Pairs\n",
+    "\n",
+    "Now it's time to evaluate the results. For each agent response, run the evaluation chain to select which output is preferred (or return a tie).\n",
+    "\n",
+    "Randomly select the input order to reduce the likelihood that one model will be preferred just because it is presented first."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "import random\n",
+    "\n",
+    "\n",
+    "def predict_preferences(dataset, results) -> list:\n",
+    "    preferences = []\n",
+    "\n",
+    "    for example, (res_a, res_b) in zip(dataset, results):\n",
+    "        input_ = example[\"inputs\"]\n",
+    "        # Flip a coin to reduce persistent position bias\n",
+    "        if random.random() < 0.5:\n",
+    "            pred_a, pred_b = res_a, res_b\n",
+    "            a, b = \"a\", \"b\"\n",
+    "        else:\n",
+    "            pred_a, pred_b = res_b, res_a\n",
+    "            a, b = \"b\", \"a\"\n",
+    "        eval_res = eval_chain.evaluate_string_pairs(\n",
+    "            prediction=pred_a[\"output\"] if isinstance(pred_a, dict) else str(pred_a),\n",
+    "            prediction_b=pred_b[\"output\"] if isinstance(pred_b, dict) else str(pred_b),\n",
+    "            input=input_,\n",
+    "        )\n",
+    "        if eval_res[\"value\"] == \"A\":\n",
+    "            preferences.append(a)\n",
+    "        elif eval_res[\"value\"] == \"B\":\n",
+    "            preferences.append(b)\n",
+    "        else:\n",
+    "            preferences.append(None)  # No preference\n",
+    "    return preferences"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "preferences = predict_preferences(dataset, results)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "**Print out the ratio of preferences.**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "OpenAI Functions Agent: 95.00%\n",
+      "None: 5.00%\n"
+     ]
+    }
+   ],
+   "source": [
+    "from collections import Counter\n",
+    "\n",
+    "name_map = {\n",
+    "    \"a\": \"OpenAI Functions Agent\",\n",
+    "    \"b\": \"Structured Chat Agent\",\n",
+    "}\n",
+    "counts = Counter(preferences)\n",
+    "pref_ratios = {k: v / len(preferences) for k, v in counts.items()}\n",
+    "for k, v in pref_ratios.items():\n",
+    "    print(f\"{name_map.get(k)}: {v:.2%}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Estimate Confidence Intervals\n",
+    "\n",
+    "The results seem pretty clear, but if you want to have a better sense of how confident we are, that model \"A\" (the OpenAI Functions Agent) is the preferred model, we can calculate confidence intervals. \n",
+    "\n",
+    "Below, use the Wilson score to estimate the confidence interval."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from math import sqrt\n",
+    "\n",
+    "\n",
+    "def wilson_score_interval(\n",
+    "    preferences: list, which: str = \"a\", z: float = 1.96\n",
+    ") -> tuple:\n",
+    "    \"\"\"Estimate the confidence interval using the Wilson score.\n",
+    "\n",
+    "    See: https://en.wikipedia.org/wiki/Binomial_proportion_confidence_interval#Wilson_score_interval\n",
+    "    for more details, including when to use it and when it should not be used.\n",
+    "    \"\"\"\n",
+    "    total_preferences = preferences.count(\"a\") + preferences.count(\"b\")\n",
+    "    n_s = preferences.count(which)\n",
+    "\n",
+    "    if total_preferences == 0:\n",
+    "        return (0, 0)\n",
+    "\n",
+    "    p_hat = n_s / total_preferences\n",
+    "\n",
+    "    denominator = 1 + (z**2) / total_preferences\n",
+    "    adjustment = (z / denominator) * sqrt(\n",
+    "        p_hat * (1 - p_hat) / total_preferences\n",
+    "        + (z**2) / (4 * total_preferences * total_preferences)\n",
+    "    )\n",
+    "    center = (p_hat + (z**2) / (2 * total_preferences)) / denominator\n",
+    "    lower_bound = min(max(center - adjustment, 0.0), 1.0)\n",
+    "    upper_bound = min(max(center + adjustment, 0.0), 1.0)\n",
+    "\n",
+    "    return (lower_bound, upper_bound)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The \"OpenAI Functions Agent\" would be preferred between 83.18% and 100.00% percent of the time (with 95% confidence).\n",
+      "The \"Structured Chat Agent\" would be preferred between 0.00% and 16.82% percent of the time (with 95% confidence).\n"
+     ]
+    }
+   ],
+   "source": [
+    "for which_, name in name_map.items():\n",
+    "    low, high = wilson_score_interval(preferences, which=which_)\n",
+    "    print(\n",
+    "        f'The \"{name}\" would be preferred between {low:.2%} and {high:.2%} percent of the time (with 95% confidence).'\n",
+    "    )"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**Print out the p-value.**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The p-value is 0.00000. If the null hypothesis is true (i.e., if the selected eval chain actually has no preference between the models),\n",
+      "then there is a 0.00038% chance of observing the OpenAI Functions Agent be preferred at least 19\n",
+      "times out of 19 trials.\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/var/folders/gf/6rnp_mbx5914kx7qmmh7xzmw0000gn/T/ipykernel_15978/384907688.py:6: DeprecationWarning: 'binom_test' is deprecated in favour of 'binomtest' from version 1.7.0 and will be removed in Scipy 1.12.0.\n",
+      "  p_value = stats.binom_test(successes, n, p=0.5, alternative=\"two-sided\")\n"
+     ]
+    }
+   ],
+   "source": [
+    "from scipy import stats\n",
+    "\n",
+    "preferred_model = max(pref_ratios, key=pref_ratios.get)\n",
+    "successes = preferences.count(preferred_model)\n",
+    "n = len(preferences) - preferences.count(None)\n",
+    "p_value = stats.binom_test(successes, n, p=0.5, alternative=\"two-sided\")\n",
+    "print(\n",
+    "    f\"\"\"The p-value is {p_value:.5f}. If the null hypothesis is true (i.e., if the selected eval chain actually has no preference between the models),\n",
+    "then there is a {p_value:.5%} chance of observing the {name_map.get(preferred_model)} be preferred at least {successes}\n",
+    "times out of {n} trials.\"\"\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<a name=\"cite_note-1\"></a>_1. Note: Automated evals are still an open research topic and are best used alongside other evaluation approaches. \n",
+    "LLM preferences exhibit biases, including banal ones like the order of outputs.\n",
+    "In choosing preferences, \"ground truth\" may not be taken into account, which may lead to scores that aren't grounded in utility._"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

docs/docs/guides/productionization/evaluation/examples/index.mdx

@@ -0,0 +1,12 @@
+---
+sidebar_position: 5
+---
+# Examples
+
+🚧 _Docs under construction_ 🚧
+
+Below are some examples for inspecting and checking different chains.
+
+import DocCardList from "@theme/DocCardList";
+
+<DocCardList />