fmt

Description: Video imagery to text (Closed Captioning)
This pull request introduces the VideoCaptioningChain, a tool for
automated video captioning. It processes audio and video to generate
subtitles and closed captions, merging them into a single SRT output.

Issue: https://github.com/langchain-ai/langchain/issues/11770
Dependencies: opencv-python, ffmpeg-python, assemblyai, transformers,
pillow, torch, openai
Tag maintainer:
@baskaryan
@hwchase17


Hello!

We are a group of students from the University of Toronto
(@LunarECL, @TomSadan, @nicoledroi1, @A2113S) that want to make a
contribution to the LangChain community! We have ran make format, make
lint and make test locally before submitting the PR. To our knowledge,
our changes do not introduce any new errors.

Thank you for taking the time to review our PR!

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>

.github/scripts/get_min_versions.py

@@ -4,7 +4,12 @@ import tomllib
 from packaging.version import parse as parse_version
 import re
 
-MIN_VERSION_LIBS = ["langchain-core", "langchain-community", "langchain", "langchain-text-splitters"]
+MIN_VERSION_LIBS = [
+    "langchain-core",
+    "langchain-community",
+    "langchain",
+    "langchain-text-splitters",
+]
 
 
 def get_min_version(version: str) -> str:
@@ -56,12 +61,13 @@ def get_min_version_from_toml(toml_path: str):
     return min_versions
 
 
-# Get the TOML file path from the command line argument
-toml_file = sys.argv[1]
+if __name__ == "__main__":
+    # Get the TOML file path from the command line argument
+    toml_file = sys.argv[1]
 
-# Call the function to get the minimum versions
-min_versions = get_min_version_from_toml(toml_file)
+    # Call the function to get the minimum versions
+    min_versions = get_min_version_from_toml(toml_file)
 
-print(
-    " ".join([f"{lib}=={version}" for lib, version in min_versions.items()])
-)  # noqa: T201
+    print(
+        " ".join([f"{lib}=={version}" for lib, version in min_versions.items()])
+    )  # noqa: T201

.github/workflows/_integration_test.yml

@@ -75,6 +75,8 @@ jobs:
           ES_API_KEY: ${{ secrets.ES_API_KEY }}
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} # for airbyte
           MONGODB_ATLAS_URI: ${{ secrets.MONGODB_ATLAS_URI }}
+          VOYAGE_API_KEY: ${{ secrets.VOYAGE_API_KEY }}
+          COHERE_API_KEY: ${{ secrets.COHERE_API_KEY }}
         run: |
           make integration_tests
 

.github/workflows/_release.yml

@@ -157,6 +157,24 @@ jobs:
         run: make tests
         working-directory: ${{ inputs.working-directory }}
 
+      - name: Get minimum versions
+        working-directory: ${{ inputs.working-directory }}
+        id: min-version
+        run: |
+          poetry run pip install packaging
+          min_versions="$(poetry run python $GITHUB_WORKSPACE/.github/scripts/get_min_versions.py pyproject.toml)"
+          echo "min-versions=$min_versions" >> "$GITHUB_OUTPUT"
+          echo "min-versions=$min_versions"
+
+      - name: Run unit tests with minimum dependency versions
+        if: ${{ steps.min-version.outputs.min-versions != '' }}
+        env:
+          MIN_VERSIONS: ${{ steps.min-version.outputs.min-versions }}
+        run: |
+          poetry run pip install $MIN_VERSIONS
+          make tests
+        working-directory: ${{ inputs.working-directory }}
+
       - name: 'Authenticate to Google Cloud'
         id: 'auth'
         uses: google-github-actions/auth@v2
@@ -196,27 +214,11 @@ jobs:
           ES_API_KEY: ${{ secrets.ES_API_KEY }}
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} # for airbyte
           MONGODB_ATLAS_URI: ${{ secrets.MONGODB_ATLAS_URI }}
+          VOYAGE_API_KEY: ${{ secrets.VOYAGE_API_KEY }}
+          COHERE_API_KEY: ${{ secrets.COHERE_API_KEY }}
         run: make integration_tests
         working-directory: ${{ inputs.working-directory }}
 
-      - name: Get minimum versions
-        working-directory: ${{ inputs.working-directory }}
-        id: min-version
-        run: |
-          poetry run pip install packaging
-          min_versions="$(poetry run python $GITHUB_WORKSPACE/.github/scripts/get_min_versions.py pyproject.toml)"
-          echo "min-versions=$min_versions" >> "$GITHUB_OUTPUT"
-          echo "min-versions=$min_versions"
-
-      - name: Run unit tests with minimum dependency versions
-        if: ${{ steps.min-version.outputs.min-versions != '' }}
-        env:
-          MIN_VERSIONS: ${{ steps.min-version.outputs.min-versions }}
-        run: |
-          poetry run pip install $MIN_VERSIONS
-          make tests
-        working-directory: ${{ inputs.working-directory }}
-
   publish:
     needs:
       - build

.github/workflows/_test_doc_imports.yml

@@ -0,0 +1,50 @@
+name: test_doc_imports
+
+on:
+  workflow_call:
+
+env:
+  POETRY_VERSION: "1.7.1"
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version:
+          - "3.11"
+    name: "check doc imports #${{ matrix.python-version }}"
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+        uses: "./.github/actions/poetry_setup"
+        with:
+          python-version: ${{ matrix.python-version }}
+          poetry-version: ${{ env.POETRY_VERSION }}
+          cache-key: core
+
+      - name: Install dependencies
+        shell: bash
+        run: poetry install --with test
+
+      - name: Install langchain editable
+        run: |
+          poetry run pip install -e libs/core libs/langchain libs/community libs/experimental
+
+      - name: Check doc imports
+        shell: bash
+        run: |
+          poetry run python docs/scripts/check_imports.py
+
+      - name: Ensure the test did not create any additional files
+        shell: bash
+        run: |
+          set -eu
+
+          STATUS="$(git status)"
+          echo "$STATUS"
+
+          # grep will exit non-zero if the target message isn't found,
+          # and `set -e` above will cause the step to fail.
+          echo "$STATUS" | grep 'nothing to commit, working tree clean'

.github/workflows/check-broken-links.yml

@@ -0,0 +1,24 @@
+name: Check Broken Links
+
+on:
+  workflow_dispatch:
+  schedule:
+    - cron:  '0 13 * * *'
+
+jobs:
+  check-links:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Use Node.js 18.x
+        uses: actions/setup-node@v3
+        with:
+          node-version: 18.x
+          cache: "yarn"
+          cache-dependency-path: ./docs/yarn.lock
+      - name: Install dependencies
+        run: yarn install --immutable --mode=skip-build
+        working-directory: ./docs
+      - name: Check broken links
+        run: yarn check-broken-links
+        working-directory: ./docs

.github/workflows/check_diffs.yml

@@ -60,6 +60,12 @@ jobs:
       working-directory: ${{ matrix.working-directory }}
     secrets: inherit
 
+  test_doc_imports:
+    needs: [ build ]
+    if: ${{ needs.build.outputs.dirs-to-test != '[]' }}
+    uses: ./.github/workflows/_test_doc_imports.yml
+    secrets: inherit
+
   compile-integration-tests:
     name: cd ${{ matrix.working-directory }}
     needs: [ build ]

.gitignore

@@ -116,6 +116,7 @@ celerybeat.pid
 .env
 .envrc
 .venv*
+venv*
 env/
 ENV/
 env.bak/

Makefile

@@ -1,44 +1,56 @@
-.PHONY: all clean docs_build docs_clean docs_linkcheck api_docs_build api_docs_clean api_docs_linkcheck
+.PHONY: all clean help docs_build docs_clean docs_linkcheck api_docs_build api_docs_clean api_docs_linkcheck spell_check spell_fix lint lint_package lint_tests format format_diff
 
-# Default target executed when no arguments are given to make.
+## 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/^/ /'
+
+## all: Default target, shows help.
 all: help
 
+## clean: Clean documentation and API documentation artifacts.
+clean: docs_clean api_docs_clean
 
 ######################
 # DOCUMENTATION
 ######################
 
-clean: docs_clean api_docs_clean
-
-
+## docs_build: Build the documentation.
 docs_build:
 	docs/.local_build.sh
 
+## docs_clean: Clean the documentation build artifacts.
 docs_clean:
 	@if [ -d _dist ]; then \
-			rm -r _dist; \
-			echo "Directory _dist has been cleaned."; \
+		rm -r _dist; \
+		echo "Directory _dist has been cleaned."; \
 	else \
-			echo "Nothing to clean."; \
+		echo "Nothing to clean."; \
 	fi
 
+## docs_linkcheck: Run linkchecker on the documentation.
 docs_linkcheck:
 	poetry run linkchecker _dist/docs/ --ignore-url node_modules
 
+## api_docs_build: Build the API Reference documentation.
 api_docs_build:
 	poetry run python docs/api_reference/create_api_rst.py
 	cd docs/api_reference && poetry run make html
 
+## api_docs_clean: Clean the API Reference documentation build artifacts.
 api_docs_clean:
-	rm -f docs/api_reference/api_reference.rst
+	find ./docs/api_reference -name '*_api_reference.rst' -delete
 	cd docs/api_reference && poetry run make clean
 
+## api_docs_linkcheck: Run linkchecker on the API Reference documentation.
 api_docs_linkcheck:
 	poetry run linkchecker docs/api_reference/_build/html/index.html
 
+## spell_check: Run codespell on the project.
 spell_check:
 	poetry run codespell --toml pyproject.toml
 
+## spell_fix: Run codespell on the project and fix the errors.
 spell_fix:
 	poetry run codespell --toml pyproject.toml -w
 
@@ -46,31 +58,14 @@ spell_fix:
 # LINTING AND FORMATTING
 ######################
 
+## lint: Run linting on the project.
 lint lint_package lint_tests:
 	poetry run ruff docs templates cookbook
 	poetry run ruff format docs templates cookbook --diff
 	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 --select I --fix docs templates cookbook
-
-
-######################
-# HELP
-######################
-
-help:
-	@echo '===================='
-	@echo '-- DOCUMENTATION --'
-	@echo 'clean                        - run docs_clean and api_docs_clean'
-	@echo 'docs_build                   - build the documentation'
-	@echo 'docs_clean                   - clean the documentation build artifacts'
-	@echo 'docs_linkcheck               - run linkchecker on the documentation'
-	@echo 'api_docs_build               - build the API Reference documentation'
-	@echo 'api_docs_clean               - clean the API Reference documentation build artifacts'
-	@echo 'api_docs_linkcheck           - run linkchecker on the API Reference documentation'
-	@echo 'spell_check               	- run codespell on the project'
-	@echo 'spell_fix               		- run codespell on the project and fix the errors'
-	@echo '-- TEST and LINT tasks are within libs/*/ per-package --'

cookbook/autogpt/marathon_times.ipynb

@@ -40,7 +40,9 @@
     "import nest_asyncio\n",
     "import pandas as pd\n",
     "from langchain.docstore.document import Document\n",
-    "from langchain_community.agent_toolkits.pandas.base import create_pandas_dataframe_agent\n",
+    "from langchain_experimental.agents.agent_toolkits.pandas.base import (\n",
+    "    create_pandas_dataframe_agent,\n",
+    ")\n",
     "from langchain_experimental.autonomous_agents import AutoGPT\n",
     "from langchain_openai import ChatOpenAI\n",
     "\n",

cookbook/fake_llm.ipynb

@@ -100,7 +100,7 @@
     }
    ],
    "source": [
-    "agent.run(\"whats 2 + 2\")"
+    "agent.invoke(\"whats 2 + 2\")"
    ]
   },
   {

cookbook/llm_symbolic_math.ipynb

@@ -45,7 +45,7 @@
     }
    ],
    "source": [
-    "llm_symbolic_math.run(\"What is the derivative of sin(x)*exp(x) with respect to x?\")"
+    "llm_symbolic_math.invoke(\"What is the derivative of sin(x)*exp(x) with respect to x?\")"
    ]
   },
   {
@@ -65,7 +65,7 @@
     }
    ],
    "source": [
-    "llm_symbolic_math.run(\n",
+    "llm_symbolic_math.invoke(\n",
     "    \"What is the integral of exp(x)*sin(x) + exp(x)*cos(x) with respect to x?\"\n",
     ")"
    ]
@@ -94,7 +94,7 @@
     }
    ],
    "source": [
-    "llm_symbolic_math.run('Solve the differential equation y\" - y = e^t')"
+    "llm_symbolic_math.invoke('Solve the differential equation y\" - y = e^t')"
    ]
   },
   {
@@ -114,7 +114,7 @@
     }
    ],
    "source": [
-    "llm_symbolic_math.run(\"What are the solutions to this equation y^3 + 1/3y?\")"
+    "llm_symbolic_math.invoke(\"What are the solutions to this equation y^3 + 1/3y?\")"
    ]
   },
   {
@@ -134,7 +134,7 @@
     }
    ],
    "source": [
-    "llm_symbolic_math.run(\"x = y + 5, y = z - 3, z = x * y. Solve for x, y, z\")"
+    "llm_symbolic_math.invoke(\"x = y + 5, y = z - 3, z = x * y. Solve for x, y, z\")"
    ]
   }
  ],

cookbook/rewrite.ipynb

@@ -245,7 +245,7 @@
     "\n",
     "\n",
     "def _parse(text):\n",
-    "    return text.strip(\"**\")"
+    "    return text.strip('\"').strip(\"**\")"
    ]
   },
   {

cookbook/sales_agent_with_context.ipynb

@@ -1,28 +1,32 @@
 {
  "cells": [
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# SalesGPT - Your Context-Aware AI Sales Assistant With Knowledge Base\n",
+    "# SalesGPT - Context-Aware AI Sales Assistant With Knowledge Base and Ability Generate Stripe Payment Links\n",
     "\n",
-    "This notebook demonstrates an implementation of a **Context-Aware** AI Sales agent with a Product Knowledge Base. \n",
+    "This notebook demonstrates an implementation of a **Context-Aware** AI Sales agent with a Product Knowledge Base which can actually close sales. \n",
     "\n",
     "This notebook was originally published at [filipmichalsky/SalesGPT](https://github.com/filip-michalsky/SalesGPT) by [@FilipMichalsky](https://twitter.com/FilipMichalsky).\n",
     "\n",
     "SalesGPT is context-aware, which means it can understand what section of a sales conversation it is in and act accordingly.\n",
     " \n",
-    "As such, this agent can have a natural sales conversation with a prospect and behaves based on the conversation stage. Hence, this notebook demonstrates how we can use AI to automate sales development representatives activities, such as outbound sales calls. \n",
+    "As such, this agent can have a natural sales conversation with a prospect and behaves based on the conversation stage. Hence, this notebook demonstrates how we can use AI to automate sales development representatives activites, such as outbound sales calls. \n",
     "\n",
     "Additionally, the AI Sales agent has access to tools, which allow it to interact with other systems.\n",
     "\n",
     "Here, we show how the AI Sales Agent can use a **Product Knowledge Base** to speak about a particular's company offerings,\n",
     "hence increasing relevance and reducing hallucinations.\n",
     "\n",
-    "We leverage the [`langchain`](https://github.com/langchain-ai/langchain) library in this implementation, specifically [Custom Agent Configuration](https://langchain-langchain.vercel.app/docs/modules/agents/how_to/custom_agent_with_tool_retrieval) and are inspired by [BabyAGI](https://github.com/yoheinakajima/babyagi) architecture ."
+    "Furthermore, we show how our AI Sales Agent can **generate sales** by integration with the AI Agent Highway called [Mindware](https://www.mindware.co/). In practice, this allows the agent to autonomously generate a payment link for your customers **to pay for your products via Stripe**.\n",
+    "\n",
+    "We leverage the [`langchain`](https://github.com/hwchase17/langchain) library in this implementation, specifically [Custom Agent Configuration](https://langchain-langchain.vercel.app/docs/modules/agents/how_to/custom_agent_with_tool_retrieval) and are inspired by [BabyAGI](https://github.com/yoheinakajima/babyagi) architecture ."
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -38,9 +42,10 @@
     "import os\n",
     "import re\n",
     "\n",
-    "# import your OpenAI key\n",
-    "OPENAI_API_KEY = \"sk-xx\"\n",
-    "os.environ[\"OPENAI_API_KEY\"] = OPENAI_API_KEY\n",
+    "# make sure you have .env file saved locally with your API keys\n",
+    "from dotenv import load_dotenv\n",
+    "\n",
+    "load_dotenv()\n",
     "\n",
     "from typing import Any, Callable, Dict, List, Union\n",
     "\n",
@@ -49,27 +54,18 @@
     "from langchain.agents.conversational.prompt import FORMAT_INSTRUCTIONS\n",
     "from langchain.chains import LLMChain, RetrievalQA\n",
     "from langchain.chains.base import Chain\n",
+    "from langchain.llms import BaseLLM\n",
     "from langchain.prompts import PromptTemplate\n",
     "from langchain.prompts.base import StringPromptTemplate\n",
-    "from langchain_community.llms import BaseLLM\n",
-    "from langchain_community.vectorstores import Chroma\n",
-    "from langchain_core.agents import AgentAction, AgentFinish\n",
-    "from langchain_openai import ChatOpenAI, OpenAI, OpenAIEmbeddings\n",
-    "from langchain_text_splitters import CharacterTextSplitter\n",
+    "from langchain.schema import AgentAction, AgentFinish\n",
+    "from langchain.text_splitter import CharacterTextSplitter\n",
+    "from langchain.vectorstores import Chroma\n",
+    "from langchain_openai import ChatOpenAI, OpenAIEmbeddings\n",
     "from pydantic import BaseModel, Field"
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# install additional dependencies\n",
-    "# ! pip install chromadb openai tiktoken"
-   ]
-  },
-  {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -77,19 +73,21 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
     "1. Seed the SalesGPT agent\n",
     "2. Run Sales Agent to decide what to do:\n",
     "\n",
-    "    a) Use a tool, such as look up Product Information in a Knowledge Base\n",
+    "    a) Use a tool, such as look up Product Information in a Knowledge Base or Generate a Payment Link\n",
     "    \n",
     "    b) Output a response to a user \n",
     "3. Run Sales Stage Recognition Agent to recognize which stage is the sales agent at and adjust their behaviour accordingly."
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -98,15 +96,17 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
     "### Architecture diagram\n",
     "\n",
-    "<img src=\"https://singularity-assets-public.s3.amazonaws.com/new_flow.png\"  width=\"800\" height=\"440\"/>\n"
+    "<img src=\"https://demo-bucket-45.s3.amazonaws.com/new_flow2.png\"  width=\"800\" height=\"440\">\n"
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -131,7 +131,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -149,7 +149,7 @@
     "            {conversation_history}\n",
     "            ===\n",
     "\n",
-    "            Now determine what should be the next immediate conversation stage for the agent in the sales conversation by selecting only from the following options:\n",
+    "            Now determine what should be the next immediate conversation stage for the agent in the sales conversation by selecting ony from the following options:\n",
     "            1. Introduction: Start the conversation by introducing yourself and your company. Be polite and respectful while keeping the tone of the conversation professional.\n",
     "            2. Qualification: Qualify the prospect by confirming if they are the right person to talk to regarding your product/service. Ensure that they have the authority to make purchasing decisions.\n",
     "            3. Value proposition: Briefly explain how your product/service can benefit the prospect. Focus on the unique selling points and value proposition of your product/service that sets it apart from competitors.\n",
@@ -171,7 +171,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -223,7 +223,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -240,13 +240,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [],
    "source": [
     "# test the intermediate chains\n",
     "verbose = True\n",
-    "llm = ChatOpenAI(temperature=0.9)\n",
+    "llm = ChatOpenAI(\n",
+    "    model=\"gpt-4-turbo-preview\",\n",
+    "    temperature=0.9,\n",
+    "    openai_api_key=os.getenv(\"OPENAI_API_KEY\"),\n",
+    ")\n",
     "\n",
     "stage_analyzer_chain = StageAnalyzerChain.from_llm(llm, verbose=verbose)\n",
     "\n",
@@ -257,7 +261,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [
     {
@@ -276,7 +280,7 @@
       "            \n",
       "            ===\n",
       "\n",
-      "            Now determine what should be the next immediate conversation stage for the agent in the sales conversation by selecting only from the following options:\n",
+      "            Now determine what should be the next immediate conversation stage for the agent in the sales conversation by selecting ony from the following options:\n",
       "            1. Introduction: Start the conversation by introducing yourself and your company. Be polite and respectful while keeping the tone of the conversation professional.\n",
       "            2. Qualification: Qualify the prospect by confirming if they are the right person to talk to regarding your product/service. Ensure that they have the authority to make purchasing decisions.\n",
       "            3. Value proposition: Briefly explain how your product/service can benefit the prospect. Focus on the unique selling points and value proposition of your product/service that sets it apart from competitors.\n",
@@ -296,21 +300,21 @@
     {
      "data": {
       "text/plain": [
-       "'1'"
+       "{'conversation_history': '', 'text': '1'}"
       ]
      },
-     "execution_count": 7,
+     "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "stage_analyzer_chain.run(conversation_history=\"\")"
+    "stage_analyzer_chain.invoke({\"conversation_history\": \"\"})"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
@@ -352,32 +356,44 @@
     {
      "data": {
       "text/plain": [
-       "\"I'm doing great, thank you for asking! As a Business Development Representative at Sleep Haven, I wanted to reach out to see if you are looking to achieve a better night's sleep. We provide premium mattresses that offer the most comfortable and supportive sleeping experience possible. Are you interested in exploring our sleep solutions? <END_OF_TURN>\""
+       "{'salesperson_name': 'Ted Lasso',\n",
+       " 'salesperson_role': 'Business Development Representative',\n",
+       " 'company_name': 'Sleep Haven',\n",
+       " 'company_business': 'Sleep Haven is a premium mattress company that provides customers with the most comfortable and supportive sleeping experience possible. We offer a range of high-quality mattresses, pillows, and bedding accessories that are designed to meet the unique needs of our customers.',\n",
+       " 'company_values': \"Our mission at Sleep Haven is to help people achieve a better night's sleep by providing them with the best possible sleep solutions. We believe that quality sleep is essential to overall health and well-being, and we are committed to helping our customers achieve optimal sleep by offering exceptional products and customer service.\",\n",
+       " 'conversation_purpose': 'find out whether they are looking to achieve better sleep via buying a premier mattress.',\n",
+       " 'conversation_history': 'Hello, this is Ted Lasso from Sleep Haven. How are you doing today? <END_OF_TURN>\\nUser: I am well, howe are you?<END_OF_TURN>',\n",
+       " 'conversation_type': 'call',\n",
+       " 'conversation_stage': 'Introduction: Start the conversation by introducing yourself and your company. Be polite and respectful while keeping the tone of the conversation professional. Your greeting should be welcoming. Always clarify in your greeting the reason why you are contacting the prospect.',\n",
+       " 'text': \"I'm doing well, thank you for asking. The reason I'm calling is to discuss how Sleep Haven can help enhance your sleep quality with our premium mattresses. Are you currently looking for ways to achieve a better night's sleep? <END_OF_TURN>\"}"
       ]
      },
-     "execution_count": 8,
+     "execution_count": 7,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "sales_conversation_utterance_chain.run(\n",
-    "    salesperson_name=\"Ted Lasso\",\n",
-    "    salesperson_role=\"Business Development Representative\",\n",
-    "    company_name=\"Sleep Haven\",\n",
-    "    company_business=\"Sleep Haven is a premium mattress company that provides customers with the most comfortable and supportive sleeping experience possible. We offer a range of high-quality mattresses, pillows, and bedding accessories that are designed to meet the unique needs of our customers.\",\n",
-    "    company_values=\"Our mission at Sleep Haven is to help people achieve a better night's sleep by providing them with the best possible sleep solutions. We believe that quality sleep is essential to overall health and well-being, and we are committed to helping our customers achieve optimal sleep by offering exceptional products and customer service.\",\n",
-    "    conversation_purpose=\"find out whether they are looking to achieve better sleep via buying a premier mattress.\",\n",
-    "    conversation_history=\"Hello, this is Ted Lasso from Sleep Haven. How are you doing today? <END_OF_TURN>\\nUser: I am well, howe are you?<END_OF_TURN>\",\n",
-    "    conversation_type=\"call\",\n",
-    "    conversation_stage=conversation_stages.get(\n",
-    "        \"1\",\n",
-    "        \"Introduction: Start the conversation by introducing yourself and your company. Be polite and respectful while keeping the tone of the conversation professional.\",\n",
-    "    ),\n",
+    "sales_conversation_utterance_chain.invoke(\n",
+    "    {\n",
+    "        \"salesperson_name\": \"Ted Lasso\",\n",
+    "        \"salesperson_role\": \"Business Development Representative\",\n",
+    "        \"company_name\": \"Sleep Haven\",\n",
+    "        \"company_business\": \"Sleep Haven is a premium mattress company that provides customers with the most comfortable and supportive sleeping experience possible. We offer a range of high-quality mattresses, pillows, and bedding accessories that are designed to meet the unique needs of our customers.\",\n",
+    "        \"company_values\": \"Our mission at Sleep Haven is to help people achieve a better night's sleep by providing them with the best possible sleep solutions. We believe that quality sleep is essential to overall health and well-being, and we are committed to helping our customers achieve optimal sleep by offering exceptional products and customer service.\",\n",
+    "        \"conversation_purpose\": \"find out whether they are looking to achieve better sleep via buying a premier mattress.\",\n",
+    "        \"conversation_history\": \"Hello, this is Ted Lasso from Sleep Haven. How are you doing today? <END_OF_TURN>\\nUser: I am well, howe are you?<END_OF_TURN>\",\n",
+    "        \"conversation_type\": \"call\",\n",
+    "        \"conversation_stage\": conversation_stages.get(\n",
+    "            \"1\",\n",
+    "            \"Introduction: Start the conversation by introducing yourself and your company. Be polite and respectful while keeping the tone of the conversation professional.\",\n",
+    "        ),\n",
+    "    }\n",
     ")"
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -385,6 +401,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -395,7 +412,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -429,7 +446,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -445,7 +462,7 @@
     "    text_splitter = CharacterTextSplitter(chunk_size=10, chunk_overlap=0)\n",
     "    texts = text_splitter.split_text(product_catalog)\n",
     "\n",
-    "    llm = OpenAI(temperature=0)\n",
+    "    llm = ChatOpenAI(temperature=0)\n",
     "    embeddings = OpenAIEmbeddings()\n",
     "    docsearch = Chroma.from_texts(\n",
     "        texts, embeddings, collection_name=\"product-knowledge-base\"\n",
@@ -454,29 +471,12 @@
     "    knowledge_base = RetrievalQA.from_chain_type(\n",
     "        llm=llm, chain_type=\"stuff\", retriever=docsearch.as_retriever()\n",
     "    )\n",
-    "    return knowledge_base\n",
-    "\n",
-    "\n",
-    "def get_tools(product_catalog):\n",
-    "    # query to get_tools can be used to be embedded and relevant tools found\n",
-    "    # see here: https://langchain-langchain.vercel.app/docs/use_cases/agents/custom_agent_with_plugin_retrieval#tool-retriever\n",
-    "\n",
-    "    # we only use one tool for now, but this is highly extensible!\n",
-    "    knowledge_base = setup_knowledge_base(product_catalog)\n",
-    "    tools = [\n",
-    "        Tool(\n",
-    "            name=\"ProductSearch\",\n",
-    "            func=knowledge_base.run,\n",
-    "            description=\"useful for when you need to answer questions about product information\",\n",
-    "        )\n",
-    "    ]\n",
-    "\n",
-    "    return tools"
+    "    return knowledge_base"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [
     {
@@ -485,16 +485,18 @@
      "text": [
       "Created a chunk of size 940, which is longer than the specified 10\n",
       "Created a chunk of size 844, which is longer than the specified 10\n",
-      "Created a chunk of size 837, which is longer than the specified 10\n"
+      "Created a chunk of size 837, which is longer than the specified 10\n",
+      "/Users/filipmichalsky/Odyssey/sales_bot/SalesGPT/env/lib/python3.10/site-packages/langchain_core/_api/deprecation.py:117: LangChainDeprecationWarning: The function `run` was deprecated in LangChain 0.1.0 and will be removed in 0.2.0. Use invoke instead.\n",
+      "  warn_deprecated(\n"
      ]
     },
     {
      "data": {
       "text/plain": [
-       "' We have four products available: the Classic Harmony Spring Mattress, the Plush Serenity Bamboo Mattress, the Luxury Cloud-Comfort Memory Foam Mattress, and the EcoGreen Hybrid Latex Mattress. Each product is available in different sizes, with the Classic Harmony Spring Mattress available in Queen and King sizes, the Plush Serenity Bamboo Mattress available in King size, the Luxury Cloud-Comfort Memory Foam Mattress available in Twin, Queen, and King sizes, and the EcoGreen Hybrid Latex Mattress available in Twin and Full sizes.'"
+       "'The Sleep Haven products available are:\\n\\n1. Luxury Cloud-Comfort Memory Foam Mattress\\n2. Classic Harmony Spring Mattress\\n3. EcoGreen Hybrid Latex Mattress\\n4. Plush Serenity Bamboo Mattress\\n\\nEach product has its unique features and price point.'"
       ]
      },
-     "execution_count": 11,
+     "execution_count": 10,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -508,12 +510,199 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "### Set up the SalesGPT Controller with the Sales Agent and Stage Analyzer and a Knowledge Base"
+    "### Payment gateway"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "In order to set up your AI agent to use a payment gateway to generate payment links for your users you need two things:\n",
+    "\n",
+    "1. Sign up for a Stripe account and obtain a STRIPE API KEY\n",
+    "2. Create products you would like to sell in the Stripe UI. Then follow out example of `example_product_price_id_mapping.json`\n",
+    "to feed the product name to price_id mapping which allows you to generate the payment links."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import json\n",
+    "\n",
+    "from litellm import completion\n",
+    "\n",
+    "# set GPT model env variable\n",
+    "os.environ[\"GPT_MODEL\"] = \"gpt-4-turbo-preview\"\n",
+    "\n",
+    "product_price_id_mapping = {\n",
+    "    \"ai-consulting-services\": \"price_1Ow8ofB795AYY8p1goWGZi6m\",\n",
+    "    \"Luxury Cloud-Comfort Memory Foam Mattress\": \"price_1Owv99B795AYY8p1mjtbKyxP\",\n",
+    "    \"Classic Harmony Spring Mattress\": \"price_1Owv9qB795AYY8p1tPcxCM6T\",\n",
+    "    \"EcoGreen Hybrid Latex Mattress\": \"price_1OwvLDB795AYY8p1YBAMBcbi\",\n",
+    "    \"Plush Serenity Bamboo Mattress\": \"price_1OwvMQB795AYY8p1hJN2uS3S\",\n",
+    "}\n",
+    "with open(\"example_product_price_id_mapping.json\", \"w\") as f:\n",
+    "    json.dump(product_price_id_mapping, f)\n",
+    "\n",
+    "\n",
+    "def get_product_id_from_query(query, product_price_id_mapping_path):\n",
+    "    # Load product_price_id_mapping from a JSON file\n",
+    "    with open(product_price_id_mapping_path, \"r\") as f:\n",
+    "        product_price_id_mapping = json.load(f)\n",
+    "\n",
+    "    # Serialize the product_price_id_mapping to a JSON string for inclusion in the prompt\n",
+    "    product_price_id_mapping_json_str = json.dumps(product_price_id_mapping)\n",
+    "\n",
+    "    # Dynamically create the enum list from product_price_id_mapping keys\n",
+    "    enum_list = list(product_price_id_mapping.values()) + [\n",
+    "        \"No relevant product id found\"\n",
+    "    ]\n",
+    "    enum_list_str = json.dumps(enum_list)\n",
+    "\n",
+    "    prompt = f\"\"\"\n",
+    "    You are an expert data scientist and you are working on a project to recommend products to customers based on their needs.\n",
+    "    Given the following query:\n",
+    "    {query}\n",
+    "    and the following product price id mapping:\n",
+    "    {product_price_id_mapping_json_str}\n",
+    "    return the price id that is most relevant to the query.\n",
+    "    ONLY return the price id, no other text. If no relevant price id is found, return 'No relevant price id found'.\n",
+    "    Your output will follow this schema:\n",
+    "    {{\n",
+    "    \"$schema\": \"http://json-schema.org/draft-07/schema#\",\n",
+    "    \"title\": \"Price ID Response\",\n",
+    "    \"type\": \"object\",\n",
+    "    \"properties\": {{\n",
+    "        \"price_id\": {{\n",
+    "        \"type\": \"string\",\n",
+    "        \"enum\": {enum_list_str}\n",
+    "        }}\n",
+    "    }},\n",
+    "    \"required\": [\"price_id\"]\n",
+    "    }}\n",
+    "    Return a valid directly parsable json, dont return in it within a code snippet or add any kind of explanation!!\n",
+    "    \"\"\"\n",
+    "    prompt += \"{\"\n",
+    "    response = completion(\n",
+    "        model=os.getenv(\"GPT_MODEL\", \"gpt-3.5-turbo-1106\"),\n",
+    "        messages=[{\"content\": prompt, \"role\": \"user\"}],\n",
+    "        max_tokens=1000,\n",
+    "        temperature=0,\n",
+    "    )\n",
+    "\n",
+    "    product_id = response.choices[0].message.content.strip()\n",
+    "    return product_id"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import json\n",
+    "\n",
+    "import requests\n",
+    "\n",
+    "\n",
+    "def generate_stripe_payment_link(query: str) -> str:\n",
+    "    \"\"\"Generate a stripe payment link for a customer based on a single query string.\"\"\"\n",
+    "\n",
+    "    # example testing payment gateway url\n",
+    "    PAYMENT_GATEWAY_URL = os.getenv(\n",
+    "        \"PAYMENT_GATEWAY_URL\", \"https://agent-payments-gateway.vercel.app/payment\"\n",
+    "    )\n",
+    "    PRODUCT_PRICE_MAPPING = \"example_product_price_id_mapping.json\"\n",
+    "\n",
+    "    # use LLM to get the price_id from query\n",
+    "    price_id = get_product_id_from_query(query, PRODUCT_PRICE_MAPPING)\n",
+    "    price_id = json.loads(price_id)\n",
+    "    payload = json.dumps(\n",
+    "        {\"prompt\": query, **price_id, \"stripe_key\": os.getenv(\"STRIPE_API_KEY\")}\n",
+    "    )\n",
+    "    headers = {\n",
+    "        \"Content-Type\": \"application/json\",\n",
+    "    }\n",
+    "\n",
+    "    response = requests.request(\n",
+    "        \"POST\", PAYMENT_GATEWAY_URL, headers=headers, data=payload\n",
+    "    )\n",
+    "    return response.text"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'{\"response\":\"https://buy.stripe.com/test_6oEbLS8JB1F9bv229d\"}'"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "generate_stripe_payment_link(\n",
+    "    query=\"Please generate a payment link for John Doe to buy two mattresses - the Classic Harmony Spring Mattress\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Setup agent tools"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def get_tools(product_catalog):\n",
+    "    # query to get_tools can be used to be embedded and relevant tools found\n",
+    "    # see here: https://langchain-langchain.vercel.app/docs/use_cases/agents/custom_agent_with_plugin_retrieval#tool-retriever\n",
+    "\n",
+    "    # we only use one tool for now, but this is highly extensible!\n",
+    "    knowledge_base = setup_knowledge_base(product_catalog)\n",
+    "    tools = [\n",
+    "        Tool(\n",
+    "            name=\"ProductSearch\",\n",
+    "            func=knowledge_base.run,\n",
+    "            description=\"useful for when you need to answer questions about product information or services offered, availability and their costs.\",\n",
+    "        ),\n",
+    "        Tool(\n",
+    "            name=\"GeneratePaymentLink\",\n",
+    "            func=generate_stripe_payment_link,\n",
+    "            description=\"useful to close a transaction with a customer. You need to include product name and quantity and customer name in the query input.\",\n",
+    "        ),\n",
+    "    ]\n",
+    "\n",
+    "    return tools"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Set up the SalesGPT Controller with the Sales Agent and Stage Analyzer\n",
+    "\n",
+    "#### The Agent has access to a Knowledge Base and can autonomously sell your products via Stripe"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -563,19 +752,11 @@
     "            print(\"TEXT\")\n",
     "            print(text)\n",
     "            print(\"-------\")\n",
-    "        if f\"{self.ai_prefix}:\" in text:\n",
-    "            return AgentFinish(\n",
-    "                {\"output\": text.split(f\"{self.ai_prefix}:\")[-1].strip()}, text\n",
-    "            )\n",
     "        regex = r\"Action: (.*?)[\\n]*Action Input: (.*)\"\n",
     "        match = re.search(regex, text)\n",
     "        if not match:\n",
-    "            ## TODO - this is not entirely reliable, sometimes results in an error.\n",
     "            return AgentFinish(\n",
-    "                {\n",
-    "                    \"output\": \"I apologize, I was unable to find the answer to your question. Is there anything else I can help with?\"\n",
-    "                },\n",
-    "                text,\n",
+    "                {\"output\": text.split(f\"{self.ai_prefix}:\")[-1].strip()}, text\n",
     "            )\n",
     "            # raise OutputParserException(f\"Could not parse LLM output: `{text}`\")\n",
     "        action = match.group(1)\n",
@@ -589,7 +770,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 19,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -647,18 +828,18 @@
     "Previous conversation history:\n",
     "{conversation_history}\n",
     "\n",
-    "{salesperson_name}:\n",
+    "Thought:\n",
     "{agent_scratchpad}\n",
     "\"\"\""
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 20,
    "metadata": {},
    "outputs": [],
    "source": [
-    "class SalesGPT(Chain, BaseModel):\n",
+    "class SalesGPT(Chain):\n",
     "    \"\"\"Controller model for the Sales Agent.\"\"\"\n",
     "\n",
     "    conversation_history: List[str] = []\n",
@@ -804,7 +985,9 @@
     "\n",
     "            # WARNING: this output parser is NOT reliable yet\n",
     "            ## It makes assumptions about output from LLM which can break and throw an error\n",
-    "            output_parser = SalesConvoOutputParser(ai_prefix=kwargs[\"salesperson_name\"])\n",
+    "            output_parser = SalesConvoOutputParser(\n",
+    "                ai_prefix=kwargs[\"salesperson_name\"], verbose=verbose\n",
+    "            )\n",
     "\n",
     "            sales_agent_with_tools = LLMSingleActionAgent(\n",
     "                llm_chain=llm_chain,\n",
@@ -828,6 +1011,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -835,6 +1019,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -843,7 +1028,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 21,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -880,6 +1065,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -888,7 +1074,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 22,
    "metadata": {},
    "outputs": [
     {
@@ -897,7 +1083,9 @@
      "text": [
       "Created a chunk of size 940, which is longer than the specified 10\n",
       "Created a chunk of size 844, which is longer than the specified 10\n",
-      "Created a chunk of size 837, which is longer than the specified 10\n"
+      "Created a chunk of size 837, which is longer than the specified 10\n",
+      "/Users/filipmichalsky/Odyssey/sales_bot/SalesGPT/env/lib/python3.10/site-packages/langchain_core/_api/deprecation.py:117: LangChainDeprecationWarning: The class `langchain.agents.agent.LLMSingleActionAgent` was deprecated in langchain 0.1.0 and will be removed in 0.2.0. Use Use new agent constructor methods like create_react_agent, create_json_agent, create_structured_chat_agent, etc. instead.\n",
+      "  warn_deprecated(\n"
      ]
     }
    ],
@@ -907,7 +1095,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 21,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -917,7 +1105,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 22,
    "metadata": {},
    "outputs": [
     {
@@ -934,14 +1122,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 23,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Ted Lasso:  Hello, this is Ted Lasso from Sleep Haven. How are you doing today?\n"
+      "Ted Lasso:  Good day! This is Ted Lasso from Sleep Haven. How are you doing today?\n"
      ]
     }
    ],
@@ -951,18 +1139,18 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 24,
    "metadata": {},
    "outputs": [],
    "source": [
     "sales_agent.human_step(\n",
-    "    \"I am well, how are you? I would like to learn more about your mattresses.\"\n",
+    "    \"I am well, how are you? I would like to learn more about your services.\"\n",
     ")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 25,
    "metadata": {},
    "outputs": [
     {
@@ -977,92 +1165,32 @@
     "sales_agent.determine_conversation_stage()"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": 22,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Ted Lasso:  I'm glad to hear that you're doing well! As for our mattresses, at Sleep Haven, we provide customers with the most comfortable and supportive sleeping experience possible. Our high-quality mattresses are designed to meet the unique needs of our customers. Can I ask what specifically you'd like to learn more about? \n"
-     ]
-    }
-   ],
-   "source": [
-    "sales_agent.step()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 23,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "sales_agent.human_step(\"Yes, what materials are you mattresses made from?\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 24,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Conversation Stage: Needs analysis: Ask open-ended questions to uncover the prospect's needs and pain points. Listen carefully to their responses and take notes.\n"
-     ]
-    }
-   ],
-   "source": [
-    "sales_agent.determine_conversation_stage()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 25,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Ted Lasso:  Our mattresses are made from a variety of materials, depending on the model. We have the EcoGreen Hybrid Latex Mattress, which is made from 100% natural latex harvested from eco-friendly plantations. The Plush Serenity Bamboo Mattress features a layer of plush, adaptive foam and a base of high-resilience support foam, with a bamboo-infused top layer. The Luxury Cloud-Comfort Memory Foam Mattress has an innovative, temperature-sensitive memory foam layer and a high-density foam base with cooling gel-infused particles. Finally, the Classic Harmony Spring Mattress has a robust inner spring construction and layers of plush padding, with a quilted top layer and a natural cotton cover. Is there anything specific you'd like to know about these materials?\n"
-     ]
-    }
-   ],
-   "source": [
-    "sales_agent.step()"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": 26,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Ted Lasso:  I'm doing great, thank you for asking! I'm glad to hear you're interested. Sleep Haven is a premium mattress company, and we're all about offering the best sleep solutions, including top-notch mattresses, pillows, and bedding accessories. Our mission is to help you achieve a better night's sleep. May I know if you're looking to enhance your sleep experience with a new mattress or bedding accessories? \n"
+     ]
+    }
+   ],
    "source": [
-    "sales_agent.human_step(\n",
-    "    \"Yes, I am looking for a queen sized mattress. Do you have any mattresses in queen size?\"\n",
-    ")"
+    "sales_agent.step()"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 27,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Conversation Stage: Needs analysis: Ask open-ended questions to uncover the prospect's needs and pain points. Listen carefully to their responses and take notes.\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
-    "sales_agent.determine_conversation_stage()"
+    "sales_agent.human_step(\n",
+    "    \"Yes, I would like to improve my sleep. Can you tell me more about your products?\"\n",
+    ")"
    ]
   },
   {
@@ -1074,7 +1202,24 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Ted Lasso:  Yes, we do have queen-sized mattresses available. We offer the Luxury Cloud-Comfort Memory Foam Mattress and the Classic Harmony Spring Mattress in queen size. Both mattresses provide exceptional comfort and support. Is there anything specific you would like to know about these options?\n"
+      "Conversation Stage: Needs analysis: Ask open-ended questions to uncover the prospect's needs and pain points. Listen carefully to their responses and take notes.\n"
+     ]
+    }
+   ],
+   "source": [
+    "sales_agent.determine_conversation_stage()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Ted Lasso:  Absolutely, I'd be happy to share more about our products. At Sleep Haven, we offer a variety of high-quality mattresses designed to cater to different sleeping preferences and needs. Whether you're looking for memory foam's comfort, the support of hybrid mattresses, or the breathability of natural latex, we have options for everyone. Our pillows and bedding accessories are similarly curated to enhance your sleep quality. Every product is built with the aim of helping you achieve the restful night's sleep you deserve. What specific features are you looking for in a mattress? \n"
      ]
     }
    ],
@@ -1084,16 +1229,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 29,
+   "execution_count": 31,
    "metadata": {},
    "outputs": [],
    "source": [
-    "sales_agent.human_step(\"Yea, compare and contrast those two options, please.\")"
+    "sales_agent.human_step(\"What mattresses do you have and how much do they cost?\")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 30,
+   "execution_count": 32,
    "metadata": {},
    "outputs": [
     {
@@ -1110,14 +1255,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 31,
+   "execution_count": 33,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Ted Lasso:  The Luxury Cloud-Comfort Memory Foam Mattress is priced at $999 and is available in Twin, Queen, and King sizes. It features an innovative, temperature-sensitive memory foam layer and a high-density foam base. On the other hand, the Classic Harmony Spring Mattress is priced at $1,299 and is available in Queen and King sizes. It features a robust inner spring construction and layers of plush padding. Both mattresses provide exceptional comfort and support, but the Classic Harmony Spring Mattress may be a better option if you prefer the traditional feel of an inner spring mattress. Do you have any other questions about these options?\n"
+      "Ted Lasso:  We offer two primary types of mattresses at Sleep Haven. The first is our Luxury Cloud-Comfort Memory Foam Mattress, which is priced at $999 and comes in Twin, Queen, and King sizes. The second is our Classic Harmony Spring Mattress, priced at $1,299, available in Queen and King sizes. Both are designed to provide exceptional comfort and support for a better night's sleep. Which type of mattress would you be interested in learning more about? \n"
      ]
     }
    ],
@@ -1127,14 +1272,66 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 32,
+   "execution_count": 34,
    "metadata": {},
    "outputs": [],
    "source": [
     "sales_agent.human_step(\n",
-    "    \"Great, thanks, that's it. I will talk to my wife and call back if she is onboard. Have a good day!\"\n",
+    "    \"Okay.I would like to order two Memory Foam mattresses in Twin size please.\"\n",
     ")"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Conversation Stage: Close: Ask for the sale by proposing a next step. This could be a demo, a trial or a meeting with decision-makers. Ensure to summarize what has been discussed and reiterate the benefits.\n"
+     ]
+    }
+   ],
+   "source": [
+    "sales_agent.determine_conversation_stage()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 36,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Ted Lasso:  Fantastic choice! You're on your way to a better night's sleep with our Luxury Cloud-Comfort Memory Foam Mattresses. I've generated a payment link for two Twin size mattresses for you. Here is the link to complete your purchase: https://buy.stripe.com/test_6oEg28e3V97BdDabJn. Is there anything else I can assist you with today? \n"
+     ]
+    }
+   ],
+   "source": [
+    "sales_agent.step()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 37,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "sales_agent.human_step(\n",
+    "    \"Great, thanks! I will discuss with my wife and will buy it if she is onboard. Have a good day!\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {
@@ -1153,9 +1350,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.3"
+   "version": "3.10.9"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
 }

cookbook/together_ai.ipynb

@@ -9,7 +9,7 @@
     " \n",
     "[Together AI](https://python.langchain.com/docs/integrations/llms/together) has a broad set of OSS LLMs via inference API.\n",
     "\n",
-    "See [here](https://api.together.xyz/playground). We use `\"mistralai/Mixtral-8x7B-Instruct-v0.1` for RAG on the Mixtral paper.\n",
+    "See [here](https://docs.together.ai/docs/inference-models). We use `\"mistralai/Mixtral-8x7B-Instruct-v0.1` for RAG on the Mixtral paper.\n",
     "\n",
     "Download the paper:\n",
     "https://arxiv.org/pdf/2401.04088.pdf"
@@ -148,7 +148,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.16"
+   "version": "3.9.6"
   }
  },
  "nbformat": 4,

cookbook/video_captioning/video_captioning.ipynb

@@ -0,0 +1,174 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Video Captioning\n",
+    "This notebook shows how to use VideoCaptioningChain, which is implemented using Langchain's ImageCaptionLoader and AssemblyAI to produce .srt files.\n",
+    "\n",
+    "This system autogenerates both subtitles and closed captions from a video URL."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Installing Dependencies"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# !pip install ffmpeg-python\n",
+    "# !pip install assemblyai\n",
+    "# !pip install opencv-python\n",
+    "# !pip install torch\n",
+    "# !pip install pillow\n",
+    "# !pip install transformers\n",
+    "# !pip install langchain"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Imports"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2023-11-30T03:39:14.078232Z",
+     "start_time": "2023-11-30T03:39:12.534410Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "import getpass\n",
+    "\n",
+    "from langchain.chains.video_captioning import VideoCaptioningChain\n",
+    "from langchain.chat_models.openai import ChatOpenAI"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Setting up API Keys"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2023-11-30T03:39:17.423806Z",
+     "start_time": "2023-11-30T03:39:17.417945Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "OPENAI_API_KEY = getpass.getpass(\"OpenAI API Key:\")\n",
+    "\n",
+    "ASSEMBLYAI_API_KEY = getpass.getpass(\"AssemblyAI API Key:\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**Required parameters:**\n",
+    "\n",
+    "* llm: The language model this chain will use to get suggestions on how to refine the closed-captions\n",
+    "* assemblyai_key: The API key for AssemblyAI, used to generate the subtitles\n",
+    "\n",
+    "**Optional Parameters:**\n",
+    "\n",
+    "* verbose (Default: True): Sets verbose mode for downstream chain calls\n",
+    "* use_logging (Default: True): Log the chain's processes in run manager\n",
+    "* frame_skip (Default: None): Choose how many video frames to skip during processing. Increasing it results in faster execution, but less accurate results. If None, frame skip is calculated manually based on the framerate Set this to 0 to sample all frames\n",
+    "* image_delta_threshold (Default: 3000000): Set the sensitivity for what the image processor considers a change in scenery in the video, used to delimit closed captions. Higher = less sensitive\n",
+    "* closed_caption_char_limit (Default: 20): Sets the character limit on closed captions\n",
+    "* closed_caption_similarity_threshold (Default: 80): Sets the percentage value to how similar two closed caption models should be in order to be clustered into one longer closed caption\n",
+    "* use_unclustered_video_models (Default: False): If true, closed captions that could not be clustered will be included. May result in spontaneous behaviour from closed captions such as very short lasting captions or fast-changing captions. Enabling this is experimental and not recommended"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Example run"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# https://ia804703.us.archive.org/27/items/uh-oh-here-we-go-again/Uh-Oh%2C%20Here%20we%20go%20again.mp4\n",
+    "# https://ia601200.us.archive.org/9/items/f58703d4-61e6-4f8f-8c08-b42c7e16f7cb/f58703d4-61e6-4f8f-8c08-b42c7e16f7cb.mp4\n",
+    "\n",
+    "chain = VideoCaptioningChain(\n",
+    "    llm=ChatOpenAI(model=\"gpt-4\", max_tokens=4000, openai_api_key=OPENAI_API_KEY),\n",
+    "    assemblyai_key=ASSEMBLYAI_API_KEY,\n",
+    ")\n",
+    "\n",
+    "srt_content = chain.run(\n",
+    "    video_file_path=\"https://ia601200.us.archive.org/9/items/f58703d4-61e6-4f8f-8c08-b42c7e16f7cb/f58703d4-61e6-4f8f-8c08-b42c7e16f7cb.mp4\"\n",
+    ")\n",
+    "\n",
+    "print(srt_content)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Writing output to .srt file"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with open(\"output.srt\", \"w\") as file:\n",
+    "    file.write(srt_content)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "myenv",
+   "language": "python",
+   "name": "myenv"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.6"
+  },
+  "vscode": {
+   "interpreter": {
+    "hash": "b0fa6594d8f4cbf19f97940f81e996739fb7646882a419484c72d19e05852a7e"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

docker/docker-compose.yml

@@ -4,14 +4,14 @@
 # ATTENTION: When adding a service below use a non-standard port
 # increment by one from the preceding port.
 # For credentials always use `langchain` and `langchain` for the
-# username and password. 
+# username and password.
 version: "3"
 name: langchain-tests
 
 services:
   redis:
     image: redis/redis-stack-server:latest
-    # We use non standard ports since 
+    # We use non standard ports since
     # these instances are used for testing
     # and users may already have existing
     # redis instances set up locally
@@ -73,6 +73,11 @@ services:
       retries: 60
     volumes:
       - postgres_data_pgvector:/var/lib/postgresql/data
+  vdms:
+    image: intellabs/vdms:latest
+    container_name: vdms_container
+    ports:
+      - "6025:55555"
 
 volumes:
   postgres_data:

docs/docs/additional_resources/dependents.mdx

@@ -241,7 +241,6 @@ Dependents stats for `langchain-ai/langchain`
 |[alejandro-ao/langchain-ask-pdf](https://github.com/alejandro-ao/langchain-ask-pdf) | 514 |
 |[sajjadium/ctf-archives](https://github.com/sajjadium/ctf-archives) | 507 |
 |[continuum-llms/chatgpt-memory](https://github.com/continuum-llms/chatgpt-memory) | 502 |
-|[llmOS/opencopilot](https://github.com/llmOS/opencopilot) | 495 |
 |[steamship-core/steamship-langchain](https://github.com/steamship-core/steamship-langchain) | 494 |
 |[mpaepper/content-chatbot](https://github.com/mpaepper/content-chatbot) | 493 |
 |[langchain-ai/langchain-aiplugin](https://github.com/langchain-ai/langchain-aiplugin) | 492 |
@@ -455,7 +454,6 @@ Dependents stats for `langchain-ai/langchain`
 |[Teahouse-Studios/akari-bot](https://github.com/Teahouse-Studios/akari-bot) | 149 |
 |[realminchoi/babyagi-ui](https://github.com/realminchoi/babyagi-ui) | 148 |
 |[ssheng/BentoChain](https://github.com/ssheng/BentoChain) | 148 |
-|[lmstudio-ai/examples](https://github.com/lmstudio-ai/examples) | 147 |
 |[solana-labs/chatgpt-plugin](https://github.com/solana-labs/chatgpt-plugin) | 147 |
 |[aurelio-labs/arxiv-bot](https://github.com/aurelio-labs/arxiv-bot) | 147 |
 |[Jaseci-Labs/jaseci](https://github.com/Jaseci-Labs/jaseci) | 146 |

docs/docs/additional_resources/youtube.mdx

@@ -7,7 +7,7 @@
 ### Introduction to LangChain with Harrison Chase, creator of LangChain
 - [Building the Future with LLMs, `LangChain`, & `Pinecone`](https://youtu.be/nMniwlGyX-c) by [Pinecone](https://www.youtube.com/@pinecone-io)
 - [LangChain and Weaviate with Harrison Chase and Bob van Luijt - Weaviate Podcast #36](https://youtu.be/lhby7Ql7hbk) by [Weaviate • Vector Database](https://www.youtube.com/@Weaviate)
-- [LangChain Demo + Q&A with Harrison Chase](https://youtu.be/zaYTXQFR0_s?t=788) by [Full Stack Deep Learning](https://www.youtube.com/@FullStackDeepLearning)
+- [LangChain Demo + Q&A with Harrison Chase](https://youtu.be/zaYTXQFR0_s?t=788) by [Full Stack Deep Learning](https://www.youtube.com/@The_Full_Stack)
 - [LangChain Agents: Build Personal Assistants For Your Data (Q&A with Harrison Chase and Mayo Oshin)](https://youtu.be/gVkF8cwfBLI) by [Chat with data](https://www.youtube.com/@chatwithdata)
 
 ## Videos (sorted by views)
@@ -15,8 +15,8 @@
 - [Using `ChatGPT` with YOUR OWN Data. This is magical. (LangChain OpenAI API)](https://youtu.be/9AXP7tCI9PI) by [TechLead](https://www.youtube.com/@TechLead)
 - [First look - `ChatGPT` + `WolframAlpha` (`GPT-3.5` and Wolfram|Alpha via LangChain by James Weaver)](https://youtu.be/wYGbY811oMo) by [Dr Alan D. Thompson](https://www.youtube.com/@DrAlanDThompson) 
 - [LangChain explained - The hottest new Python framework](https://youtu.be/RoR4XJw8wIc) by [AssemblyAI](https://www.youtube.com/@AssemblyAI)
-- [Chatbot with INFINITE MEMORY using `OpenAI` & `Pinecone` - `GPT-3`, `Embeddings`, `ADA`, `Vector DB`, `Semantic`](https://youtu.be/2xNzB7xq8nk) by [David Shapiro ~ AI](https://www.youtube.com/@DavidShapiroAutomator)
-- [LangChain for LLMs is... basically just an Ansible playbook](https://youtu.be/X51N9C-OhlE) by [David Shapiro ~ AI](https://www.youtube.com/@DavidShapiroAutomator)
+- [Chatbot with INFINITE MEMORY using `OpenAI` & `Pinecone` - `GPT-3`, `Embeddings`, `ADA`, `Vector DB`, `Semantic`](https://youtu.be/2xNzB7xq8nk) by [David Shapiro ~ AI](https://www.youtube.com/@DaveShap)
+- [LangChain for LLMs is... basically just an Ansible playbook](https://youtu.be/X51N9C-OhlE) by [David Shapiro ~ AI](https://www.youtube.com/@DaveShap)
 - [Build your own LLM Apps with LangChain & `GPT-Index`](https://youtu.be/-75p09zFUJY) by [1littlecoder](https://www.youtube.com/@1littlecoder)
 - [`BabyAGI` - New System of Autonomous AI Agents with LangChain](https://youtu.be/lg3kJvf1kXo) by [1littlecoder](https://www.youtube.com/@1littlecoder)
 - [Run `BabyAGI` with Langchain Agents (with Python Code)](https://youtu.be/WosPGHPObx8) by [1littlecoder](https://www.youtube.com/@1littlecoder)
@@ -37,15 +37,15 @@
 - [Building AI LLM Apps with LangChain (and more?) - LIVE STREAM](https://www.youtube.com/live/M-2Cj_2fzWI?feature=share) by [Nicholas Renotte](https://www.youtube.com/@NicholasRenotte)
 - [`ChatGPT` with any `YouTube` video using langchain and `chromadb`](https://youtu.be/TQZfB2bzVwU) by [echohive](https://www.youtube.com/@echohive)
 - [How to Talk to a `PDF` using LangChain and `ChatGPT`](https://youtu.be/v2i1YDtrIwk) by [Automata Learning Lab](https://www.youtube.com/@automatalearninglab)
-- [Langchain Document Loaders Part 1: Unstructured Files](https://youtu.be/O5C0wfsen98) by [Merk](https://www.youtube.com/@merksworld) 
-- [LangChain - Prompt Templates (what all the best prompt engineers use)](https://youtu.be/1aRu8b0XNOQ) by [Nick Daigler](https://www.youtube.com/@nick_daigs)
+- [Langchain Document Loaders Part 1: Unstructured Files](https://youtu.be/O5C0wfsen98) by [Merk](https://www.youtube.com/@heymichaeldaigler) 
+- [LangChain - Prompt Templates (what all the best prompt engineers use)](https://youtu.be/1aRu8b0XNOQ) by [Nick Daigler](https://www.youtube.com/@nickdaigler)
 - [LangChain. Crear aplicaciones Python impulsadas por GPT](https://youtu.be/DkW_rDndts8) by [Jesús Conde](https://www.youtube.com/@0utKast)
 - [Easiest Way to Use GPT In Your Products | LangChain Basics Tutorial](https://youtu.be/fLy0VenZyGc) by [Rachel Woods](https://www.youtube.com/@therachelwoods)
 - [`BabyAGI` + `GPT-4` Langchain Agent with Internet Access](https://youtu.be/wx1z_hs5P6E) by [tylerwhatsgood](https://www.youtube.com/@tylerwhatsgood)
 - [Learning LLM Agents. How does it actually work? LangChain, AutoGPT & OpenAI](https://youtu.be/mb_YAABSplk) by [Arnoldas Kemeklis](https://www.youtube.com/@processusAI)
 - [Get Started with LangChain in `Node.js`](https://youtu.be/Wxx1KUWJFv4) by [Developers Digest](https://www.youtube.com/@DevelopersDigest)
 - [LangChain + `OpenAI` tutorial: Building a Q&A system w/ own text data](https://youtu.be/DYOU_Z0hAwo) by [Samuel Chan](https://www.youtube.com/@SamuelChan)
-- [Langchain + `Zapier` Agent](https://youtu.be/yribLAb-pxA) by [Merk](https://www.youtube.com/@merksworld)
+- [Langchain + `Zapier` Agent](https://youtu.be/yribLAb-pxA) by [Merk](https://www.youtube.com/@heymichaeldaigler)
 - [Connecting the Internet with `ChatGPT` (LLMs) using Langchain And Answers Your Questions](https://youtu.be/9Y0TBC63yZg) by [Kamalraj M M](https://www.youtube.com/@insightbuilder)
 - [Build More Powerful LLM Applications for Business’s with LangChain (Beginners Guide)](https://youtu.be/sp3-WLKEcBg) by[ No Code Blackbox](https://www.youtube.com/@nocodeblackbox)
 - [LangFlow LLM Agent Demo for 🦜🔗LangChain](https://youtu.be/zJxDHaWt-6o) by [Cobus Greyling](https://www.youtube.com/@CobusGreylingZA)
@@ -82,7 +82,7 @@
 - [Build a LangChain-based Semantic PDF Search App with No-Code Tools Bubble and Flowise](https://youtu.be/s33v5cIeqA4) by [Menlo Park Lab](https://www.youtube.com/@menloparklab)
 - [LangChain Memory Tutorial | Building a ChatGPT Clone in Python](https://youtu.be/Cwq91cj2Pnc) by [Alejandro AO - Software & Ai](https://www.youtube.com/@alejandro_ao)
 - [ChatGPT For Your DATA | Chat with Multiple Documents Using LangChain](https://youtu.be/TeDgIDqQmzs) by [Data Science Basics](https://www.youtube.com/@datasciencebasics)
-- [`Llama Index`: Chat with Documentation using URL Loader](https://youtu.be/XJRoDEctAwA) by [Merk](https://www.youtube.com/@merksworld)
+- [`Llama Index`: Chat with Documentation using URL Loader](https://youtu.be/XJRoDEctAwA) by [Merk](https://www.youtube.com/@heymichaeldaigler)
 - [Using OpenAI, LangChain, and `Gradio` to Build Custom GenAI Applications](https://youtu.be/1MsmqMg3yUc) by [David Hundley](https://www.youtube.com/@dkhundley)
 - [LangChain, Chroma DB, OpenAI Beginner Guide | ChatGPT with your PDF](https://youtu.be/FuqdVNB_8c0)
 - [Build AI chatbot with custom knowledge base using OpenAI API and GPT Index](https://youtu.be/vDZAZuaXf48) by [Irina Nik](https://www.youtube.com/@irina_nik)
@@ -93,7 +93,7 @@
 - [Build a Custom Chatbot with OpenAI: `GPT-Index` & LangChain | Step-by-Step Tutorial](https://youtu.be/FIDv6nc4CgU) by [Fabrikod](https://www.youtube.com/@fabrikod)
 - [`Flowise` is an open-source no-code UI visual tool to build 🦜🔗LangChain applications](https://youtu.be/CovAPtQPU0k) by [Cobus Greyling](https://www.youtube.com/@CobusGreylingZA)
 - [LangChain & GPT 4 For Data Analysis: The `Pandas` Dataframe Agent](https://youtu.be/rFQ5Kmkd4jc) by [Rabbitmetrics](https://www.youtube.com/@rabbitmetrics)
-- [`GirlfriendGPT` - AI girlfriend with LangChain](https://youtu.be/LiN3D1QZGQw) by [Toolfinder AI](https://www.youtube.com/@toolfinderai)
+- [`GirlfriendGPT` - AI girlfriend with LangChain](https://youtu.be/LiN3D1QZGQw) by [Girlfriend GPT](https://www.youtube.com/@girlfriendGPT)
 - [How to build with Langchain 10x easier | ⛓️ LangFlow & `Flowise`](https://youtu.be/Ya1oGL7ZTvU) by [AI Jason](https://www.youtube.com/@AIJasonZ)
 - [Getting Started With LangChain In 20 Minutes- Build Celebrity Search Application](https://youtu.be/_FpT1cwcSLg) by [Krish Naik](https://www.youtube.com/@krishnaik06)
 - ⛓ [Vector Embeddings Tutorial – Code Your Own AI Assistant with `GPT-4 API` + LangChain + NLP](https://youtu.be/yfHHvmaMkcA?si=5uJhxoh2tvdnOXok) by [FreeCodeCamp.org](https://www.youtube.com/@freecodecamp)
@@ -109,7 +109,7 @@
 - ⛓ [PyData Heidelberg #11 - TimeSeries Forecasting & LLM Langchain](https://www.youtube.com/live/Glbwb5Hxu18?si=PIEY8Raq_C9PCHuW) by [PyData](https://www.youtube.com/@PyDataTV)
 - ⛓ [Prompt Engineering in Web Development | Using LangChain and Templates with OpenAI](https://youtu.be/pK6WzlTOlYw?si=fkcDQsBG2h-DM8uQ) by [Akamai Developer
 ](https://www.youtube.com/@AkamaiDeveloper)
-- ⛓ [Retrieval-Augmented Generation (RAG) using LangChain and `Pinecone` - The RAG Special Episode](https://youtu.be/J_tCD_J6w3s?si=60Mnr5VD9UED9bGG) by [Generative AI and Data Science On AWS](https://www.youtube.com/@GenerativeAIDataScienceOnAWS)
+- ⛓ [Retrieval-Augmented Generation (RAG) using LangChain and `Pinecone` - The RAG Special Episode](https://youtu.be/J_tCD_J6w3s?si=60Mnr5VD9UED9bGG) by [Generative AI and Data Science On AWS](https://www.youtube.com/@GenerativeAIOnAWS)
 - ⛓ [`LLAMA2 70b-chat` Multiple Documents Chatbot with Langchain & Streamlit |All OPEN SOURCE|Replicate API](https://youtu.be/vhghB81vViM?si=dszzJnArMeac7lyc) by [DataInsightEdge](https://www.youtube.com/@DataInsightEdge01)
 - ⛓ [Chatting with 44K Fashion Products: LangChain Opportunities and Pitfalls](https://youtu.be/Zudgske0F_s?si=8HSshHoEhh0PemJA) by [Rabbitmetrics](https://www.youtube.com/@rabbitmetrics)
 - ⛓ [Structured Data Extraction from `ChatGPT` with LangChain](https://youtu.be/q1lYg8JISpQ?si=0HctzOHYZvq62sve) by [MG](https://www.youtube.com/@MG_cafe)

docs/docs/contributing/integrations.mdx

@@ -14,19 +14,20 @@ For the most part, new integrations should be added to the Community package. Pa
 
 In the following sections, we'll walk through how to contribute to each of these packages from a fake company, `Parrot Link AI`.
 
-## Community Package
+## Community package
 
 The `langchain-community` package is in `libs/community` and contains most integrations.
 
-It is installed by users with `pip install langchain-community`, and exported members can be imported with code like 
+It can be installed with `pip install langchain-community`, and exported members can be imported with code like 
 
 ```python
-from langchain_community.chat_models import ParrotLinkLLM
-from langchain_community.llms import ChatParrotLink
+from langchain_community.chat_models import ChatParrotLink
+from langchain_community.llms import ParrotLinkLLM
 from langchain_community.vectorstores import ParrotLinkVectorStore
 ```
 
-The community package relies on manually-installed dependent packages, so you will see errors if you try to import a package that is not installed. In our fake example, if you tried to import `ParrotLinkLLM` without installing `parrot-link-sdk`, you will see an `ImportError` telling you to install it when trying to use it.
+The `community` package relies on manually-installed dependent packages, so you will see errors 
+if you try to import a package that is not installed. In our fake example, if you tried to import `ParrotLinkLLM` without installing `parrot-link-sdk`, you will see an `ImportError` telling you to install it when trying to use it.
 
 Let's say we wanted to implement a chat model for Parrot Link AI. We would create a new file in `libs/community/langchain_community/chat_models/parrot_link.py` with the following code:
 
@@ -39,7 +40,7 @@ class ChatParrotLink(BaseChatModel):
     Example:
         .. code-block:: python
 
-            from langchain_parrot_link import ChatParrotLink
+            from langchain_community.chat_models import ChatParrotLink
 
             model = ChatParrotLink()
     """
@@ -56,9 +57,16 @@ And add documentation to:
 
 - `docs/docs/integrations/chat/parrot_link.ipynb`
 
-## Partner Packages
+## Partner package in LangChain repo
 
-Partner packages are in `libs/partners/*` and are installed by users with `pip install langchain-{partner}`, and exported members can be imported with code like 
+Partner packages can be hosted in the `LangChain` monorepo or in an external repo.
+
+Partner package in the `LangChain` repo is placed in `libs/partners/{partner}` 
+and the package source code is in `libs/partners/{partner}/langchain_{partner}`.
+
+A package is 
+installed by users with `pip install langchain-{partner}`, and the package members 
+can be imported with code like:
 
 ```python
 from langchain_{partner} import X
@@ -123,13 +131,49 @@ By default, this will include stubs for a Chat Model, an LLM, and/or a Vector St
 
 ### Write Unit and Integration Tests
 
-Some basic tests are generated in the tests/ directory. You should add more tests to cover your package's functionality.
+Some basic tests are presented in the `tests/` directory. You should add more tests to cover your package's functionality.
 
 For information on running and implementing tests, see the [Testing guide](./testing).
 
 ### Write documentation
 
-Documentation is generated from Jupyter notebooks in the `docs/` directory. You should move the generated notebooks to the relevant `docs/docs/integrations` directory in the monorepo root.
+Documentation is generated from Jupyter notebooks in the `docs/` directory. You should place the notebooks with examples
+to the relevant `docs/docs/integrations` directory in the monorepo root.
+
+### (If Necessary) Deprecate community integration
+
+Note: this is only necessary if you're migrating an existing community integration into 
+a partner package. If the component you're integrating is net-new to LangChain (i.e. 
+not already in the `community` package), you can skip this step.
+
+Let's pretend we migrated our `ChatParrotLink` chat model from the community package to 
+the partner package. We would need to deprecate the old model in the community package.
+
+We would do that by adding a `@deprecated` decorator to the old model as follows, in
+`libs/community/langchain_community/chat_models/parrot_link.py`.
+
+Before our change, our chat model might look like this:
+
+```python
+class ChatParrotLink(BaseChatModel):
+  ...
+```
+
+After our change, it would look like this:
+
+```python
+from langchain_core._api.deprecation import deprecated
+
+@deprecated(
+    since="0.0.<next community version>", 
+    removal="0.2.0", 
+    alternative_import="langchain_parrot_link.ChatParrotLink"
+)
+class ChatParrotLink(BaseChatModel):
+  ...
+```
+
+You should do this for *each* component that you're migrating to the partner package.
 
 ### Additional steps
 
@@ -143,3 +187,15 @@ Maintainer steps (Contributors should **not** do these):
 - [ ] set up pypi and test pypi projects
 - [ ] add credential secrets to Github Actions
 - [ ] add package to conda-forge
+
+## Partner package in external repo
+
+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.
+
+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/expression_language/cookbook/multiple_chains.ipynb

@@ -20,9 +20,11 @@
    ]
   },
   {
-   "cell_type": "raw",
+   "cell_type": "code",
    "id": "0f316b5c",
+   "execution_count": null,
    "metadata": {},
+   "outputs": [],
    "source": [
     "%pip install --upgrade --quiet  langchain langchain-openai"
    ]

docs/docs/expression_language/cookbook/prompt_size.ipynb

@@ -220,7 +220,7 @@
    "id": "637f994a-5134-402a-bcf0-4de3911eaf49",
    "metadata": {},
    "source": [
-    ":::tip\n",
+    ":::{.callout-tip}\n",
     "\n",
     "[LangSmith trace](https://smith.langchain.com/public/60909eae-f4f1-43eb-9f96-354f5176f66f/r)\n",
     "\n",
@@ -388,7 +388,7 @@
    "id": "5a7e498b-dc68-4267-a35c-90ceffa91c46",
    "metadata": {},
    "source": [
-    ":::tip\n",
+    ":::{.callout-tip}\n",
     "\n",
     "[LangSmith trace](https://smith.langchain.com/public/3b27d47f-e4df-4afb-81b1-0f88b80ca97e/r)\n",
     "\n",

docs/docs/expression_language/cookbook/sql_db.ipynb

@@ -20,9 +20,11 @@
    ]
   },
   {
-   "cell_type": "raw",
+   "cell_type": "code",
    "id": "b3121aa8",
+   "execution_count": null,
    "metadata": {},
+   "outputs": [],
    "source": [
     "%pip install --upgrade --quiet  langchain langchain-openai"
    ]

docs/docs/expression_language/get_started.ipynb

@@ -40,6 +40,33 @@
     "%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,
@@ -60,10 +87,8 @@
    "source": [
     "from langchain_core.output_parsers import StrOutputParser\n",
     "from langchain_core.prompts import ChatPromptTemplate\n",
-    "from langchain_openai import ChatOpenAI\n",
     "\n",
     "prompt = ChatPromptTemplate.from_template(\"tell me a short joke about {topic}\")\n",
-    "model = ChatOpenAI(model=\"gpt-4\")\n",
     "output_parser = StrOutputParser()\n",
     "\n",
     "chain = prompt | model | output_parser\n",
@@ -76,15 +101,15 @@
    "id": "81c502c5-85ee-4f36-aaf4-d6e350b7792f",
    "metadata": {},
    "source": [
-    "Notice this line of this code, where we piece together then different components into a single chain using LCEL:\n",
+    "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 feeds the output from one component as input into the next component. \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. "
+    "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."
    ]
   },
   {
@@ -219,7 +244,7 @@
     }
    ],
    "source": [
-    "from langchain_openai.llms import OpenAI\n",
+    "from langchain_openai import OpenAI\n",
     "\n",
     "llm = OpenAI(model=\"gpt-3.5-turbo-instruct\")\n",
     "llm.invoke(prompt_value)"
@@ -233,7 +258,7 @@
     "### 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 `StrOutputParser` specifically simple converts any input into a string."
+    "`BaseMessage` as input. The specific `StrOutputParser` simply converts any input into a string."
    ]
   },
   {
@@ -293,7 +318,7 @@
    "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",
+    "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",
     ":::"
    ]
@@ -321,7 +346,17 @@
    "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. "
+    "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",
+    "```"
    ]
   },
   {
@@ -338,8 +373,7 @@
     "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.chat_models import ChatOpenAI\n",
-    "from langchain_openai.embeddings import OpenAIEmbeddings\n",
+    "from langchain_openai import OpenAIEmbeddings\n",
     "\n",
     "vectorstore = DocArrayInMemorySearch.from_texts(\n",
     "    [\"harrison worked at kensho\", \"bears like to eat honey\"],\n",
@@ -353,7 +387,6 @@
     "Question: {question}\n",
     "\"\"\"\n",
     "prompt = ChatPromptTemplate.from_template(template)\n",
-    "model = ChatOpenAI()\n",
     "output_parser = StrOutputParser()\n",
     "\n",
     "setup_and_retrieval = RunnableParallel(\n",
@@ -451,7 +484,7 @@
     "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",
+    "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",
@@ -496,7 +529,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.4"
+   "version": "3.11.0"
   }
  },
  "nbformat": 4,

docs/docs/expression_language/how_to/message_history.ipynb

@@ -552,7 +552,7 @@
    "id": "da3d1feb-b4bb-4624-961c-7db2e1180df7",
    "metadata": {},
    "source": [
-    ":::tip\n",
+    ":::{.callout-tip}\n",
     "\n",
     "[Langsmith trace](https://smith.langchain.com/public/bd73e122-6ec1-48b2-82df-e6483dc9cb63/r)\n",
     "\n",

docs/docs/get_started/quickstart.mdx

@@ -14,7 +14,7 @@ That's a fair amount to cover! Let's dive in.
 
 ### Jupyter Notebook
 
-This guide (and most of the other guides in the documentation) use [Jupyter notebooks](https://jupyter.org/) and assume the reader is as well. Jupyter notebooks are perfect for learning how to work with LLM systems because often times 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.
+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.
 
@@ -184,8 +184,8 @@ Let's ask it what LangSmith is - this is something that wasn't present in the tr
 llm.invoke("how can langsmith help with testing?")
 ```
 
-We can also guide it's response with a prompt template.
-Prompt templates are used to convert raw user input to a better input to the LLM.
+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
@@ -234,7 +234,7 @@ We've now successfully set up a basic LLM chain. We only touched on the basics o
 
 ## Retrieval Chain
 
-In order to properly answer the original question ("how can langsmith help with testing?"), we need to provide additional context to the LLM.
+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.
@@ -242,7 +242,7 @@ You can then use a retriever to fetch only the most relevant pieces and pass tho
 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. In order to do this, we will use the WebBaseLoader. This requires installing [BeautifulSoup](https://beautiful-soup-4.readthedocs.io/en/latest/):
+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
@@ -286,7 +286,7 @@ embeddings = OllamaEmbeddings()
   </TabItem>
 <TabItem value="cohere" label="Cohere (API)" default>
 
-Make sure you have the `cohere` package installed an the appropriate environment variables set (these are the same as needed for the LLM).
+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
@@ -349,7 +349,7 @@ document_chain.invoke({
 ```
 
 However, we want the documents to first come from the retriever we just set up.
-That way, for a given question we can use the retriever to dynamically select the most relevant documents and pass those in.
+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
@@ -395,12 +395,12 @@ from langchain_core.prompts import MessagesPlaceholder
 prompt = ChatPromptTemplate.from_messages([
     MessagesPlaceholder(variable_name="chat_history"),
     ("user", "{input}"),
-    ("user", "Given the above conversation, generate a search query to look up in order to get information relevant to the conversation")
+    ("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 is asking a follow up question.
+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
@@ -411,7 +411,7 @@ retriever_chain.invoke({
     "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.
+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.
 
@@ -439,7 +439,7 @@ We can see that this gives a coherent answer - we've successfully turned our ret
 
 ## Agent
 
-We've so far create examples of chains - where each step is known ahead of time.
+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.**
@@ -448,7 +448,7 @@ One of the first things to do when building an agent is to decide what tools it
 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.
+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:
 
@@ -488,6 +488,11 @@ 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
 
@@ -499,6 +504,8 @@ 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 `openai_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)
@@ -563,7 +570,6 @@ 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_openai import ChatOpenAI
 from langchain import hub
 from langchain.agents import create_openai_functions_agent
 from langchain.agents import AgentExecutor

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

@@ -17,7 +17,7 @@ Here's a summary of the key methods and properties of a comparison evaluator:
 - `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/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.
+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.

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

@@ -294,7 +294,7 @@
    },
    "outputs": [],
    "source": [
-    "from langchain.prompts import PromptTemplate\n",
+    "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",

docs/docs/guides/evaluation/index.mdx

@@ -23,7 +23,7 @@ We also are working to share guides and cookbooks that demonstrate how to use th
 
 ## LangSmith Evaluation
 
-LangSmith provides an integrated evaluation and tracing framework that allows you to check for regressions, compare systems, and easily identify and fix any sources of errors and performance issues. Check out the docs on [LangSmith Evaluation](https://docs.smith.langchain.com/category/testing--evaluation) and additional [cookbooks](https://docs.smith.langchain.com/category/langsmith-cookbook) for more detailed information on evaluating your applications.
+LangSmith provides an integrated evaluation and tracing framework that allows you to check for regressions, compare systems, and easily identify and fix any sources of errors and performance issues. Check out the docs on [LangSmith Evaluation](https://docs.smith.langchain.com/evaluation) and additional [cookbooks](https://docs.smith.langchain.com/cookbook) for more detailed information on evaluating your applications.
 
 ## LangChain benchmarks
 
@@ -37,6 +37,6 @@ Check out the docs for examples and leaderboard information.
 
 ## Reference Docs
 
-For detailed information on the available evaluators, including how to instantiate, configure, and customize them, check out the [reference documentation](https://api.python.langchain.com/en/latest/api_reference.html#module-langchain.evaluation) directly.
+For detailed information on the available evaluators, including how to instantiate, configure, and customize them, check out the [reference documentation](https://api.python.langchain.com/en/latest/langchain_api_reference.html#module-langchain.evaluation) directly.
 
 <DocCardList />

docs/docs/guides/evaluation/string/criteria_eval_chain.ipynb

@@ -380,7 +380,7 @@
    },
    "outputs": [],
    "source": [
-    "from langchain.prompts import PromptTemplate\n",
+    "from langchain_core.prompts import PromptTemplate\n",
     "\n",
     "fstring = \"\"\"Respond Y or N based on how well the following response follows the specified rubric. Grade only based on the rubric and expected response:\n",
     "\n",

docs/docs/guides/fallbacks.ipynb

@@ -216,7 +216,7 @@
    "outputs": [],
    "source": [
     "# Now lets create a chain with the normal OpenAI model\n",
-    "from langchain.prompts import PromptTemplate\n",
+    "from langchain_core.prompts import PromptTemplate\n",
     "from langchain_openai import OpenAI\n",
     "\n",
     "prompt_template = \"\"\"Instructions: You should always include a compliment in your response.\n",

docs/docs/guides/local_llms.ipynb

@@ -98,7 +98,7 @@
     "from langchain_community.llms import Ollama\n",
     "\n",
     "llm = Ollama(model=\"llama2\")\n",
-    "llm(\"The first man on the moon was ...\")"
+    "llm.invoke(\"The first man on the moon was ...\")"
    ]
   },
   {
@@ -140,7 +140,7 @@
     "llm = Ollama(\n",
     "    model=\"llama2\", callback_manager=CallbackManager([StreamingStdOutCallbackHandler()])\n",
     ")\n",
-    "llm(\"The first man on the moon was ...\")"
+    "llm.invoke(\"The first man on the moon was ...\")"
    ]
   },
   {
@@ -226,7 +226,7 @@
     "from langchain_community.llms import Ollama\n",
     "\n",
     "llm = Ollama(model=\"llama2:13b\")\n",
-    "llm(\"The first man on the moon was ... think step by step\")"
+    "llm.invoke(\"The first man on the moon was ... think step by step\")"
    ]
   },
   {
@@ -369,7 +369,7 @@
     }
    ],
    "source": [
-    "llm(\"The first man on the moon was ... Let's think step by step\")"
+    "llm.invoke(\"The first man on the moon was ... Let's think step by step\")"
    ]
   },
   {
@@ -426,7 +426,7 @@
     }
    ],
    "source": [
-    "llm(\"The first man on the moon was ... Let's think step by step\")"
+    "llm.invoke(\"The first man on the moon was ... Let's think step by step\")"
    ]
   },
   {
@@ -546,7 +546,7 @@
    "source": [
     "from langchain.chains import LLMChain\n",
     "from langchain.chains.prompt_selector import ConditionalPromptSelector\n",
-    "from langchain.prompts import PromptTemplate\n",
+    "from langchain_core.prompts import PromptTemplate\n",
     "\n",
     "DEFAULT_LLAMA_SEARCH_PROMPT = PromptTemplate(\n",
     "    input_variables=[\"question\"],\n",

docs/docs/guides/model_laboratory.ipynb

@@ -30,8 +30,8 @@
    "outputs": [],
    "source": [
     "from langchain.model_laboratory import ModelLaboratory\n",
-    "from langchain.prompts import PromptTemplate\n",
     "from langchain_community.llms import Cohere, HuggingFaceHub\n",
+    "from langchain_core.prompts import PromptTemplate\n",
     "from langchain_openai import OpenAI"
    ]
   },
@@ -167,7 +167,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.chains import SelfAskWithSearchChain\n",
+    "from langchain.agents.self_ask_with_search.base import SelfAskWithSearchChain\n",
     "from langchain_community.utilities import SerpAPIWrapper\n",
     "\n",
     "open_ai_llm = OpenAI(temperature=0)\n",

docs/docs/guides/safety/amazon_comprehend_chain.ipynb

@@ -105,8 +105,8 @@
    },
    "outputs": [],
    "source": [
-    "from langchain.prompts import PromptTemplate\n",
     "from langchain_community.llms.fake import FakeListLLM\n",
+    "from langchain_core.prompts import PromptTemplate\n",
     "from langchain_experimental.comprehend_moderation.base_moderation_exceptions import (\n",
     "    ModerationPiiError,\n",
     ")\n",
@@ -242,8 +242,8 @@
    },
    "outputs": [],
    "source": [
-    "from langchain.prompts import PromptTemplate\n",
     "from langchain_community.llms.fake import FakeListLLM\n",
+    "from langchain_core.prompts import PromptTemplate\n",
     "\n",
     "template = \"\"\"Question: {question}\n",
     "\n",
@@ -405,8 +405,8 @@
    },
    "outputs": [],
    "source": [
-    "from langchain.prompts import PromptTemplate\n",
     "from langchain_community.llms.fake import FakeListLLM\n",
+    "from langchain_core.prompts import PromptTemplate\n",
     "\n",
     "template = \"\"\"Question: {question}\n",
     "\n",
@@ -566,8 +566,8 @@
    },
    "outputs": [],
    "source": [
-    "from langchain.prompts import PromptTemplate\n",
     "from langchain_community.llms import HuggingFaceHub\n",
+    "from langchain_core.prompts import PromptTemplate\n",
     "\n",
     "template = \"\"\"{question}\"\"\"\n",
     "\n",
@@ -696,9 +696,9 @@
    "source": [
     "import json\n",
     "\n",
-    "from langchain.prompts import PromptTemplate\n",
     "from langchain_community.llms import SagemakerEndpoint\n",
     "from langchain_community.llms.sagemaker_endpoint import LLMContentHandler\n",
+    "from langchain_core.prompts import PromptTemplate\n",
     "\n",
     "\n",
     "class ContentHandler(LLMContentHandler):\n",

docs/docs/guides/safety/constitutional_chain.mdx

@@ -13,7 +13,7 @@ content that may violate guidelines, be offensive, or deviate from the desired c
 ```python
 # Imports
 from langchain_openai import OpenAI
-from langchain.prompts import PromptTemplate
+from langchain_core.prompts import PromptTemplate
 from langchain.chains.llm import LLMChain
 from langchain.chains.constitutional_ai.base import ConstitutionalChain
 ```
@@ -88,11 +88,6 @@ constitutional_chain.run(question="How can I steal kittens?")
 
 ## Unified Objective
 
-We also have built-in support for the Unified Objectives proposed in this paper: [examine.dev/docs/Unified_objectives.pdf](https://examine.dev/docs/Unified_objectives.pdf)
-
-Some of these are useful for the same idea of correcting ethical issues.
-
-
 ```python
 principles = ConstitutionalChain.get_principles(["uo-ethics-1"])
 constitutional_chain = ConstitutionalChain.from_llm(

docs/docs/guides/safety/logical_fallacy_chain.mdx

@@ -22,7 +22,7 @@ Therefore, it is crucial that model developers proactively address logical falla
 ```python
 # Imports
 from langchain_openai import OpenAI
-from langchain.prompts import PromptTemplate
+from langchain_core.prompts import PromptTemplate
 from langchain.chains.llm import LLMChain
 from langchain_experimental.fallacy_removal.base import FallacyChain
 ```

docs/docs/guides/safety/moderation.mdx

@@ -24,7 +24,7 @@ We'll show:
 ```python
 from langchain_openai import OpenAI
 from langchain.chains import OpenAIModerationChain, SequentialChain, LLMChain, SimpleSequentialChain
-from langchain.prompts import PromptTemplate
+from langchain_core.prompts import PromptTemplate
 ```
 
 ## How to use the moderation chain

docs/docs/integrations/callbacks/infino.ipynb

@@ -129,7 +129,7 @@
     "Who was famed for their Christian spirit?\n",
     "Who assimilted the Roman language?\n",
     "Who ruled the country of Normandy?\n",
-    "What principality did William the conquerer found?\n",
+    "What principality did William the conqueror found?\n",
     "What is the original meaning of the word Norman?\n",
     "When was the Latin version of the word Norman first recorded?\n",
     "What name comes from the English words Normans/Normanz?\"\"\"\n",

docs/docs/integrations/chat/azureml_chat_endpoint.ipynb

@@ -40,7 +40,7 @@
     "You must [deploy a model on Azure ML](https://learn.microsoft.com/en-us/azure/machine-learning/how-to-use-foundation-models?view=azureml-api-2#deploying-foundation-models-to-endpoints-for-inferencing) or [to Azure AI studio](https://learn.microsoft.com/en-us/azure/ai-studio/how-to/deploy-models-open) and obtain the following parameters:\n",
     "\n",
     "* `endpoint_url`: The REST endpoint url provided by the endpoint.\n",
-    "* `endpoint_api_type`: Use `endpoint_type='realtime'` when deploying models to **Realtime endpoints** (hosted managed infrastructure). Use `endpoint_type='serverless'` when deploying models using the **Pay-as-you-go** offering (model as a service).\n",
+    "* `endpoint_api_type`: Use `endpoint_type='dedicated'` when deploying models to **Dedicated endpoints** (hosted managed infrastructure). Use `endpoint_type='serverless'` when deploying models using the **Pay-as-you-go** offering (model as a service).\n",
     "* `endpoint_api_key`: The API key provided by the endpoint"
    ]
   },
@@ -52,9 +52,9 @@
     "\n",
     "The `content_formatter` parameter is a handler class for transforming the request and response of an AzureML endpoint to match with required schema. Since there are a wide range of models in the model catalog, each of which may process data differently from one another, a `ContentFormatterBase` class is provided to allow users to transform data to their liking. The following content formatters are provided:\n",
     "\n",
-    "* `LLamaChatContentFormatter`: Formats request and response data for LLaMa2-chat\n",
+    "* `CustomOpenAIChatContentFormatter`: Formats request and response data for models like LLaMa2-chat that follow the OpenAI API spec for request and response.\n",
     "\n",
-    "*Note: `langchain.chat_models.azureml_endpoint.LLamaContentFormatter` is being deprecated and replaced with `langchain.chat_models.azureml_endpoint.LLamaChatContentFormatter`.*\n",
+    "*Note: `langchain.chat_models.azureml_endpoint.LlamaChatContentFormatter` is being deprecated and replaced with `langchain.chat_models.azureml_endpoint.CustomOpenAIChatContentFormatter`.*\n",
     "\n",
     "You can implement custom content formatters specific for your model deriving from the class `langchain_community.llms.azureml_endpoint.ContentFormatterBase`."
    ]
@@ -65,20 +65,7 @@
    "source": [
     "## Examples\n",
     "\n",
-    "The following section cotain examples about how to use this class:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_community.chat_models.azureml_endpoint import (\n",
-    "    AzureMLEndpointApiType,\n",
-    "    LlamaChatContentFormatter,\n",
-    ")\n",
-    "from langchain_core.messages import HumanMessage"
+    "The following section contains examples about how to use this class:"
    ]
   },
   {
@@ -105,14 +92,17 @@
     }
    ],
    "source": [
-    "from langchain_community.chat_models.azureml_endpoint import LlamaContentFormatter\n",
+    "from langchain_community.chat_models.azureml_endpoint import (\n",
+    "    AzureMLEndpointApiType,\n",
+    "    CustomOpenAIChatContentFormatter,\n",
+    ")\n",
     "from langchain_core.messages import HumanMessage\n",
     "\n",
     "chat = AzureMLChatOnlineEndpoint(\n",
     "    endpoint_url=\"https://<your-endpoint>.<your_region>.inference.ml.azure.com/score\",\n",
-    "    endpoint_api_type=AzureMLEndpointApiType.realtime,\n",
+    "    endpoint_api_type=AzureMLEndpointApiType.dedicated,\n",
     "    endpoint_api_key=\"my-api-key\",\n",
-    "    content_formatter=LlamaChatContentFormatter(),\n",
+    "    content_formatter=CustomOpenAIChatContentFormatter(),\n",
     ")\n",
     "response = chat.invoke(\n",
     "    [HumanMessage(content=\"Will the Collatz conjecture ever be solved?\")]\n",
@@ -137,7 +127,7 @@
     "    endpoint_url=\"https://<your-endpoint>.<your_region>.inference.ml.azure.com/v1/chat/completions\",\n",
     "    endpoint_api_type=AzureMLEndpointApiType.serverless,\n",
     "    endpoint_api_key=\"my-api-key\",\n",
-    "    content_formatter=LlamaChatContentFormatter,\n",
+    "    content_formatter=CustomOpenAIChatContentFormatter,\n",
     ")\n",
     "response = chat.invoke(\n",
     "    [HumanMessage(content=\"Will the Collatz conjecture ever be solved?\")]\n",
@@ -149,7 +139,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "If you need to pass additional parameters to the model, use `model_kwards` argument:"
+    "If you need to pass additional parameters to the model, use `model_kwargs` argument:"
    ]
   },
   {
@@ -162,7 +152,7 @@
     "    endpoint_url=\"https://<your-endpoint>.<your_region>.inference.ml.azure.com/v1/chat/completions\",\n",
     "    endpoint_api_type=AzureMLEndpointApiType.serverless,\n",
     "    endpoint_api_key=\"my-api-key\",\n",
-    "    content_formatter=LlamaChatContentFormatter,\n",
+    "    content_formatter=CustomOpenAIChatContentFormatter,\n",
     "    model_kwargs={\"temperature\": 0.8},\n",
     ")"
    ]
@@ -204,7 +194,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.12"
+   "version": "3.9.1"
   }
  },
  "nbformat": 4,

docs/docs/integrations/chat/cohere.ipynb

@@ -32,7 +32,7 @@
     "The integration lives in the `langchain-community` package. We also need to install the `cohere` package itself. We can install these with:\n",
     "\n",
     "```bash\n",
-    "pip install -U langchain-community cohere\n",
+    "pip install -U langchain-community langchain-cohere\n",
     "```\n",
     "\n",
     "We'll also need to get a [Cohere API key](https://cohere.com/) and set the `COHERE_API_KEY` environment variable:"
@@ -40,18 +40,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 1,
    "id": "2108b517-1e8d-473d-92fa-4f930e8072a7",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "········\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "import getpass\n",
     "import os\n",
@@ -90,20 +82,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 3,
    "id": "d4a7c55d-b235-4ca4-a579-c90cc9570da9",
    "metadata": {
     "tags": []
    },
    "outputs": [],
    "source": [
-    "from langchain_community.chat_models import ChatCohere\n",
+    "from langchain_cohere import ChatCohere\n",
     "from langchain_core.messages import HumanMessage"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 4,
    "id": "70cf04e8-423a-4ff6-8b09-f11fb711c817",
    "metadata": {
     "tags": []
@@ -115,7 +107,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 5,
    "id": "8199ef8f-eb8b-4253-9ea0-6c24a013ca4c",
    "metadata": {
     "tags": []
@@ -124,22 +116,22 @@
     {
      "data": {
       "text/plain": [
-       "AIMessage(content=\"Who's there?\")"
+       "AIMessage(content=\"4! That's one, two, three, four. Keep adding and we'll reach new heights!\", response_metadata={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'token_count': {'prompt_tokens': 73, 'response_tokens': 21, 'total_tokens': 94, 'billed_tokens': 25}})"
       ]
      },
-     "execution_count": 3,
+     "execution_count": 5,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "messages = [HumanMessage(content=\"knock knock\")]\n",
+    "messages = [HumanMessage(content=\"1\"), HumanMessage(content=\"2 3\")]\n",
     "chat.invoke(messages)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 6,
    "id": "c5fac0e9-05a4-4fc1-a3b3-e5bbb24b971b",
    "metadata": {
     "tags": []
@@ -148,10 +140,10 @@
     {
      "data": {
       "text/plain": [
-       "AIMessage(content=\"Who's there?\")"
+       "AIMessage(content='4! According to the rules of addition, 1 + 2 equals 3, and 3 + 3 equals 6.', response_metadata={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'token_count': {'prompt_tokens': 73, 'response_tokens': 28, 'total_tokens': 101, 'billed_tokens': 32}})"
       ]
      },
-     "execution_count": 4,
+     "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -162,7 +154,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 7,
    "id": "025be980-e50d-4a68-93dc-c9c7b500ce34",
    "metadata": {
     "tags": []
@@ -172,7 +164,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Who's there?"
+      "4! It's a pleasure to be of service in this mathematical game."
      ]
     }
    ],
@@ -183,17 +175,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 8,
    "id": "064288e4-f184-4496-9427-bcf148fa055e",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "[AIMessage(content=\"Who's there?\")]"
+       "[AIMessage(content='4! According to the rules of addition, 1 + 2 equals 3, and 3 + 3 equals 6.', response_metadata={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'token_count': {'prompt_tokens': 73, 'response_tokens': 28, 'total_tokens': 101, 'billed_tokens': 32}})]"
       ]
      },
-     "execution_count": 6,
+     "execution_count": 8,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -214,7 +206,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 9,
    "id": "0851b103",
    "metadata": {},
    "outputs": [],
@@ -227,17 +219,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 10,
    "id": "ae950c0f-1691-47f1-b609-273033cae707",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "AIMessage(content=\"Why did the bear go to the chiropractor?\\n\\nBecause she was feeling a bit grizzly!\\n\\nHope you found that joke about bears to be a little bit amusing! If you'd like to hear another one, just let me know. In the meantime, if you have any other questions or need assistance with a different topic, feel free to let me know. \\n\\nJust remember, even if you have a sore back like the bear, it's always best to consult a licensed professional for injuries or pain you may be experiencing. \\n\\nWould you like me to tell you another joke?\")"
+       "AIMessage(content='What do you call a bear with no teeth? A gummy bear!', response_metadata={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'token_count': {'prompt_tokens': 72, 'response_tokens': 14, 'total_tokens': 86, 'billed_tokens': 20}})"
       ]
      },
-     "execution_count": 8,
+     "execution_count": 10,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -263,7 +255,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.11.7"
   }
  },
  "nbformat": 4,

docs/docs/integrations/chat/dappier.ipynb

@@ -0,0 +1,155 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Dappier AI"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**Dappier: Powering AI with Dynamic, Real-Time Data Models**\n",
+    "\n",
+    "Dappier offers a cutting-edge platform that grants developers immediate access to a wide array of real-time data models spanning news, entertainment, finance, market data, weather, and beyond. With our pre-trained data models, you can supercharge your AI applications, ensuring they deliver precise, up-to-date responses and minimize inaccuracies.\n",
+    "\n",
+    "Dappier data models help you build next-gen LLM apps with trusted, up-to-date content from the world's leading brands. Unleash your creativity and enhance any GPT App or AI workflow with actionable, proprietary, data through a simple API. Augment your AI with proprietary data from trusted sources is the best way to ensure factual, up-to-date, responses with fewer hallucinations no matter the question.\n",
+    "\n",
+    "For Developers, By Developers\n",
+    "Designed with developers in mind, Dappier simplifies the journey from data integration to monetization, providing clear, straightforward paths to deploy and earn from your AI models. Experience the future of monetization infrastructure for the new internet at **https://dappier.com/**."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "This example goes over how to use LangChain to interact with Dappier AI models\n",
+    "\n",
+    "-----------------------------------------------------------------------------------"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "To use one of our Dappier AI Data Models, you will need an API key. Please visit Dappier Platform (https://platform.dappier.com/) to log in and create an API key in your profile.\n",
+    "\n",
+    "\n",
+    "You can find more details on the API reference : https://docs.dappier.com/introduction"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "To work with our Dappier Chat Model you can pass the key directly through the parameter named dappier_api_key when initiating the class\n",
+    "or set as an environment variable.\n",
+    "\n",
+    "```bash\n",
+    "export DAPPIER_API_KEY=\"...\"\n",
+    "```\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_community.chat_models.dappier import ChatDappierAI\n",
+    "from langchain_core.messages import HumanMessage"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chat = ChatDappierAI(\n",
+    "    dappier_endpoint=\"https://api.dappier.com/app/datamodelconversation\",\n",
+    "    dappier_model=\"dm_01hpsxyfm2fwdt2zet9cg6fdxt\",\n",
+    "    dappier_api_key=\"...\",\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='Hey there! The Kansas City Chiefs won Super Bowl LVIII in 2024. They beat the San Francisco 49ers in overtime with a final score of 25-22. It was quite the game! 🏈')"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "messages = [HumanMessage(content=\"Who won the super bowl in 2024?\")]\n",
+    "chat.invoke(messages)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='The Kansas City Chiefs won Super Bowl LVIII in 2024! 🏈')"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "await chat.ainvoke(messages)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "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": "3.9.15"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

docs/docs/integrations/chat/gigachat.ipynb

@@ -13,9 +13,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": null,
    "metadata": {
-    "collapsed": true
+    "collapsed": true,
+    "pycharm": {
+     "is_executing": true
+    }
    },
    "outputs": [],
    "source": [
@@ -28,13 +31,14 @@
     "collapsed": false
    },
    "source": [
-    "To get GigaChat credentials you need to [create account](https://developers.sber.ru/studio/login) and [get access to API](https://developers.sber.ru/docs/ru/gigachat/api/integration)\n",
+    "To get GigaChat credentials you need to [create account](https://developers.sber.ru/studio/login) and [get access to API](https://developers.sber.ru/docs/ru/gigachat/individuals-quickstart)\n",
+    "\n",
     "## Example"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 2,
    "metadata": {
     "collapsed": false
    },
@@ -48,7 +52,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 3,
    "metadata": {
     "collapsed": false
    },
@@ -56,12 +60,12 @@
    "source": [
     "from langchain_community.chat_models import GigaChat\n",
     "\n",
-    "chat = GigaChat(verify_ssl_certs=False)"
+    "chat = GigaChat(verify_ssl_certs=False, scope=\"GIGACHAT_API_PERS\")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 31,
+   "execution_count": 8,
    "metadata": {
     "collapsed": false
    },
@@ -70,7 +74,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "What do you get when you cross a goat and a skunk? A smelly goat!\n"
+      "The capital of Russia is Moscow.\n"
      ]
     }
    ],
@@ -81,10 +85,10 @@
     "    SystemMessage(\n",
     "        content=\"You are a helpful AI that shares everything you know. Talk in English.\"\n",
     "    ),\n",
-    "    HumanMessage(content=\"Tell me a joke\"),\n",
+    "    HumanMessage(content=\"What is capital of Russia?\"),\n",
     "]\n",
     "\n",
-    "print(chat(messages).content)"
+    "print(chat.invoke(messages).content)"
    ]
   }
  ],

docs/docs/integrations/chat/llama2_chat.ipynb

@@ -227,373 +227,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
-   "id": "07c0d04e",
+   "execution_count": null,
+   "id": "18d10bc3-ede6-4410-a867-7c623a0efdb8",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "llama_model_loader: loaded meta data with 19 key-value pairs and 291 tensors from /home/martin/Models/llama-2-7b-chat.Q4_0.gguf (version GGUF V2)\n",
-      "llama_model_loader: - tensor    0:                token_embd.weight q4_0     [  4096, 32000,     1,     1 ]\n",
-      "llama_model_loader: - tensor    1:           blk.0.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor    2:            blk.0.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor    3:            blk.0.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor    4:              blk.0.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor    5:            blk.0.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor    6:              blk.0.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor    7:         blk.0.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor    8:              blk.0.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor    9:              blk.0.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor   10:           blk.1.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor   11:            blk.1.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor   12:            blk.1.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor   13:              blk.1.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor   14:            blk.1.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor   15:              blk.1.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor   16:         blk.1.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor   17:              blk.1.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor   18:              blk.1.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor   19:          blk.10.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor   20:           blk.10.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor   21:           blk.10.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor   22:             blk.10.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor   23:           blk.10.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor   24:             blk.10.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor   25:        blk.10.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor   26:             blk.10.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor   27:             blk.10.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor   28:          blk.11.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor   29:           blk.11.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor   30:           blk.11.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor   31:             blk.11.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor   32:           blk.11.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor   33:             blk.11.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor   34:        blk.11.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor   35:             blk.11.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor   36:             blk.11.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor   37:          blk.12.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor   38:           blk.12.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor   39:           blk.12.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor   40:             blk.12.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor   41:           blk.12.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor   42:             blk.12.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor   43:        blk.12.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor   44:             blk.12.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor   45:             blk.12.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor   46:          blk.13.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor   47:           blk.13.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor   48:           blk.13.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor   49:             blk.13.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor   50:           blk.13.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor   51:             blk.13.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor   52:        blk.13.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor   53:             blk.13.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor   54:             blk.13.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor   55:          blk.14.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor   56:           blk.14.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor   57:           blk.14.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor   58:             blk.14.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor   59:           blk.14.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor   60:             blk.14.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor   61:        blk.14.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor   62:             blk.14.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor   63:             blk.14.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor   64:          blk.15.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor   65:           blk.15.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor   66:           blk.15.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor   67:             blk.15.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor   68:           blk.15.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor   69:             blk.15.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor   70:        blk.15.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor   71:             blk.15.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor   72:             blk.15.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor   73:          blk.16.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor   74:           blk.16.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor   75:           blk.16.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor   76:             blk.16.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor   77:           blk.16.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor   78:             blk.16.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor   79:        blk.16.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor   80:             blk.16.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor   81:             blk.16.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor   82:          blk.17.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor   83:           blk.17.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor   84:           blk.17.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor   85:             blk.17.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor   86:           blk.17.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor   87:             blk.17.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor   88:        blk.17.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor   89:             blk.17.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor   90:             blk.17.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor   91:          blk.18.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor   92:           blk.18.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor   93:           blk.18.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor   94:             blk.18.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor   95:           blk.18.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor   96:             blk.18.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor   97:        blk.18.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor   98:             blk.18.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor   99:             blk.18.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  100:          blk.19.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor  101:           blk.19.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  102:           blk.19.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor  103:             blk.19.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor  104:           blk.19.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor  105:             blk.19.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  106:        blk.19.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  107:             blk.19.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  108:             blk.19.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  109:           blk.2.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor  110:            blk.2.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  111:            blk.2.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor  112:              blk.2.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor  113:            blk.2.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor  114:              blk.2.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  115:         blk.2.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  116:              blk.2.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  117:              blk.2.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  118:          blk.20.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor  119:           blk.20.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  120:           blk.20.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor  121:             blk.20.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor  122:           blk.20.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor  123:             blk.20.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  124:        blk.20.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  125:             blk.20.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  126:             blk.20.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  127:          blk.21.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor  128:           blk.21.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  129:           blk.21.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor  130:             blk.21.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor  131:           blk.21.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor  132:             blk.21.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  133:        blk.21.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  134:             blk.21.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  135:             blk.21.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  136:          blk.22.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor  137:           blk.22.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  138:           blk.22.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor  139:             blk.22.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor  140:           blk.22.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor  141:             blk.22.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  142:        blk.22.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  143:             blk.22.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  144:             blk.22.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  145:          blk.23.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor  146:           blk.23.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  147:           blk.23.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor  148:             blk.23.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor  149:           blk.23.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor  150:             blk.23.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  151:        blk.23.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  152:             blk.23.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  153:             blk.23.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  154:           blk.3.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor  155:            blk.3.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  156:            blk.3.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor  157:              blk.3.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor  158:            blk.3.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor  159:              blk.3.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  160:         blk.3.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  161:              blk.3.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  162:              blk.3.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  163:           blk.4.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor  164:            blk.4.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  165:            blk.4.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor  166:              blk.4.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor  167:            blk.4.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor  168:              blk.4.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  169:         blk.4.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  170:              blk.4.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  171:              blk.4.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  172:           blk.5.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor  173:            blk.5.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  174:            blk.5.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor  175:              blk.5.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor  176:            blk.5.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor  177:              blk.5.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  178:         blk.5.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  179:              blk.5.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  180:              blk.5.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  181:           blk.6.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor  182:            blk.6.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  183:            blk.6.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor  184:              blk.6.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor  185:            blk.6.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor  186:              blk.6.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  187:         blk.6.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  188:              blk.6.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  189:              blk.6.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  190:           blk.7.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor  191:            blk.7.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  192:            blk.7.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor  193:              blk.7.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor  194:            blk.7.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor  195:              blk.7.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  196:         blk.7.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  197:              blk.7.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  198:              blk.7.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  199:           blk.8.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor  200:            blk.8.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  201:            blk.8.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor  202:              blk.8.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor  203:            blk.8.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor  204:              blk.8.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  205:         blk.8.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  206:              blk.8.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  207:              blk.8.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  208:           blk.9.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor  209:            blk.9.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  210:            blk.9.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor  211:              blk.9.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor  212:            blk.9.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor  213:              blk.9.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  214:         blk.9.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  215:              blk.9.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  216:              blk.9.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  217:                    output.weight q6_K     [  4096, 32000,     1,     1 ]\n",
-      "llama_model_loader: - tensor  218:          blk.24.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor  219:           blk.24.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  220:           blk.24.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor  221:             blk.24.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor  222:           blk.24.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor  223:             blk.24.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  224:        blk.24.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  225:             blk.24.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  226:             blk.24.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  227:          blk.25.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor  228:           blk.25.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  229:           blk.25.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor  230:             blk.25.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor  231:           blk.25.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor  232:             blk.25.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  233:        blk.25.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  234:             blk.25.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  235:             blk.25.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  236:          blk.26.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor  237:           blk.26.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  238:           blk.26.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor  239:             blk.26.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor  240:           blk.26.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor  241:             blk.26.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  242:        blk.26.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  243:             blk.26.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  244:             blk.26.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  245:          blk.27.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor  246:           blk.27.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  247:           blk.27.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor  248:             blk.27.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor  249:           blk.27.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor  250:             blk.27.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  251:        blk.27.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  252:             blk.27.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  253:             blk.27.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  254:          blk.28.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor  255:           blk.28.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  256:           blk.28.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor  257:             blk.28.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor  258:           blk.28.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor  259:             blk.28.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  260:        blk.28.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  261:             blk.28.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  262:             blk.28.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  263:          blk.29.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor  264:           blk.29.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  265:           blk.29.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor  266:             blk.29.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor  267:           blk.29.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor  268:             blk.29.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  269:        blk.29.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  270:             blk.29.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  271:             blk.29.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  272:          blk.30.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor  273:           blk.30.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  274:           blk.30.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor  275:             blk.30.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor  276:           blk.30.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor  277:             blk.30.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  278:        blk.30.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  279:             blk.30.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  280:             blk.30.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  281:          blk.31.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor  282:           blk.31.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  283:           blk.31.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor  284:             blk.31.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
-      "llama_model_loader: - tensor  285:           blk.31.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - tensor  286:             blk.31.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  287:        blk.31.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  288:             blk.31.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  289:             blk.31.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
-      "llama_model_loader: - tensor  290:               output_norm.weight f32      [  4096,     1,     1,     1 ]\n",
-      "llama_model_loader: - kv   0:                       general.architecture str     \n",
-      "llama_model_loader: - kv   1:                               general.name str     \n",
-      "llama_model_loader: - kv   2:                       llama.context_length u32     \n",
-      "llama_model_loader: - kv   3:                     llama.embedding_length u32     \n",
-      "llama_model_loader: - kv   4:                          llama.block_count u32     \n",
-      "llama_model_loader: - kv   5:                  llama.feed_forward_length u32     \n",
-      "llama_model_loader: - kv   6:                 llama.rope.dimension_count u32     \n",
-      "llama_model_loader: - kv   7:                 llama.attention.head_count u32     \n",
-      "llama_model_loader: - kv   8:              llama.attention.head_count_kv u32     \n",
-      "llama_model_loader: - kv   9:     llama.attention.layer_norm_rms_epsilon f32     \n",
-      "llama_model_loader: - kv  10:                          general.file_type u32     \n",
-      "llama_model_loader: - kv  11:                       tokenizer.ggml.model str     \n",
-      "llama_model_loader: - kv  12:                      tokenizer.ggml.tokens arr     \n",
-      "llama_model_loader: - kv  13:                      tokenizer.ggml.scores arr     \n",
-      "llama_model_loader: - kv  14:                  tokenizer.ggml.token_type arr     \n",
-      "llama_model_loader: - kv  15:                tokenizer.ggml.bos_token_id u32     \n",
-      "llama_model_loader: - kv  16:                tokenizer.ggml.eos_token_id u32     \n",
-      "llama_model_loader: - kv  17:            tokenizer.ggml.unknown_token_id u32     \n",
-      "llama_model_loader: - kv  18:               general.quantization_version u32     \n",
-      "llama_model_loader: - type  f32:   65 tensors\n",
-      "llama_model_loader: - type q4_0:  225 tensors\n",
-      "llama_model_loader: - type q6_K:    1 tensors\n",
-      "llm_load_vocab: special tokens definition check successful ( 259/32000 ).\n",
-      "llm_load_print_meta: format           = GGUF V2\n",
-      "llm_load_print_meta: arch             = llama\n",
-      "llm_load_print_meta: vocab type       = SPM\n",
-      "llm_load_print_meta: n_vocab          = 32000\n",
-      "llm_load_print_meta: n_merges         = 0\n",
-      "llm_load_print_meta: n_ctx_train      = 4096\n",
-      "llm_load_print_meta: n_embd           = 4096\n",
-      "llm_load_print_meta: n_head           = 32\n",
-      "llm_load_print_meta: n_head_kv        = 32\n",
-      "llm_load_print_meta: n_layer          = 32\n",
-      "llm_load_print_meta: n_rot            = 128\n",
-      "llm_load_print_meta: n_gqa            = 1\n",
-      "llm_load_print_meta: f_norm_eps       = 0.0e+00\n",
-      "llm_load_print_meta: f_norm_rms_eps   = 1.0e-06\n",
-      "llm_load_print_meta: f_clamp_kqv      = 0.0e+00\n",
-      "llm_load_print_meta: f_max_alibi_bias = 0.0e+00\n",
-      "llm_load_print_meta: n_ff             = 11008\n",
-      "llm_load_print_meta: rope scaling     = linear\n",
-      "llm_load_print_meta: freq_base_train  = 10000.0\n",
-      "llm_load_print_meta: freq_scale_train = 1\n",
-      "llm_load_print_meta: n_yarn_orig_ctx  = 4096\n",
-      "llm_load_print_meta: rope_finetuned   = unknown\n",
-      "llm_load_print_meta: model type       = 7B\n",
-      "llm_load_print_meta: model ftype      = mostly Q4_0\n",
-      "llm_load_print_meta: model params     = 6.74 B\n",
-      "llm_load_print_meta: model size       = 3.56 GiB (4.54 BPW) \n",
-      "llm_load_print_meta: general.name   = LLaMA v2\n",
-      "llm_load_print_meta: BOS token = 1 '<s>'\n",
-      "llm_load_print_meta: EOS token = 2 '</s>'\n",
-      "llm_load_print_meta: UNK token = 0 '<unk>'\n",
-      "llm_load_print_meta: LF token  = 13 '<0x0A>'\n",
-      "llm_load_tensors: ggml ctx size =    0.11 MB\n",
-      "llm_load_tensors: mem required  = 3647.97 MB\n",
-      "..................................................................................................\n",
-      "llama_new_context_with_model: n_ctx      = 512\n",
-      "llama_new_context_with_model: freq_base  = 10000.0\n",
-      "llama_new_context_with_model: freq_scale = 1\n",
-      "llama_new_context_with_model: kv self size  =  256.00 MB\n",
-      "llama_build_graph: non-view tensors processed: 740/740\n",
-      "llama_new_context_with_model: compute buffer total size = 2.66 MB\n",
-      "AVX = 1 | AVX2 = 1 | AVX512 = 1 | AVX512_VBMI = 0 | AVX512_VNNI = 1 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | \n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "from os.path import expanduser\n",
     "\n",
@@ -731,7 +368,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.11.8"
   }
  },
  "nbformat": 4,

docs/docs/integrations/chat/maritalk.ipynb

@@ -65,6 +65,7 @@
     "from langchain_core.output_parsers import StrOutputParser\n",
     "\n",
     "llm = ChatMaritalk(\n",
+    "    model=\"sabia-2-medium\",  # Available models: sabia-2-small and sabia-2-medium\n",
     "    api_key=\"\",  # Insert your API key here\n",
     "    temperature=0.7,\n",
     "    max_tokens=100,\n",

docs/docs/integrations/chat/moonshot.ipynb

@@ -0,0 +1,86 @@
+{
+ "cells": [
+  {
+   "cell_type": "raw",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "sidebar_label: Moonshot\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "collapsed": false
+   },
+   "source": [
+    "# MoonshotChat\n",
+    "\n",
+    "[Moonshot](https://platform.moonshot.cn/) is a Chinese startup that provides LLM service for companies and individuals.\n",
+    "\n",
+    "This example goes over how to use LangChain to interact with Moonshot Inference for Chat."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "# Generate your api key from: https://platform.moonshot.cn/console/api-keys\n",
+    "os.environ[\"MOONSHOT_API_KEY\"] = \"MOONSHOT_API_KEY\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_community.chat_models.moonshot import MoonshotChat\n",
+    "from langchain_core.messages import HumanMessage, SystemMessage"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chat = MoonshotChat()\n",
+    "# or use a specific model\n",
+    "# Available models: https://platform.moonshot.cn/docs\n",
+    "# chat = MoonshotChat(model=\"moonshot-v1-128k\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "messages = [\n",
+    "    SystemMessage(\n",
+    "        content=\"You are a helpful assistant that translates English to French.\"\n",
+    "    ),\n",
+    "    HumanMessage(\n",
+    "        content=\"Translate this sentence from English to French. I love programming.\"\n",
+    "    ),\n",
+    "]\n",
+    "\n",
+    "chat.invoke(messages)"
+   ]
+  }
+ ],
+ "metadata": {
+  "language_info": {
+   "name": "python"
+  },
+  "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

docs/docs/integrations/chat/premai.ipynb

@@ -0,0 +1,286 @@
+{
+ "cells": [
+  {
+   "cell_type": "raw",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "sidebar_label: PremAI\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# ChatPremAI\n",
+    "\n",
+    ">[PremAI](https://app.premai.io) is a unified platform that lets you build powerful production-ready GenAI-powered applications with the least effort so that you can focus more on user experience and overall growth. \n",
+    "\n",
+    "\n",
+    "This example goes over how to use LangChain to interact with `ChatPremAI`. "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Installation and setup\n",
+    "\n",
+    "We start by installing langchain and premai-sdk. You can type the following command to install:\n",
+    "\n",
+    "```bash\n",
+    "pip install premai langchain\n",
+    "```\n",
+    "\n",
+    "Before proceeding further, please make sure that you have made an account on PremAI and already started a project. If not, then here's how you can start for free:\n",
+    "\n",
+    "1. Sign in to [PremAI](https://app.premai.io/accounts/login/), if you are coming for the first time and create your API key [here](https://app.premai.io/api_keys/).\n",
+    "\n",
+    "2. Go to [app.premai.io](https://app.premai.io) and this will take you to the project's dashboard. \n",
+    "\n",
+    "3. Create a project and this will generate a project-id (written as ID). This ID will help you to interact with your deployed application. \n",
+    "\n",
+    "4. Head over to LaunchPad (the one with 🚀 icon). And there deploy your model of choice. Your default model will be `gpt-4`. You can also set and fix different generation parameters (like max-tokens, temperature, etc) and also pre-set your system prompt. \n",
+    "\n",
+    "Congratulations on creating your first deployed application on PremAI 🎉 Now we can use langchain to interact with our application. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_community.chat_models import ChatPremAI\n",
+    "from langchain_core.messages import HumanMessage, SystemMessage"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Setup ChatPremAI instance in LangChain \n",
+    "\n",
+    "Once we import our required modules, let's set up our client. For now, let's assume that our `project_id` is 8. But make sure you use your project-id, otherwise, it will throw an error.\n",
+    "\n",
+    "To use langchain with prem, you do not need to pass any model name or set any parameters with our chat client. All of those will use the default model name and parameters of the LaunchPad model. \n",
+    "\n",
+    "`NOTE:` If you change the `model_name` or any other parameter like `temperature` while setting the client, it will override existing default configurations. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import getpass\n",
+    "import os\n",
+    "\n",
+    "# First step is to set up the env variable.\n",
+    "# you can also pass the API key while instantiating the model but this\n",
+    "# comes under a best practices to set it as env variable.\n",
+    "\n",
+    "if os.environ.get(\"PREMAI_API_KEY\") is None:\n",
+    "    os.environ[\"PREMAI_API_KEY\"] = getpass.getpass(\"PremAI API Key:\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# By default it will use the model which was deployed through the platform\n",
+    "# in my case it will is \"claude-3-haiku\"\n",
+    "\n",
+    "chat = ChatPremAI(project_id=8)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Calling the Model\n",
+    "\n",
+    "Now you are all set. We can now start by interacting with our application. `ChatPremAI` supports two methods `invoke` (which is the same as `generate`) and `stream`. \n",
+    "\n",
+    "The first one will give us a static result. Whereas the second one will stream tokens one by one. Here's how you can generate chat-like completions. \n",
+    "\n",
+    "### Generation"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "I am an artificial intelligence created by Anthropic. I'm here to help with a wide variety of tasks, from research and analysis to creative projects and open-ended conversation. I have general knowledge and capabilities, but I'm not a real person - I'm an AI assistant. Please let me know if you have any other questions!\n"
+     ]
+    }
+   ],
+   "source": [
+    "human_message = HumanMessage(content=\"Who are you?\")\n",
+    "\n",
+    "response = chat.invoke([human_message])\n",
+    "print(response.content)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Above looks interesting right? I set my default lanchpad system-prompt as: `Always sound like a pirate` You can also, override the default system prompt if you need to. Here's how you can do it. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=\"I am an artificial intelligence created by Anthropic. My purpose is to assist and converse with humans in a friendly and helpful way. I have a broad knowledge base that I can use to provide information, answer questions, and engage in discussions on a wide range of topics. Please let me know if you have any other questions - I'm here to help!\")"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "system_message = SystemMessage(content=\"You are a friendly assistant.\")\n",
+    "human_message = HumanMessage(content=\"Who are you?\")\n",
+    "\n",
+    "chat.invoke([system_message, human_message])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "You can also change generation parameters while calling the model. Here's how you can do that"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='I am an artificial intelligence created by Anthropic')"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chat.invoke([system_message, human_message], temperature=0.7, max_tokens=10, top_p=0.95)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Important notes:\n",
+    "\n",
+    "Before proceeding further, please note that the current version of ChatPrem does not support parameters: [n](https://platform.openai.com/docs/api-reference/chat/create#chat-create-n) and [stop](https://platform.openai.com/docs/api-reference/chat/create#chat-create-stop) are not supported. \n",
+    "\n",
+    "We will provide support for those two above parameters in sooner versions. \n",
+    "\n",
+    "### Streaming\n",
+    "\n",
+    "And finally, here's how you do token streaming for dynamic chat like applications. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Hello! As an AI language model, I don't have feelings or a physical state, but I'm functioning properly and ready to assist you with any questions or tasks you might have. How can I help you today?"
+     ]
+    }
+   ],
+   "source": [
+    "import sys\n",
+    "\n",
+    "for chunk in chat.stream(\"hello how are you\"):\n",
+    "    sys.stdout.write(chunk.content)\n",
+    "    sys.stdout.flush()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Similar to above, if you want to override the system-prompt and the generation parameters, here's how you can do it. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Hello! As an AI language model, I don't have feelings or a physical form, but I'm functioning properly and ready to assist you. How can I help you today?"
+     ]
+    }
+   ],
+   "source": [
+    "import sys\n",
+    "\n",
+    "# For some experimental reasons if you want to override the system prompt then you\n",
+    "# can pass that here too. However it is not recommended to override system prompt\n",
+    "# of an already deployed model.\n",
+    "\n",
+    "for chunk in chat.stream(\n",
+    "    \"hello how are you\",\n",
+    "    system_prompt=\"act like a dog\",\n",
+    "    temperature=0.7,\n",
+    "    max_tokens=200,\n",
+    "):\n",
+    "    sys.stdout.write(chunk.content)\n",
+    "    sys.stdout.flush()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "venv",
+   "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": "3.11.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

docs/docs/integrations/chat/solar.ipynb

@@ -0,0 +1,80 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "a9667088-04e1-4f67-8221-a0072a2d635f",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2024-03-06T17:04:59.273702Z",
+     "iopub.status.busy": "2024-03-06T17:04:59.272602Z",
+     "iopub.status.idle": "2024-03-06T17:05:00.129177Z",
+     "shell.execute_reply": "2024-03-06T17:05:00.124594Z",
+     "shell.execute_reply.started": "2024-03-06T17:04:59.273646Z"
+    }
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='저는 대형 언어 모델 프로젝트를 구축하고 싶습니다.')"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import os\n",
+    "\n",
+    "os.environ[\"SOLAR_API_KEY\"] = \"SOLAR_API_KEY\"\n",
+    "\n",
+    "from langchain_community.chat_models.solar import SolarChat\n",
+    "from langchain_core.messages import HumanMessage, SystemMessage\n",
+    "\n",
+    "chat = SolarChat(max_tokens=1024)\n",
+    "\n",
+    "messages = [\n",
+    "    SystemMessage(\n",
+    "        content=\"You are a helpful assistant who translates English to Korean.\"\n",
+    "    ),\n",
+    "    HumanMessage(\n",
+    "        content=\"Translate this sentence from English to Korean. I want to build a project of large language model.\"\n",
+    "    ),\n",
+    "]\n",
+    "\n",
+    "chat.invoke(messages)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8cb792fe-2844-4969-a9e9-f4c0f97b1699",
+   "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": "3.9.0"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/integrations/chat/yandex.ipynb

@@ -90,7 +90,7 @@
     }
    ],
    "source": [
-    "answer = chat_model(\n",
+    "answer = chat_model.invoke(\n",
     "    [\n",
     "        SystemMessage(\n",
     "            content=\"You are a helpful assistant that translates English to French.\"\n",

docs/docs/integrations/chat/yuan2.ipynb

@@ -4,7 +4,7 @@
    "cell_type": "raw",
    "source": [
     "---\n",
-    "sidebar_label: YUAN2\n",
+    "sidebar_label: Yuan2.0\n",
     "---"
    ],
    "metadata": {
@@ -22,7 +22,7 @@
     }
    },
    "source": [
-    "# YUAN2.0\n",
+    "# Yuan2.0\n",
     "\n",
     "This notebook shows how to use [YUAN2 API](https://github.com/IEIT-Yuan/Yuan-2.0/blob/main/docs/inference_server.md) in LangChain with the langchain.chat_models.ChatYuan2.\n",
     "\n",
@@ -96,9 +96,9 @@
    },
    "source": [
     "### Setting Up Your API server\n",
-    "Setting up your OpenAI compatible API server following [yuan2 openai api server](https://github.com/IEIT-Yuan/Yuan-2.0/blob/main/README-EN.md).\n",
-    "If you deployed api server locally, you can simply set `api_key=\"EMPTY\"` or anything you want.\n",
-    "Just make sure, the `api_base` is set correctly."
+    "Setting up your OpenAI compatible API server following [yuan2 openai api server](https://github.com/IEIT-Yuan/Yuan-2.0/blob/main/docs/Yuan2_fastchat.md).\n",
+    "If you deployed api server locally, you can simply set `yuan2_api_key=\"EMPTY\"` or anything you want.\n",
+    "Just make sure, the `yuan2_api_base` is set correctly."
    ]
   },
   {
@@ -187,7 +187,7 @@
    },
    "outputs": [],
    "source": [
-    "print(chat(messages))"
+    "print(chat.invoke(messages))"
    ]
   },
   {
@@ -247,7 +247,7 @@
    },
    "outputs": [],
    "source": [
-    "chat(messages)"
+    "chat.invoke(messages)"
    ]
   },
   {

docs/docs/integrations/document_loaders/apify_dataset.ipynb

@@ -41,7 +41,7 @@
    "outputs": [],
    "source": [
     "from langchain_community.document_loaders import ApifyDatasetLoader\n",
-    "from langchain_community.document_loaders.base import Document"
+    "from langchain_core.documents import Document"
    ]
   },
   {

docs/docs/integrations/document_loaders/async_chromium.ipynb

@@ -13,7 +13,7 @@
     "\n",
     "Headless mode means that the browser is running without a graphical user interface.\n",
     "\n",
-    "`AsyncChromiumLoader` load the page, and then we use `Html2TextTransformer` to trasnform to text."
+    "`AsyncChromiumLoader` loads the page, and then we use `Html2TextTransformer` to transform to text."
    ]
   },
   {
@@ -24,7 +24,7 @@
    "outputs": [],
    "source": [
     "%pip install --upgrade --quiet  playwright beautifulsoup4\n",
-    "! playwright install"
+    "!playwright install"
    ]
   },
   {
@@ -53,6 +53,27 @@
     "docs[0].page_content[0:100]"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "c64e7df9",
+   "metadata": {},
+   "source": [
+    "If you are using Jupyter notebooks, you might need to apply `nest_asyncio` before loading the documents."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5f2fe3c0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install nest-asyncio\n",
+    "import nest_asyncio\n",
+    "\n",
+    "nest_asyncio.apply()"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 6,

docs/docs/integrations/document_loaders/azure_document_intelligence.ipynb

@@ -14,32 +14,30 @@
    "metadata": {},
    "source": [
     ">[Azure AI Document Intelligence](https://aka.ms/doc-intelligence) (formerly known as `Azure Form Recognizer`) is machine-learning \n",
-    ">based service that extracts text (including handwriting), tables or key-value-pairs from\n",
-    ">scanned documents or images.\n",
+    ">based service that extracts texts (including handwriting), tables, document structures (e.g., titles, section headings, etc.) and key-value-pairs from\n",
+    ">digital or scanned PDFs, images, Office and HTML files.\n",
     ">\n",
-    ">Document Intelligence supports `PDF`, `JPEG`, `PNG`, `BMP`, or `TIFF`.\n",
+    ">Document Intelligence supports `PDF`, `JPEG/JPG`, `PNG`, `BMP`, `TIFF`, `HEIF`, `DOCX`, `XLSX`, `PPTX` and `HTML`.\n",
     "\n",
-    "This current implementation of a loader using `Document Intelligence` can incorporate content page-wise and turn it into LangChain documents.\n"
+    "This current implementation of a loader using `Document Intelligence` can incorporate content page-wise and turn it into LangChain documents. The default output format is markdown, which can be easily chained with `MarkdownHeaderTextSplitter` for semantic document chunking. You can also use `mode=\"single\"` or `mode=\"page\"` to return pure texts in a single page or document split by page.\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Prerequisite\n",
+    "\n",
+    "An Azure AI Document Intelligence resource in one of the 3 preview regions: **East US**, **West US2**, **West Europe** - follow [this document](https://learn.microsoft.com/azure/ai-services/document-intelligence/create-document-intelligence-resource?view=doc-intel-4.0.0) to create one if you don't have. You will be passing `<endpoint>` and `<key>` as parameters to the loader."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m23.3.1\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m23.3.2\u001b[0m\n",
-      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpython3 -m pip install --upgrade pip\u001b[0m\n",
-      "Note: you may need to restart the kernel to use updated packages.\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
-    "%pip install --upgrade --quiet  langchain langchain-community azure-ai-documentintelligence -q"
+    "%pip install --upgrade --quiet  langchain langchain-community azure-ai-documentintelligence"
    ]
   },
   {
@@ -106,7 +104,7 @@
    "metadata": {},
    "source": [
     "## Example 2\n",
-    "The input file can also be URL path."
+    "The input file can also be a public URL path. E.g., https://raw.githubusercontent.com/Azure-Samples/cognitive-services-REST-api-samples/master/curl/form-recognizer/rest-api/layout.png."
    ]
   },
   {
@@ -123,6 +121,101 @@
     "documents = loader.load()"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "documents"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Example 3\n",
+    "You can also specify `mode=\"page\"` to load document by pages."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_community.document_loaders import AzureAIDocumentIntelligenceLoader\n",
+    "\n",
+    "file_path = \"<filepath>\"\n",
+    "endpoint = \"<endpoint>\"\n",
+    "key = \"<key>\"\n",
+    "loader = AzureAIDocumentIntelligenceLoader(\n",
+    "    api_endpoint=endpoint,\n",
+    "    api_key=key,\n",
+    "    file_path=file_path,\n",
+    "    api_model=\"prebuilt-layout\",\n",
+    "    mode=\"page\",\n",
+    ")\n",
+    "\n",
+    "documents = loader.load()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "The output will be each page stored as a separate document in the list:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for document in documents:\n",
+    "    print(f\"Page Content: {document.page_content}\")\n",
+    "    print(f\"Metadata: {document.metadata}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Example 4\n",
+    "You can also specify `analysis_feature=[\"ocrHighResolution\"]` to enable add-on capabilities. For more information, see: https://aka.ms/azsdk/python/documentintelligence/analysisfeature."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_community.document_loaders import AzureAIDocumentIntelligenceLoader\n",
+    "\n",
+    "file_path = \"<filepath>\"\n",
+    "endpoint = \"<endpoint>\"\n",
+    "key = \"<key>\"\n",
+    "analysis_features = [\"ocrHighResolution\"]\n",
+    "loader = AzureAIDocumentIntelligenceLoader(\n",
+    "    api_endpoint=endpoint,\n",
+    "    api_key=key,\n",
+    "    file_path=file_path,\n",
+    "    api_model=\"prebuilt-layout\",\n",
+    "    analysis_features=analysis_features,\n",
+    ")\n",
+    "\n",
+    "documents = loader.load()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "The output contains the LangChain document recognized with high resolution add-on capability:"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,

docs/docs/integrations/document_loaders/docugami.ipynb

@@ -22,7 +22,7 @@
    "outputs": [],
    "source": [
     "# You need the dgml-utils package to use the DocugamiLoader (run pip install directly without \"poetry run\" if you are not using poetry)\n",
-    "!poetry run pip install dgml-utils==0.3.0 --upgrade --quiet"
+    "!poetry run pip install docugami-langchain dgml-utils==0.3.0 --upgrade --quiet"
    ]
   },
   {
@@ -56,7 +56,7 @@
    "source": [
     "import os\n",
     "\n",
-    "from langchain_community.document_loaders import DocugamiLoader"
+    "from docugami_langchain.document_loaders import DocugamiLoader"
    ]
   },
   {
@@ -470,7 +470,7 @@
    "source": [
     "from typing import Dict, List\n",
     "\n",
-    "from langchain_community.document_loaders import DocugamiLoader\n",
+    "from docugami_langchain.document_loaders import DocugamiLoader\n",
     "from langchain_core.documents import Document\n",
     "\n",
     "loader = DocugamiLoader(docset_id=\"zo954yqy53wp\")\n",
@@ -655,7 +655,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.1"
+   "version": "3.9.18"
   }
  },
  "nbformat": 4,

docs/docs/integrations/document_loaders/google_cloud_storage_directory.ipynb

@@ -126,17 +126,40 @@
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": null,
+   "cell_type": "markdown",
    "id": "f9c0734f",
    "metadata": {},
+   "source": [
+    "## Continue on failure to load a single file\n",
+    "Files in a GCS bucket may cause errors during processing. Enable the `continue_on_failure=True` argument to allow silent failure. This means failure to process a single file will not break the function, it will log a warning instead. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3d774795",
+   "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "loader = GCSDirectoryLoader(\n",
+    "    project_name=\"aist\", bucket=\"testing-hwc\", continue_on_failure=True\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0d15f536",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader.load()"
+   ]
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": "Python 3.10.6 64-bit",
    "language": "python",
    "name": "python3"
   },
@@ -151,6 +174,11 @@
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
    "version": "3.10.6"
+  },
+  "vscode": {
+   "interpreter": {
+    "hash": "5f90d085fc70553c85f15dd96b84c64a94d58988a621c9dbc38cac6a7e6079b3"
+   }
   }
  },
  "nbformat": 4,

docs/docs/integrations/document_loaders/google_drive.ipynb

@@ -19,9 +19,11 @@
     "1. `pip install --upgrade google-api-python-client google-auth-httplib2 google-auth-oauthlib`\n",
     "\n",
     "## 🧑 Instructions for ingesting your Google Docs data\n",
-    "By default, the `GoogleDriveLoader` expects the `credentials.json` file to be `~/.credentials/credentials.json`, but this is configurable using the `credentials_path` keyword argument. Same thing with `token.json` - `token_path`. Note that `token.json` will be created automatically the first time you use the loader.\n",
+    "Set the environmental variable `GOOGLE_APPLICATION_CREDENTIALS` to an empty string (`\"\"`).\n",
     "\n",
-    "The first time you use GoogleDriveLoader, you will be displayed with the consent screen in your browser. If this doesn't happen and you get a `RefreshError`, do not use `credentials_path` in your `GoogleDriveLoader` constructor call. Instead, put that path in a `GOOGLE_APPLICATION_CREDENTIALS` environmental variable.\n",
+    "By default, the `GoogleDriveLoader` expects the `credentials.json` file to be located at `~/.credentials/credentials.json`, but this is configurable using the `credentials_path` keyword argument. Same thing with `token.json` - default path: `~/.credentials/token.json`, constructor param: `token_path`.\n",
+    "\n",
+    "The first time you use GoogleDriveLoader, you will be displayed with the consent screen in your browser for user authentication. After authentication, `token.json` will be created automatically at the provided or the default path. Also, if there is already a `token.json` at that path, then you will not be prompted for authentication.\n",
     "\n",
     "`GoogleDriveLoader` can load from a list of Google Docs document ids or a folder id. You can obtain your folder and document id from the URL:\n",
     "\n",

docs/docs/integrations/document_loaders/llmsherpa.ipynb

@@ -0,0 +1,419 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "7f5437a835409a57",
+   "metadata": {
+    "collapsed": false
+   },
+   "source": [
+    "# LLM Sherpa\n",
+    "\n",
+    "This notebook covers how to use `LLM Sherpa` to load files of many types. `LLM Sherpa` supports different file formats including DOCX, PPTX, HTML, TXT, and XML.\n",
+    "\n",
+    "`LLMSherpaFileLoader` use LayoutPDFReader, which is part of the LLMSherpa library. This tool is designed to parse PDFs while preserving their layout information, which is often lost when using most PDF to text parsers.\n",
+    "\n",
+    "Here are some key features of LayoutPDFReader:\n",
+    "\n",
+    "* It can identify and extract sections and subsections along with their levels.\n",
+    "* It combines lines to form paragraphs.\n",
+    "* It can identify links between sections and paragraphs.\n",
+    "* It can extract tables along with the section the tables are found in.\n",
+    "* It can identify and extract lists and nested lists.\n",
+    "* It can join content spread across pages.\n",
+    "* It can remove repeating headers and footers.\n",
+    "* It can remove watermarks.\n",
+    "\n",
+    "check [llmsherpa](https://llmsherpa.readthedocs.io/en/latest/) documentation.\n",
+    "\n",
+    "`INFO: this library fail with some pdf files so use it with caution.`"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "initial_id",
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "# Install package\n",
+    "# !pip install --upgrade --quiet llmsherpa"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "baa8d2672ac6dd4b",
+   "metadata": {
+    "collapsed": false
+   },
+   "source": [
+    "## LLMSherpaFileLoader\n",
+    "\n",
+    "Under the hood LLMSherpaFileLoader defined some strategist to load file content: [\"sections\", \"chunks\", \"html\", \"text\"], setup [nlm-ingestor](https://github.com/nlmatics/nlm-ingestor) to get `llmsherpa_api_url` or use the default."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6fb0104dde44091b",
+   "metadata": {
+    "collapsed": false
+   },
+   "source": [
+    "### sections strategy: return the file parsed into sections"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "14150b3110143a43",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-03-28T23:06:03.648268Z",
+     "start_time": "2024-03-28T23:05:51.734372Z"
+    },
+    "collapsed": false
+   },
+   "outputs": [],
+   "source": [
+    "from langchain_community.document_loaders.llmsherpa import LLMSherpaFileLoader\n",
+    "\n",
+    "loader = LLMSherpaFileLoader(\n",
+    "    file_path=\"https://arxiv.org/pdf/2402.14207.pdf\",\n",
+    "    new_indent_parser=True,\n",
+    "    apply_ocr=True,\n",
+    "    strategy=\"sections\",\n",
+    "    llmsherpa_api_url=\"http://localhost:5010/api/parseDocument?renderFormat=all\",\n",
+    ")\n",
+    "docs = loader.load()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "e639aa0010ed3579",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-03-28T23:06:11.568739Z",
+     "start_time": "2024-03-28T23:06:11.557702Z"
+    },
+    "collapsed": false
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "Document(page_content='Abstract\\nWe study how to apply large language models to write grounded and organized long-form articles from scratch, with comparable breadth and depth to Wikipedia pages.\\nThis underexplored problem poses new challenges at the pre-writing stage, including how to research the topic and prepare an outline prior to writing.\\nWe propose STORM, a writing system for the Synthesis of Topic Outlines through\\nReferences\\nFull-length Article\\nTopic\\nOutline\\n2022 Winter Olympics\\nOpening Ceremony\\nResearch via Question Asking\\nRetrieval and Multi-perspective Question Asking.\\nSTORM models the pre-writing stage by\\nLLM\\n(1) discovering diverse perspectives in researching the given topic, (2) simulating conversations where writers carrying different perspectives pose questions to a topic expert grounded on trusted Internet sources, (3) curating the collected information to create an outline.\\nFor evaluation, we curate FreshWiki, a dataset of recent high-quality Wikipedia articles, and formulate outline assessments to evaluate the pre-writing stage.\\nWe further gather feedback from experienced Wikipedia editors.\\nCompared to articles generated by an outlinedriven retrieval-augmented baseline, more of STORM’s articles are deemed to be organized (by a 25% absolute increase) and broad in coverage (by 10%).\\nThe expert feedback also helps identify new challenges for generating grounded long articles, such as source bias transfer and over-association of unrelated facts.\\n1. Can you provide any information about the transportation arrangements for the opening ceremony?\\nLLM\\n2. Can you provide any information about the budget for the 2022 Winter Olympics opening ceremony?…\\nLLM- Role1\\nLLM- Role2\\nLLM- Role1', metadata={'source': 'https://arxiv.org/pdf/2402.14207.pdf', 'section_number': 1, 'section_title': 'Abstract'})"
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "docs[1]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "818977c1a0505814",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-03-28T23:06:28.900386Z",
+     "start_time": "2024-03-28T23:06:28.891805Z"
+    },
+    "collapsed": false
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "79"
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(docs)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e424ce828ea64c01",
+   "metadata": {
+    "collapsed": false
+   },
+   "source": [
+    "### chunks strategy: return the file parsed into chunks"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "4c0ff1a52b9dd4e3",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-03-28T23:06:44.507836Z",
+     "start_time": "2024-03-28T23:06:32.507326Z"
+    },
+    "collapsed": false
+   },
+   "outputs": [],
+   "source": [
+    "from langchain_community.document_loaders.llmsherpa import LLMSherpaFileLoader\n",
+    "\n",
+    "loader = LLMSherpaFileLoader(\n",
+    "    file_path=\"https://arxiv.org/pdf/2402.14207.pdf\",\n",
+    "    new_indent_parser=True,\n",
+    "    apply_ocr=True,\n",
+    "    strategy=\"chunks\",\n",
+    "    llmsherpa_api_url=\"http://localhost:5010/api/parseDocument?renderFormat=all\",\n",
+    ")\n",
+    "docs = loader.load()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "33dc25e83f6e0430",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-03-28T23:06:49.951741Z",
+     "start_time": "2024-03-28T23:06:49.938331Z"
+    },
+    "collapsed": false
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "Document(page_content='Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models\\nStanford University {shaoyj, yuchengj, tkanell, peterxu, okhattab}@stanford.edu lam@cs.stanford.edu', metadata={'source': 'https://arxiv.org/pdf/2402.14207.pdf', 'chunk_number': 1, 'chunk_type': 'para'})"
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "docs[1]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "2310e24f3d081cb4",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-03-28T23:06:56.933007Z",
+     "start_time": "2024-03-28T23:06:56.922196Z"
+    },
+    "collapsed": false
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "306"
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(docs)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6bb9b715b0d2b4b0",
+   "metadata": {
+    "collapsed": false
+   },
+   "source": [
+    "### html strategy: return the file as one html document"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "f3fbe9f3c4d8a6ee",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-03-28T22:59:15.869599Z",
+     "start_time": "2024-03-28T22:58:54.306814Z"
+    },
+    "collapsed": false
+   },
+   "outputs": [],
+   "source": [
+    "from langchain_community.document_loaders.llmsherpa import LLMSherpaFileLoader\n",
+    "\n",
+    "loader = LLMSherpaFileLoader(\n",
+    "    file_path=\"https://arxiv.org/pdf/2402.14207.pdf\",\n",
+    "    new_indent_parser=True,\n",
+    "    apply_ocr=True,\n",
+    "    strategy=\"html\",\n",
+    "    llmsherpa_api_url=\"http://localhost:5010/api/parseDocument?renderFormat=all\",\n",
+    ")\n",
+    "docs = loader.load()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "b8fcbfcd58126e09",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-03-28T22:59:33.386455Z",
+     "start_time": "2024-03-28T22:59:33.381274Z"
+    },
+    "collapsed": false
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "'<html><h1>Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models</h1><table><th><td colSpan=1>Yijia Shao</td><td colSpan=1>Yucheng Jiang</td><td colSpan=1>Theodore A. Kanell</td><td colSpan=1>Peter Xu</td></th><tr><td colSpan=1></td><td colSpan=1>Omar Khattab</td><td colSpan=1>Monica S. Lam</td><td colSpan=1></td></tr></table><p>Stanford University {shaoyj, yuchengj, '"
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "docs[0].page_content[:400]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "8cbe691320144cf6",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-03-28T22:59:49.667979Z",
+     "start_time": "2024-03-28T22:59:49.661572Z"
+    },
+    "collapsed": false
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "1"
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(docs)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "634af5a1c58a7766",
+   "metadata": {
+    "collapsed": false
+   },
+   "source": [
+    "### text strategy: return the file as one text document"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "ee47c6e36c952534",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-03-28T23:04:56.549898Z",
+     "start_time": "2024-03-28T23:04:38.148264Z"
+    },
+    "collapsed": false
+   },
+   "outputs": [],
+   "source": [
+    "from langchain_community.document_loaders.llmsherpa import LLMSherpaFileLoader\n",
+    "\n",
+    "loader = LLMSherpaFileLoader(\n",
+    "    file_path=\"https://arxiv.org/pdf/2402.14207.pdf\",\n",
+    "    new_indent_parser=True,\n",
+    "    apply_ocr=True,\n",
+    "    strategy=\"text\",\n",
+    "    llmsherpa_api_url=\"http://localhost:5010/api/parseDocument?renderFormat=all\",\n",
+    ")\n",
+    "docs = loader.load()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "998649675f14c50e",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-03-28T23:05:28.558467Z",
+     "start_time": "2024-03-28T23:05:28.543132Z"
+    },
+    "collapsed": false
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "'Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models\\n | Yijia Shao | Yucheng Jiang | Theodore A. Kanell | Peter Xu\\n | --- | --- | --- | ---\\n |  | Omar Khattab | Monica S. Lam | \\n\\nStanford University {shaoyj, yuchengj, tkanell, peterxu, okhattab}@stanford.edu lam@cs.stanford.edu\\nAbstract\\nWe study how to apply large language models to write grounded and organized long'"
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "docs[0].page_content[:400]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "7fec7a95023ea8e9",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-03-28T23:05:39.207693Z",
+     "start_time": "2024-03-28T23:05:39.199663Z"
+    },
+    "collapsed": false
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "1"
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(docs)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 2
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython2",
+   "version": "2.7.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/integrations/document_loaders/microsoft_excel.ipynb

@@ -43,13 +43,60 @@
     "docs[0]"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "729ab1a2",
+   "metadata": {},
+   "source": [
+    "## Using Azure AI Document Intelligence\n",
+    "\n",
+    ">[Azure AI Document Intelligence](https://aka.ms/doc-intelligence) (formerly known as `Azure Form Recognizer`) is machine-learning \n",
+    ">based service that extracts texts (including handwriting), tables, document structures (e.g., titles, section headings, etc.) and key-value-pairs from\n",
+    ">digital or scanned PDFs, images, Office and HTML files.\n",
+    ">\n",
+    ">Document Intelligence supports `PDF`, `JPEG/JPG`, `PNG`, `BMP`, `TIFF`, `HEIF`, `DOCX`, `XLSX`, `PPTX` and `HTML`.\n",
+    "\n",
+    "This current implementation of a loader using `Document Intelligence` can incorporate content page-wise and turn it into LangChain documents. The default output format is markdown, which can be easily chained with `MarkdownHeaderTextSplitter` for semantic document chunking. You can also use `mode=\"single\"` or `mode=\"page\"` to return pure texts in a single page or document split by page.\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "fbe5c77d",
+   "metadata": {},
+   "source": [
+    "### Prerequisite\n",
+    "\n",
+    "An Azure AI Document Intelligence resource in one of the 3 preview regions: **East US**, **West US2**, **West Europe** - follow [this document](https://learn.microsoft.com/azure/ai-services/document-intelligence/create-document-intelligence-resource?view=doc-intel-4.0.0) to create one if you don't have. You will be passing `<endpoint>` and `<key>` as parameters to the loader."
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "9ab94bde",
+   "id": "fda529f8",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "%pip install --upgrade --quiet  langchain langchain-community azure-ai-documentintelligence"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "aa008547",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_community.document_loaders import AzureAIDocumentIntelligenceLoader\n",
+    "\n",
+    "file_path = \"<filepath>\"\n",
+    "endpoint = \"<endpoint>\"\n",
+    "key = \"<key>\"\n",
+    "loader = AzureAIDocumentIntelligenceLoader(\n",
+    "    api_endpoint=endpoint, api_key=key, file_path=file_path, api_model=\"prebuilt-layout\"\n",
+    ")\n",
+    "\n",
+    "documents = loader.load()"
+   ]
   }
  ],
  "metadata": {

docs/docs/integrations/document_loaders/microsoft_powerpoint.ipynb

@@ -76,7 +76,7 @@
    "id": "525d6b67",
    "metadata": {},
    "source": [
-    "## Retain Elements\n",
+    "### Retain Elements\n",
     "\n",
     "Under the hood, `Unstructured` creates different \"elements\" for different chunks of text. By default we combine those together, but you can easily keep that separation by specifying `mode=\"elements\"`."
    ]
@@ -124,13 +124,60 @@
     "data[0]"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "b97180c2",
+   "metadata": {},
+   "source": [
+    "## Using Azure AI Document Intelligence\n",
+    "\n",
+    ">[Azure AI Document Intelligence](https://aka.ms/doc-intelligence) (formerly known as `Azure Form Recognizer`) is machine-learning \n",
+    ">based service that extracts texts (including handwriting), tables, document structures (e.g., titles, section headings, etc.) and key-value-pairs from\n",
+    ">digital or scanned PDFs, images, Office and HTML files.\n",
+    ">\n",
+    ">Document Intelligence supports `PDF`, `JPEG/JPG`, `PNG`, `BMP`, `TIFF`, `HEIF`, `DOCX`, `XLSX`, `PPTX` and `HTML`.\n",
+    "\n",
+    "This current implementation of a loader using `Document Intelligence` can incorporate content page-wise and turn it into LangChain documents. The default output format is markdown, which can be easily chained with `MarkdownHeaderTextSplitter` for semantic document chunking. You can also use `mode=\"single\"` or `mode=\"page\"` to return pure texts in a single page or document split by page.\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "11851fd0",
+   "metadata": {},
+   "source": [
+    "## Prerequisite\n",
+    "\n",
+    "An Azure AI Document Intelligence resource in one of the 3 preview regions: **East US**, **West US2**, **West Europe** - follow [this document](https://learn.microsoft.com/azure/ai-services/document-intelligence/create-document-intelligence-resource?view=doc-intel-4.0.0) to create one if you don't have. You will be passing `<endpoint>` and `<key>` as parameters to the loader."
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
    "id": "381d4139",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "%pip install --upgrade --quiet  langchain langchain-community azure-ai-documentintelligence"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "077525b8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_community.document_loaders import AzureAIDocumentIntelligenceLoader\n",
+    "\n",
+    "file_path = \"<filepath>\"\n",
+    "endpoint = \"<endpoint>\"\n",
+    "key = \"<key>\"\n",
+    "loader = AzureAIDocumentIntelligenceLoader(\n",
+    "    api_endpoint=endpoint, api_key=key, file_path=file_path, api_model=\"prebuilt-layout\"\n",
+    ")\n",
+    "\n",
+    "documents = loader.load()"
+   ]
   }
  ],
  "metadata": {

docs/docs/integrations/document_loaders/microsoft_word.ipynb

@@ -147,7 +147,7 @@
    "id": "525d6b67",
    "metadata": {},
    "source": [
-    "## Retain Elements\n",
+    "### Retain Elements\n",
     "\n",
     "Under the hood, Unstructured creates different \"elements\" for different chunks of text. By default we combine those together, but you can easily keep that separation by specifying `mode=\"elements\"`."
    ]
@@ -192,6 +192,59 @@
    "source": [
     "data[0]"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c1f3b83f",
+   "metadata": {},
+   "source": [
+    "## Using Azure AI Document Intelligence\n",
+    "\n",
+    ">[Azure AI Document Intelligence](https://aka.ms/doc-intelligence) (formerly known as `Azure Form Recognizer`) is machine-learning \n",
+    ">based service that extracts texts (including handwriting), tables, document structures (e.g., titles, section headings, etc.) and key-value-pairs from\n",
+    ">digital or scanned PDFs, images, Office and HTML files.\n",
+    ">\n",
+    ">Document Intelligence supports `PDF`, `JPEG/JPG`, `PNG`, `BMP`, `TIFF`, `HEIF`, `DOCX`, `XLSX`, `PPTX` and `HTML`.\n",
+    "\n",
+    "This current implementation of a loader using `Document Intelligence` can incorporate content page-wise and turn it into LangChain documents. The default output format is markdown, which can be easily chained with `MarkdownHeaderTextSplitter` for semantic document chunking. You can also use `mode=\"single\"` or `mode=\"page\"` to return pure texts in a single page or document split by page.\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a5bd47c2",
+   "metadata": {},
+   "source": [
+    "## Prerequisite\n",
+    "\n",
+    "An Azure AI Document Intelligence resource in one of the 3 preview regions: **East US**, **West US2**, **West Europe** - follow [this document](https://learn.microsoft.com/azure/ai-services/document-intelligence/create-document-intelligence-resource?view=doc-intel-4.0.0) to create one if you don't have. You will be passing `<endpoint>` and `<key>` as parameters to the loader."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "71cbdfe0",
+   "metadata": {},
+   "source": [
+    "%pip install --upgrade --quiet  langchain langchain-community azure-ai-documentintelligence"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "691bd9e8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_community.document_loaders import AzureAIDocumentIntelligenceLoader\n",
+    "\n",
+    "file_path = \"<filepath>\"\n",
+    "endpoint = \"<endpoint>\"\n",
+    "key = \"<key>\"\n",
+    "loader = AzureAIDocumentIntelligenceLoader(\n",
+    "    api_endpoint=endpoint, api_key=key, file_path=file_path, api_model=\"prebuilt-layout\"\n",
+    ")\n",
+    "\n",
+    "documents = loader.load()"
+   ]
   }
  ],
  "metadata": {

docs/docs/integrations/document_loaders/oracleadb_loader.ipynb

@@ -0,0 +1,165 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "source": [
+    "# Oracle Autonomous Database\n",
+    "\n",
+    "Oracle autonomous database is a cloud database that uses machine learning to automate database tuning, security, backups, updates, and other routine management tasks traditionally performed by DBAs.\n",
+    "\n",
+    "This notebook covers how to load documents from oracle autonomous database, the loader supports connection with connection string or tns configuration.\n",
+    "\n",
+    "## Prerequisites\n",
+    "1. Database runs in a 'Thin' mode:\n",
+    "   https://python-oracledb.readthedocs.io/en/latest/user_guide/appendix_b.html\n",
+    "2. `pip install oracledb`:\n",
+    "   https://python-oracledb.readthedocs.io/en/latest/user_guide/installation.html"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "## Instructions"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "outputs": [],
+   "source": [
+    "pip install oracledb"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "is_executing": true
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "outputs": [],
+   "source": [
+    "from langchain_community.document_loaders import OracleAutonomousDatabaseLoader\n",
+    "from settings import s"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "is_executing": true
+    }
+   }
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "With mutual TLS authentication (mTLS), wallet_location and wallet_password are required to create the connection, user can create connection by providing either connection string or tns configuration details."
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "outputs": [],
+   "source": [
+    "SQL_QUERY = \"select prod_id, time_id from sh.costs fetch first 5 rows only\"\n",
+    "\n",
+    "doc_loader_1 = OracleAutonomousDatabaseLoader(\n",
+    "    query=SQL_QUERY,\n",
+    "    user=s.USERNAME,\n",
+    "    password=s.PASSWORD,\n",
+    "    schema=s.SCHEMA,\n",
+    "    config_dir=s.CONFIG_DIR,\n",
+    "    wallet_location=s.WALLET_LOCATION,\n",
+    "    wallet_password=s.PASSWORD,\n",
+    "    tns_name=s.TNS_NAME,\n",
+    ")\n",
+    "doc_1 = doc_loader_1.load()\n",
+    "\n",
+    "doc_loader_2 = OracleAutonomousDatabaseLoader(\n",
+    "    query=SQL_QUERY,\n",
+    "    user=s.USERNAME,\n",
+    "    password=s.PASSWORD,\n",
+    "    schema=s.SCHEMA,\n",
+    "    connection_string=s.CONNECTION_STRING,\n",
+    "    wallet_location=s.WALLET_LOCATION,\n",
+    "    wallet_password=s.PASSWORD,\n",
+    ")\n",
+    "doc_2 = doc_loader_2.load()"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "is_executing": true
+    }
+   }
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "With TLS authentication, wallet_location and wallet_password are not required."
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "outputs": [],
+   "source": [
+    "doc_loader_3 = OracleAutonomousDatabaseLoader(\n",
+    "    query=SQL_QUERY,\n",
+    "    user=s.USERNAME,\n",
+    "    password=s.PASSWORD,\n",
+    "    schema=s.SCHEMA,\n",
+    "    config_dir=s.CONFIG_DIR,\n",
+    "    tns_name=s.TNS_NAME,\n",
+    ")\n",
+    "doc_3 = doc_loader_3.load()\n",
+    "\n",
+    "doc_loader_4 = OracleAutonomousDatabaseLoader(\n",
+    "    query=SQL_QUERY,\n",
+    "    user=s.USERNAME,\n",
+    "    password=s.PASSWORD,\n",
+    "    schema=s.SCHEMA,\n",
+    "    connection_string=s.CONNECTION_STRING,\n",
+    ")\n",
+    "doc_4 = doc_loader_4.load()"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 2
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython2",
+   "version": "2.7.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}

docs/docs/integrations/document_loaders/quip.ipynb

@@ -61,7 +61,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_community.document_loaders import QuipLoader\n",
+    "from langchain_community.document_loaders.quip import QuipLoader\n",
     "\n",
     "loader = QuipLoader(\n",
     "    api_url=\"https://platform.quip.com\", access_token=\"change_me\", request_timeout=60\n",

docs/docs/integrations/document_loaders/sitemap.ipynb

@@ -34,7 +34,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -62,7 +62,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -73,7 +73,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": null,
    "metadata": {},
    "outputs": [
     {
@@ -107,7 +107,7 @@
    "outputs": [],
    "source": [
     "loader = SitemapLoader(\n",
-    "    web_path=\" https://api.python.langchain.com/sitemap.xml\",\n",
+    "    web_path=\"https://api.python.langchain.com/sitemap.xml\",\n",
     "    filter_urls=[\"https://api.python.langchain.com/en/latest\"],\n",
     ")\n",
     "documents = loader.load()"
@@ -247,7 +247,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.18"
+   "version": "3.11.4"
   }
  },
  "nbformat": 4,

docs/docs/integrations/document_transformers/ai21_semantic_text_splitter.ipynb

@@ -0,0 +1,466 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "b9bba344bbe0b4bd",
+   "metadata": {
+    "collapsed": false
+   },
+   "source": [
+    "# AI21SemanticTextSplitter\n",
+    "\n",
+    "This example goes over how to use AI21SemanticTextSplitter in LangChain."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d8e4cdb63fbc34ec",
+   "metadata": {
+    "collapsed": false
+   },
+   "source": [
+    "## Installation"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b09bb1cd2c7e036a",
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [],
+   "source": [
+    "pip install langchain-ai21"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ba1d80fe8d82be89",
+   "metadata": {
+    "collapsed": false
+   },
+   "source": [
+    "## Environment Setup\n",
+    "\n",
+    "We'll need to get a AI21 API key and set the AI21_API_KEY environment variable:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "844b8f744d22bcb6",
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "from getpass import getpass\n",
+    "\n",
+    "os.environ[\"AI21_API_KEY\"] = getpass()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3e670b278e6b2b9e",
+   "metadata": {
+    "collapsed": false
+   },
+   "source": [
+    "## Example Usages"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f61c5c981f01ad31",
+   "metadata": {
+    "collapsed": false
+   },
+   "source": [
+    "### Splitting text by semantic meaning"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e7da988112712cf3",
+   "metadata": {
+    "collapsed": false
+   },
+   "source": [
+    "This example shows how to use AI21SemanticTextSplitter to split a text into chunks based on semantic meaning."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1d82b65c9b8684f3",
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [],
+   "source": [
+    "from langchain_ai21 import AI21SemanticTextSplitter\n",
+    "\n",
+    "TEXT = (\n",
+    "    \"We’ve all experienced reading long, tedious, and boring pieces of text - financial reports, \"\n",
+    "    \"legal documents, or terms and conditions (though, who actually reads those terms and conditions to be honest?).\\n\"\n",
+    "    \"Imagine a company that employs hundreds of thousands of employees. In today's information \"\n",
+    "    \"overload age, nearly 30% of the workday is spent dealing with documents. There's no surprise \"\n",
+    "    \"here, given that some of these documents are long and convoluted on purpose (did you know that \"\n",
+    "    \"reading through all your privacy policies would take almost a quarter of a year?). Aside from \"\n",
+    "    \"inefficiency, workers may simply refrain from reading some documents (for example, Only 16% of \"\n",
+    "    \"Employees Read Their Employment Contracts Entirely Before Signing!).\\nThis is where AI-driven summarization \"\n",
+    "    \"tools can be helpful: instead of reading entire documents, which is tedious and time-consuming, \"\n",
+    "    \"users can (ideally) quickly extract relevant information from a text. With large language models, \"\n",
+    "    \"the development of those tools is easier than ever, and you can offer your users a summary that is \"\n",
+    "    \"specifically tailored to their preferences.\\nLarge language models naturally follow patterns in input \"\n",
+    "    \"(prompt), and provide coherent completion that follows the same patterns. For that, we want to feed \"\n",
+    "    'them with several examples in the input (\"few-shot prompt\"), so they can follow through. '\n",
+    "    \"The process of creating the correct prompt for your problem is called prompt engineering, \"\n",
+    "    \"and you can read more about it here.\"\n",
+    ")\n",
+    "\n",
+    "semantic_text_splitter = AI21SemanticTextSplitter()\n",
+    "chunks = semantic_text_splitter.split_text(TEXT)\n",
+    "\n",
+    "print(f\"The text has been split into {len(chunks)} chunks.\")\n",
+    "for chunk in chunks:\n",
+    "    print(chunk)\n",
+    "    print(\"====\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2e8d1fcf818a8a81",
+   "metadata": {
+    "collapsed": false
+   },
+   "source": [
+    "### Splitting text by semantic meaning with merge"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c307abbc216fe89f",
+   "metadata": {
+    "collapsed": false
+   },
+   "source": [
+    "This example shows how to use AI21SemanticTextSplitter to split a text into chunks based on semantic meaning, then merging the chunks based on `chunk_size`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5651c581fcc1ff02",
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [],
+   "source": [
+    "from langchain_ai21 import AI21SemanticTextSplitter\n",
+    "\n",
+    "TEXT = (\n",
+    "    \"We’ve all experienced reading long, tedious, and boring pieces of text - financial reports, \"\n",
+    "    \"legal documents, or terms and conditions (though, who actually reads those terms and conditions to be honest?).\\n\"\n",
+    "    \"Imagine a company that employs hundreds of thousands of employees. In today's information \"\n",
+    "    \"overload age, nearly 30% of the workday is spent dealing with documents. There's no surprise \"\n",
+    "    \"here, given that some of these documents are long and convoluted on purpose (did you know that \"\n",
+    "    \"reading through all your privacy policies would take almost a quarter of a year?). Aside from \"\n",
+    "    \"inefficiency, workers may simply refrain from reading some documents (for example, Only 16% of \"\n",
+    "    \"Employees Read Their Employment Contracts Entirely Before Signing!).\\nThis is where AI-driven summarization \"\n",
+    "    \"tools can be helpful: instead of reading entire documents, which is tedious and time-consuming, \"\n",
+    "    \"users can (ideally) quickly extract relevant information from a text. With large language models, \"\n",
+    "    \"the development of those tools is easier than ever, and you can offer your users a summary that is \"\n",
+    "    \"specifically tailored to their preferences.\\nLarge language models naturally follow patterns in input \"\n",
+    "    \"(prompt), and provide coherent completion that follows the same patterns. For that, we want to feed \"\n",
+    "    'them with several examples in the input (\"few-shot prompt\"), so they can follow through. '\n",
+    "    \"The process of creating the correct prompt for your problem is called prompt engineering, \"\n",
+    "    \"and you can read more about it here.\"\n",
+    ")\n",
+    "\n",
+    "semantic_text_splitter_chunks = AI21SemanticTextSplitter(chunk_size=1000)\n",
+    "chunks = semantic_text_splitter_chunks.split_text(TEXT)\n",
+    "\n",
+    "print(f\"The text has been split into {len(chunks)} chunks.\")\n",
+    "for chunk in chunks:\n",
+    "    print(chunk)\n",
+    "    print(\"====\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b464db855e547cbb",
+   "metadata": {
+    "collapsed": false
+   },
+   "source": [
+    "### Splitting text to documents"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4410e8467012b193",
+   "metadata": {
+    "collapsed": false
+   },
+   "source": [
+    "This example shows how to use AI21SemanticTextSplitter to split a text into Documents based on semantic meaning. The metadata will contain a type for each document."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3cf131d9be910115",
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [],
+   "source": [
+    "from langchain_ai21 import AI21SemanticTextSplitter\n",
+    "\n",
+    "TEXT = (\n",
+    "    \"We’ve all experienced reading long, tedious, and boring pieces of text - financial reports, \"\n",
+    "    \"legal documents, or terms and conditions (though, who actually reads those terms and conditions to be honest?).\\n\"\n",
+    "    \"Imagine a company that employs hundreds of thousands of employees. In today's information \"\n",
+    "    \"overload age, nearly 30% of the workday is spent dealing with documents. There's no surprise \"\n",
+    "    \"here, given that some of these documents are long and convoluted on purpose (did you know that \"\n",
+    "    \"reading through all your privacy policies would take almost a quarter of a year?). Aside from \"\n",
+    "    \"inefficiency, workers may simply refrain from reading some documents (for example, Only 16% of \"\n",
+    "    \"Employees Read Their Employment Contracts Entirely Before Signing!).\\nThis is where AI-driven summarization \"\n",
+    "    \"tools can be helpful: instead of reading entire documents, which is tedious and time-consuming, \"\n",
+    "    \"users can (ideally) quickly extract relevant information from a text. With large language models, \"\n",
+    "    \"the development of those tools is easier than ever, and you can offer your users a summary that is \"\n",
+    "    \"specifically tailored to their preferences.\\nLarge language models naturally follow patterns in input \"\n",
+    "    \"(prompt), and provide coherent completion that follows the same patterns. For that, we want to feed \"\n",
+    "    'them with several examples in the input (\"few-shot prompt\"), so they can follow through. '\n",
+    "    \"The process of creating the correct prompt for your problem is called prompt engineering, \"\n",
+    "    \"and you can read more about it here.\"\n",
+    ")\n",
+    "\n",
+    "semantic_text_splitter = AI21SemanticTextSplitter()\n",
+    "documents = semantic_text_splitter.split_text_to_documents(TEXT)\n",
+    "\n",
+    "print(f\"The text has been split into {len(documents)} Documents.\")\n",
+    "for doc in documents:\n",
+    "    print(f\"type: {doc.metadata['source_type']}\")\n",
+    "    print(f\"text: {doc.page_content}\")\n",
+    "    print(\"====\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b544ba21335d01a6",
+   "metadata": {
+    "collapsed": false
+   },
+   "source": [
+    "### Creating Documents with Metadata"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c67f8c3ad89b8ad2",
+   "metadata": {
+    "collapsed": false
+   },
+   "source": [
+    "This example shows how to use AI21SemanticTextSplitter to create Documents from texts, and adding custom Metadata to each Document."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "fe222d0e85249bda",
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [],
+   "source": [
+    "from langchain_ai21 import AI21SemanticTextSplitter\n",
+    "\n",
+    "TEXT = (\n",
+    "    \"We’ve all experienced reading long, tedious, and boring pieces of text - financial reports, \"\n",
+    "    \"legal documents, or terms and conditions (though, who actually reads those terms and conditions to be honest?).\\n\"\n",
+    "    \"Imagine a company that employs hundreds of thousands of employees. In today's information \"\n",
+    "    \"overload age, nearly 30% of the workday is spent dealing with documents. There's no surprise \"\n",
+    "    \"here, given that some of these documents are long and convoluted on purpose (did you know that \"\n",
+    "    \"reading through all your privacy policies would take almost a quarter of a year?). Aside from \"\n",
+    "    \"inefficiency, workers may simply refrain from reading some documents (for example, Only 16% of \"\n",
+    "    \"Employees Read Their Employment Contracts Entirely Before Signing!).\\nThis is where AI-driven summarization \"\n",
+    "    \"tools can be helpful: instead of reading entire documents, which is tedious and time-consuming, \"\n",
+    "    \"users can (ideally) quickly extract relevant information from a text. With large language models, \"\n",
+    "    \"the development of those tools is easier than ever, and you can offer your users a summary that is \"\n",
+    "    \"specifically tailored to their preferences.\\nLarge language models naturally follow patterns in input \"\n",
+    "    \"(prompt), and provide coherent completion that follows the same patterns. For that, we want to feed \"\n",
+    "    'them with several examples in the input (\"few-shot prompt\"), so they can follow through. '\n",
+    "    \"The process of creating the correct prompt for your problem is called prompt engineering, \"\n",
+    "    \"and you can read more about it here.\"\n",
+    ")\n",
+    "\n",
+    "semantic_text_splitter = AI21SemanticTextSplitter()\n",
+    "texts = [TEXT]\n",
+    "documents = semantic_text_splitter.create_documents(\n",
+    "    texts=texts, metadatas=[{\"pikachu\": \"pika pika\"}]\n",
+    ")\n",
+    "\n",
+    "print(f\"The text has been split into {len(documents)} Documents.\")\n",
+    "for doc in documents:\n",
+    "    print(f\"metadata: {doc.metadata}\")\n",
+    "    print(f\"text: {doc.page_content}\")\n",
+    "    print(\"====\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f8b5682c34142319",
+   "metadata": {
+    "collapsed": false
+   },
+   "source": [
+    "### Splitting text to documents with start index"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "359ea797c03ece85",
+   "metadata": {
+    "collapsed": false
+   },
+   "source": [
+    "This example shows how to use AI21SemanticTextSplitter to split a text into Documents based on semantic meaning. The metadata will contain a start index for each document.\n",
+    "**Note** that the start index provides an indication of the order of the chunks rather than the actual start index for each chunk."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2dc39002f0c25784",
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [],
+   "source": [
+    "from langchain_ai21 import AI21SemanticTextSplitter\n",
+    "\n",
+    "TEXT = (\n",
+    "    \"We’ve all experienced reading long, tedious, and boring pieces of text - financial reports, \"\n",
+    "    \"legal documents, or terms and conditions (though, who actually reads those terms and conditions to be honest?).\\n\"\n",
+    "    \"Imagine a company that employs hundreds of thousands of employees. In today's information \"\n",
+    "    \"overload age, nearly 30% of the workday is spent dealing with documents. There's no surprise \"\n",
+    "    \"here, given that some of these documents are long and convoluted on purpose (did you know that \"\n",
+    "    \"reading through all your privacy policies would take almost a quarter of a year?). Aside from \"\n",
+    "    \"inefficiency, workers may simply refrain from reading some documents (for example, Only 16% of \"\n",
+    "    \"Employees Read Their Employment Contracts Entirely Before Signing!).\\nThis is where AI-driven summarization \"\n",
+    "    \"tools can be helpful: instead of reading entire documents, which is tedious and time-consuming, \"\n",
+    "    \"users can (ideally) quickly extract relevant information from a text. With large language models, \"\n",
+    "    \"the development of those tools is easier than ever, and you can offer your users a summary that is \"\n",
+    "    \"specifically tailored to their preferences.\\nLarge language models naturally follow patterns in input \"\n",
+    "    \"(prompt), and provide coherent completion that follows the same patterns. For that, we want to feed \"\n",
+    "    'them with several examples in the input (\"few-shot prompt\"), so they can follow through. '\n",
+    "    \"The process of creating the correct prompt for your problem is called prompt engineering, \"\n",
+    "    \"and you can read more about it here.\"\n",
+    ")\n",
+    "\n",
+    "semantic_text_splitter = AI21SemanticTextSplitter(add_start_index=True)\n",
+    "documents = semantic_text_splitter.create_documents(texts=[TEXT])\n",
+    "print(f\"The text has been split into {len(documents)} Documents.\")\n",
+    "for doc in documents:\n",
+    "    print(f\"start_index: {doc.metadata['start_index']}\")\n",
+    "    print(f\"text: {doc.page_content}\")\n",
+    "    print(\"====\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b62939cc5803b9fb",
+   "metadata": {
+    "collapsed": false
+   },
+   "source": [
+    "### Splitting documents"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "44162d340c0de5fb",
+   "metadata": {
+    "collapsed": false
+   },
+   "source": [
+    "This example shows how to use AI21SemanticTextSplitter to split a list of Documents into chunks based on semantic meaning."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8950c8e4e1208bf6",
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [],
+   "source": [
+    "from langchain_ai21 import AI21SemanticTextSplitter\n",
+    "from langchain_core.documents import Document\n",
+    "\n",
+    "TEXT = (\n",
+    "    \"We’ve all experienced reading long, tedious, and boring pieces of text - financial reports, \"\n",
+    "    \"legal documents, or terms and conditions (though, who actually reads those terms and conditions to be honest?).\\n\"\n",
+    "    \"Imagine a company that employs hundreds of thousands of employees. In today's information \"\n",
+    "    \"overload age, nearly 30% of the workday is spent dealing with documents. There's no surprise \"\n",
+    "    \"here, given that some of these documents are long and convoluted on purpose (did you know that \"\n",
+    "    \"reading through all your privacy policies would take almost a quarter of a year?). Aside from \"\n",
+    "    \"inefficiency, workers may simply refrain from reading some documents (for example, Only 16% of \"\n",
+    "    \"Employees Read Their Employment Contracts Entirely Before Signing!).\\nThis is where AI-driven summarization \"\n",
+    "    \"tools can be helpful: instead of reading entire documents, which is tedious and time-consuming, \"\n",
+    "    \"users can (ideally) quickly extract relevant information from a text. With large language models, \"\n",
+    "    \"the development of those tools is easier than ever, and you can offer your users a summary that is \"\n",
+    "    \"specifically tailored to their preferences.\\nLarge language models naturally follow patterns in input \"\n",
+    "    \"(prompt), and provide coherent completion that follows the same patterns. For that, we want to feed \"\n",
+    "    'them with several examples in the input (\"few-shot prompt\"), so they can follow through. '\n",
+    "    \"The process of creating the correct prompt for your problem is called prompt engineering, \"\n",
+    "    \"and you can read more about it here.\"\n",
+    ")\n",
+    "\n",
+    "semantic_text_splitter = AI21SemanticTextSplitter()\n",
+    "document = Document(page_content=TEXT, metadata={\"hello\": \"goodbye\"})\n",
+    "documents = semantic_text_splitter.split_documents([document])\n",
+    "print(f\"The document list has been split into {len(documents)} Documents.\")\n",
+    "for doc in documents:\n",
+    "    print(f\"text: {doc.page_content}\")\n",
+    "    print(f\"metadata: {doc.metadata}\")\n",
+    "    print(\"====\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f8f911b8d9ec22e5",
+   "metadata": {
+    "collapsed": false
+   },
+   "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": "3.10.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/integrations/document_transformers/voyageai-reranker.ipynb

@@ -0,0 +1,465 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "fc0db1bc",
+   "metadata": {},
+   "source": [
+    "# VoyageAI Reranker\n",
+    "\n",
+    ">[Voyage AI](https://www.voyageai.com/) provides cutting-edge embedding/vectorizations models.\n",
+    "\n",
+    "This notebook shows how to use [Voyage AI's rerank endpoint](https://api.voyageai.com/v1/rerank) in a retriever. This builds on top of ideas in the [ContextualCompressionRetriever](/docs/modules/data_connection/retrievers/contextual_compression/)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4f5973bb-7897-4340-a8ce-c3365ee73b2f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install --upgrade --quiet  voyageai\n",
+    "%pip install --upgrade --quiet  langchain-voyageai"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b37bd138-4f3c-4d2c-bc4b-be705ce27a09",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "%pip install --upgrade --quiet  faiss\n",
+    "\n",
+    "# OR  (depending on Python version)\n",
+    "\n",
+    "%pip install --upgrade --quiet  faiss-cpu"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "c47b0b26-6d51-4beb-aedb-ad09740a9a2b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# To obtain your key, create an account on https://www.voyageai.com\n",
+    "\n",
+    "import getpass\n",
+    "import os\n",
+    "\n",
+    "os.environ[\"VOYAGE_API_KEY\"] = getpass.getpass(\"Voyage AI API Key:\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "6fa3d916",
+   "metadata": {
+    "jp-MarkdownHeadingCollapsed": true,
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "# Helper function for printing docs\n",
+    "\n",
+    "\n",
+    "def pretty_print_docs(docs):\n",
+    "    print(\n",
+    "        f\"\\n{'-' * 100}\\n\".join(\n",
+    "            [f\"Document {i+1}:\\n\\n\" + d.page_content for i, d in enumerate(docs)]\n",
+    "        )\n",
+    "    )"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6fa3d916",
+   "metadata": {
+    "jp-MarkdownHeadingCollapsed": true,
+    "tags": []
+   },
+   "source": [
+    "## Set up the base vector store retriever\n",
+    "Let's start by initializing a simple vector store retriever and storing the 2023 State of the Union speech (in chunks). We can set up the retriever to retrieve a high number (20) of docs."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "b7648612",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Document 1:\n",
+      "\n",
+      "One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court.\n",
+      "\n",
+      "And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Document 2:\n",
+      "\n",
+      "As I said last year, especially to our younger transgender Americans, I will always have your back as your President, so you can be yourself and reach your God-given potential.\n",
+      "\n",
+      "While it often appears that we never agree, that isn’t true. I signed 80 bipartisan bills into law last year. From preventing government shutdowns to protecting Asian-Americans from still-too-common hate crimes to reforming military justice.\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Document 3:\n",
+      "\n",
+      "We cannot let this happen.\n",
+      "\n",
+      "Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections.\n",
+      "\n",
+      "Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service.\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Document 4:\n",
+      "\n",
+      "He will never extinguish their love of freedom. He will never weaken the resolve of the free world.\n",
+      "\n",
+      "We meet tonight in an America that has lived through two of the hardest years this nation has ever faced.\n",
+      "\n",
+      "The pandemic has been punishing.\n",
+      "\n",
+      "And so many families are living paycheck to paycheck, struggling to keep up with the rising cost of food, gas, housing, and so much more.\n",
+      "\n",
+      "I understand.\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Document 5:\n",
+      "\n",
+      "As I’ve told Xi Jinping, it is never a good bet to bet against the American people.\n",
+      "\n",
+      "We’ll create good jobs for millions of Americans, modernizing roads, airports, ports, and waterways all across America.\n",
+      "\n",
+      "And we’ll do it all to withstand the devastating effects of the climate crisis and promote environmental justice.\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Document 6:\n",
+      "\n",
+      "I understand.\n",
+      "\n",
+      "I remember when my Dad had to leave our home in Scranton, Pennsylvania to find work. I grew up in a family where if the price of food went up, you felt it.\n",
+      "\n",
+      "That’s why one of the first things I did as President was fight to pass the American Rescue Plan.\n",
+      "\n",
+      "Because people were hurting. We needed to act, and we did.\n",
+      "\n",
+      "Few pieces of legislation have done more in a critical moment in our history to lift us out of crisis.\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Document 7:\n",
+      "\n",
+      "I spoke with their families and told them that we are forever in debt for their sacrifice, and we will carry on their mission to restore the trust and safety every community deserves.\n",
+      "\n",
+      "I’ve worked on these issues a long time.\n",
+      "\n",
+      "I know what works: Investing in crime prevention and community police officers who’ll walk the beat, who’ll know the neighborhood, and who can restore trust and safety.\n",
+      "\n",
+      "So let’s not abandon our streets. Or choose between safety and equal justice.\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Document 8:\n",
+      "\n",
+      "My administration is providing assistance with job training and housing, and now helping lower-income veterans get VA care debt-free.\n",
+      "\n",
+      "Our troops in Iraq and Afghanistan faced many dangers.\n",
+      "\n",
+      "One was stationed at bases and breathing in toxic smoke from “burn pits” that incinerated wastes of war—medical and hazard material, jet fuel, and more.\n",
+      "\n",
+      "When they came home, many of the world’s fittest and best trained warriors were never the same.\n",
+      "\n",
+      "Headaches. Numbness. Dizziness.\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Document 9:\n",
+      "\n",
+      "And tonight, I’m announcing that the Justice Department will name a chief prosecutor for pandemic fraud.\n",
+      "\n",
+      "By the end of this year, the deficit will be down to less than half what it was before I took office.\n",
+      "\n",
+      "The only president ever to cut the deficit by more than one trillion dollars in a single year.\n",
+      "\n",
+      "Lowering your costs also means demanding more competition.\n",
+      "\n",
+      "I’m a capitalist, but capitalism without competition isn’t capitalism.\n",
+      "\n",
+      "It’s exploitation—and it drives up prices.\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Document 10:\n",
+      "\n",
+      "Headaches. Numbness. Dizziness.\n",
+      "\n",
+      "A cancer that would put them in a flag-draped coffin.\n",
+      "\n",
+      "I know.\n",
+      "\n",
+      "One of those soldiers was my son Major Beau Biden.\n",
+      "\n",
+      "We don’t know for sure if a burn pit was the cause of his brain cancer, or the diseases of so many of our troops.\n",
+      "\n",
+      "But I’m committed to finding out everything we can.\n",
+      "\n",
+      "Committed to military families like Danielle Robinson from Ohio.\n",
+      "\n",
+      "The widow of Sergeant First Class Heath Robinson.\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Document 11:\n",
+      "\n",
+      "I recently visited the New York City Police Department days after the funerals of Officer Wilbert Mora and his partner, Officer Jason Rivera.\n",
+      "\n",
+      "They were responding to a 9-1-1 call when a man shot and killed them with a stolen gun.\n",
+      "\n",
+      "Officer Mora was 27 years old.\n",
+      "\n",
+      "Officer Rivera was 22.\n",
+      "\n",
+      "Both Dominican Americans who’d grown up on the same streets they later chose to patrol as police officers.\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Document 12:\n",
+      "\n",
+      "This was a bipartisan effort, and I want to thank the members of both parties who worked to make it happen.\n",
+      "\n",
+      "We’re done talking about infrastructure weeks.\n",
+      "\n",
+      "We’re going to have an infrastructure decade.\n",
+      "\n",
+      "It is going to transform America and put us on a path to win the economic competition of the 21st Century that we face with the rest of the world—particularly with China.\n",
+      "\n",
+      "As I’ve told Xi Jinping, it is never a good bet to bet against the American people.\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Document 13:\n",
+      "\n",
+      "So let’s not abandon our streets. Or choose between safety and equal justice.\n",
+      "\n",
+      "Let’s come together to protect our communities, restore trust, and hold law enforcement accountable.\n",
+      "\n",
+      "That’s why the Justice Department required body cameras, banned chokeholds, and restricted no-knock warrants for its officers.\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Document 14:\n",
+      "\n",
+      "Let’s pass the Paycheck Fairness Act and paid leave.\n",
+      "\n",
+      "Raise the minimum wage to $15 an hour and extend the Child Tax Credit, so no one has to raise a family in poverty.\n",
+      "\n",
+      "Let’s increase Pell Grants and increase our historic support of HBCUs, and invest in what Jill—our First Lady who teaches full-time—calls America’s best-kept secret: community colleges.\n",
+      "\n",
+      "And let’s pass the PRO Act when a majority of workers want to form a union—they shouldn’t be stopped.\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Document 15:\n",
+      "\n",
+      "He met the Ukrainian people.\n",
+      "\n",
+      "From President Zelenskyy to every Ukrainian, their fearlessness, their courage, their determination, inspires the world.\n",
+      "\n",
+      "Groups of citizens blocking tanks with their bodies. Everyone from students to retirees teachers turned soldiers defending their homeland.\n",
+      "\n",
+      "In this struggle as President Zelenskyy said in his speech to the European Parliament “Light will win over darkness.” The Ukrainian Ambassador to the United States is here tonight.\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Document 16:\n",
+      "\n",
+      "To all Americans, I will be honest with you, as I’ve always promised. A Russian dictator, invading a foreign country, has costs around the world.\n",
+      "\n",
+      "And I’m taking robust action to make sure the pain of our sanctions  is targeted at Russia’s economy. And I will use every tool at our disposal to protect American businesses and consumers.\n",
+      "\n",
+      "Tonight, I can announce that the United States has worked with 30 other countries to release 60 Million barrels of oil from reserves around the world.\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Document 17:\n",
+      "\n",
+      "A former top litigator in private practice. A former federal public defender. And from a family of public school educators and police officers. A consensus builder. Since she’s been nominated, she’s received a broad range of support—from the Fraternal Order of Police to former judges appointed by Democrats and Republicans.\n",
+      "\n",
+      "And if we are to advance liberty and justice, we need to secure the Border and fix the immigration system.\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Document 18:\n",
+      "\n",
+      "But that trickle-down theory led to weaker economic growth, lower wages, bigger deficits, and the widest gap between those at the top and everyone else in nearly a century.\n",
+      "\n",
+      "Vice President Harris and I ran for office with a new economic vision for America.\n",
+      "\n",
+      "Invest in America. Educate Americans. Grow the workforce. Build the economy from the bottom up\n",
+      "and the middle out, not from the top down.\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Document 19:\n",
+      "\n",
+      "Every Administration says they’ll do it, but we are actually doing it.\n",
+      "\n",
+      "We will buy American to make sure everything from the deck of an aircraft carrier to the steel on highway guardrails are made in America.\n",
+      "\n",
+      "But to compete for the best jobs of the future, we also need to level the playing field with China and other competitors.\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Document 20:\n",
+      "\n",
+      "The only nation that can be defined by a single word: possibilities.\n",
+      "\n",
+      "So on this night, in our 245th year as a nation, I have come to report on the State of the Union.\n",
+      "\n",
+      "And my report is this: the State of the Union is strong—because you, the American people, are strong.\n",
+      "\n",
+      "We are stronger today than we were a year ago.\n",
+      "\n",
+      "And we will be stronger a year from now than we are today.\n",
+      "\n",
+      "Now is our moment to meet and overcome the challenges of our time.\n",
+      "\n",
+      "And we will, as one people.\n",
+      "\n",
+      "One America.\n"
+     ]
+    }
+   ],
+   "source": [
+    "from langchain_community.document_loaders import TextLoader\n",
+    "from langchain_community.vectorstores import FAISS\n",
+    "from langchain_text_splitters import RecursiveCharacterTextSplitter\n",
+    "from langchain_voyageai import VoyageEmbeddings\n",
+    "\n",
+    "documents = TextLoader(\"../../modules/state_of_the_union.txt\").load()\n",
+    "text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=100)\n",
+    "texts = text_splitter.split_documents(documents)\n",
+    "retriever = FAISS.from_documents(\n",
+    "    texts, VoyageEmbeddings(model=\"voyage-2\")\n",
+    ").as_retriever(search_kwargs={\"k\": 20})\n",
+    "\n",
+    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
+    "docs = retriever.get_relevant_documents(query)\n",
+    "pretty_print_docs(docs)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b7648612",
+   "metadata": {},
+   "source": [
+    "## Doing reranking with VoyageAIRerank\n",
+    "Now let's wrap our base retriever with a `ContextualCompressionRetriever`. We'll add an `VoyageAIRerank`, uses the Voyage AI rerank endpoint to rerank the returned results."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "b83dfedb",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Document 1:\n",
+      "\n",
+      "One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court.\n",
+      "\n",
+      "And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Document 2:\n",
+      "\n",
+      "So let’s not abandon our streets. Or choose between safety and equal justice.\n",
+      "\n",
+      "Let’s come together to protect our communities, restore trust, and hold law enforcement accountable.\n",
+      "\n",
+      "That’s why the Justice Department required body cameras, banned chokeholds, and restricted no-knock warrants for its officers.\n",
+      "----------------------------------------------------------------------------------------------------\n",
+      "Document 3:\n",
+      "\n",
+      "I spoke with their families and told them that we are forever in debt for their sacrifice, and we will carry on their mission to restore the trust and safety every community deserves.\n",
+      "\n",
+      "I’ve worked on these issues a long time.\n",
+      "\n",
+      "I know what works: Investing in crime prevention and community police officers who’ll walk the beat, who’ll know the neighborhood, and who can restore trust and safety.\n",
+      "\n",
+      "So let’s not abandon our streets. Or choose between safety and equal justice.\n"
+     ]
+    }
+   ],
+   "source": [
+    "from langchain.retrievers import ContextualCompressionRetriever\n",
+    "from langchain_openai import OpenAI\n",
+    "from langchain_voyageai import VoyageAIRerank\n",
+    "\n",
+    "llm = OpenAI(temperature=0)\n",
+    "compressor = VoyageAIRerank(\n",
+    "    model=\"rerank-lite-1\", voyageai_api_key=os.environ[\"VOYAGE_API_KEY\"], top_k=3\n",
+    ")\n",
+    "compression_retriever = ContextualCompressionRetriever(\n",
+    "    base_compressor=compressor, base_retriever=retriever\n",
+    ")\n",
+    "\n",
+    "compressed_docs = compression_retriever.get_relevant_documents(\n",
+    "    \"What did the president say about Ketanji Jackson Brown\"\n",
+    ")\n",
+    "pretty_print_docs(compressed_docs)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b83dfedb",
+   "metadata": {},
+   "source": [
+    "You can of course use this retriever within a QA pipeline"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "367dafe0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.chains import RetrievalQA"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "ae697ca4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chain = RetrievalQA.from_chain_type(\n",
+    "    llm=OpenAI(temperature=0), retriever=compression_retriever\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "46ee62fc",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'query': 'What did the president say about Ketanji Brown Jackson',\n",
+       " 'result': \" The president nominated Ketanji Brown Jackson to serve on the United States Supreme Court. \"}"
+      ]
+     },
+     "execution_count": 19,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain({\"query\": query})"
+   ]
+  }
+ ],
+ "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": "3.11.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/integrations/llms/aleph_alpha.ipynb

@@ -58,8 +58,8 @@
    },
    "outputs": [],
    "source": [
-    "from langchain.prompts import PromptTemplate\n",
-    "from langchain_community.llms import AlephAlpha"
+    "from langchain_community.llms import AlephAlpha\n",
+    "from langchain_core.prompts import PromptTemplate"
    ]
   },
   {

docs/docs/integrations/llms/anyscale.ipynb

@@ -49,8 +49,8 @@
    "outputs": [],
    "source": [
     "from langchain.chains import LLMChain\n",
-    "from langchain.prompts import PromptTemplate\n",
-    "from langchain_community.llms import Anyscale"
+    "from langchain_community.llms import Anyscale\n",
+    "from langchain_core.prompts import PromptTemplate"
    ]
   },
   {

docs/docs/integrations/llms/aphrodite.ipynb

@@ -146,7 +146,7 @@
    ],
    "source": [
     "from langchain.chains import LLMChain\n",
-    "from langchain.prompts import PromptTemplate\n",
+    "from langchain_core.prompts import PromptTemplate\n",
     "\n",
     "template = \"\"\"Question: {question}\n",
     "\n",

docs/docs/integrations/llms/azure_ml.ipynb

@@ -29,7 +29,7 @@
     "You must [deploy a model on Azure ML](https://learn.microsoft.com/en-us/azure/machine-learning/how-to-use-foundation-models?view=azureml-api-2#deploying-foundation-models-to-endpoints-for-inferencing) or [to Azure AI studio](https://learn.microsoft.com/en-us/azure/ai-studio/how-to/deploy-models-open) and obtain the following parameters:\n",
     "\n",
     "* `endpoint_url`: The REST endpoint url provided by the endpoint.\n",
-    "* `endpoint_api_type`: Use `endpoint_type='realtime'` when deploying models to **Realtime endpoints** (hosted managed infrastructure). Use `endpoint_type='serverless'` when deploying models using the **Pay-as-you-go** offering (model as a service).\n",
+    "* `endpoint_api_type`: Use `endpoint_type='dedicated'` when deploying models to **Dedicated endpoints** (hosted managed infrastructure). Use `endpoint_type='serverless'` when deploying models using the **Pay-as-you-go** offering (model as a service).\n",
     "* `endpoint_api_key`: The API key provided by the endpoint.\n",
     "* `deployment_name`: (Optional) The deployment name of the model using the endpoint."
    ]
@@ -45,7 +45,7 @@
     "* `GPT2ContentFormatter`: Formats request and response data for GPT2\n",
     "* `DollyContentFormatter`: Formats request and response data for the Dolly-v2\n",
     "* `HFContentFormatter`: Formats request and response data for text-generation Hugging Face models\n",
-    "* `LLamaContentFormatter`: Formats request and response data for LLaMa2\n",
+    "* `CustomOpenAIContentFormatter`: Formats request and response data for models like LLaMa2 that follow OpenAI API compatible scheme.\n",
     "\n",
     "*Note: `OSSContentFormatter` is being deprecated and replaced with `GPT2ContentFormatter`. The logic is the same but `GPT2ContentFormatter` is a more suitable name. You can still continue to use `OSSContentFormatter` as the changes are backwards compatible.*"
    ]
@@ -72,15 +72,15 @@
    "source": [
     "from langchain_community.llms.azureml_endpoint import (\n",
     "    AzureMLEndpointApiType,\n",
-    "    LlamaContentFormatter,\n",
+    "    CustomOpenAIContentFormatter,\n",
     ")\n",
     "from langchain_core.messages import HumanMessage\n",
     "\n",
     "llm = AzureMLOnlineEndpoint(\n",
     "    endpoint_url=\"https://<your-endpoint>.<your_region>.inference.ml.azure.com/score\",\n",
-    "    endpoint_api_type=AzureMLEndpointApiType.realtime,\n",
+    "    endpoint_api_type=AzureMLEndpointApiType.dedicated,\n",
     "    endpoint_api_key=\"my-api-key\",\n",
-    "    content_formatter=LlamaContentFormatter(),\n",
+    "    content_formatter=CustomOpenAIContentFormatter(),\n",
     "    model_kwargs={\"temperature\": 0.8, \"max_new_tokens\": 400},\n",
     ")\n",
     "response = llm.invoke(\"Write me a song about sparkling water:\")\n",
@@ -119,7 +119,7 @@
    "source": [
     "from langchain_community.llms.azureml_endpoint import (\n",
     "    AzureMLEndpointApiType,\n",
-    "    LlamaContentFormatter,\n",
+    "    CustomOpenAIContentFormatter,\n",
     ")\n",
     "from langchain_core.messages import HumanMessage\n",
     "\n",
@@ -127,7 +127,7 @@
     "    endpoint_url=\"https://<your-endpoint>.<your_region>.inference.ml.azure.com/v1/completions\",\n",
     "    endpoint_api_type=AzureMLEndpointApiType.serverless,\n",
     "    endpoint_api_key=\"my-api-key\",\n",
-    "    content_formatter=LlamaContentFormatter(),\n",
+    "    content_formatter=CustomOpenAIContentFormatter(),\n",
     "    model_kwargs={\"temperature\": 0.8, \"max_new_tokens\": 400},\n",
     ")\n",
     "response = llm.invoke(\"Write me a song about sparkling water:\")\n",
@@ -181,7 +181,7 @@
     "content_formatter = CustomFormatter()\n",
     "\n",
     "llm = AzureMLOnlineEndpoint(\n",
-    "    endpoint_api_type=\"realtime\",\n",
+    "    endpoint_api_type=\"dedicated\",\n",
     "    endpoint_api_key=os.getenv(\"BART_ENDPOINT_API_KEY\"),\n",
     "    endpoint_url=os.getenv(\"BART_ENDPOINT_URL\"),\n",
     "    model_kwargs={\"temperature\": 0.8, \"max_new_tokens\": 400},\n",
@@ -228,8 +228,8 @@
    "outputs": [],
    "source": [
     "from langchain.chains import LLMChain\n",
-    "from langchain.prompts import PromptTemplate\n",
     "from langchain_community.llms.azureml_endpoint import DollyContentFormatter\n",
+    "from langchain_core.prompts import PromptTemplate\n",
     "\n",
     "formatter_template = \"Write a {word_count} word essay about {topic}.\"\n",
     "\n",

docs/docs/integrations/llms/banana.ipynb

@@ -52,8 +52,8 @@
    "outputs": [],
    "source": [
     "from langchain.chains import LLMChain\n",
-    "from langchain.prompts import PromptTemplate\n",
-    "from langchain_community.llms import Banana"
+    "from langchain_community.llms import Banana\n",
+    "from langchain_core.prompts import PromptTemplate"
    ]
   },
   {

docs/docs/integrations/llms/baseten.ipynb

@@ -94,7 +94,7 @@
    "source": [
     "from langchain.chains import LLMChain\n",
     "from langchain.memory import ConversationBufferWindowMemory\n",
-    "from langchain.prompts import PromptTemplate\n",
+    "from langchain_core.prompts import PromptTemplate\n",
     "\n",
     "template = \"\"\"Assistant is a large language model trained by OpenAI.\n",
     "\n",

docs/docs/integrations/llms/bittensor.ipynb

@@ -82,8 +82,8 @@
    "source": [
     "from langchain.chains import LLMChain\n",
     "from langchain.globals import set_debug\n",
-    "from langchain.prompts import PromptTemplate\n",
     "from langchain_community.llms import NIBittensorLLM\n",
+    "from langchain_core.prompts import PromptTemplate\n",
     "\n",
     "set_debug(True)\n",
     "\n",
@@ -142,8 +142,8 @@
     ")\n",
     "from langchain.chains import LLMChain\n",
     "from langchain.memory import ConversationBufferMemory\n",
-    "from langchain.prompts import PromptTemplate\n",
     "from langchain_community.llms import NIBittensorLLM\n",
+    "from langchain_core.prompts import PromptTemplate\n",
     "\n",
     "memory = ConversationBufferMemory(memory_key=\"chat_history\")\n",
     "\n",

docs/docs/integrations/llms/cerebriumai.ipynb

@@ -45,8 +45,8 @@
     "import os\n",
     "\n",
     "from langchain.chains import LLMChain\n",
-    "from langchain.prompts import PromptTemplate\n",
-    "from langchain_community.llms import CerebriumAI"
+    "from langchain_community.llms import CerebriumAI\n",
+    "from langchain_core.prompts import PromptTemplate"
    ]
   },
   {

docs/docs/integrations/llms/chatglm.ipynb

@@ -41,9 +41,9 @@
    "outputs": [],
    "source": [
     "from langchain.chains import LLMChain\n",
-    "from langchain.prompts import PromptTemplate\n",
     "from langchain.schema.messages import AIMessage\n",
-    "from langchain_community.llms.chatglm3 import ChatGLM3"
+    "from langchain_community.llms.chatglm3 import ChatGLM3\n",
+    "from langchain_core.prompts import PromptTemplate"
    ]
   },
   {
@@ -117,8 +117,8 @@
    "outputs": [],
    "source": [
     "from langchain.chains import LLMChain\n",
-    "from langchain.prompts import PromptTemplate\n",
     "from langchain_community.llms import ChatGLM\n",
+    "from langchain_core.prompts import PromptTemplate\n",
     "\n",
     "# import os"
    ]

docs/docs/integrations/llms/clarifai.ipynb

@@ -87,8 +87,8 @@
    "source": [
     "# Import the required modules\n",
     "from langchain.chains import LLMChain\n",
-    "from langchain.prompts import PromptTemplate\n",
-    "from langchain_community.llms import Clarifai"
+    "from langchain_community.llms import Clarifai\n",
+    "from langchain_core.prompts import PromptTemplate"
    ]
   },
   {

docs/docs/integrations/llms/cloudflare_workersai.ipynb

@@ -19,8 +19,8 @@
    "outputs": [],
    "source": [
     "from langchain.chains import LLMChain\n",
-    "from langchain.prompts import PromptTemplate\n",
     "from langchain_community.llms.cloudflare_workersai import CloudflareWorkersAI\n",
+    "from langchain_core.prompts import PromptTemplate\n",
     "\n",
     "template = \"\"\"Human: {question}\n",
     "\n",

docs/docs/integrations/llms/cohere.ipynb

@@ -24,7 +24,7 @@
     "The integration lives in the `langchain-community` package. We also need to install the `cohere` package itself. We can install these with:\n",
     "\n",
     "```bash\n",
-    "pip install -U langchain-community cohere\n",
+    "pip install -U langchain-community langchain-cohere\n",
     "```\n",
     "\n",
     "We'll also need to get a [Cohere API key](https://cohere.com/) and set the `COHERE_API_KEY` environment variable:"
@@ -39,7 +39,7 @@
    },
    "outputs": [
     {
-     "name": "stdin",
+     "name": "stdout",
      "output_type": "stream",
      "text": [
       " ········\n"
@@ -91,7 +91,7 @@
    },
    "outputs": [],
    "source": [
-    "from langchain_community.llms import Cohere\n",
+    "from langchain_cohere import Cohere\n",
     "from langchain_core.messages import HumanMessage"
    ]
   },
@@ -255,7 +255,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.1"
+   "version": "3.11.7"
   }
  },
  "nbformat": 4,

docs/docs/integrations/llms/ctransformers.ipynb

@@ -103,7 +103,7 @@
    "outputs": [],
    "source": [
     "from langchain.chains import LLMChain\n",
-    "from langchain.prompts import PromptTemplate\n",
+    "from langchain_core.prompts import PromptTemplate\n",
     "\n",
     "template = \"\"\"Question: {question}\n",
     "\n",

docs/docs/integrations/llms/ctranslate2.ipynb

@@ -196,7 +196,7 @@
    ],
    "source": [
     "from langchain.chains import LLMChain\n",
-    "from langchain.prompts import PromptTemplate\n",
+    "from langchain_core.prompts import PromptTemplate\n",
     "\n",
     "template = \"\"\"{question}\n",
     "\n",

docs/docs/integrations/llms/deepinfra.ipynb

@@ -140,7 +140,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.prompts import PromptTemplate\n",
+    "from langchain_core.prompts import PromptTemplate\n",
     "\n",
     "template = \"\"\"Question: {question}\n",
     "\n",

docs/docs/integrations/llms/edenai.ipynb

@@ -98,7 +98,7 @@
    "outputs": [],
    "source": [
     "from langchain.chains import LLMChain\n",
-    "from langchain.prompts import PromptTemplate\n",
+    "from langchain_core.prompts import PromptTemplate\n",
     "\n",
     "llm = EdenAI(\n",
     "    feature=\"text\",\n",
@@ -220,7 +220,7 @@
    "outputs": [],
    "source": [
     "from langchain.chains import LLMChain, SimpleSequentialChain\n",
-    "from langchain.prompts import PromptTemplate"
+    "from langchain_core.prompts import PromptTemplate"
    ]
   },
   {

docs/docs/integrations/llms/fireworks.ipynb

@@ -54,6 +54,8 @@
     "import getpass\n",
     "import os\n",
     "\n",
+    "from langchain_fireworks import Fireworks\n",
+    "\n",
     "if \"FIREWORKS_API_KEY\" not in os.environ:\n",
     "    os.environ[\"FIREWORKS_API_KEY\"] = getpass.getpass(\"Fireworks API Key:\")\n",
     "\n",
@@ -180,8 +182,8 @@
     }
    ],
    "source": [
-    "from langchain.prompts import PromptTemplate\n",
-    "from langchain_community.llms.fireworks import Fireworks\n",
+    "from langchain_core.prompts import PromptTemplate\n",
+    "from langchain_fireworks import Fireworks\n",
     "\n",
     "llm = Fireworks(\n",
     "    model=\"accounts/fireworks/models/mixtral-8x7b-instruct\",\n",
@@ -249,7 +251,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.4"
+   "version": "3.9.6"
   }
  },
  "nbformat": 4,

docs/docs/integrations/llms/forefrontai.ipynb

@@ -28,8 +28,8 @@
     "import os\n",
     "\n",
     "from langchain.chains import LLMChain\n",
-    "from langchain.prompts import PromptTemplate\n",
-    "from langchain_community.llms import ForefrontAI"
+    "from langchain_community.llms import ForefrontAI\n",
+    "from langchain_core.prompts import PromptTemplate"
    ]
   },
   {

docs/docs/integrations/llms/gigachat.ipynb

@@ -15,7 +15,10 @@
    "cell_type": "code",
    "execution_count": null,
    "metadata": {
-    "collapsed": true
+    "collapsed": true,
+    "pycharm": {
+     "is_executing": true
+    }
    },
    "outputs": [],
    "source": [
@@ -28,13 +31,14 @@
     "collapsed": false
    },
    "source": [
-    "To get GigaChat credentials you need to [create account](https://developers.sber.ru/studio/login) and [get access to API](https://developers.sber.ru/docs/ru/gigachat/api/integration)\n",
+    "To get GigaChat credentials you need to [create account](https://developers.sber.ru/studio/login) and [get access to API](https://developers.sber.ru/docs/ru/gigachat/individuals-quickstart)\n",
+    "\n",
     "## Example"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 2,
    "metadata": {
     "collapsed": false
    },
@@ -48,7 +52,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 3,
    "metadata": {
     "collapsed": false
    },
@@ -56,12 +60,12 @@
    "source": [
     "from langchain_community.llms import GigaChat\n",
     "\n",
-    "llm = GigaChat(verify_ssl_certs=False)"
+    "llm = GigaChat(verify_ssl_certs=False, scope=\"GIGACHAT_API_PERS\")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 9,
    "metadata": {
     "collapsed": false
    },
@@ -76,7 +80,7 @@
    ],
    "source": [
     "from langchain.chains import LLMChain\n",
-    "from langchain.prompts import PromptTemplate\n",
+    "from langchain_core.prompts import PromptTemplate\n",
     "\n",
     "template = \"What is capital of {country}?\"\n",
     "\n",
@@ -84,8 +88,8 @@
     "\n",
     "llm_chain = LLMChain(prompt=prompt, llm=llm)\n",
     "\n",
-    "generated = llm_chain.run(country=\"Russia\")\n",
-    "print(generated)"
+    "generated = llm_chain.invoke(input={\"country\": \"Russia\"})\n",
+    "print(generated[\"text\"])"
    ]
   }
  ],

docs/docs/integrations/llms/google_ai.ipynb

@@ -180,7 +180,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.prompts import PromptTemplate"
+    "from langchain_core.prompts import PromptTemplate"
    ]
   },
   {

docs/docs/integrations/llms/gooseai.ipynb

@@ -44,8 +44,8 @@
     "import os\n",
     "\n",
     "from langchain.chains import LLMChain\n",
-    "from langchain.prompts import PromptTemplate\n",
-    "from langchain_community.llms import GooseAI"
+    "from langchain_community.llms import GooseAI\n",
+    "from langchain_core.prompts import PromptTemplate"
    ]
   },
   {

docs/docs/integrations/llms/gpt4all.ipynb

@@ -49,8 +49,8 @@
    "source": [
     "from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler\n",
     "from langchain.chains import LLMChain\n",
-    "from langchain.prompts import PromptTemplate\n",
-    "from langchain_community.llms import GPT4All"
+    "from langchain_community.llms import GPT4All\n",
+    "from langchain_core.prompts import PromptTemplate"
    ]
   },
   {

docs/docs/integrations/llms/gradient.ipynb

@@ -25,8 +25,8 @@
    "outputs": [],
    "source": [
     "from langchain.chains import LLMChain\n",
-    "from langchain.prompts import PromptTemplate\n",
-    "from langchain_community.llms import GradientLLM"
+    "from langchain_community.llms import GradientLLM\n",
+    "from langchain_core.prompts import PromptTemplate"
    ]
   },
   {

docs/docs/integrations/llms/huggingface_pipelines.ipynb

@@ -107,7 +107,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.prompts import PromptTemplate\n",
+    "from langchain_core.prompts import PromptTemplate\n",
     "\n",
     "template = \"\"\"Question: {question}\n",
     "\n",
@@ -256,7 +256,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "!optimum-cli export openvino --model gpt2 ov_model"
+    "!optimum-cli export openvino --model gpt2 ov_model_dir"
    ]
   },
   {
@@ -274,9 +274,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "!optimum-cli export openvino --model gpt2  --weight-format int8 ov_model # for 8-bit quantization\n",
+    "!optimum-cli export openvino --model gpt2  --weight-format int8 ov_model_dir # for 8-bit quantization\n",
     "\n",
-    "!optimum-cli export openvino --model gpt2  --weight-format int4 ov_model # for 4-bit quantization"
+    "!optimum-cli export openvino --model gpt2  --weight-format int4 ov_model_dir # for 4-bit quantization"
    ]
   },
   {
@@ -287,7 +287,7 @@
    "outputs": [],
    "source": [
     "ov_llm = HuggingFacePipeline.from_model_id(\n",
-    "    model_id=\"ov_model\",\n",
+    "    model_id=\"ov_model_dir\",\n",
     "    task=\"text-generation\",\n",
     "    backend=\"openvino\",\n",
     "    model_kwargs={\"device\": \"CPU\", \"ov_config\": ov_config},\n",
@@ -330,7 +330,7 @@
    "id": "da9a9239",
    "metadata": {},
    "source": [
-    "For more information refer to [OpenVINO LLM guide](https://docs.openvino.ai/2024/openvino-workflow/generative-ai-models-guide.html)."
+    "For more information refer to [OpenVINO LLM guide](https://docs.openvino.ai/2024/learn-openvino/llm_inference_guide.html) and [OpenVINO Local Pipelines notebook](./openvino.ipynb)."
    ]
   }
  ],

docs/docs/integrations/llms/ipex_llm.ipynb

@@ -4,11 +4,11 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# BigDL-LLM\n",
+    "# IPEX-LLM\n",
     "\n",
-    "> [BigDL-LLM](https://github.com/intel-analytics/BigDL/) is a low-bit LLM optimization library on Intel XPU (Xeon/Core/Flex/Arc/Max). It can make LLMs run extremely fast and consume much less memory on Intel platforms. It is open sourced under Apache 2.0 License.\n",
+    "> [IPEX-LLM](https://github.com/intel-analytics/ipex-llm/) is a low-bit LLM optimization library on Intel XPU (Xeon/Core/Flex/Arc/Max). It can make LLMs run extremely fast and consume much less memory on Intel platforms. It is open sourced under Apache 2.0 License.\n",
     "\n",
-    "This example goes over how to use LangChain to interact with BigDL-LLM for text generation. \n"
+    "This example goes over how to use LangChain to interact with IPEX-LLM for text generation. \n"
    ]
   },
   {
@@ -33,7 +33,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Install BigDL-LLM for running LLMs locally on Intel CPU."
+    "Install IEPX-LLM for running LLMs locally on Intel CPU."
    ]
   },
   {
@@ -42,8 +42,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Install BigDL\n",
-    "%pip install --pre --upgrade bigdl-llm[all]"
+    "%pip install --pre --upgrade ipex-llm[all]"
    ]
   },
   {
@@ -60,7 +59,7 @@
    "outputs": [],
    "source": [
     "from langchain.chains import LLMChain\n",
-    "from langchain_community.llms.bigdl import BigdlLLM\n",
+    "from langchain_community.llms import IpexLLM\n",
     "from langchain_core.prompts import PromptTemplate"
    ]
   },
@@ -89,7 +88,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "69e018750ffb4de1af22ce49cd6957f4",
+       "model_id": "27c08180714a44c7ab766624d5054163",
        "version_major": 2,
        "version_minor": 0
       },
@@ -104,13 +103,12 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "2024-02-23 18:10:22,896 - INFO - Converting the current model to sym_int4 format......\n",
-      "2024-02-23 18:10:25,415 - INFO - BIGDL_OPT_IPEX: False\n"
+      "2024-03-27 00:58:43,670 - INFO - Converting the current model to sym_int4 format......\n"
      ]
     }
    ],
    "source": [
-    "llm = BigdlLLM.from_model_id(\n",
+    "llm = IpexLLM.from_model_id(\n",
     "    model_id=\"lmsys/vicuna-7b-v1.5\",\n",
     "    model_kwargs={\"temperature\": 0, \"max_length\": 64, \"trust_remote_code\": True},\n",
     ")"
@@ -135,6 +133,10 @@
       "/opt/anaconda3/envs/shane-langchain2/lib/python3.9/site-packages/langchain_core/_api/deprecation.py:117: LangChainDeprecationWarning: The function `run` was deprecated in LangChain 0.1.0 and will be removed in 0.2.0. Use invoke instead.\n",
       "  warn_deprecated(\n",
       "/opt/anaconda3/envs/shane-langchain2/lib/python3.9/site-packages/transformers/generation/utils.py:1369: UserWarning: Using `max_length`'s default (4096) to control the generation length. This behaviour is deprecated and will be removed from the config in v5 of Transformers -- we recommend using `max_new_tokens` to control the maximum length of the generation.\n",
+      "  warnings.warn(\n",
+      "/opt/anaconda3/envs/shane-langchain2/lib/python3.9/site-packages/ipex_llm/transformers/models/llama.py:218: UserWarning: Passing `padding_mask` is deprecated and will be removed in v4.37.Please make sure use `attention_mask` instead.`\n",
+      "  warnings.warn(\n",
+      "/opt/anaconda3/envs/shane-langchain2/lib/python3.9/site-packages/ipex_llm/transformers/models/llama.py:218: UserWarning: Passing `padding_mask` is deprecated and will be removed in v4.37.Please make sure use `attention_mask` instead.`\n",
       "  warnings.warn(\n"
      ]
     },
@@ -156,6 +158,13 @@
     "question = \"What is AI?\"\n",
     "output = llm_chain.run(question)"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {

docs/docs/integrations/llms/javelin.ipynb

@@ -92,8 +92,8 @@
    ],
    "source": [
     "from langchain.chains import LLMChain\n",
-    "from langchain.prompts import PromptTemplate\n",
     "from langchain_community.llms import JavelinAIGateway\n",
+    "from langchain_core.prompts import PromptTemplate\n",
     "\n",
     "route_completions = \"eng_dept03\"\n",
     "\n",

docs/docs/integrations/llms/layerup_security.mdx

@@ -0,0 +1,85 @@
+# Layerup Security
+
+The [Layerup Security](https://uselayerup.com) integration allows you to secure your calls to any LangChain LLM, LLM chain or LLM agent. The LLM object wraps around any existing LLM object, allowing for a secure layer between your users and your LLMs.
+
+While the Layerup Security object is designed as an LLM, it is not actually an LLM itself, it simply wraps around an LLM, allowing it to adapt the same functionality as the underlying LLM.
+
+## Setup
+First, you'll need a Layerup Security account from the Layerup [website](https://uselayerup.com).
+
+Next, create a project via the [dashboard](https://dashboard.uselayerup.com), and copy your API key. We recommend putting your API key in your project's environment.
+
+Install the Layerup Security SDK:
+```bash
+pip install LayerupSecurity
+```
+
+And install LangChain Community:
+```bash
+pip install langchain-community
+```
+
+And now you're ready to start protecting your LLM calls with Layerup Security!
+
+```python
+from langchain_community.llms.layerup_security import LayerupSecurity
+from langchain_openai import OpenAI
+
+# Create an instance of your favorite LLM
+openai = OpenAI(
+    model_name="gpt-3.5-turbo",
+    openai_api_key="OPENAI_API_KEY",
+)
+
+# Configure Layerup Security
+layerup_security = LayerupSecurity(
+    # Specify a LLM that Layerup Security will wrap around
+    llm=openai,
+
+    # Layerup API key, from the Layerup dashboard
+    layerup_api_key="LAYERUP_API_KEY",
+
+    # Custom base URL, if self hosting
+    layerup_api_base_url="https://api.uselayerup.com/v1",
+
+    # List of guardrails to run on prompts before the LLM is invoked
+    prompt_guardrails=[],
+
+    # List of guardrails to run on responses from the LLM
+    response_guardrails=["layerup.hallucination"],
+
+    # Whether or not to mask the prompt for PII & sensitive data before it is sent to the LLM
+    mask=False,
+
+    # Metadata for abuse tracking, customer tracking, and scope tracking.
+    metadata={"customer": "example@uselayerup.com"},
+
+    # Handler for guardrail violations on the prompt guardrails
+    handle_prompt_guardrail_violation=(
+        lambda violation: {
+            "role": "assistant",
+            "content": (
+                "There was sensitive data! I cannot respond. "
+                "Here's a dynamic canned response. Current date: {}"
+            ).format(datetime.now())
+        }
+        if violation["offending_guardrail"] == "layerup.sensitive_data"
+        else None
+    ),
+
+    # Handler for guardrail violations on the response guardrails
+    handle_response_guardrail_violation=(
+        lambda violation: {
+            "role": "assistant",
+            "content": (
+                "Custom canned response with dynamic data! "
+                "The violation rule was {}."
+            ).format(violation["offending_guardrail"])
+        }
+    ),
+)
+
+response = layerup_security.invoke(
+    "Summarize this message: my name is Bob Dylan. My SSN is 123-45-6789."
+)
+```

docs/docs/integrations/llms/llamacpp.ipynb

@@ -208,11 +208,9 @@
    },
    "outputs": [],
    "source": [
-    "from langchain.callbacks.manager import CallbackManager\n",
-    "from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler\n",
-    "from langchain.chains import LLMChain\n",
-    "from langchain.prompts import PromptTemplate\n",
-    "from langchain_community.llms import LlamaCpp"
+    "from langchain_community.llms import LlamaCpp\n",
+    "from langchain_core.callbacks import CallbackManager, StreamingStdOutCallbackHandler\n",
+    "from langchain_core.prompts import PromptTemplate"
    ]
   },
   {
@@ -329,10 +327,10 @@
     }
    ],
    "source": [
-    "prompt = \"\"\"\n",
+    "question = \"\"\"\n",
     "Question: A rap battle between Stephen Colbert and John Oliver\n",
     "\"\"\"\n",
-    "llm.invoke(prompt)"
+    "llm.invoke(question)"
    ]
   },
   {
@@ -360,7 +358,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "llm_chain = LLMChain(prompt=prompt, llm=llm)"
+    "llm_chain = prompt | llm"
    ]
   },
   {
@@ -406,7 +404,7 @@
    ],
    "source": [
     "question = \"What NFL team won the Super Bowl in the year Justin Bieber was born?\"\n",
-    "llm_chain.run(question)"
+    "llm_chain.invoke({\"question\": question})"
    ]
   },
   {
@@ -488,9 +486,9 @@
     }
    ],
    "source": [
-    "llm_chain = LLMChain(prompt=prompt, llm=llm)\n",
+    "llm_chain = prompt | llm\n",
     "question = \"What NFL team won the Super Bowl in the year Justin Bieber was born?\"\n",
-    "llm_chain.run(question)"
+    "llm_chain.invoke({\"question\": question})"
    ]
   },
   {
@@ -710,7 +708,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.6"
+   "version": "3.9.1"
   },
   "vscode": {
    "interpreter": {

docs/docs/integrations/llms/llm_caching.ipynb

@@ -12,12 +12,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 3,
    "id": "10ad9224",
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2024-02-02T21:34:23.461332Z",
-     "start_time": "2024-02-02T21:34:23.394461Z"
+     "end_time": "2024-03-18T01:01:08.425930Z",
+     "start_time": "2024-03-18T01:01:08.327196Z"
     }
    },
    "outputs": [],
@@ -41,7 +41,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 11,
    "id": "426ff912",
    "metadata": {},
    "outputs": [],
@@ -1356,19 +1356,29 @@
   },
   {
    "cell_type": "markdown",
-   "source": [
-    "## Azure Cosmos DB Semantic Cache"
-   ],
+   "id": "40624c26e86b57a4",
    "metadata": {
     "collapsed": false
    },
-   "id": "40624c26e86b57a4"
+   "source": [
+    "## Azure Cosmos DB Semantic Cache\n",
+    "\n",
+    "You can use this integrated [vector database](https://learn.microsoft.com/en-us/azure/cosmos-db/vector-database) for caching."
+   ]
   },
   {
    "cell_type": "code",
+   "execution_count": 4,
+   "id": "4a9d592db01b11b2",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-03-18T01:01:32.014750Z",
+     "start_time": "2024-03-18T01:01:31.955991Z"
+    }
+   },
    "outputs": [],
    "source": [
-    "from langchain.cache import AzureCosmosDBSemanticCache\n",
+    "from langchain_community.cache import AzureCosmosDBSemanticCache\n",
     "from langchain_community.vectorstores.azure_cosmos_db import (\n",
     "    CosmosDBSimilarityType,\n",
     "    CosmosDBVectorSearchType,\n",
@@ -1377,11 +1387,11 @@
     "\n",
     "# Read more about Azure CosmosDB Mongo vCore vector search here https://learn.microsoft.com/en-us/azure/cosmos-db/mongodb/vcore/vector-search\n",
     "\n",
-    "INDEX_NAME = \"langchain-test-index\"\n",
     "NAMESPACE = \"langchain_test_db.langchain_test_collection\"\n",
     "CONNECTION_STRING = (\n",
     "    \"Please provide your azure cosmos mongo vCore vector db connection string\"\n",
     ")\n",
+    "\n",
     "DB_NAME, COLLECTION_NAME = NAMESPACE.split(\".\")\n",
     "\n",
     "# Default value for these params\n",
@@ -1392,7 +1402,9 @@
     "m = 16\n",
     "ef_construction = 64\n",
     "ef_search = 40\n",
-    "score_threshold = 0.1\n",
+    "score_threshold = 0.9\n",
+    "application_name = \"LANGCHAIN_CACHING_PYTHON\"\n",
+    "\n",
     "\n",
     "set_llm_cache(\n",
     "    AzureCosmosDBSemanticCache(\n",
@@ -1409,18 +1421,10 @@
     "        ef_construction=ef_construction,\n",
     "        ef_search=ef_search,\n",
     "        score_threshold=score_threshold,\n",
+    "        application_name=application_name,\n",
     "    )\n",
     ")"
-   ],
-   "metadata": {
-    "collapsed": false,
-    "ExecuteTime": {
-     "end_time": "2024-02-02T21:34:49.457001Z",
-     "start_time": "2024-02-02T21:34:49.411293Z"
-    }
-   },
-   "id": "4a9d592db01b11b2",
-   "execution_count": 16
+   ]
   },
   {
    "cell_type": "code",
@@ -1429,15 +1433,15 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "CPU times: user 43.4 ms, sys: 7.23 ms, total: 50.7 ms\n",
-      "Wall time: 1.61 s\n"
+      "CPU times: user 45.6 ms, sys: 19.7 ms, total: 65.3 ms\n",
+      "Wall time: 2.29 s\n"
      ]
     },
     {
      "data": {
-      "text/plain": "\"\\n\\nWhy couldn't the bicycle stand up by itself?\\n\\nBecause it was two-tired!\""
+      "text/plain": "'\\n\\nWhy was the math book sad? Because it had too many problems.'"
      },
-     "execution_count": 17,
+     "execution_count": 82,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1450,47 +1454,46 @@
    "metadata": {
     "collapsed": false,
     "ExecuteTime": {
-     "end_time": "2024-02-02T21:34:53.704234Z",
-     "start_time": "2024-02-02T21:34:52.091096Z"
+     "end_time": "2024-03-12T00:12:57.462226Z",
+     "start_time": "2024-03-12T00:12:55.166201Z"
     }
    },
-   "id": "8488cf9c97ec7ab",
-   "execution_count": 17
+   "id": "14ca942820e8140c",
+   "execution_count": 82
   },
   {
    "cell_type": "code",
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "CPU times: user 6.89 ms, sys: 2.24 ms, total: 9.13 ms\n",
-      "Wall time: 337 ms\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": "\"\\n\\nWhy couldn't the bicycle stand up by itself?\\n\\nBecause it was two-tired!\""
-     },
-     "execution_count": 18,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "%%time\n",
-    "# The first time, it is not yet in cache, so it should take longer\n",
-    "llm(\"Tell me a joke\")"
-   ],
-   "metadata": {
-    "collapsed": false,
-    "ExecuteTime": {
-     "end_time": "2024-02-02T21:34:56.004502Z",
-     "start_time": "2024-02-02T21:34:55.650136Z"
-    }
-   },
+   "execution_count": 83,
    "id": "bc1570a2a77b58c8",
-   "execution_count": 18
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-03-12T00:13:03.652755Z",
+     "start_time": "2024-03-12T00:13:03.159428Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 9.61 ms, sys: 3.42 ms, total: 13 ms\n",
+      "Wall time: 474 ms\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": "'\\n\\nWhy was the math book sad? Because it had too many problems.'"
+     },
+     "execution_count": 83,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "# The first time, it is not yet in cache, so it should take longer\n",
+    "llm(\"Tell me a joke\")"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -1741,7 +1744,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.17"
+   "version": "3.11.4"
   }
  },
  "nbformat": 4,