x

Fixing a typo in the example code in the docstring...

You have to start somewhere though right?

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>

.github/CONTRIBUTING.md

@@ -14,8 +14,8 @@ Please do not try to push directly to this repo unless you are a maintainer.
 Please follow the checked-in pull request template when opening pull requests. Note related issues and tag relevant
 maintainers.
 
-Pull requests cannot land without passing the formatting, linting and testing checks first. See
-[Common Tasks](#-common-tasks) for how to run these checks locally.
+Pull requests cannot land without passing the formatting, linting and testing checks first. See [Testing](#testing) and
+[Formatting and Linting](#formatting-and-linting) for how to run these checks locally.
 
 It's essential that we maintain great documentation and testing. If you:
 - Fix a bug
@@ -59,43 +59,85 @@ we do not want these to get in the way of getting good code into the codebase.
 
 ## 🚀 Quick Start
 
-> **Note:** You can run this repository locally (which is described below) or in a [development container](https://containers.dev/) (which is described in the [.devcontainer folder](https://github.com/hwchase17/langchain/tree/master/.devcontainer)).
+This quick start describes running the repository locally.
+For a [development container](https://containers.dev/), see the [.devcontainer folder](https://github.com/hwchase17/langchain/tree/master/.devcontainer).
 
-This project uses [Poetry](https://python-poetry.org/) v1.5.1 as a dependency manager. Check out Poetry's [documentation on how to install it](https://python-poetry.org/docs/#installation) on your system before proceeding.
+### Dependency Management: Poetry and other env/dependency managers
 
-❗Note: If you use `Conda` or `Pyenv` as your environment/package manager, avoid dependency conflicts by doing the following first:
-1. *Before installing Poetry*, create and activate a new Conda env (e.g. `conda create -n langchain python=3.9`)
-2. Install Poetry v1.5.1 (see above)
-3. Tell Poetry to use the virtualenv python environment (`poetry config virtualenvs.prefer-active-python true`)
-4. Continue with the following steps.
+This project uses [Poetry](https://python-poetry.org/) v1.5.1+ as a dependency manager.
+
+❗Note: *Before installing Poetry*, if you use `Conda`, create and activate a new Conda env (e.g. `conda create -n langchain python=3.9`)
+
+Install Poetry: **[documentation on how to install it](https://python-poetry.org/docs/#installation)**.
+
+❗Note: If you use `Conda` or `Pyenv` as your environment/package manager, after installing Poetry,
+tell Poetry to use the virtualenv python environment (`poetry config virtualenvs.prefer-active-python true`)
+
+### Core vs. Experimental
 
 There are two separate projects in this repository:
 - `langchain`: core langchain code, abstractions, and use cases
-- `langchain.experimental`: more experimental code
+- `langchain.experimental`: see the [Experimental README](../libs/experimental/README.md) for more information.
 
-Each of these has their OWN development environment.
-In order to run any of the commands below, please move into their respective directories.
-For example, to contribute to `langchain` run `cd libs/langchain` before getting started with the below.
+Each of these has their own development environment. Docs are run from the top-level makefile, but development
+is split across separate test & release flows.
 
-To install requirements:
+For this quickstart, start with langchain core:
+
+```bash
+cd libs/langchain
+```
+
+### Local Development Dependencies
+
+Install langchain development requirements (for running langchain, running examples, linting, formatting, tests, and coverage):
 
 ```bash
 poetry install --with test
 ```
 
-This will install all requirements for running the package, examples, linting, formatting, tests, and coverage.
+Then verify dependency installation:
 
-❗Note: If during installation you receive a `WheelFileValidationError` for `debugpy`, please make sure you are running Poetry v1.5.1. This bug was present in older versions of Poetry (e.g. 1.4.1) and has been resolved in newer releases. If you are still seeing this bug on v1.5.1, you may also try disabling "modern installation" (`poetry config installer.modern-installation false`) and re-installing requirements. See [this `debugpy` issue](https://github.com/microsoft/debugpy/issues/1246) for more details.
+```bash
+make test
+```
 
-Now assuming `make` and `pytest` are installed, you should be able to run the common tasks in the following section. To double check, run `make test` under `libs/langchain`, all tests should pass. If they don't, you may need to pip install additional dependencies, such as `numexpr` and `openapi_schema_pydantic`.
+If the tests don't pass, you may need to pip install additional dependencies, such as `numexpr` and `openapi_schema_pydantic`.
 
-## ✅ Common Tasks
+If during installation you receive a `WheelFileValidationError` for `debugpy`, please make sure you are running
+Poetry v1.5.1+. This bug was present in older versions of Poetry (e.g. 1.4.1) and has been resolved in newer releases.
+If you are still seeing this bug on v1.5.1, you may also try disabling "modern installation"
+(`poetry config installer.modern-installation false`) and re-installing requirements.
+See [this `debugpy` issue](https://github.com/microsoft/debugpy/issues/1246) for more details.
 
-Type `make` for a list of common tasks.
+### Testing
 
-### Code Formatting
+_some test dependencies are optional; see section about optional dependencies_.
 
-Formatting for this project is done via a combination of [Black](https://black.readthedocs.io/en/stable/) and [isort](https://pycqa.github.io/isort/).
+Unit tests cover modular logic that does not require calls to outside APIs.
+If you add new logic, please add a unit test.
+
+To run unit tests:
+
+```bash
+make test
+```
+
+To run unit tests in Docker:
+
+```bash
+make docker_tests
+```
+
+There are also [integration tests and code-coverage](../libs/langchain/tests/README.md) available.
+
+### Formatting and Linting
+
+Run these locally before submitting a PR; the CI system will check also.
+
+#### Code Formatting
+
+Formatting for this project is done via a combination of [Black](https://black.readthedocs.io/en/stable/) and [ruff](https://docs.astral.sh/ruff/rules/).
 
 To run formatting for this project:
 
@@ -111,9 +153,9 @@ make format_diff
 
 This is especially useful when you have made changes to a subset of the project and want to ensure your changes are properly formatted without affecting the rest of the codebase.
 
-### Linting
+#### Linting
 
-Linting for this project is done via a combination of [Black](https://black.readthedocs.io/en/stable/), [isort](https://pycqa.github.io/isort/), [flake8](https://flake8.pycqa.org/en/latest/), and [mypy](http://mypy-lang.org/).
+Linting for this project is done via a combination of [Black](https://black.readthedocs.io/en/stable/), [ruff](https://docs.astral.sh/ruff/rules/), and [mypy](http://mypy-lang.org/).
 
 To run linting for this project:
 
@@ -131,7 +173,7 @@ This can be very helpful when you've made changes to only certain parts of the p
 
 We recognize linting can be annoying - if you do not want to do it, please contact a project maintainer, and they can help you with it. We do not want this to be a blocker for good code getting contributed.
 
-### Spellcheck
+#### Spellcheck
 
 Spellchecking for this project is done via [codespell](https://github.com/codespell-project/codespell).
 Note that `codespell` finds common typos, so it could have false-positive (correctly spelled but rarely used) and false-negatives (not finding misspelled) words.
@@ -157,17 +199,7 @@ If codespell is incorrectly flagging a word, you can skip spellcheck for that wo
 ignore-words-list = 'momento,collison,ned,foor,reworkd,parth,whats,aapply,mysogyny,unsecure'
 ```
 
-### Coverage
-
-Code coverage (i.e. the amount of code that is covered by unit tests) helps identify areas of the code that are potentially more or less brittle.
-
-To get a report of current coverage, run the following:
-
-```bash
-make coverage
-```
-
-### Working with Optional Dependencies
+## Working with Optional Dependencies
 
 Langchain relies heavily on optional dependencies to keep the Langchain package lightweight.
 
@@ -192,51 +224,7 @@ To introduce the dependency to the pyproject.toml file correctly, please do the
 test makes use of lightweight fixtures to test the logic of the code.
 5. Please use the `@pytest.mark.requires(package_name)` decorator for any tests that require the dependency.
 
-### Testing
-
-See section about optional dependencies.
-
-#### Unit Tests
-
-Unit tests cover modular logic that does not require calls to outside APIs.
-
-To run unit tests:
-
-```bash
-make test
-```
-
-To run unit tests in Docker:
-
-```bash
-make docker_tests
-```
-
-If you add new logic, please add a unit test.
-
-
-
-#### Integration Tests
-
-Integration tests cover logic that requires making calls to outside APIs (often integration with other services).
-
-**warning** Almost no tests should be integration tests.
-
-  Tests that require making network connections make it difficult for other
-  developers to test the code.
-
-  Instead favor relying on `responses` library and/or mock.patch to mock
-  requests using small fixtures.
-
-To run integration tests:
-
-```bash
-make integration_tests
-```
-
-If you add support for a new external API, please add a new integration test.
-
-### Adding a Jupyter Notebook
+## Adding a Jupyter Notebook
 
 If you are adding a Jupyter Notebook example, you'll want to install the optional `dev` dependencies.
 
@@ -259,6 +247,12 @@ When you run `poetry install`, the `langchain` package is installed as editable
 While the code is split between `langchain` and `langchain.experimental`, the documentation is one holistic thing.
 This covers how to get started contributing to documentation.
 
+From the top-level of this repo, install documentation dependencies:
+
+```bash
+poetry install
+```
+
 ### Contribute Documentation
 
 The docs directory contains Documentation and API Reference.

.github/workflows/doc_lint.yml

@@ -19,4 +19,4 @@ jobs:
       run: |
         # We should not encourage imports directly from main init file
         # Expect for hub
-        git grep 'from langchain import' docs | grep -vE 'from langchain import (hub)' && exit 1 || exit 0
+        git grep 'from langchain import' docs/{extras,docs_skeleton,snippets} | grep -vE 'from langchain import (hub)' && exit 1 || exit 0

.github/workflows/scheduled_test.yml

@@ -34,12 +34,19 @@ jobs:
           working-directory: libs/langchain
           cache-key: scheduled
 
+      - name: 'Authenticate to Google Cloud'
+        id: 'auth'
+        uses: 'google-github-actions/auth@v1'
+        with:
+          credentials_json: '${{ secrets.GOOGLE_CREDENTIALS }}'
+
       - name: Install dependencies
         working-directory: libs/langchain
         shell: bash
         run: |
           echo "Running scheduled tests, installing dependencies with poetry..."
           poetry install --with=test_integration
+          poetry run pip install google-cloud-aiplatform
 
       - name: Run tests
         shell: bash

Makefile

@@ -42,7 +42,8 @@ spell_fix:
 ######################
 
 help:
-	@echo '----'
+	@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'
@@ -51,4 +52,5 @@ help:
 	@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 'spell_fix               		- run codespell on the project and fix the errors'
+	@echo '-- TEST and LINT tasks are within libs/*/ per-package --'

docs/_scripts/model_feat_table.py

@@ -0,0 +1,150 @@
+import os
+from pathlib import Path
+
+from langchain import chat_models, llms
+from langchain.chat_models.base import BaseChatModel, SimpleChatModel
+from langchain.llms.base import BaseLLM, LLM
+
+INTEGRATIONS_DIR = (
+    Path(os.path.abspath(__file__)).parents[1] / "extras" / "integrations"
+)
+LLM_IGNORE = ("FakeListLLM", "OpenAIChat", "PromptLayerOpenAIChat")
+LLM_FEAT_TABLE_CORRECTION = {
+    "TextGen": {"_astream": False, "_agenerate": False},
+    "Ollama": {
+        "_stream": False,
+    },
+    "PromptLayerOpenAI": {"batch_generate": False, "batch_agenerate": False},
+}
+CHAT_MODEL_IGNORE = ("FakeListChatModel", "HumanInputChatModel")
+CHAT_MODEL_FEAT_TABLE_CORRECTION = {
+    "ChatMLflowAIGateway": {"_agenerate": False},
+    "PromptLayerChatOpenAI": {"_stream": False, "_astream": False},
+    "ChatKonko": {"_astream": False, "_agenerate": False},
+}
+
+LLM_TEMPLATE = """\
+---
+sidebar_position: 0
+sidebar_class_name: hidden
+---
+
+# LLMs
+
+import DocCardList from "@theme/DocCardList";
+
+## Features (natively supported)
+All LLMs implement the Runnable interface, which comes with default implementations of all methods, ie. `ainvoke`, `batch`, `abatch`, `stream`, `astream`. This gives all LLMs basic support for async, streaming and batch, which by default is implemented as below:
+- *Async* support defaults to calling the respective sync method in asyncio's default thread pool executor. This lets other async functions in your application make progress while the LLM is being executed, by moving this call to a background thread.
+- *Streaming* support defaults to returning an `Iterator` (or `AsyncIterator` in the case of async streaming) of a single value, the final result returned by the underlying LLM provider. This obviously doesn't give you token-by-token streaming, which requires native support from the LLM provider, but ensures your code that expects an iterator of tokens can work for any of our LLM integrations.
+- *Batch* support defaults to calling the underlying LLM in parallel for each input by making use of a thread pool executor (in the sync batch case) or `asyncio.gather` (in the async batch case). The concurrency can be controlled with the `max_concurrency` key in `RunnableConfig`.
+
+Each LLM integration can optionally provide native implementations for async, streaming or batch, which, for providers that support it, can be more efficient. The table shows, for each integration, which features have been implemented with native support.
+
+{table}
+
+<DocCardList />
+"""
+
+CHAT_MODEL_TEMPLATE = """\
+---
+sidebar_position: 1
+sidebar_class_name: hidden
+---
+
+# Chat models
+
+import DocCardList from "@theme/DocCardList";
+
+## Features (natively supported)
+All ChatModels implement the Runnable interface, which comes with default implementations of all methods, ie. `ainvoke`, `batch`, `abatch`, `stream`, `astream`. This gives all ChatModels basic support for async, streaming and batch, which by default is implemented as below:
+- *Async* support defaults to calling the respective sync method in asyncio's default thread pool executor. This lets other async functions in your application make progress while the ChatModel is being executed, by moving this call to a background thread.
+- *Streaming* support defaults to returning an `Iterator` (or `AsyncIterator` in the case of async streaming) of a single value, the final result returned by the underlying ChatModel provider. This obviously doesn't give you token-by-token streaming, which requires native support from the ChatModel provider, but ensures your code that expects an iterator of tokens can work for any of our ChatModel integrations.
+- *Batch* support defaults to calling the underlying ChatModel in parallel for each input by making use of a thread pool executor (in the sync batch case) or `asyncio.gather` (in the async batch case). The concurrency can be controlled with the `max_concurrency` key in `RunnableConfig`.
+
+Each ChatModel integration can optionally provide native implementations to truly enable async or streaming.
+The table shows, for each integration, which features have been implemented with native support.
+
+{table}
+
+<DocCardList />
+"""
+
+
+def get_llm_table():
+    llm_feat_table = {}
+    for cm in llms.__all__:
+        llm_feat_table[cm] = {}
+        cls = getattr(llms, cm)
+        if issubclass(cls, LLM):
+            for feat in ("_stream", "_astream", ("_acall", "_agenerate")):
+                if isinstance(feat, tuple):
+                    feat, name = feat
+                else:
+                    feat, name = feat, feat
+                llm_feat_table[cm][name] = getattr(cls, feat) != getattr(LLM, feat)
+        else:
+            for feat in [
+                "_stream",
+                "_astream",
+                ("_generate", "batch_generate"),
+                "_agenerate",
+                ("_agenerate", "batch_agenerate"),
+            ]:
+                if isinstance(feat, tuple):
+                    feat, name = feat
+                else:
+                    feat, name = feat, feat
+                llm_feat_table[cm][name] = getattr(cls, feat) != getattr(BaseLLM, feat)
+    final_feats = {
+        k: v
+        for k, v in {**llm_feat_table, **LLM_FEAT_TABLE_CORRECTION}.items()
+        if k not in LLM_IGNORE
+    }
+
+    header = [
+        "model",
+        "_agenerate",
+        "_stream",
+        "_astream",
+        "batch_generate",
+        "batch_agenerate",
+    ]
+    title = ["Model", "Invoke", "Async invoke", "Stream", "Async stream", "Batch", "Async batch"]
+    rows = [title, [":-"] + [":-:"] * (len(title) - 1)]
+    for llm, feats in sorted(final_feats.items()):
+        rows += [[llm, "✅"] + ["✅" if feats.get(h) else "❌" for h in header[1:]]]
+    return "\n".join(["|".join(row) for row in rows])
+
+
+def get_chat_model_table():
+    feat_table = {}
+    for cm in chat_models.__all__:
+        feat_table[cm] = {}
+        cls = getattr(chat_models, cm)
+        if issubclass(cls, SimpleChatModel):
+            comparison_cls = SimpleChatModel
+        else:
+            comparison_cls = BaseChatModel
+        for feat in ("_stream", "_astream", "_agenerate"):
+            feat_table[cm][feat] = getattr(cls, feat) != getattr(comparison_cls, feat)
+    final_feats = {
+        k: v
+        for k, v in {**feat_table, **CHAT_MODEL_FEAT_TABLE_CORRECTION}.items()
+        if k not in CHAT_MODEL_IGNORE
+    }
+    header = ["model", "_agenerate", "_stream", "_astream"]
+    title = ["Model", "Invoke", "Async invoke", "Stream", "Async stream"]
+    rows = [title, [":-"] + [":-:"] * (len(title) - 1)]
+    for llm, feats in sorted(final_feats.items()):
+        rows += [[llm, "✅"] + ["✅" if feats.get(h) else "❌" for h in header[1:]]]
+    return "\n".join(["|".join(row) for row in rows])
+
+
+if __name__ == "__main__":
+    llm_page = LLM_TEMPLATE.format(table=get_llm_table())
+    with open(INTEGRATIONS_DIR / "llms" / "index.mdx", "w") as f:
+        f.write(llm_page)
+    chat_model_page = CHAT_MODEL_TEMPLATE.format(table=get_chat_model_table())
+    with open(INTEGRATIONS_DIR / "chat" / "index.mdx", "w") as f:
+        f.write(chat_model_page)

docs/api_reference/create_api_rst.py

@@ -1,7 +1,6 @@
 """Script for auto-generating api_reference.rst."""
 import importlib
 import inspect
-import os
 import typing
 from pathlib import Path
 from typing import TypedDict, Sequence, List, Dict, Literal, Union, Optional

docs/docs_skeleton/docs/expression_language/index.mdx

@@ -21,7 +21,7 @@ With LCEL syntax, any components that can be run in parallel automatically are.
 
 **Seamless LangSmith Tracing Integration**
 As your chains get more and more complex, it becomes increasingly important to understand what exactly is happening at every step.
-With LCEL, **all** steps are automatically logged to [LangSmith](smith.langchain.com) for maximal observability and debuggability.
+With LCEL, **all** steps are automatically logged to [LangSmith](https://smith.langchain.com) for maximal observability and debuggability.
 
 #### [Interface](/docs/expression_language/interface)
 The base interface shared by all LCEL objects

docs/docs_skeleton/docusaurus.config.js

@@ -71,9 +71,9 @@ const config = {
               test: /\.ipynb$/,
               loader: "raw-loader",
               resolve: {
-                fullySpecified: false
-              }
-            }
+                fullySpecified: false,
+              },
+            },
           ],
         },
       }),
@@ -158,16 +158,16 @@ const config = {
             position: "left",
           },
           {
-            type: 'docSidebar',
-            position: 'left',
-            sidebarId: 'use_cases',
-            label: 'Use cases',
+            type: "docSidebar",
+            position: "left",
+            sidebarId: "use_cases",
+            label: "Use cases",
           },
           {
-            type: 'docSidebar',
-            position: 'left',
-            sidebarId: 'integrations',
-            label: 'Integrations',
+            type: "docSidebar",
+            position: "left",
+            sidebarId: "integrations",
+            label: "Integrations",
           },
           {
             href: "https://api.python.langchain.com",
@@ -187,9 +187,9 @@ const config = {
           // Please keep GitHub link to the right for consistency.
           {
             href: "https://github.com/hwchase17/langchain",
-            position: 'right',
-            className: 'header-github-link',
-            'aria-label': 'GitHub repository',
+            position: "right",
+            className: "header-github-link",
+            "aria-label": "GitHub repository",
           },
         ],
       },
@@ -239,6 +239,14 @@ const config = {
         copyright: `Copyright © ${new Date().getFullYear()} LangChain, Inc.`,
       },
     }),
+
+  scripts: [
+    "/js/google_analytics.js",
+    {
+      src: "https://www.googletagmanager.com/gtag/js?id=G-9B66JQQH2F",
+      async: true,
+    },
+  ],
 };
 
 module.exports = config;

docs/docs_skeleton/sidebars.js

@@ -99,8 +99,8 @@ module.exports = {
       label: "Components",
       collapsible: false,
       items: [
-        { type: "category", label: "LLMs", collapsed: true, items: [{type:"autogenerated", dirName: "integrations/llms" }], link: {type: "generated-index", slug: "integrations/llms" }},
-        { type: "category", label: "Chat models", collapsed: true, items: [{type:"autogenerated", dirName: "integrations/chat" }], link: {type: "generated-index", slug: "integrations/chat" }},
+        { type: "category", label: "LLMs", collapsed: true, items: [{type:"autogenerated", dirName: "integrations/llms" }], link: { type: 'doc', id: "integrations/llms/index"}},
+        { type: "category", label: "Chat models", collapsed: true, items: [{type:"autogenerated", dirName: "integrations/chat" }], link: { type: 'doc', id: "integrations/chat/index"}},
         { type: "category", label: "Document loaders", collapsed: true, items: [{type:"autogenerated", dirName: "integrations/document_loaders" }], link: {type: "generated-index", slug: "integrations/document_loaders" }},
         { type: "category", label: "Document transformers", collapsed: true, items: [{type: "autogenerated", dirName: "integrations/document_transformers" }], link: {type: "generated-index", slug: "integrations/document_transformers" }},
         { type: "category", label: "Text embedding models", collapsed: true, items: [{type: "autogenerated", dirName: "integrations/text_embedding" }], link: {type: "generated-index", slug: "integrations/text_embedding" }},

docs/docs_skeleton/static/js/google_analytics.js

@@ -0,0 +1,7 @@
+window.dataLayer = window.dataLayer || [];
+function gtag() {
+  dataLayer.push(arguments);
+}
+gtag("js", new Date());
+
+gtag("config", "G-9B66JQQH2F");

docs/docs_skeleton/vercel.json

@@ -1,5 +1,9 @@
 {
   "redirects": [
+    {
+      "source": "/docs/modules/agents/agents/examples/mrkl_chat(.html?)",
+      "destination": "/docs/modules/agents/"
+    },
     {
       "source": "/docs/use_cases(/?)",
       "destination": "/docs/use_cases/question_answering/"
@@ -1968,6 +1972,18 @@
       "source": "/docs/modules/data_connection/document_loaders/integrations/youtube_transcript",
       "destination": "/docs/integrations/document_loaders/youtube_transcript"
     },
+    {
+      "source": "/docs/integrations/document_loaders/Etherscan",
+      "destination": "/docs/integrations/document_loaders/etherscan"
+    },
+    {
+      "source": "/docs/integrations/document_loaders/merge_doc_loader",
+      "destination": "/docs/integrations/document_loaders/merge_doc"
+    },
+    {
+      "source": "/docs/integrations/document_loaders/recursive_url_loader",
+      "destination": "/docs/integrations/document_loaders/recursive_url"
+    },
     {
       "source": "/en/latest/modules/indexes/text_splitters/examples/markdown_header_metadata.html",
       "destination": "/docs/modules/data_connection/document_transformers/text_splitters/markdown_header_metadata"

docs/extras/expression_language/cookbook/multiple_chains.ipynb

@@ -95,7 +95,7 @@
     }
    ],
    "source": [
-    "question_generator.invoke({\"warm\"})"
+    "question_generator.invoke(\"warm\")"
    ]
   },
   {
@@ -116,7 +116,7 @@
     }
    ],
    "source": [
-    "prompt = question_generator.invoke({\"warm\"})\n",
+    "prompt = question_generator.invoke(\"warm\")\n",
     "model.invoke(prompt)"
    ]
   },

docs/extras/expression_language/how_to/fallbacks.ipynb

@@ -277,7 +277,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.10.1"
   }
  },
  "nbformat": 4,

docs/extras/expression_language/how_to/functions.ipynb

@@ -14,12 +14,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 77,
+   "execution_count": 4,
    "id": "6bb221b3",
    "metadata": {},
    "outputs": [],
    "source": [
     "from langchain.schema.runnable import RunnableLambda\n",
+    "from langchain.prompts import ChatPromptTemplate\n",
+    "from langchain.chat_models import ChatOpenAI\n",
+    "from operator import itemgetter\n",
     "\n",
     "def length_function(text):\n",
     "    return len(text)\n",
@@ -31,6 +34,7 @@
     "    return _multiple_length_function(_dict[\"text1\"], _dict[\"text2\"])\n",
     "\n",
     "prompt = ChatPromptTemplate.from_template(\"what is {a} + {b}\")\n",
+    "model = ChatOpenAI()\n",
     "\n",
     "chain1 = prompt | model\n",
     "\n",
@@ -42,7 +46,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 78,
+   "execution_count": 5,
    "id": "5488ec85",
    "metadata": {},
    "outputs": [
@@ -52,7 +56,7 @@
        "AIMessage(content='3 + 9 equals 12.', additional_kwargs={}, example=False)"
       ]
      },
-     "execution_count": 78,
+     "execution_count": 5,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -73,17 +77,18 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 139,
+   "execution_count": 9,
    "id": "80b3b5f6-5d58-44b9-807e-cce9a46bf49f",
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.schema.runnable import RunnableConfig"
+    "from langchain.schema.runnable import RunnableConfig\n",
+    "from langchain.schema.output_parser import StrOutputParser"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 149,
+   "execution_count": 10,
    "id": "ff0daf0c-49dd-4d21-9772-e5fa133c5f36",
    "metadata": {},
    "outputs": [],
@@ -109,7 +114,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 152,
+   "execution_count": 12,
    "id": "1a5e709e-9d75-48c7-bb9c-503251990505",
    "metadata": {},
    "outputs": [
@@ -132,6 +137,14 @@
     "    RunnableLambda(parse_or_fix).invoke(\"{foo: bar}\", {\"tags\": [\"my-tag\"], \"callbacks\": [cb]})\n",
     "    print(cb)"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "29f55c38",
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {
@@ -150,7 +163,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.10.1"
   }
  },
  "nbformat": 4,

docs/extras/expression_language/how_to/map.ipynb

@@ -12,18 +12,18 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 2,
    "id": "7e1873d6-d4b6-43ac-96a1-edcf178201e0",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "{'joke': AIMessage(content=\"Why don't bears wear shoes? \\nBecause they have bear feet!\", additional_kwargs={}, example=False),\n",
-       " 'poem': AIMessage(content=\"In twilight's embrace, a bear's gentle lumber,\\nSilent strength, nature's awe, a humble slumber.\", additional_kwargs={}, example=False)}"
+       "{'joke': AIMessage(content=\"Why don't bears wear shoes? \\n\\nBecause they have bear feet!\", additional_kwargs={}, example=False),\n",
+       " 'poem': AIMessage(content=\"In woodland depths, bear prowls with might,\\nSilent strength, nature's sovereign, day and night.\", additional_kwargs={}, example=False)}"
       ]
      },
-     "execution_count": 5,
+     "execution_count": 2,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -38,7 +38,7 @@
     "joke_chain = ChatPromptTemplate.from_template(\"tell me a joke about {topic}\") | model\n",
     "poem_chain = ChatPromptTemplate.from_template(\"write a 2-line poem about {topic}\") | model\n",
     "\n",
-    "map_chain = RunnableMap({\"joke\": chain1, \"poem\": chain2,})\n",
+    "map_chain = RunnableMap({\"joke\": joke_chain, \"poem\": poem_chain,})\n",
     "\n",
     "map_chain.invoke({\"topic\": \"bear\"})"
    ]
@@ -54,7 +54,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 3,
    "id": "267d1460-53c1-4fdb-b2c3-b6a1eb7fccff",
    "metadata": {},
    "outputs": [
@@ -64,7 +64,7 @@
        "'Harrison worked at Kensho.'"
       ]
      },
-     "execution_count": 4,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -191,7 +191,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.10.1"
   }
  },
  "nbformat": 4,

docs/extras/guides/deployments/template_repos.mdx

@@ -47,13 +47,13 @@ A minimal example on how to deploy LangChain to [Kinsta](https://kinsta.com) usi
 
 A minimal example of how to deploy LangChain to [Fly.io](https://fly.io/) using Flask.
 
-## [Digitalocean App Platform](https://github.com/homanp/digitalocean-langchain)
+## [DigitalOcean App Platform](https://github.com/homanp/digitalocean-langchain)
 
 A minimal example of how to deploy LangChain to DigitalOcean App Platform.
 
 ## [CI/CD Google Cloud Build + Dockerfile + Serverless Google Cloud Run](https://github.com/g-emarco/github-assistant)
 
-Boilerplate LangChain project on how to deploy to Google Cloud Run using Docker with Cloud Build CI/CD pipeline
+Boilerplate LangChain project on how to deploy to Google Cloud Run using Docker with Cloud Build CI/CD pipeline.
 
 ## [Google Cloud Run](https://github.com/homanp/gcp-langchain)
 

docs/extras/integrations/chat/fireworks.ipynb

@@ -0,0 +1,255 @@
+{
+ "cells": [
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "642fd21c-600a-47a1-be96-6e1438b421a9",
+   "metadata": {},
+   "source": [
+    "# ChatFireworks\n",
+    "\n",
+    ">[Fireworks](https://app.fireworks.ai/) accelerates product development on generative AI by creating an innovative AI experiment and production platform. \n",
+    "\n",
+    "This example goes over how to use LangChain to interact with `ChatFireworks` models."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "d00d850917865298",
+   "metadata": {
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
+   },
+   "outputs": [],
+   "source": [
+    "from langchain.chat_models.fireworks import ChatFireworks\n",
+    "from langchain.schema import SystemMessage, HumanMessage\n",
+    "import os"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f28ebf8b-f14f-46c7-9962-8b8dc42e31be",
+   "metadata": {},
+   "source": [
+    "# Setup\n",
+    "Contact Fireworks AI for the an API Key to access our models\n",
+    "\n",
+    "Set up your model using a model id. If the model is not set, the default model is fireworks-llama-v2-7b-chat."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "d096fb14-8acc-4047-9cd0-c842430c3a1d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Initialize a Fireworks Chat model\n",
+    "os.environ['FIREWORKS_API_KEY'] = \"<your_api_key>\"  # Change this to your own API key\n",
+    "chat = ChatFireworks(model=\"accounts/fireworks/models/llama-v2-13b-chat\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d8f13144-37cf-47a5-b5a0-e3cdf76d9a72",
+   "metadata": {},
+   "source": [
+    "# Calling the Model\n",
+    "\n",
+    "You can use the LLMs to call the model for specified message(s). \n",
+    "\n",
+    "See the full, most up-to-date model list on [app.fireworks.ai](https://app.fireworks.ai)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "72340871-ae2f-415f-b399-0777d32dc379",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# ChatFireworks Wrapper\n",
+    "system_message = SystemMessage(content=\"You are to chat with the user.\")\n",
+    "human_message = HumanMessage(content=\"Who are you?\")\n",
+    "response = chat([system_message, human_message])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "2d6ef879-69e3-422b-8379-bb980b70fe55",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=\"Hello! My name is LLaMA, I'm a large language model trained by a team of researcher at Meta AI. My primary function is to assist users with tasks and answer questions to the best of my ability. I am capable of understanding and responding to natural language input, and I am here to help you with any questions or tasks you may have. Is there anything specific you would like to know or discuss?\", additional_kwargs={}, example=False)"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "response"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "68c6b1fa-2ff7-4a63-8d88-3cec302180b8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Setting additional parameters: temperature, max_tokens, top_p\n",
+    "chat = ChatFireworks(model=\"accounts/fireworks/models/llama-v2-13b-chat\", model_kwargs={\"temperature\":1, \"max_tokens\": 20, \"top_p\": 1})\n",
+    "system_message = SystemMessage(content=\"You are to chat with the user.\")\n",
+    "human_message = HumanMessage(content=\"How's the weather today?\")\n",
+    "response = chat([system_message, human_message])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "a09025f8-e4c3-4005-a8fc-c9c774b03a64",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=\"Oh, you know, it's just another beautiful day in the virtual world! The sun\", additional_kwargs={}, example=False)"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "response"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d93aa186-39cf-4e1a-aa32-01ed31d43bc8",
+   "metadata": {},
+   "source": [
+    "# ChatFireworks Wrapper with generate"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "cbe29efc-37c3-4c83-8b84-b8bba1a1e589",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chat = ChatFireworks()\n",
+    "message = HumanMessage(content=\"Hello\")\n",
+    "response = chat.generate([[message], [message]])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "35109f36-9519-47a6-a223-25639123e836",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "LLMResult(generations=[[ChatGeneration(text=\"Hello! It's nice to meet you. I'm here to help answer any questions you may have, while being respectful and safe. Please feel free to ask me anything, and I will do my best to provide helpful and positive responses. Is there something specific you would like to know or discuss?\", generation_info={'finish_reason': 'stop'}, message=AIMessage(content=\"Hello! It's nice to meet you. I'm here to help answer any questions you may have, while being respectful and safe. Please feel free to ask me anything, and I will do my best to provide helpful and positive responses. Is there something specific you would like to know or discuss?\", additional_kwargs={}, example=False))], [ChatGeneration(text=\"Hello! *smiling* I'm here to help you with any questions or concerns you may have. Please feel free to ask me anything, and I will do my best to provide helpful, respectful, and honest responses. I'm programmed to avoid any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content, and to provide socially unbiased and positive responses. Is there anything specific you would like to talk about or ask?\", generation_info={'finish_reason': 'stop'}, message=AIMessage(content=\"Hello! *smiling* I'm here to help you with any questions or concerns you may have. Please feel free to ask me anything, and I will do my best to provide helpful, respectful, and honest responses. I'm programmed to avoid any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content, and to provide socially unbiased and positive responses. Is there anything specific you would like to talk about or ask?\", additional_kwargs={}, example=False))]], llm_output={'model': 'accounts/fireworks/models/llama-v2-7b-chat'}, run=[RunInfo(run_id=UUID('f137463e-e1c7-454a-8b85-b999ce20e0f2')), RunInfo(run_id=UUID('f3ef1138-92de-4e01-900b-991e34a647a7'))])"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "response"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "92c2cabb-9eaf-4c49-b0e5-a5de5a7d920e",
+   "metadata": {},
+   "source": [
+    "# ChatFireworks Wrapper with stream"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "12717a29-fb7d-4a4d-860b-40435452b065",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "Hello! I'm just\n",
+      " an AI assistant,\n",
+      " here to help answer your\n",
+      " questions and provide information in\n",
+      " a responsible and respectful manner\n",
+      ". I'm not able\n",
+      " to access personal information or provide\n",
+      " any content that could be considered\n",
+      " harmful, uneth\n",
+      "ical, racist, sex\n",
+      "ist, toxic, dangerous\n",
+      ", or illegal. My purpose\n",
+      " is to assist and provide helpful\n",
+      " responses that are socially un\n",
+      "biased and positive in nature\n",
+      ". Is there something specific you\n",
+      " would like to know or discuss\n",
+      "?\n"
+     ]
+    }
+   ],
+   "source": [
+    "llm = ChatFireworks()\n",
+    "\n",
+    "for token in llm.stream(\"Who are you\"):\n",
+    "    print(token.content)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "02991e05-a38e-47d4-9ab3-7e630a8ead55",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/extras/integrations/chat/google_vertex_ai_palm.ipynb

@@ -5,7 +5,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Google Cloud Platform Vertex AI PaLM \n",
+    "# GCP Vertex AI \n",
     "\n",
     "Note: This is seperate from the Google PaLM integration. Google has chosen to offer an enterprise version of PaLM through GCP, and this supports the models made available through there. \n",
     "\n",
@@ -31,7 +31,7 @@
    },
    "outputs": [],
    "source": [
-    "#!pip install google-cloud-aiplatform"
+    "#!pip install langchain google-cloud-aiplatform"
    ]
   },
   {
@@ -41,12 +41,7 @@
    "outputs": [],
    "source": [
     "from langchain.chat_models import ChatVertexAI\n",
-    "from langchain.prompts.chat import (\n",
-    "    ChatPromptTemplate,\n",
-    "    SystemMessagePromptTemplate,\n",
-    "    HumanMessagePromptTemplate,\n",
-    ")\n",
-    "from langchain.schema import HumanMessage, SystemMessage"
+    "from langchain.prompts import ChatPromptTemplate"
    ]
   },
   {
@@ -60,82 +55,78 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 34,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "system = \"You are a helpful assistant who translate English to French\"\n",
+    "human = \"Translate this sentence from English to French. I love programming.\"\n",
+    "prompt = ChatPromptTemplate.from_messages(\n",
+    "    [(\"system\", system), (\"human\",  human)]\n",
+    ")\n",
+    "messages = prompt.format_messages()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "AIMessage(content='Sure, here is the translation of the sentence \"I love programming\" from English to French:\\n\\nJ\\'aime programmer.', additional_kwargs={}, example=False)"
+       "AIMessage(content=\" J'aime la programmation.\", additional_kwargs={}, example=False)"
       ]
      },
-     "execution_count": 4,
+     "execution_count": 9,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "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",
     "chat(messages)"
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "You can make use of templating by using a `MessagePromptTemplate`. You can build a `ChatPromptTemplate` from one or more `MessagePromptTemplates`. You can use `ChatPromptTemplate`'s `format_prompt` -- this returns a `PromptValue`, which you can convert to a string or Message object, depending on whether you want to use the formatted value as input to an llm or chat model.\n",
-    "\n",
-    "For convenience, there is a `from_template` method exposed on the template. If you were to use this template, this is what it would look like:"
+    "If we want to construct a simple chain that takes user specified parameters:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 12,
    "metadata": {},
    "outputs": [],
    "source": [
-    "template = (\n",
-    "    \"You are a helpful assistant that translates {input_language} to {output_language}.\"\n",
-    ")\n",
-    "system_message_prompt = SystemMessagePromptTemplate.from_template(template)\n",
-    "human_template = \"{text}\"\n",
-    "human_message_prompt = HumanMessagePromptTemplate.from_template(human_template)"
+    "system = \"You are a helpful assistant that translates {input_language} to {output_language}.\"\n",
+    "human = \"{text}\"\n",
+    "prompt = ChatPromptTemplate.from_messages(\n",
+    "    [(\"system\", system), (\"human\",  human)]\n",
+    ")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 13,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "AIMessage(content='Sure, here is the translation of \"I love programming\" in French:\\n\\nJ\\'aime programmer.', additional_kwargs={}, example=False)"
+       "AIMessage(content=' 私はプログラミングが大好きです。', additional_kwargs={}, example=False)"
       ]
      },
-     "execution_count": 7,
+     "execution_count": 13,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "chat_prompt = ChatPromptTemplate.from_messages(\n",
-    "    [system_message_prompt, human_message_prompt]\n",
-    ")\n",
-    "\n",
-    "# get a chat completion from the formatted messages\n",
-    "chat(\n",
-    "    chat_prompt.format_prompt(\n",
-    "        input_language=\"English\", output_language=\"French\", text=\"I love programming.\"\n",
-    "    ).to_messages()\n",
+    "chain = prompt | chat\n",
+    "chain.invoke(\n",
+    "    {\"input_language\": \"English\", \"output_language\": \"Japanese\", \"text\": \"I love programming\"}\n",
     ")"
    ]
   },
@@ -153,60 +144,129 @@
     "tags": []
    },
    "source": [
+    "## Code generation chat models\n",
     "You can now leverage the Codey API for code chat within Vertex AI. The model name is:\n",
     "- codechat-bison: for code assistance"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 18,
    "metadata": {
-    "execution": {
-     "iopub.execute_input": "2023-06-17T21:30:43.974841Z",
-     "iopub.status.busy": "2023-06-17T21:30:43.974431Z",
-     "iopub.status.idle": "2023-06-17T21:30:44.248119Z",
-     "shell.execute_reply": "2023-06-17T21:30:44.247362Z",
-     "shell.execute_reply.started": "2023-06-17T21:30:43.974820Z"
-    },
     "tags": []
    },
    "outputs": [],
    "source": [
-    "chat = ChatVertexAI(model_name=\"codechat-bison\")"
+    "chat = ChatVertexAI(\n",
+    "    model_name=\"codechat-bison\",\n",
+    "    max_output_tokens=1000,\n",
+    "    temperature=0.5\n",
+    ")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 20,
    "metadata": {
-    "execution": {
-     "iopub.execute_input": "2023-06-17T21:30:45.146093Z",
-     "iopub.status.busy": "2023-06-17T21:30:45.145752Z",
-     "iopub.status.idle": "2023-06-17T21:30:47.449126Z",
-     "shell.execute_reply": "2023-06-17T21:30:47.448609Z",
-     "shell.execute_reply.started": "2023-06-17T21:30:45.146069Z"
-    },
     "tags": []
    },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      " ```python\n",
+      "def is_prime(x): \n",
+      "    if (x <= 1): \n",
+      "        return False\n",
+      "    for i in range(2, x): \n",
+      "        if (x % i == 0): \n",
+      "            return False\n",
+      "    return True\n",
+      "```\n"
+     ]
+    }
+   ],
+   "source": [
+    "# For simple string in string out usage, we can use the `predict` method:\n",
+    "print(chat.predict(\"Write a Python function to identify all prime numbers\"))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Asynchronous calls\n",
+    "\n",
+    "We can make asynchronous calls via the `agenerate` and `ainvoke` methods."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import asyncio\n",
+    "# import nest_asyncio\n",
+    "# nest_asyncio.apply()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "AIMessage(content='The following Python function can be used to identify all prime numbers up to a given integer:\\n\\n```\\ndef is_prime(n):\\n  \"\"\"\\n  Determines whether the given integer is prime.\\n\\n  Args:\\n    n: The integer to be tested for primality.\\n\\n  Returns:\\n    True if n is prime, False otherwise.\\n  \"\"\"\\n\\n  # Check if n is divisible by 2.\\n  if n % 2 == 0:\\n    return False\\n\\n  # Check if n is divisible by any integer from 3 to the square root', additional_kwargs={}, example=False)"
+       "LLMResult(generations=[[ChatGeneration(text=\" J'aime la programmation.\", generation_info=None, message=AIMessage(content=\" J'aime la programmation.\", additional_kwargs={}, example=False))]], llm_output={}, run=[RunInfo(run_id=UUID('223599ef-38f8-4c79-ac6d-a5013060eb9d'))])"
       ]
      },
-     "execution_count": 4,
+     "execution_count": 35,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "messages = [\n",
-    "    HumanMessage(\n",
-    "        content=\"How do I create a python function to identify all prime numbers?\"\n",
-    "    )\n",
-    "]\n",
-    "chat(messages)"
+    "chat = ChatVertexAI(\n",
+    "    model_name=\"chat-bison\",\n",
+    "    max_output_tokens=1000,\n",
+    "    temperature=0.7,\n",
+    "    top_p=0.95,\n",
+    "    top_k=40,\n",
+    ")\n",
+    "\n",
+    "asyncio.run(chat.agenerate([messages]))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 36,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=' अहं प्रोग्रामिंग प्रेमामि', additional_kwargs={}, example=False)"
+      ]
+     },
+     "execution_count": 36,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "asyncio.run(chain.ainvoke({\"input_language\": \"English\", \"output_language\": \"Sanskrit\", \"text\": \"I love programming\"}))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Streaming calls\n",
+    "\n",
+    "We can also stream outputs via the `stream` method:"
    ]
   },
   {
@@ -214,14 +274,51 @@
    "execution_count": null,
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "import sys"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      " 1. China (1,444,216,107)\n",
+      "2. India (1,393,409,038)\n",
+      "3. United States (332,403,650)\n",
+      "4. Indonesia (273,523,615)\n",
+      "5. Pakistan (220,892,340)\n",
+      "6. Brazil (212,559,409)\n",
+      "7. Nigeria (206,139,589)\n",
+      "8. Bangladesh (164,689,383)\n",
+      "9. Russia (145,934,462)\n",
+      "10. Mexico (128,932,488)\n",
+      "11. Japan (126,476,461)\n",
+      "12. Ethiopia (115,063,982)\n",
+      "13. Philippines (109,581,078)\n",
+      "14. Egypt (102,334,404)\n",
+      "15. Vietnam (97,338,589)"
+     ]
+    }
+   ],
+   "source": [
+    "prompt = ChatPromptTemplate.from_messages([(\"human\", \"List out the 15 most populous countries in the world\")])\n",
+    "messages = prompt.format_messages()\n",
+    "for chunk in chat.stream(messages):\n",
+    "    sys.stdout.write(chunk.content)\n",
+    "    sys.stdout.flush()"
+   ]
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": "poetry-venv",
    "language": "python",
-   "name": "python3"
+   "name": "poetry-venv"
   },
   "language_info": {
    "codemirror_mode": {

docs/extras/integrations/chat/index.mdx

@@ -0,0 +1,39 @@
+---
+sidebar_position: 1
+sidebar_class_name: hidden
+---
+
+# Chat models
+
+import DocCardList from "@theme/DocCardList";
+
+## Features (natively supported)
+All ChatModels implement the Runnable interface, which comes with default implementations of all methods, ie. `ainvoke`, `batch`, `abatch`, `stream`, `astream`. This gives all ChatModels basic support for async, streaming and batch, which by default is implemented as below:
+- *Async* support defaults to calling the respective sync method in asyncio's default thread pool executor. This lets other async functions in your application make progress while the ChatModel is being executed, by moving this call to a background thread.
+- *Streaming* support defaults to returning an `Iterator` (or `AsyncIterator` in the case of async streaming) of a single value, the final result returned by the underlying ChatModel provider. This obviously doesn't give you token-by-token streaming, which requires native support from the ChatModel provider, but ensures your code that expects an iterator of tokens can work for any of our ChatModel integrations.
+- *Batch* support defaults to calling the underlying ChatModel in parallel for each input by making use of a thread pool executor (in the sync batch case) or `asyncio.gather` (in the async batch case). The concurrency can be controlled with the `max_concurrency` key in `RunnableConfig`.
+
+Each ChatModel integration can optionally provide native implementations to truly enable async or streaming.
+The table shows, for each integration, which features have been implemented with native support.
+
+Model|Invoke|Async invoke|Stream|Async stream
+:-|:-:|:-:|:-:|:-:
+AzureChatOpenAI|✅|✅|✅|✅
+BedrockChat|✅|❌|✅|❌
+ChatAnthropic|✅|✅|✅|✅
+ChatAnyscale|✅|✅|✅|✅
+ChatGooglePalm|✅|✅|❌|❌
+ChatJavelinAIGateway|✅|✅|❌|❌
+ChatKonko|✅|❌|❌|❌
+ChatLiteLLM|✅|✅|✅|✅
+ChatMLflowAIGateway|✅|❌|❌|❌
+ChatOllama|✅|❌|✅|❌
+ChatOpenAI|✅|✅|✅|✅
+ChatVertexAI|✅|✅|✅|❌
+ErnieBotChat|✅|❌|❌|❌
+JinaChat|✅|✅|✅|✅
+MiniMaxChat|✅|✅|❌|❌
+PromptLayerChatOpenAI|✅|❌|❌|❌
+QianfanChatEndpoint|✅|✅|✅|✅
+
+<DocCardList />

docs/extras/integrations/chat/vllm.ipynb

@@ -0,0 +1,174 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "eb7e5679-aa06-47e4-a1a3-b6b70e604017",
+   "metadata": {},
+   "source": [
+    "# vLLM Chat\n",
+    "\n",
+    "vLLM can be deployed as a server that mimics the OpenAI API protocol. This allows vLLM to be used as a drop-in replacement for applications using OpenAI API. This server can be queried in the same format as OpenAI API.\n",
+    "\n",
+    "This notebook covers how to get started with vLLM chat models using langchain's `ChatOpenAI` **as it is**."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "060a2e3d-d42f-4221-bd09-a9a06544dcd3",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from langchain.chat_models import ChatOpenAI\n",
+    "from langchain.prompts.chat import (\n",
+    "    ChatPromptTemplate,\n",
+    "    SystemMessagePromptTemplate,\n",
+    "    AIMessagePromptTemplate,\n",
+    "    HumanMessagePromptTemplate,\n",
+    ")\n",
+    "from langchain.schema import AIMessage, HumanMessage, SystemMessage"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "bf24d732-68a9-44fd-b05d-4903ce5620c6",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "inference_server_url = \"http://localhost:8000/v1\"\n",
+    "\n",
+    "chat = ChatOpenAI(\n",
+    "    model=\"mosaicml/mpt-7b\",\n",
+    "    openai_api_key=\"EMPTY\",\n",
+    "    openai_api_base=inference_server_url,\n",
+    "    max_tokens=5,\n",
+    "    temperature=0,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "aea4e363-5688-4b07-82ed-6aa8153c2377",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=' Io amo programmare', additional_kwargs={}, example=False)"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "messages = [\n",
+    "    SystemMessage(\n",
+    "        content=\"You are a helpful assistant that translates English to Italian.\"\n",
+    "    ),\n",
+    "    HumanMessage(\n",
+    "        content=\"Translate the following sentence from English to Italian: I love programming.\"\n",
+    "    ),\n",
+    "]\n",
+    "chat(messages)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "55fc7046-a6dc-4720-8c0c-24a6db76a4f4",
+   "metadata": {},
+   "source": [
+    "You can make use of templating by using a `MessagePromptTemplate`. You can build a `ChatPromptTemplate` from one or more `MessagePromptTemplates`. You can use ChatPromptTemplate's format_prompt -- this returns a `PromptValue`, which you can convert to a string or `Message` object, depending on whether you want to use the formatted value as input to an llm or chat model.\n",
+    "\n",
+    "For convenience, there is a `from_template` method exposed on the template. If you were to use this template, this is what it would look like:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "123980e9-0dee-4ce5-bde6-d964dd90129c",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "template = (\n",
+    "    \"You are a helpful assistant that translates {input_language} to {output_language}.\"\n",
+    ")\n",
+    "system_message_prompt = SystemMessagePromptTemplate.from_template(template)\n",
+    "human_template = \"{text}\"\n",
+    "human_message_prompt = HumanMessagePromptTemplate.from_template(human_template)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "b2fb8c59-8892-4270-85a2-4f8ab276b75d",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=' I love programming too.', additional_kwargs={}, example=False)"
+      ]
+     },
+     "execution_count": 17,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chat_prompt = ChatPromptTemplate.from_messages(\n",
+    "    [system_message_prompt, human_message_prompt]\n",
+    ")\n",
+    "\n",
+    "# get a chat completion from the formatted messages\n",
+    "chat(\n",
+    "    chat_prompt.format_prompt(\n",
+    "        input_language=\"English\", output_language=\"Italian\", text=\"I love programming.\"\n",
+    "    ).to_messages()\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0bbd9861-2b94-4920-8708-b690004f4c4d",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "conda_pytorch_p310",
+   "language": "python",
+   "name": "conda_pytorch_p310"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/extras/integrations/document_loaders/async_html.ipynb

@@ -5,9 +5,9 @@
    "id": "e229e34c",
    "metadata": {},
    "source": [
-    "# AsyncHtmlLoader\n",
+    "# AsyncHtml\n",
     "\n",
-    "AsyncHtmlLoader loads raw HTML from a list of urls concurrently."
+    "`AsyncHtmlLoader` loads raw HTML from a list of URLs concurrently."
    ]
   },
   {
@@ -99,7 +99,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.16"
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,

docs/extras/integrations/document_loaders/aws_s3_directory.ipynb

@@ -1,156 +1,159 @@
 {
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "a634365e",
-   "metadata": {},
-   "source": [
-    "# AWS S3 Directory\n",
-    "\n",
-    ">[Amazon Simple Storage Service (Amazon S3)](https://docs.aws.amazon.com/AmazonS3/latest/userguide/using-folders.html) is an object storage service\n",
-    "\n",
-    ">[AWS S3 Directory](https://docs.aws.amazon.com/AmazonS3/latest/userguide/using-folders.html)\n",
-    "\n",
-    "This covers how to load document objects from an `AWS S3 Directory` object."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "49815096",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "#!pip install boto3"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "2f0cd6a5",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from langchain.document_loaders import S3DirectoryLoader"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "321cc7f1",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "loader = S3DirectoryLoader(\"testing-hwc\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "2b11d155",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "loader.load()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "0690c40a",
-   "metadata": {},
-   "source": [
-    "## Specifying a prefix\n",
-    "You can also specify a prefix for more finegrained control over what files to load."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "72d44781",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "loader = S3DirectoryLoader(\"testing-hwc\", prefix=\"fake\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "2d3c32db",
-   "metadata": {},
-   "outputs": [
+  "cells": [
     {
-     "data": {
-      "text/plain": [
-       "[Document(page_content='Lorem ipsum dolor sit amet.', lookup_str='', metadata={'source': 's3://testing-hwc/fake.docx'}, lookup_index=0)]"
+      "cell_type": "markdown",
+      "id": "a634365e",
+      "metadata": {},
+      "source": [
+        "# AWS S3 Directory\n",
+        "\n",
+        ">[Amazon Simple Storage Service (Amazon S3)](https://docs.aws.amazon.com/AmazonS3/latest/userguide/using-folders.html) is an object storage service\n",
+        "\n",
+        ">[AWS S3 Directory](https://docs.aws.amazon.com/AmazonS3/latest/userguide/using-folders.html)\n",
+        "\n",
+        "This covers how to load document objects from an `AWS S3 Directory` object."
       ]
-     },
-     "execution_count": 6,
-     "metadata": {},
-     "output_type": "execute_result"
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "49815096",
+      "metadata": {
+        "tags": []
+      },
+      "outputs": [],
+      "source": [
+        "#!pip install boto3"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 2,
+      "id": "2f0cd6a5",
+      "metadata": {
+        "tags": []
+      },
+      "outputs": [],
+      "source": [
+        "from langchain.document_loaders import S3DirectoryLoader"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 3,
+      "id": "321cc7f1",
+      "metadata": {
+        "tags": []
+      },
+      "outputs": [],
+      "source": [
+        "loader = S3DirectoryLoader(\"testing-hwc\")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "2b11d155",
+      "metadata": {
+        "tags": []
+      },
+      "outputs": [],
+      "source": [
+        "loader.load()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "0690c40a",
+      "metadata": {},
+      "source": [
+        "## Specifying a prefix\n",
+        "You can also specify a prefix for more finegrained control over what files to load."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 5,
+      "id": "72d44781",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "loader = S3DirectoryLoader(\"testing-hwc\", prefix=\"fake\")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 6,
+      "id": "2d3c32db",
+      "metadata": {},
+      "outputs": [
+        {
+          "data": {
+            "text/plain": [
+              "[Document(page_content='Lorem ipsum dolor sit amet.', lookup_str='', metadata={'source': 's3://testing-hwc/fake.docx'}, lookup_index=0)]"
+            ]
+          },
+          "execution_count": 6,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "loader.load()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "## Configuring the AWS Boto3 client\n",
+        "You can configure the AWS [Boto3](https://boto3.amazonaws.com/v1/documentation/api/latest/index.html) client by passing\n",
+        "named arguments when creating the S3DirectoryLoader.\n",
+        "This is useful for instance when AWS credentials can't be set as environment variables.\n",
+        "See the [list of parameters](https://boto3.amazonaws.com/v1/documentation/api/latest/reference/core/session.html#boto3.session.Session) that can be configured."
+      ],
+      "metadata": {},
+      "id": "91a7ac07"
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "outputs": [],
+      "source": [
+        "loader = S3DirectoryLoader(\"testing-hwc\", aws_access_key_id=\"xxxx\", aws_secret_access_key=\"yyyy\")"
+      ],
+      "metadata": {},
+      "id": "f485ec8c"
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "outputs": [],
+      "source": [
+        "loader.load()"
+      ],
+      "metadata": {},
+      "id": "c0fa76ae"
+    }
+  ],
+  "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"
     }
-   ],
-   "source": [
-    "loader.load()"
-   ]
   },
-  {
-   "cell_type": "markdown",
-   "source": [
-    "## Configuring the AWS Boto3 client\n",
-    "You can configure the AWS [Boto3](https://boto3.amazonaws.com/v1/documentation/api/latest/index.html) client by passing\n",
-    "named arguments when creating the S3DirectoryLoader.\n",
-    "This is useful for instance when AWS credentials can't be set as environment variables.\n",
-    "See the [list of parameters](https://boto3.amazonaws.com/v1/documentation/api/latest/reference/core/session.html#boto3.session.Session) that can be configured."
-   ],
-   "metadata": {}
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "outputs": [],
-   "source": [
-    "loader = S3DirectoryLoader(\"testing-hwc\", aws_access_key_id=\"xxxx\", aws_secret_access_key=\"yyyy\")"
-   ],
-   "metadata": {}
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "outputs": [],
-   "source": [
-    "loader.load()"
-   ],
-   "metadata": {}
-  }
- ],
- "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
-}
+  "nbformat": 4,
+  "nbformat_minor": 5
+}

docs/extras/integrations/document_loaders/aws_s3_file.ipynb

@@ -1,121 +1,122 @@
 {
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "66a7777e",
-   "metadata": {},
-   "source": [
-    "# AWS S3 File\n",
-    "\n",
-    ">[Amazon Simple Storage Service (Amazon S3)](https://docs.aws.amazon.com/AmazonS3/latest/userguide/using-folders.html) is an object storage service.\n",
-    "\n",
-    ">[AWS S3 Buckets](https://docs.aws.amazon.com/AmazonS3/latest/userguide/UsingBucket.html)\n",
-    "\n",
-    "This covers how to load document objects from an `AWS S3 File` object."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "9ec8a3b3",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.document_loaders import S3FileLoader"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "43128d8d",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "#!pip install boto3"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "35d6809a",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "loader = S3FileLoader(\"testing-hwc\", \"fake.docx\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "efd6be84",
-   "metadata": {},
-   "outputs": [
+  "cells": [
     {
-     "data": {
-      "text/plain": [
-       "[Document(page_content='Lorem ipsum dolor sit amet.', lookup_str='', metadata={'source': 's3://testing-hwc/fake.docx'}, lookup_index=0)]"
+      "cell_type": "markdown",
+      "id": "66a7777e",
+      "metadata": {},
+      "source": [
+        "# AWS S3 File\n",
+        "\n",
+        ">[Amazon Simple Storage Service (Amazon S3)](https://docs.aws.amazon.com/AmazonS3/latest/userguide/using-folders.html) is an object storage service.\n",
+        "\n",
+        ">[AWS S3 Buckets](https://docs.aws.amazon.com/AmazonS3/latest/userguide/UsingBucket.html)\n",
+        "\n",
+        "This covers how to load document objects from an `AWS S3 File` object."
       ]
-     },
-     "execution_count": 9,
-     "metadata": {},
-     "output_type": "execute_result"
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 1,
+      "id": "9ec8a3b3",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from langchain.document_loaders import S3FileLoader"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 2,
+      "id": "43128d8d",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "#!pip install boto3"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 8,
+      "id": "35d6809a",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "loader = S3FileLoader(\"testing-hwc\", \"fake.docx\")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 9,
+      "id": "efd6be84",
+      "metadata": {},
+      "outputs": [
+        {
+          "data": {
+            "text/plain": [
+              "[Document(page_content='Lorem ipsum dolor sit amet.', lookup_str='', metadata={'source': 's3://testing-hwc/fake.docx'}, lookup_index=0)]"
+            ]
+          },
+          "execution_count": 9,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "loader.load()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "93689594",
+      "metadata": {},
+      "source": [
+        "## Configuring the AWS Boto3 client\n",
+        "You can configure the AWS [Boto3](https://boto3.amazonaws.com/v1/documentation/api/latest/index.html) client by passing\n",
+        "named arguments when creating the S3DirectoryLoader.\n",
+        "This is useful for instance when AWS credentials can't be set as environment variables.\n",
+        "See the [list of parameters](https://boto3.amazonaws.com/v1/documentation/api/latest/reference/core/session.html#boto3.session.Session) that can be configured."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "outputs": [],
+      "source": [
+        "loader = S3FileLoader(\"testing-hwc\", \"fake.docx\", aws_access_key_id=\"xxxx\", aws_secret_access_key=\"yyyy\")"
+      ],
+      "metadata": {},
+      "id": "43106ee8"
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "outputs": [],
+      "source": [
+        "loader.load()"
+      ],
+      "metadata": {},
+      "id": "1764a727"
+    }
+  ],
+  "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"
     }
-   ],
-   "source": [
-    "loader.load()"
-   ]
   },
-  {
-   "cell_type": "markdown",
-   "id": "93689594",
-   "metadata": {},
-   "source": [
-    "## Configuring the AWS Boto3 client\n",
-    "You can configure the AWS [Boto3](https://boto3.amazonaws.com/v1/documentation/api/latest/index.html) client by passing\n",
-    "named arguments when creating the S3DirectoryLoader.\n",
-    "This is useful for instance when AWS credentials can't be set as environment variables.\n",
-    "See the [list of parameters](https://boto3.amazonaws.com/v1/documentation/api/latest/reference/core/session.html#boto3.session.Session) that can be configured."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "outputs": [],
-   "source": [
-    "loader = S3FileLoader(\"testing-hwc\", \"fake.docx\", aws_access_key_id=\"xxxx\", aws_secret_access_key=\"yyyy\")"
-   ],
-   "metadata": {}
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "outputs": [],
-   "source": [
-    "loader.load()"
-   ],
-   "metadata": {}
-  }
- ],
- "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
-}
-
+  "nbformat": 4,
+  "nbformat_minor": 5
+}

docs/extras/integrations/document_loaders/etherscan.ipynb

@@ -5,12 +5,17 @@
    "id": "1ab83660",
    "metadata": {},
    "source": [
-    "# Etherscan Loader\n",
+    "# Etherscan\n",
+    "\n",
+    ">[Etherscan](https://docs.etherscan.io/)  is the leading blockchain explorer, search, API and analytics platform for Ethereum, \n",
+    "a decentralized smart contracts platform.\n",
+    "\n",
+    "\n",
     "## Overview\n",
     "\n",
-    "The Etherscan loader use etherscan api to load transaction histories under specific account on Ethereum Mainnet.\n",
+    "The `Etherscan` loader use `Etherscan API` to load transacactions histories under specific account on `Ethereum Mainnet`.\n",
     "\n",
-    "You will need a Etherscan api key to proceed. The free api key has 5 calls per second quota.\n",
+    "You will need a `Etherscan api key` to proceed. The free api key has 5 calls per seconds quota.\n",
     "\n",
     "The loader supports the following six functinalities:\n",
     "* Retrieve normal transactions under specific account on Ethereum Mainet\n",
@@ -47,7 +52,7 @@
    "id": "d72d4e22",
    "metadata": {},
    "source": [
-    "# Setup"
+    "## Setup"
    ]
   },
   {
@@ -86,7 +91,7 @@
    "id": "3bcbb63e",
    "metadata": {},
    "source": [
-    "# Create a ERC20 transaction loader"
+    "## Create a ERC20 transaction loader"
    ]
   },
   {
@@ -136,7 +141,7 @@
    "id": "2a1ecce0",
    "metadata": {},
    "source": [
-    "# Create a normal transaction loader with customized parameters"
+    "## Create a normal transaction loader with customized parameters"
    ]
   },
   {
@@ -212,7 +217,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.2"
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,

docs/extras/integrations/document_loaders/mediawikidump.ipynb

@@ -4,7 +4,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# MediaWikiDump\n",
+    "# MediaWiki Dump\n",
     "\n",
     ">[MediaWiki XML Dumps](https://www.mediawiki.org/wiki/Manual:Importing_XML_dumps) contain the content of a wiki (wiki pages with all their revisions), without the site-related data. A XML dump does not create a full backup of the wiki database, the dump does not contain user accounts, images, edit logs, etc.\n",
     "\n",
@@ -122,7 +122,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.6"
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,

docs/extras/integrations/document_loaders/merge_doc.ipynb

@@ -5,7 +5,7 @@
    "id": "dd7c3503",
    "metadata": {},
    "source": [
-    "# MergeDocLoader\n",
+    "# Merge Documents Loader\n",
     "\n",
     "Merge the documents returned from a set of specified data loaders."
    ]
@@ -96,7 +96,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.16"
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,

docs/extras/integrations/document_loaders/nuclia.ipynb

@@ -1,17 +1,28 @@
 {
  "cells": [
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Nuclia Understanding API document loader\n",
+    "# Nuclia\n",
     "\n",
-    "[Nuclia](https://nuclia.com) automatically indexes your unstructured data from any internal and external source, providing optimized search results and generative answers. It can handle video and audio transcription, image content extraction, and document parsing.\n",
+    ">[Nuclia](https://nuclia.com) automatically indexes your unstructured data from any internal and external source, providing optimized search results and generative answers. It can handle video and audio transcription, image content extraction, and document parsing.\n",
     "\n",
-    "The Nuclia Understanding API supports the processing of unstructured data, including text, web pages, documents, and audio/video contents. It extracts all texts wherever they are (using speech-to-text or OCR when needed), it also extracts metadata, embedded files (like images in a PDF), and web links. If machine learning is enabled, it identifies entities, provides a summary of the content and generates embeddings for all the sentences.\n",
-    "\n",
-    "To use the Nuclia Understanding API, you need to have a Nuclia account. You can create one for free at [https://nuclia.cloud](https://nuclia.cloud), and then [create a NUA key](https://docs.nuclia.dev/docs/docs/using/understanding/intro)."
+    ">The `Nuclia Understanding API` supports the processing of unstructured data, including text, web pages, documents, and audio/video contents. It extracts all texts wherever they are (using speech-to-text or OCR when needed), it also extracts metadata, embedded files (like images in a PDF), and web links. If machine learning is enabled, it identifies entities, provides a summary of the content and generates embeddings for all the sentences.\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Setup"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "To use the `Nuclia Understanding API`, you need to have a Nuclia account. You can create one for free at [https://nuclia.cloud](https://nuclia.cloud), and then [create a NUA key](https://docs.nuclia.dev/docs/docs/using/understanding/intro)."
    ]
   },
   {
@@ -37,10 +48,11 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
+    "## Example\n",
+    "\n",
     "To use the Nuclia document loader, you need to instantiate a `NucliaUnderstandingAPI` tool:"
    ]
   },
@@ -67,7 +79,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -95,7 +106,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -121,7 +131,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "langchain",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -135,10 +145,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.5"
-  },
-  "orig_nbformat": 4
+   "version": "3.10.12"
+  }
  },
  "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
 }

docs/extras/integrations/document_loaders/pyspark_dataframe.ipynb

@@ -1,11 +1,10 @@
 {
  "cells": [
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# PySpark DataFrame Loader\n",
+    "# PySpark\n",
     "\n",
     "This notebook goes over how to load data from a [PySpark](https://spark.apache.org/docs/latest/api/python/) DataFrame."
    ]
@@ -147,9 +146,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.9"
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
 }

docs/extras/integrations/document_loaders/recursive_url.ipynb

@@ -5,7 +5,7 @@
    "id": "5a7cc773",
    "metadata": {},
    "source": [
-    "# Recursive URL Loader\n",
+    "# Recursive URL\n",
     "\n",
     "We may want to process load all URLs under a root directory.\n",
     "\n",
@@ -170,7 +170,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.16"
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,

docs/extras/integrations/document_loaders/youtube_audio.ipynb

@@ -1,16 +1,15 @@
 {
  "cells": [
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "e48afb8d",
    "metadata": {},
    "source": [
-    "# Loading documents from a YouTube url\n",
+    "# YouTube audio\n",
     "\n",
     "Building chat or QA applications on YouTube videos is a topic of high interest.\n",
     "\n",
-    "Below we show how to easily go from a YouTube url to text to chat!\n",
+    "Below we show how to easily go from a `YouTube url` to `audio of the video` to `text` to `chat`!\n",
     "\n",
     "We wil use the `OpenAIWhisperParser`, which will use the OpenAI Whisper API to transcribe audio to text, \n",
     "and the  `OpenAIWhisperParserLocal` for local support and running on private clouds or on premise.\n",
@@ -82,9 +81,7 @@
    "cell_type": "code",
    "execution_count": 2,
    "id": "23e1e134",
-   "metadata": {
-    "scrolled": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
@@ -128,9 +125,7 @@
    "cell_type": "code",
    "execution_count": 3,
    "id": "72a94fd8",
-   "metadata": {
-    "scrolled": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
@@ -293,7 +288,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -307,7 +302,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.11"
+   "version": "3.10.12"
   },
   "vscode": {
    "interpreter": {

docs/extras/integrations/llms/fireworks.ipynb

@@ -19,7 +19,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.llms.fireworks import Fireworks, FireworksChat\n",
+    "from langchain.llms.fireworks import Fireworks\n",
     "from langchain.prompts import PromptTemplate\nfrom langchain.chains import LLMChain\n",
     "from langchain.prompts.chat import (\n",
     "    ChatPromptTemplate,\n",
@@ -48,8 +48,8 @@
    "outputs": [],
    "source": [
     "# Initialize a Fireworks LLM\n",
-    "os.environ['FIREWORKS_API_KEY'] = \"<YOUR_API_KEY>\"  # Change this to your own API key\n",
-    "llm = Fireworks(model_id=\"accounts/fireworks/models/llama-v2-13b-chat\")"
+    "os.environ['FIREWORKS_API_KEY'] = \"<your_api_key>\"  # Change this to your own API key\n",
+    "llm = Fireworks(model=\"accounts/fireworks/models/llama-v2-13b-chat\")"
    ]
   },
   {
@@ -61,28 +61,7 @@
     "\n",
     "You can use the LLMs to call the model for specified prompt(s). \n",
     "\n",
-    "Currently supported models: \n",
-    "\n",
-    "*   Falcon\n",
-    "    *   `accounts/fireworks/models/falcon-7b`\n",
-    "    *   `accounts/fireworks/models/falcon-40b-w8a16`\n",
-    "*   Llama 2\n",
-    "    *   `accounts/fireworks/models/llama-v2-7b`\n",
-    "    *   `accounts/fireworks/models/llama-v2-7b-w8a16`\n",
-    "    *   `accounts/fireworks/models/llama-v2-7b-chat`\n",
-    "    *   `accounts/fireworks/models/llama-v2-7b-chat-w8a16`\n",
-    "    *   `accounts/fireworks/models/llama-v2-13b`\n",
-    "    *   `accounts/fireworks/models/llama-v2-13b-w8a16`\n",
-    "    *   `accounts/fireworks/models/llama-v2-13b-chat`\n",
-    "    *   `accounts/fireworks/models/llama-v2-13b-chat-w8a16`\n",
-    "    *   `accounts/fireworks/models/llama-v2-70b-chat-4gpu`\n",
-    "*   StarCoder\n",
-    "    *   `accounts/fireworks/models/starcoder-1b-w8a16-1gpu`\n",
-    "    *   `accounts/fireworks/models/starcoder-3b-w8a16-1gpu`\n",
-    "    *   `accounts/fireworks/models/starcoder-7b-w8a16-1gpu`\n",
-    "    *   `accounts/fireworks/models/starcoder-16b-w8a16`\n",
-    "\n",
-    "See the full, most up-to-date list on [app.fireworks.ai](https://app.fireworks.ai)."
+    "See the full, most up-to-date model list on [app.fireworks.ai](https://app.fireworks.ai)."
    ]
   },
   {
@@ -95,29 +74,17 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Is it Tom Brady, Aaron Rodgers, or someone else? It's a tough question to answer, and there are strong arguments for each of these quarterbacks. Here are some of the reasons why each of these quarterbacks could be considered the best:\n",
       "\n",
-      "Tom Brady:\n",
       "\n",
-      "* He has the most Super Bowl wins (6) of any quarterback in NFL history.\n",
-      "* He has been named Super Bowl MVP four times, more than any other player.\n",
-      "* He has led the New England Patriots to 18 playoff victories, the most in NFL history.\n",
-      "* He has thrown for over 70,000 yards in his career, the most of any quarterback in NFL history.\n",
-      "* He has thrown for 50 or more touchdowns in a season four times, the most of any quarterback in NFL history.\n",
+      "It's a question that's been debated for years, and there are plenty of strong candidates. Here are some of the top quarterbacks in the league right now:\n",
       "\n",
-      "Aaron Rodgers:\n",
+      "1. Tom Brady (New England Patriots): Brady is widely considered one of the greatest quarterbacks of all time, and for good reason. He's led the Patriots to six Super Bowl wins and has been named Super Bowl MVP four times. He's known for his precision passing and ability to read defenses.\n",
+      "2. Aaron Rodgers (Green Bay Packers): Rodgers is another top-tier quarterback who's known for his accuracy and ability to make plays outside of the pocket. He's led the Packers to a Super Bowl win and has been named NFL MVP twice.\n",
+      "3. Drew Brees (New Orleans Saints): Brees is one of the most prolific passers in NFL history, and he's shown no signs of slowing down. He's led the Saints to a Super Bowl win and has been named NFL MVP once.\n",
+      "4. Russell Wilson (Seattle Seahawks): Wilson is a dynamic quarterback who's known for his ability to make plays with his legs and his arm. He's led the Seahawks to a Super Bowl win and has been named NFL MVP once.\n",
+      "5. Patrick Mahomes (Kansas City Chiefs): Mahomes is a young quarterback who's quickly become one of the best in the league. He led the Chiefs to a Super Bowl win last season and has been named NFL MVP twice. He's known for his incredible arm talent and ability to make plays outside of the pocket.\n",
       "\n",
-      "* He has led the Green Bay Packers to a Super Bowl victory in 2010.\n",
-      "* He has been named Super Bowl MVP once.\n",
-      "* He has thrown for over 40,000 yards in his career, the most of any quarterback in NFL history.\n",
-      "* He has thrown for 40 or more touchdowns in a season three times, the most of any quarterback in NFL history.\n",
-      "* He has a career passer rating of 103.1, the highest of any quarterback in NFL history.\n",
-      "\n",
-      "So, who's the best quarterback in the NFL? It's a tough call, but here's my opinion:\n",
-      "\n",
-      "I think Aaron Rodgers is the best quarterback in the NFL right now. He has led the Packers to a Super Bowl victory and has had some incredible seasons, including the 2011 season when he threw for 45 touchdowns and just 6 interceptions. He has a strong arm, great accuracy, and is incredibly mobile for a quarterback of his size. He also has a great sense of timing and knows when to take risks and when to play it safe.\n",
-      "\n",
-      "Tom Brady is a close second, though. He has an incredible track record of success, including six Super Bowl victories, and has been one of the most consistent quarterbacks in the league for the past two decades. He has a strong arm and is incredibly accurate\n"
+      "Of course, there are other great quarterbacks in the league as well, such as Ben Roethlisberger, Matt Ryan, and Deshaun Watson. Ultimately, the \"best\" quarterback is a matter of personal opinion and depends on how you define \"best.\" Some people might value accuracy and precision passing, while others might prefer a quarterback who can make plays with their legs. Either way, the NFL is filled with talented quarterbacks who are making incredible plays every week.\n"
      ]
     }
    ],
@@ -137,7 +104,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "[[Generation(text='\\nThe best cricket player in 2016 is a matter of opinion, but some of the top contenders for the title include:\\n\\n1. Virat Kohli (India): Kohli had a phenomenal year in 2016, scoring over 1,000 runs in Test cricket, including four centuries, and averaging over 70. He also scored heavily in ODI cricket, with an average of over 80.\\n2. Steve Smith (Australia): Smith had a remarkable year in 2016, leading Australia to a Test series victory in India and scoring over 1,000 runs in the format, including five centuries. He also averaged over 60 in ODI cricket.\\n3. KL Rahul (India): Rahul had a breakout year in 2016, scoring over 1,000 runs in Test cricket, including four centuries, and averaging over 60. He also scored heavily in ODI cricket, with an average of over 70.\\n4. Joe Root (England): Root had a solid year in 2016, scoring over 1,000 runs in Test cricket, including four centuries, and averaging over 50. He also scored heavily in ODI cricket, with an average of over 80.\\n5. Quinton de Kock (South Africa): De Kock had a remarkable year in 2016, scoring over 1,000 runs in ODI cricket, including six centuries, and averaging over 80. He also scored heavily in Test cricket, with an average of over 50.\\n\\nThese are just a few of the top contenders for the title of best cricket player in 2016, but there were many other talented players who also had impressive years. Ultimately, the answer to this question is subjective and depends on individual opinions and criteria for evaluation.', generation_info=None)], [Generation(text=\"\\nThis is a tough one, as there are so many great players in the league right now. But if I had to choose one, I'd say LeBron James is the best basketball player in the league. He's a once-in-a-generation talent who can dominate the game in so many ways. He's got incredible speed, strength, and court vision, and he's always finding new ways to improve his game. Plus, he's been doing it at an elite level for over a decade now, which is just amazing.\\n\\nBut don't just take my word for it - there are plenty of other great players in the league who could make a strong case for being the best. Guys like Kevin Durant, Steph Curry, James Harden, and Giannis Antetokounmpo are all having incredible seasons, and they've all got their own unique skills and strengths that make them special. So ultimately, it's up to you to decide who you think is the best basketball player in the league.\", generation_info=None)]]\n"
+      "[[Generation(text=\"\\n\\nNote: This is a subjective question, and the answer will depend on individual opinions and perspectives.\\n\\nThere are many great cricket players, and it's difficult to identify a single best player. However, here are some of the top performers in 2016:\\n\\n1. Virat Kohli (India): Kohli had an outstanding year in all formats of the game, scoring heavily in Tests, ODIs, and T20Is. He was especially impressive in the Test series against England, where he scored four centuries and averaged over 100.\\n2. Steve Smith (Australia): Smith had a phenomenal year as well, leading Australia to a Test series win in India and averaging over 100 in the longer format. He also scored a century in the ODI series against Pakistan.\\n3. Kane Williamson (New Zealand): Williamson had a consistent year, scoring heavily in all formats and leading New Zealand to a Test series win against Australia. He also won the ICC Test Player of the Year award.\\n4. Joe Root (England): Root had a solid year, scoring three hundreds in the Test series against Pakistan and India, and averaging over 50 in Tests.\\n5. AB de Villiers (South Africa): De Villiers had a brilliant year in ODIs, scoring four hundreds and averaging over 100. He also had a good year in Tests, scoring two hundreds and averaging over 50.\\n6. Quinton de Kock (South Africa): De Kock had a great year behind the wickets, scoring heavily in all formats and averaging over 50 in Tests.\\n7. Rohit Sharma (India): Sharma had a fantastic year in ODIs, scoring four hundreds and averaging over 100. He also had a good year in Tests, scoring two hundreds and averaging over 40.\\n8. David Warner (Australia): Warner had a great year in ODIs, scoring three hundreds and averaging over 100. He also had a good year in Tests, scoring two hundreds and averaging over 40.\\n\\nThese are just a few examples of top performers in 2016, and opinions on the best player will vary depending on individual perspectives\", generation_info=None)], [Generation(text='\\n\\nThere are a lot of great players in the NBA, and opinions on who\\'s the best can vary depending on personal preferences and criteria for evaluation. However, here are some of the top candidates for the title of best basketball player in the league based on their recent performances and achievements:\\n\\n1. LeBron James: James is a four-time NBA champion and four-time MVP, and is widely regarded as one of the greatest players of all time. He has led the Los Angeles Lakers to the best record in the Western Conference this season and is averaging 25.7 points, 7.9 rebounds, and 7.4 assists per game.\\n2. Giannis Antetokounmpo: Antetokounmpo, known as the \"Greek Freak,\" is a dominant force in the paint and has led the Milwaukee Bucks to the best record in the Eastern Conference. He is averaging 30.5 points, 12.6 rebounds, and 5.9 assists per game, and is a strong contender for the MVP award.\\n3. Stephen Curry: Curry is a three-time NBA champion and two-time MVP, and is known for his incredible shooting ability. He has led the Golden State Warriors to the playoffs despite injuries to key players, and is averaging 23.5 points, 5.2 rebounds, and 5.2 assists per game.\\n4. Kevin Durant: Durant is a two-time NBA champion and four-time scoring champion, and is one of the most skilled scorers in the league. He has led the Brooklyn Nets to the playoffs in their first season since moving from New Jersey, and is averaging 27.2 points, 7.2 rebounds, and 6.4 assists per game.\\n5. James Harden: Harden is a three-time scoring champion and has led the Houston Rockets to the playoffs for the past eight seasons. He is averaging 35.4 points, 8.3 rebounds, and 7.5 assists per game, and is a strong contender for the MVP award.\\n\\nUltimately, determining the best basketball player in the league is subjective and depends on individual opinions and criteria. However, these five players are among', generation_info=None)]]\n"
      ]
     }
    ],
@@ -161,13 +128,13 @@
      "output_type": "stream",
      "text": [
       "\n",
-      "Kansas City in December is quite cold, with temperatures typically r\n"
+      "Kansas City's weather in December can be quite chilly,\n"
      ]
     }
    ],
    "source": [
     "# Setting additional parameters: temperature, max_tokens, top_p\n",
-    "llm = Fireworks(model_id=\"accounts/fireworks/models/llama-v2-13b-chat\", temperature=0.7, max_tokens=15, top_p=1.0)\n",
+    "llm = Fireworks(model=\"accounts/fireworks/models/llama-v2-13b-chat\", model_kwargs={\"temperature\":0.7, \"max_tokens\":15, \"top_p\":1.0})\n",
     "print(llm(\"What's the weather like in Kansas City in December?\"))"
    ]
   },
@@ -192,30 +159,140 @@
      "output_type": "stream",
      "text": [
       "\n",
-      "Naming a company can be a fun and creative process! Here are a few name ideas for a company that makes football helmets:\n",
       "\n",
-      "1. Helix Headgear: This name plays off the idea of the helix shape of a football helmet and could be a memorable and catchy name for a company.\n",
-      "2. Gridiron Gear: \"Gridiron\" is a term used to describe a football field, and \"gear\" refers to the products the company sells. This name is straightforward and easy to understand.\n",
-      "3. Cushion Crusaders: This name emphasizes the protective qualities of football helmets and could appeal to customers looking for safety-conscious products.\n",
-      "4. Helmet Heroes: This name has a fun, heroic tone and could appeal to customers looking for high-quality products.\n",
-      "5. Tackle Tech: \"Tackle\" is a term used in football to describe a player's attempt to stop an opponent, and \"tech\" refers to the technology used in the helmets. This name could appeal to customers interested in innovative products.\n",
-      "6. Padded Protection: This name emphasizes the protective qualities of football helmets and could appeal to customers looking for products that prioritize safety.\n",
-      "7. Gridiron Gear Co.: This name is simple and straightforward, and it clearly conveys the company's focus on football-related products.\n",
-      "8. Helmet Haven: This name has a soothing, protective tone and could appeal to customers looking for a reliable brand.\n",
+      "Assistant: That's a great question! There are many factors to consider when choosing a name for a company that makes football helmets. Here are a few suggestions:\n",
       "\n",
-      "Remember to choose a name that reflects your company's values and mission, and that resonates with your target market. Good luck with your company!\n"
+      "1. Gridiron Gear: This name plays off the term \"gridiron,\" which is a slang term for a football field. It also suggests that the company's products are high-quality and durable, like gear used in a gridiron game.\n",
+      "2. Helmet Headquarters: This name is straightforward and to the point. It clearly communicates that the company is a leading manufacturer of football helmets.\n",
+      "3. Tackle Tough: This name plays off the idea of tackling a tough opponent on the football field. It suggests that the company's helmets are designed to protect players from even the toughest hits.\n",
+      "4. Block Breakthrough: This name is a play on words that suggests the company's helmets are breaking through the competition. It also implies that the company is innovative and forward-thinking.\n",
+      "5. First Down Fashion: This name combines the idea of scoring a first down on the football field with the idea of fashionable clothing. It suggests that the company's helmets are not only functional but also stylish.\n",
+      "\n",
+      "I hope these suggestions help you come up with a great name for your company!\n"
      ]
     }
    ],
    "source": [
     "human_message_prompt = HumanMessagePromptTemplate.from_template(\"What is a good name for a company that makes {product}?\")\n",
     "chat_prompt_template = ChatPromptTemplate.from_messages([human_message_prompt])\n",
-    "chat = FireworksChat()\n",
+    "chat = Fireworks()\n",
     "chain = LLMChain(llm=chat, prompt=chat_prompt_template)\n",
     "output = chain.run(\"football helmets\")\n",
     "\n",
     "print(output)"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "25812db3-23a6-41dd-8636-5a49c52bb6eb",
+   "metadata": {},
+   "source": [
+    "# Run Stream"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "26d67ecf-9290-4ec2-8b39-ff17fc99620f",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      " Tom Brady, Aaron Rod\n",
+      "gers, or Drew Bre\n",
+      "es?\n",
+      "Some people might\n",
+      " say Tom Brady, who\n",
+      " has won six Super Bowls\n",
+      " and four Super Bowl MVP\n",
+      " awards, is the best quarter\n",
+      "back in the NFL. O\n",
+      "thers might argue that Aaron\n",
+      " Rodgers, who has led\n",
+      " his team to a Super Bowl\n",
+      " victory and has been named the\n",
+      " NFL MVP twice, is\n",
+      " the best. Still, others\n",
+      " might say that Drew Bre\n",
+      "es, who holds the NFL\n",
+      " record for most career passing yards\n",
+      " and has led his team to\n",
+      " a Super Bowl victory, is\n",
+      " the best.\n",
+      "But what\n",
+      " if I told you there'\n",
+      "s actually a fourth quarterback\n",
+      " who could make a strong case\n",
+      " for being the best in the\n",
+      " NFL? Meet Russell Wilson\n",
+      ", the Seattle Seahaw\n",
+      "ks' dynamic signal-call\n",
+      "er who has led his team\n",
+      " to a Super Bowl victory and\n",
+      " has been named the NFL M\n",
+      "VP twice.\n",
+      "Wilson\n",
+      " has a unique combination of physical\n",
+      " and mental skills that set him\n",
+      " apart from other quarterbacks\n",
+      " in the league. He'\n",
+      "s incredibly athletic,\n",
+      " with the ability to make plays\n",
+      " with his feet and his arm\n",
+      ", and he's also\n",
+      " highly intelligent, with a\n",
+      " quick mind and the ability to\n",
+      " read defenses like a pro\n",
+      ".\n",
+      "But what really\n",
+      " sets Wilson apart is his\n",
+      " leadership ability. He'\n",
+      "s a natural-born\n",
+      " leader who has a way\n",
+      " of inspiring his team\n",
+      "mates and getting them\n",
+      " to buy into his vision\n",
+      " for the game. He\n",
+      "'s also an excellent\n",
+      " communicator, who can\n",
+      " articulate his strategy\n",
+      " and game plan in a\n",
+      " way that his teamm\n",
+      "ates can understand and execute\n",
+      ".\n",
+      "So, who\n",
+      "'s the best quarter\n",
+      "back in the NFL?\n",
+      " It's hard to\n",
+      " say for sure, but\n",
+      " if you ask me,\n",
+      " Russell Wilson is definitely in\n",
+      " the conversation. He'\n",
+      "s got the physical skills\n",
+      ", the mental skills,\n",
+      " and the leadership ability to\n",
+      " be the best of the\n",
+      " best.\n"
+     ]
+    }
+   ],
+   "source": [
+    "llm = Fireworks()\n",
+    "generator = llm.stream(\"Who's the best quarterback in the NFL?\")\n",
+    "\n",
+    "for token in generator:\n",
+    "    print(token)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e3a35e0b-c875-493a-8143-d802d273247c",
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {

docs/extras/integrations/llms/google_vertex_ai_palm.ipynb

@@ -4,7 +4,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Google Vertex AI PaLM \n",
+    "# GCP Vertex AI\n",
     "\n",
     "**Note:** This is separate from the `Google PaLM` integration, it exposes [Vertex AI PaLM API](https://cloud.google.com/vertex-ai/docs/generative-ai/learn/overview) on `Google Cloud`. \n"
    ]
@@ -41,32 +41,56 @@
    },
    "outputs": [],
    "source": [
-    "#!pip install google-cloud-aiplatform"
+    "#!pip install langchain google-cloud-aiplatform"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
     "from langchain.llms import VertexAI"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      " Python is a widely used, interpreted, object-oriented, and high-level programming language with dynamic semantics, used for general-purpose programming. It is known for its readability, simplicity, and versatility. Here are some of the pros and cons of Python:\n",
+      "\n",
+      "**Pros:**\n",
+      "\n",
+      "- **Easy to learn:** Python is known for its simple and intuitive syntax, making it easy for beginners to learn. It has a relatively shallow learning curve compared to other programming languages.\n",
+      "\n",
+      "- **Versatile:** Python is a general-purpose programming language, meaning it can be used for a wide variety of tasks, including web development, data science, machine\n"
+     ]
+    }
+   ],
+   "source": [
+    "llm = VertexAI()\n",
+    "print(llm(\"What are some of the pros and cons of Python as a programming language?\"))"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Question-answering example"
+    "## Using in a chain"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.prompts import PromptTemplate\nfrom langchain.chains import LLMChain"
+    "from langchain.prompts import PromptTemplate"
    ]
   },
   {
@@ -78,17 +102,7 @@
     "template = \"\"\"Question: {question}\n",
     "\n",
     "Answer: Let's think step by step.\"\"\"\n",
-    "\n",
-    "prompt = PromptTemplate(template=template, input_variables=[\"question\"])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "llm = VertexAI()"
+    "prompt = PromptTemplate.from_template(template)"
    ]
   },
   {
@@ -97,29 +111,26 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "llm_chain = LLMChain(prompt=prompt, llm=llm)"
+    "chain = prompt | llm"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [
     {
-     "data": {
-      "text/plain": [
-       "'Justin Bieber was born on March 1, 1994. The Super Bowl in 1994 was won by the San Francisco 49ers.\\nThe final answer: San Francisco 49ers.'"
-      ]
-     },
-     "execution_count": 8,
-     "metadata": {},
-     "output_type": "execute_result"
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      " Justin Bieber was born on March 1, 1994. Bill Clinton was the president of the United States from January 20, 1993, to January 20, 2001.\n",
+      "The final answer is Bill Clinton\n"
+     ]
     }
    ],
    "source": [
-    "question = \"What NFL team won the Super Bowl in the year Justin Beiber was born?\"\n",
-    "\n",
-    "llm_chain.run(question)"
+    "question = \"Who was the president in the year Justin Beiber was born?\"\n",
+    "print(chain.invoke({\"question\": question}))"
    ]
   },
   {
@@ -140,78 +151,200 @@
     "- `code-gecko`: for code completion"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "metadata": {
-    "execution": {
-     "iopub.execute_input": "2023-06-17T21:16:53.149438Z",
-     "iopub.status.busy": "2023-06-17T21:16:53.149065Z",
-     "iopub.status.idle": "2023-06-17T21:16:53.421824Z",
-     "shell.execute_reply": "2023-06-17T21:16:53.421136Z",
-     "shell.execute_reply.started": "2023-06-17T21:16:53.149415Z"
-    },
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "llm = VertexAI(model_name=\"code-bison\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "metadata": {
-    "execution": {
-     "iopub.execute_input": "2023-06-17T21:17:11.179077Z",
-     "iopub.status.busy": "2023-06-17T21:17:11.178686Z",
-     "iopub.status.idle": "2023-06-17T21:17:11.182499Z",
-     "shell.execute_reply": "2023-06-17T21:17:11.181895Z",
-     "shell.execute_reply.started": "2023-06-17T21:17:11.179052Z"
-    },
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "llm_chain = LLMChain(prompt=prompt, llm=llm)"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": 15,
    "metadata": {
-    "execution": {
-     "iopub.execute_input": "2023-06-17T21:18:47.024785Z",
-     "iopub.status.busy": "2023-06-17T21:18:47.024230Z",
-     "iopub.status.idle": "2023-06-17T21:18:49.352249Z",
-     "shell.execute_reply": "2023-06-17T21:18:49.351695Z",
-     "shell.execute_reply.started": "2023-06-17T21:18:47.024762Z"
-    },
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "llm = VertexAI(model_name=\"code-bison\", max_output_tokens=1000, temperature=0.3)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "question = \"Write a python function that checks if a string is a valid email address\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {
     "tags": []
    },
    "outputs": [
     {
-     "data": {
-      "text/plain": [
-       "'```python\\ndef is_prime(n):\\n  \"\"\"\\n  Determines if a number is prime.\\n\\n  Args:\\n    n: The number to be tested.\\n\\n  Returns:\\n    True if the number is prime, False otherwise.\\n  \"\"\"\\n\\n  # Check if the number is 1.\\n  if n == 1:\\n    return False\\n\\n  # Check if the number is 2.\\n  if n == 2:\\n    return True\\n\\n'"
-      ]
-     },
-     "execution_count": 15,
-     "metadata": {},
-     "output_type": "execute_result"
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "```python\n",
+      "import re\n",
+      "\n",
+      "def is_valid_email(email):\n",
+      "    pattern = re.compile(r\"[^@]+@[^@]+\\.[^@]+\")\n",
+      "    return pattern.match(email)\n",
+      "```\n"
+     ]
     }
    ],
    "source": [
-    "question = \"Write a python function that identifies if the number is a prime number?\"\n",
-    "\n",
-    "llm_chain.run(question)"
+    "print(llm(question))"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Using models deployed on Vertex Model Garden"
+    "## Full generation info\n",
+    "\n",
+    "We can use the `generate` method to get back extra metadata like [safety attributes](https://cloud.google.com/vertex-ai/docs/generative-ai/learn/responsible-ai#safety_attribute_confidence_scoring) and not just text completions"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[[GenerationChunk(text='```python\\nimport re\\n\\ndef is_valid_email(email):\\n    pattern = re.compile(r\"[^@]+@[^@]+\\\\.[^@]+\")\\n    return pattern.match(email)\\n```', generation_info={'is_blocked': False, 'safety_attributes': {'Health': 0.1}})]]"
+      ]
+     },
+     "execution_count": 23,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "result = llm.generate([question])\n",
+    "result.generations"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Asynchronous calls\n",
+    "\n",
+    "With `agenerate` we can make asynchronous calls"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# If running in a Jupyter notebook you'll need to install nest_asyncio\n",
+    "\n",
+    "# !pip install nest_asyncio"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import asyncio\n",
+    "# import nest_asyncio\n",
+    "# nest_asyncio.apply()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "LLMResult(generations=[[GenerationChunk(text='```python\\nimport re\\n\\ndef is_valid_email(email):\\n    pattern = re.compile(r\"[^@]+@[^@]+\\\\.[^@]+\")\\n    return pattern.match(email)\\n```', generation_info={'is_blocked': False, 'safety_attributes': {'Health': 0.1}})]], llm_output=None, run=[RunInfo(run_id=UUID('caf74e91-aefb-48ac-8031-0c505fcbbcc6'))])"
+      ]
+     },
+     "execution_count": 25,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "asyncio.run(llm.agenerate([question]))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Streaming calls\n",
+    "\n",
+    "With `stream` we can stream results from the model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import sys"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "```python\n",
+      "import re\n",
+      "\n",
+      "def is_valid_email(email):\n",
+      "  \"\"\"\n",
+      "  Checks if a string is a valid email address.\n",
+      "\n",
+      "  Args:\n",
+      "    email: The string to check.\n",
+      "\n",
+      "  Returns:\n",
+      "    True if the string is a valid email address, False otherwise.\n",
+      "  \"\"\"\n",
+      "\n",
+      "  # Check for a valid email address format.\n",
+      "  if not re.match(r\"^[A-Za-z0-9\\.\\+_-]+@[A-Za-z0-9\\._-]+\\.[a-zA-Z]*$\", email):\n",
+      "    return False\n",
+      "\n",
+      "  # Check if the domain name exists.\n",
+      "  try:\n",
+      "    domain = email.split(\"@\")[1]\n",
+      "    socket.gethostbyname(domain)\n",
+      "  except socket.gaierror:\n",
+      "    return False\n",
+      "\n",
+      "  return True\n",
+      "```"
+     ]
+    }
+   ],
+   "source": [
+    "for chunk in llm.stream(question):\n",
+    "    sys.stdout.write(chunk)\n",
+    "    sys.stdout.flush()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Vertex Model Garden"
    ]
   },
   {
@@ -248,7 +381,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "llm(\"What is the meaning of life?\")"
+    "print(llm(\"What is the meaning of life?\"))"
    ]
   },
   {
@@ -264,8 +397,6 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.prompts import PromptTemplate\n",
-    "\n",
     "prompt = PromptTemplate.from_template(\"What is the meaning of {thing}?\")"
    ]
   },
@@ -275,9 +406,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "llm_oss_chain = prompt | llm\n",
-    "\n",
-    "llm_oss_chain.invoke({\"thing\": \"life\"})"
+    "chian = prompt | llm\n",
+    "print(chain.invoke({\"thing\": \"life\"}))"
    ]
   }
  ],

docs/extras/integrations/llms/huggingface_pipelines.ipynb

@@ -46,7 +46,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": null,
    "id": "165ae236-962a-4763-8052-c4836d78a5d2",
    "metadata": {
     "tags": []
@@ -75,18 +75,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": null,
    "id": "3acf0069",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      " First, we need to understand what is an electroencephalogram. An electroencephalogram is a recording of brain activity. It is a recording of brain activity that is made by placing electrodes on the scalp. The electrodes are placed\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "from langchain.prompts import PromptTemplate\n",
     "\n",
@@ -101,6 +93,42 @@
     "\n",
     "print(chain.invoke({\"question\": question}))"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "dbbc3a37",
+   "metadata": {},
+   "source": [
+    "### Batch GPU Inference\n",
+    "\n",
+    "If running on a device with GPU, you can also run inference on the GPU in batch mode."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "097ba62f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "gpu_llm = HuggingFacePipeline.from_model_id(\n",
+    "    model_id=\"bigscience/bloom-1b7\",\n",
+    "    task=\"text-generation\",\n",
+    "    device=0,  # -1 for CPU\n",
+    "    batch_size=2,  # adjust as needed based on GPU map and model size.\n",
+    "    model_kwargs={\"temperature\": 0, \"max_length\": 64},\n",
+    ")\n",
+    "\n",
+    "gpu_chain = prompt | gpu_llm.bind(stop=[\"\\n\\n\"])\n",
+    "\n",
+    "questions = []\n",
+    "for i in range(4):\n",
+    "    questions.append({\"question\": f\"What is the number {i} in french?\"})\n",
+    "\n",
+    "answers = gpu_chain.batch(questions)\n",
+    "for answer in answers:\n",
+    "    print(answer)"
+   ]
   }
  ],
  "metadata": {
@@ -119,7 +147,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.2"
+   "version": "3.8.10"
   }
  },
  "nbformat": 4,

docs/extras/integrations/llms/index.mdx

@@ -0,0 +1,93 @@
+---
+sidebar_position: 0
+sidebar_class_name: hidden
+---
+
+# LLMs
+
+import DocCardList from "@theme/DocCardList";
+
+## Features (natively supported)
+All LLMs implement the Runnable interface, which comes with default implementations of all methods, ie. `ainvoke`, `batch`, `abatch`, `stream`, `astream`. This gives all LLMs basic support for async, streaming and batch, which by default is implemented as below:
+- *Async* support defaults to calling the respective sync method in asyncio's default thread pool executor. This lets other async functions in your application make progress while the LLM is being executed, by moving this call to a background thread.
+- *Streaming* support defaults to returning an `Iterator` (or `AsyncIterator` in the case of async streaming) of a single value, the final result returned by the underlying LLM provider. This obviously doesn't give you token-by-token streaming, which requires native support from the LLM provider, but ensures your code that expects an iterator of tokens can work for any of our LLM integrations.
+- *Batch* support defaults to calling the underlying LLM in parallel for each input by making use of a thread pool executor (in the sync batch case) or `asyncio.gather` (in the async batch case). The concurrency can be controlled with the `max_concurrency` key in `RunnableConfig`.
+
+Each LLM integration can optionally provide native implementations for async, streaming or batch, which, for providers that support it, can be more efficient. The table shows, for each integration, which features have been implemented with native support.
+
+Model|Invoke|Async invoke|Stream|Async stream|Batch|Async batch
+:-|:-:|:-:|:-:|:-:|:-:|:-:
+AI21|✅|❌|❌|❌|❌|❌
+AlephAlpha|✅|❌|❌|❌|❌|❌
+AmazonAPIGateway|✅|❌|❌|❌|❌|❌
+Anthropic|✅|✅|✅|✅|❌|❌
+Anyscale|✅|❌|❌|❌|❌|❌
+Aviary|✅|❌|❌|❌|❌|❌
+AzureMLOnlineEndpoint|✅|❌|❌|❌|❌|❌
+AzureOpenAI|✅|✅|✅|✅|✅|✅
+Banana|✅|❌|❌|❌|❌|❌
+Baseten|✅|❌|❌|❌|❌|❌
+Beam|✅|❌|❌|❌|❌|❌
+Bedrock|✅|❌|✅|❌|❌|❌
+CTransformers|✅|✅|❌|❌|❌|❌
+CTranslate2|✅|❌|❌|❌|✅|❌
+CerebriumAI|✅|❌|❌|❌|❌|❌
+ChatGLM|✅|❌|❌|❌|❌|❌
+Clarifai|✅|❌|❌|❌|❌|❌
+Cohere|✅|✅|❌|❌|❌|❌
+Databricks|✅|❌|❌|❌|❌|❌
+DeepInfra|✅|❌|❌|❌|❌|❌
+DeepSparse|✅|❌|❌|❌|❌|❌
+EdenAI|✅|✅|❌|❌|❌|❌
+Fireworks|✅|✅|❌|❌|✅|✅
+FireworksChat|✅|✅|❌|❌|✅|✅
+ForefrontAI|✅|❌|❌|❌|❌|❌
+GPT4All|✅|❌|❌|❌|❌|❌
+GooglePalm|✅|❌|❌|❌|✅|❌
+GooseAI|✅|❌|❌|❌|❌|❌
+GradientLLM|✅|✅|❌|❌|❌|❌
+HuggingFaceEndpoint|✅|❌|❌|❌|❌|❌
+HuggingFaceHub|✅|❌|❌|❌|❌|❌
+HuggingFacePipeline|✅|❌|❌|❌|❌|❌
+HuggingFaceTextGenInference|✅|✅|✅|✅|❌|❌
+HumanInputLLM|✅|❌|❌|❌|❌|❌
+JavelinAIGateway|✅|✅|❌|❌|❌|❌
+KoboldApiLLM|✅|❌|❌|❌|❌|❌
+LlamaCpp|✅|❌|✅|❌|❌|❌
+ManifestWrapper|✅|❌|❌|❌|❌|❌
+Minimax|✅|❌|❌|❌|❌|❌
+MlflowAIGateway|✅|❌|❌|❌|❌|❌
+Modal|✅|❌|❌|❌|❌|❌
+MosaicML|✅|❌|❌|❌|❌|❌
+NIBittensorLLM|✅|❌|❌|❌|❌|❌
+NLPCloud|✅|❌|❌|❌|❌|❌
+Nebula|✅|❌|❌|❌|❌|❌
+OctoAIEndpoint|✅|❌|❌|❌|❌|❌
+Ollama|✅|❌|❌|❌|❌|❌
+OpaquePrompts|✅|❌|❌|❌|❌|❌
+OpenAI|✅|✅|✅|✅|✅|✅
+OpenLLM|✅|✅|❌|❌|❌|❌
+OpenLM|✅|✅|✅|✅|✅|✅
+Petals|✅|❌|❌|❌|❌|❌
+PipelineAI|✅|❌|❌|❌|❌|❌
+Predibase|✅|❌|❌|❌|❌|❌
+PredictionGuard|✅|❌|❌|❌|❌|❌
+PromptLayerOpenAI|✅|❌|❌|❌|❌|❌
+QianfanLLMEndpoint|✅|✅|✅|✅|❌|❌
+RWKV|✅|❌|❌|❌|❌|❌
+Replicate|✅|❌|✅|❌|❌|❌
+SagemakerEndpoint|✅|❌|❌|❌|❌|❌
+SelfHostedHuggingFaceLLM|✅|❌|❌|❌|❌|❌
+SelfHostedPipeline|✅|❌|❌|❌|❌|❌
+StochasticAI|✅|❌|❌|❌|❌|❌
+TextGen|✅|❌|❌|❌|❌|❌
+TitanTakeoff|✅|❌|✅|❌|❌|❌
+Tongyi|✅|❌|❌|❌|❌|❌
+VLLM|✅|❌|❌|❌|✅|❌
+VLLMOpenAI|✅|✅|✅|✅|✅|✅
+VertexAI|✅|✅|✅|❌|✅|✅
+VertexAIModelGarden|✅|✅|❌|❌|✅|✅
+Writer|✅|❌|❌|❌|❌|❌
+Xinference|✅|❌|❌|❌|❌|❌
+
+<DocCardList />

docs/extras/integrations/memory/dynamodb_chat_message_history.ipynb

@@ -1,350 +1,352 @@
 {
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "91c6a7ef",
-   "metadata": {},
-   "source": [
-    "# Dynamodb Chat Message History\n",
-    "\n",
-    "This notebook goes over how to use Dynamodb to store chat message history."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "3f608be0",
-   "metadata": {},
-   "source": [
-    "First make sure you have correctly configured the [AWS CLI](https://docs.aws.amazon.com/cli/latest/userguide/cli-chap-configure.html). Then make sure you have installed boto3."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "030d784f",
-   "metadata": {},
-   "source": [
-    "Next, create the DynamoDB Table where we will be storing messages:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "id": "93ce1811",
-   "metadata": {},
-   "outputs": [
+  "cells": [
     {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "0\n"
-     ]
-    }
-   ],
-   "source": [
-    "import boto3\n",
-    "\n",
-    "# Get the service resource.\n",
-    "dynamodb = boto3.resource(\"dynamodb\")\n",
-    "\n",
-    "# Create the DynamoDB table.\n",
-    "table = dynamodb.create_table(\n",
-    "    TableName=\"SessionTable\",\n",
-    "    KeySchema=[{\"AttributeName\": \"SessionId\", \"KeyType\": \"HASH\"}],\n",
-    "    AttributeDefinitions=[{\"AttributeName\": \"SessionId\", \"AttributeType\": \"S\"}],\n",
-    "    BillingMode=\"PAY_PER_REQUEST\",\n",
-    ")\n",
-    "\n",
-    "# Wait until the table exists.\n",
-    "table.meta.client.get_waiter(\"table_exists\").wait(TableName=\"SessionTable\")\n",
-    "\n",
-    "# Print out some data about the table.\n",
-    "print(table.item_count)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "1a9b310b",
-   "metadata": {},
-   "source": [
-    "## DynamoDBChatMessageHistory"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "id": "d15e3302",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.memory.chat_message_histories import DynamoDBChatMessageHistory\n",
-    "\n",
-    "history = DynamoDBChatMessageHistory(table_name=\"SessionTable\", session_id=\"0\")\n",
-    "\n",
-    "history.add_user_message(\"hi!\")\n",
-    "\n",
-    "history.add_ai_message(\"whats up?\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "id": "64fc465e",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": "[HumanMessage(content='hi!', additional_kwargs={}, example=False),\n AIMessage(content='whats up?', additional_kwargs={}, example=False),\n HumanMessage(content='hi!', additional_kwargs={}, example=False),\n AIMessage(content='whats up?', additional_kwargs={}, example=False)]"
-     },
-     "execution_count": 12,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "history.messages"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "955f1b15",
-   "metadata": {},
-   "source": [
-    "## DynamoDBChatMessageHistory with Custom Endpoint URL\n",
-    "\n",
-    "Sometimes it is useful to specify the URL to the AWS endpoint to connect to. For instance, when you are running locally against [Localstack](https://localstack.cloud/). For those cases you can specify the URL via the `endpoint_url` parameter in the constructor."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "id": "225713c8",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.memory.chat_message_histories import DynamoDBChatMessageHistory\n",
-    "\n",
-    "history = DynamoDBChatMessageHistory(\n",
-    "    table_name=\"SessionTable\",\n",
-    "    session_id=\"0\",\n",
-    "    endpoint_url=\"http://localhost.localstack.cloud:4566\",\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "source": [
-    "## DynamoDBChatMessageHistory With Different Keys Composite Keys\n",
-    "The default key for DynamoDBChatMessageHistory is ```{\"SessionId\": self.session_id}```, but you can modify this to match your table design.\n",
-    "\n",
-    "### Primary Key Name\n",
-    "You may modify the primary key by passing in a primary_key_name value in the constructor, resulting in the following:\n",
-    "```{self.primary_key_name: self.session_id}```\n",
-    "\n",
-    "### Composite Keys\n",
-    "When using an existing DynamoDB table, you may need to modify the key structure from the default of to something including a Sort Key. To do this you may use the ```key``` parameter.\n",
-    "\n",
-    "Passing a value for key will override the primary_key parameter, and the resulting key structure will be the passed value.\n"
-   ],
-   "metadata": {
-    "collapsed": false
-   }
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "0\n"
-     ]
+      "cell_type": "markdown",
+      "id": "91c6a7ef",
+      "metadata": {},
+      "source": [
+        "# Dynamodb Chat Message History\n",
+        "\n",
+        "This notebook goes over how to use Dynamodb to store chat message history."
+      ]
     },
     {
-     "data": {
-      "text/plain": "[HumanMessage(content='hello, composite dynamodb table!', additional_kwargs={}, example=False)]"
-     },
-     "execution_count": 14,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain.memory.chat_message_histories import DynamoDBChatMessageHistory\n",
-    "\n",
-    "composite_table = dynamodb.create_table(\n",
-    "    TableName=\"CompositeTable\",\n",
-    "    KeySchema=[{\"AttributeName\": \"PK\", \"KeyType\": \"HASH\"}, {\"AttributeName\": \"SK\", \"KeyType\": \"RANGE\"}],\n",
-    "    AttributeDefinitions=[{\"AttributeName\": \"PK\", \"AttributeType\": \"S\"}, {\"AttributeName\": \"SK\", \"AttributeType\": \"S\"}],\n",
-    "    BillingMode=\"PAY_PER_REQUEST\",\n",
-    ")\n",
-    "\n",
-    "# Wait until the table exists.\n",
-    "composite_table.meta.client.get_waiter(\"table_exists\").wait(TableName=\"CompositeTable\")\n",
-    "\n",
-    "# Print out some data about the table.\n",
-    "print(composite_table.item_count)\n",
-    "\n",
-    "my_key = {\n",
-    "    \"PK\": \"session_id::0\",\n",
-    "    \"SK\":  \"langchain_history\",\n",
-    "}\n",
-    "\n",
-    "composite_key_history = DynamoDBChatMessageHistory(\n",
-    "    table_name=\"CompositeTable\",\n",
-    "    session_id=\"0\",\n",
-    "    endpoint_url=\"http://localhost.localstack.cloud:4566\",\n",
-    "    key=my_key,\n",
-    ")\n",
-    "\n",
-    "composite_key_history.add_user_message(\"hello, composite dynamodb table!\")\n",
-    "\n",
-    "composite_key_history.messages"
-   ],
-   "metadata": {
-    "collapsed": false
-   }
-  },
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "id": "3b33c988",
-   "metadata": {},
-   "source": [
-    "## Agent with DynamoDB Memory"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "id": "f92d9499",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.agents import Tool\n",
-    "from langchain.memory import ConversationBufferMemory\n",
-    "from langchain.chat_models import ChatOpenAI\n",
-    "from langchain.agents import initialize_agent\n",
-    "from langchain.agents import AgentType\n",
-    "from langchain.utilities import PythonREPL\n",
-    "from getpass import getpass\n",
-    "\n",
-    "message_history = DynamoDBChatMessageHistory(table_name=\"SessionTable\", session_id=\"1\")\n",
-    "memory = ConversationBufferMemory(\n",
-    "    memory_key=\"chat_history\", chat_memory=message_history, return_messages=True\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 16,
-   "id": "1167eeba",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "python_repl = PythonREPL()\n",
-    "\n",
-    "# You can create the tool to pass to an agent\n",
-    "tools = [\n",
-    "    Tool(\n",
-    "        name=\"python_repl\",\n",
-    "        description=\"A Python shell. Use this to execute python commands. Input should be a valid python command. If you want to see the output of a value, you should print it out with `print(...)`.\",\n",
-    "        func=python_repl.run,\n",
-    "    )\n",
-    "]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 17,
-   "id": "fce085c5",
-   "metadata": {},
-   "outputs": [
+      "cell_type": "markdown",
+      "id": "3f608be0",
+      "metadata": {},
+      "source": [
+        "First make sure you have correctly configured the [AWS CLI](https://docs.aws.amazon.com/cli/latest/userguide/cli-chap-configure.html). Then make sure you have installed boto3."
+      ]
+    },
     {
-     "ename": "ValidationError",
-     "evalue": "1 validation error for ChatOpenAI\n__root__\n  Did not find openai_api_key, please add an environment variable `OPENAI_API_KEY` which contains it, or pass  `openai_api_key` as a named parameter. (type=value_error)",
-     "output_type": "error",
-     "traceback": [
-      "\u001B[0;31m---------------------------------------------------------------------------\u001B[0m",
-      "\u001B[0;31mValidationError\u001B[0m                           Traceback (most recent call last)",
-      "Cell \u001B[0;32mIn[17], line 1\u001B[0m\n\u001B[0;32m----> 1\u001B[0m llm \u001B[38;5;241m=\u001B[39m \u001B[43mChatOpenAI\u001B[49m\u001B[43m(\u001B[49m\u001B[43mtemperature\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[38;5;241;43m0\u001B[39;49m\u001B[43m)\u001B[49m\n\u001B[1;32m      2\u001B[0m agent_chain \u001B[38;5;241m=\u001B[39m initialize_agent(\n\u001B[1;32m      3\u001B[0m     tools,\n\u001B[1;32m      4\u001B[0m     llm,\n\u001B[0;32m   (...)\u001B[0m\n\u001B[1;32m      7\u001B[0m     memory\u001B[38;5;241m=\u001B[39mmemory,\n\u001B[1;32m      8\u001B[0m )\n",
-      "File \u001B[0;32m~/Documents/projects/langchain/libs/langchain/langchain/load/serializable.py:74\u001B[0m, in \u001B[0;36mSerializable.__init__\u001B[0;34m(self, **kwargs)\u001B[0m\n\u001B[1;32m     73\u001B[0m \u001B[38;5;28;01mdef\u001B[39;00m \u001B[38;5;21m__init__\u001B[39m(\u001B[38;5;28mself\u001B[39m, \u001B[38;5;241m*\u001B[39m\u001B[38;5;241m*\u001B[39mkwargs: Any) \u001B[38;5;241m-\u001B[39m\u001B[38;5;241m>\u001B[39m \u001B[38;5;28;01mNone\u001B[39;00m:\n\u001B[0;32m---> 74\u001B[0m     \u001B[38;5;28;43msuper\u001B[39;49m\u001B[43m(\u001B[49m\u001B[43m)\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[38;5;21;43m__init__\u001B[39;49m\u001B[43m(\u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43mkwargs\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m     75\u001B[0m     \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_lc_kwargs \u001B[38;5;241m=\u001B[39m kwargs\n",
-      "File \u001B[0;32m~/Documents/projects/langchain/.venv/lib/python3.9/site-packages/pydantic/main.py:341\u001B[0m, in \u001B[0;36mpydantic.main.BaseModel.__init__\u001B[0;34m()\u001B[0m\n",
-      "\u001B[0;31mValidationError\u001B[0m: 1 validation error for ChatOpenAI\n__root__\n  Did not find openai_api_key, please add an environment variable `OPENAI_API_KEY` which contains it, or pass  `openai_api_key` as a named parameter. (type=value_error)"
-     ]
+      "cell_type": "markdown",
+      "id": "030d784f",
+      "metadata": {},
+      "source": [
+        "Next, create the DynamoDB Table where we will be storing messages:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 10,
+      "id": "93ce1811",
+      "metadata": {},
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "0\n"
+          ]
+        }
+      ],
+      "source": [
+        "import boto3\n",
+        "\n",
+        "# Get the service resource.\n",
+        "dynamodb = boto3.resource(\"dynamodb\")\n",
+        "\n",
+        "# Create the DynamoDB table.\n",
+        "table = dynamodb.create_table(\n",
+        "    TableName=\"SessionTable\",\n",
+        "    KeySchema=[{\"AttributeName\": \"SessionId\", \"KeyType\": \"HASH\"}],\n",
+        "    AttributeDefinitions=[{\"AttributeName\": \"SessionId\", \"AttributeType\": \"S\"}],\n",
+        "    BillingMode=\"PAY_PER_REQUEST\",\n",
+        ")\n",
+        "\n",
+        "# Wait until the table exists.\n",
+        "table.meta.client.get_waiter(\"table_exists\").wait(TableName=\"SessionTable\")\n",
+        "\n",
+        "# Print out some data about the table.\n",
+        "print(table.item_count)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "1a9b310b",
+      "metadata": {},
+      "source": [
+        "## DynamoDBChatMessageHistory"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 11,
+      "id": "d15e3302",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from langchain.memory.chat_message_histories import DynamoDBChatMessageHistory\n",
+        "\n",
+        "history = DynamoDBChatMessageHistory(table_name=\"SessionTable\", session_id=\"0\")\n",
+        "\n",
+        "history.add_user_message(\"hi!\")\n",
+        "\n",
+        "history.add_ai_message(\"whats up?\")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 12,
+      "id": "64fc465e",
+      "metadata": {},
+      "outputs": [
+        {
+          "data": {
+            "text/plain": "[HumanMessage(content='hi!', additional_kwargs={}, example=False),\n AIMessage(content='whats up?', additional_kwargs={}, example=False),\n HumanMessage(content='hi!', additional_kwargs={}, example=False),\n AIMessage(content='whats up?', additional_kwargs={}, example=False)]"
+          },
+          "execution_count": 12,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "history.messages"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "955f1b15",
+      "metadata": {},
+      "source": [
+        "## DynamoDBChatMessageHistory with Custom Endpoint URL\n",
+        "\n",
+        "Sometimes it is useful to specify the URL to the AWS endpoint to connect to. For instance, when you are running locally against [Localstack](https://localstack.cloud/). For those cases you can specify the URL via the `endpoint_url` parameter in the constructor."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 13,
+      "id": "225713c8",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from langchain.memory.chat_message_histories import DynamoDBChatMessageHistory\n",
+        "\n",
+        "history = DynamoDBChatMessageHistory(\n",
+        "    table_name=\"SessionTable\",\n",
+        "    session_id=\"0\",\n",
+        "    endpoint_url=\"http://localhost.localstack.cloud:4566\",\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "## DynamoDBChatMessageHistory With Different Keys Composite Keys\n",
+        "The default key for DynamoDBChatMessageHistory is ```{\"SessionId\": self.session_id}```, but you can modify this to match your table design.\n",
+        "\n",
+        "### Primary Key Name\n",
+        "You may modify the primary key by passing in a primary_key_name value in the constructor, resulting in the following:\n",
+        "```{self.primary_key_name: self.session_id}```\n",
+        "\n",
+        "### Composite Keys\n",
+        "When using an existing DynamoDB table, you may need to modify the key structure from the default of to something including a Sort Key. To do this you may use the ```key``` parameter.\n",
+        "\n",
+        "Passing a value for key will override the primary_key parameter, and the resulting key structure will be the passed value.\n"
+      ],
+      "metadata": {
+        "collapsed": false
+      },
+      "id": "c9bc0693"
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 14,
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "0\n"
+          ]
+        },
+        {
+          "data": {
+            "text/plain": "[HumanMessage(content='hello, composite dynamodb table!', additional_kwargs={}, example=False)]"
+          },
+          "execution_count": 14,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "from langchain.memory.chat_message_histories import DynamoDBChatMessageHistory\n",
+        "\n",
+        "composite_table = dynamodb.create_table(\n",
+        "    TableName=\"CompositeTable\",\n",
+        "    KeySchema=[{\"AttributeName\": \"PK\", \"KeyType\": \"HASH\"}, {\"AttributeName\": \"SK\", \"KeyType\": \"RANGE\"}],\n",
+        "    AttributeDefinitions=[{\"AttributeName\": \"PK\", \"AttributeType\": \"S\"}, {\"AttributeName\": \"SK\", \"AttributeType\": \"S\"}],\n",
+        "    BillingMode=\"PAY_PER_REQUEST\",\n",
+        ")\n",
+        "\n",
+        "# Wait until the table exists.\n",
+        "composite_table.meta.client.get_waiter(\"table_exists\").wait(TableName=\"CompositeTable\")\n",
+        "\n",
+        "# Print out some data about the table.\n",
+        "print(composite_table.item_count)\n",
+        "\n",
+        "my_key = {\n",
+        "    \"PK\": \"session_id::0\",\n",
+        "    \"SK\":  \"langchain_history\",\n",
+        "}\n",
+        "\n",
+        "composite_key_history = DynamoDBChatMessageHistory(\n",
+        "    table_name=\"CompositeTable\",\n",
+        "    session_id=\"0\",\n",
+        "    endpoint_url=\"http://localhost.localstack.cloud:4566\",\n",
+        "    key=my_key,\n",
+        ")\n",
+        "\n",
+        "composite_key_history.add_user_message(\"hello, composite dynamodb table!\")\n",
+        "\n",
+        "composite_key_history.messages"
+      ],
+      "metadata": {
+        "collapsed": false
+      },
+      "id": "a7fa0331"
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "id": "3b33c988",
+      "metadata": {},
+      "source": [
+        "## Agent with DynamoDB Memory"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 15,
+      "id": "f92d9499",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from langchain.agents import Tool\n",
+        "from langchain.memory import ConversationBufferMemory\n",
+        "from langchain.chat_models import ChatOpenAI\n",
+        "from langchain.agents import initialize_agent\n",
+        "from langchain.agents import AgentType\n",
+        "from langchain.utilities import PythonREPL\n",
+        "from getpass import getpass\n",
+        "\n",
+        "message_history = DynamoDBChatMessageHistory(table_name=\"SessionTable\", session_id=\"1\")\n",
+        "memory = ConversationBufferMemory(\n",
+        "    memory_key=\"chat_history\", chat_memory=message_history, return_messages=True\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 16,
+      "id": "1167eeba",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "python_repl = PythonREPL()\n",
+        "\n",
+        "# You can create the tool to pass to an agent\n",
+        "tools = [\n",
+        "    Tool(\n",
+        "        name=\"python_repl\",\n",
+        "        description=\"A Python shell. Use this to execute python commands. Input should be a valid python command. If you want to see the output of a value, you should print it out with `print(...)`.\",\n",
+        "        func=python_repl.run,\n",
+        "    )\n",
+        "]"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 17,
+      "id": "fce085c5",
+      "metadata": {},
+      "outputs": [
+        {
+          "ename": "ValidationError",
+          "evalue": "1 validation error for ChatOpenAI\n__root__\n  Did not find openai_api_key, please add an environment variable `OPENAI_API_KEY` which contains it, or pass  `openai_api_key` as a named parameter. (type=value_error)",
+          "output_type": "error",
+          "traceback": [
+            "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+            "\u001b[0;31mValidationError\u001b[0m                           Traceback (most recent call last)",
+            "Cell \u001b[0;32mIn[17], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m llm \u001b[38;5;241m=\u001b[39m \u001b[43mChatOpenAI\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtemperature\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m      2\u001b[0m agent_chain \u001b[38;5;241m=\u001b[39m initialize_agent(\n\u001b[1;32m      3\u001b[0m     tools,\n\u001b[1;32m      4\u001b[0m     llm,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m      7\u001b[0m     memory\u001b[38;5;241m=\u001b[39mmemory,\n\u001b[1;32m      8\u001b[0m )\n",
+            "File \u001b[0;32m~/Documents/projects/langchain/libs/langchain/langchain/load/serializable.py:74\u001b[0m, in \u001b[0;36mSerializable.__init__\u001b[0;34m(self, **kwargs)\u001b[0m\n\u001b[1;32m     73\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m__init__\u001b[39m(\u001b[38;5;28mself\u001b[39m, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs: Any) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m---> 74\u001b[0m     \u001b[38;5;28;43msuper\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[38;5;21;43m__init__\u001b[39;49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m     75\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_lc_kwargs \u001b[38;5;241m=\u001b[39m kwargs\n",
+            "File \u001b[0;32m~/Documents/projects/langchain/.venv/lib/python3.9/site-packages/pydantic/main.py:341\u001b[0m, in \u001b[0;36mpydantic.main.BaseModel.__init__\u001b[0;34m()\u001b[0m\n",
+            "\u001b[0;31mValidationError\u001b[0m: 1 validation error for ChatOpenAI\n__root__\n  Did not find openai_api_key, please add an environment variable `OPENAI_API_KEY` which contains it, or pass  `openai_api_key` as a named parameter. (type=value_error)"
+          ]
+        }
+      ],
+      "source": [
+        "llm = ChatOpenAI(temperature=0)\n",
+        "agent_chain = initialize_agent(\n",
+        "    tools,\n",
+        "    llm,\n",
+        "    agent=AgentType.CHAT_CONVERSATIONAL_REACT_DESCRIPTION,\n",
+        "    verbose=True,\n",
+        "    memory=memory,\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "952a3103",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "agent_chain.run(input=\"Hello!\")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "54c4aaf4",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "agent_chain.run(input=\"Who owns Twitter?\")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "f9013118",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "agent_chain.run(input=\"My name is Bob.\")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "405e5315",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "agent_chain.run(input=\"Who am I?\")\n"
+      ]
+    }
+  ],
+  "metadata": {
+    "kernelspec": {
+      "display_name": "Python 3 (ipykernel)",
+      "language": "python",
+      "name": "python3"
+    },
+    "language_info": {
+      "codemirror_mode": {
+        "name": "ipython",
+        "version": 3
+      },
+      "file_extension": ".py",
+      "mimetype": "text/x-python",
+      "name": "python",
+      "nbconvert_exporter": "python",
+      "pygments_lexer": "ipython3",
+      "version": "3.11.3"
     }
-   ],
-   "source": [
-    "llm = ChatOpenAI(temperature=0)\n",
-    "agent_chain = initialize_agent(\n",
-    "    tools,\n",
-    "    llm,\n",
-    "    agent=AgentType.CHAT_CONVERSATIONAL_REACT_DESCRIPTION,\n",
-    "    verbose=True,\n",
-    "    memory=memory,\n",
-    ")"
-   ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "952a3103",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "agent_chain.run(input=\"Hello!\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "54c4aaf4",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "agent_chain.run(input=\"Who owns Twitter?\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "f9013118",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "agent_chain.run(input=\"My name is Bob.\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "405e5315",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "agent_chain.run(input=\"Who am I?\")\n"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.3"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}
+  "nbformat": 4,
+  "nbformat_minor": 5
+}

docs/extras/integrations/platforms/google.mdx

@@ -2,6 +2,35 @@
 
 All functionality related to Google Platform
 
+## LLMs
+
+### Vertex AI
+
+Access PaLM LLMs like `text-bison` and `code-bison` via Google Cloud.
+
+```python
+from langchain.llms import VertexAI
+```
+
+### Model Garden
+
+Access PaLM and hundreds of OSS models via Vertex AI Model Garden.
+
+```python
+from langchain.llms import VertexAIModelGarden
+```
+
+## Chat models
+
+### Vertex AI
+
+Access PaLM chat models like `chat-bison` and `codechat-bison` via Google Cloud.
+
+```python
+from langchain.chat_models import ChatVertexAI
+```
+
+
 ## Document Loader
 ### Google BigQuery
 

docs/extras/integrations/providers/argilla.mdx

@@ -5,7 +5,7 @@
 >[Argilla](https://argilla.io/) is an open-source data curation platform for LLMs.
 > Using Argilla, everyone can build robust language models through faster data curation 
 > using both human and machine feedback. We provide support for each step in the MLOps cycle, 
-> from data labeling to model monitoring.
+> from data labelling to model monitoring.
 
 ## Installation and Setup
 

docs/extras/integrations/providers/elasticsearch.mdx

@@ -18,7 +18,7 @@ Example: Run a single-node Elasticsearch instance with security disabled. This i
 
 #### Deploy Elasticsearch on Elastic Cloud
 
-Elastic Cloud is a managed Elasticsearch service. Signup for a [free trial](https://cloud.elastic.co/registration?storm=langchain-notebook).
+Elastic Cloud is a managed Elasticsearch service. Signup for a [free trial](https://cloud.elastic.co/registration?utm_source=langchain&utm_content=documentation).
 
 ### Install Client
 

docs/extras/integrations/retrievers/kay.ipynb

@@ -0,0 +1,207 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "263f914c-9d67-4316-8b3d-03c3b99ba9d8",
+   "metadata": {},
+   "source": [
+    "Kay.ai\n",
+    "=\n",
+    "\n",
+    "> Data API built for RAG 🕵️ We are curating the world's largest datasets as high-quality embeddings so your AI agents can retrieve context on the fly. Latest models, fast retrieval, and zero infra.\n",
+    "\n",
+    "This notebook shows you how to retrieve datasets supported by [Kay](https://kay.ai/). You can currently search SEC Filings and Press Releases of US companies. Visit [kay.ai](https://kay.ai) for the latest data drops. For any questions, join our [discord](https://discord.gg/hAnE4e5T6M) or [tweet at us](https://twitter.com/vishalrohra_)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "fc507b8e-ea51-417c-93da-42bf998a1195",
+   "metadata": {},
+   "source": [
+    "Installation\n",
+    "=\n",
+    "\n",
+    "First you will need to install the [`kay` package](https://pypi.org/project/kay/). You will also need an API key: you can get one for free at [https://kay.ai](https://kay.ai/). Once you have an API key, you must set it as an environment variable `KAY_API_KEY`.\n",
+    "\n",
+    "`KayAiRetriever` has a static `.create()` factory method that takes the following arguments:\n",
+    "\n",
+    "* `dataset_id: string` required -- A Kay dataset id. This is a collection of data about a particular entity such as companies, people, or places. For example, try `\"company\"` \n",
+    "* `data_type: List[string]` optional -- This is a category within a  dataset based on its origin or format, such as ‘SEC Filings’, ‘Press Releases’, or ‘Reports’ within the “company” dataset. For example, try [\"10-K\", \"10-Q\", \"PressRelease\"] under the “company” dataset. If left empty, Kay will retrieve the most relevant context across all types.\n",
+    "* `num_contexts: int` optional, defaults to 6 -- The number of document chunks to retrieve on each call to `get_relevant_documents()`"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c923bea0-585a-4f62-8662-efc167e8d793",
+   "metadata": {},
+   "source": [
+    "Examples\n",
+    "=\n",
+    "\n",
+    "Basic Retriever Usage\n",
+    "-"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "f7b8c99c-0341-4f3c-912f-a11e98f7de71",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdin",
+     "output_type": "stream",
+     "text": [
+      " ········\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Setup API key\n",
+    "from getpass import getpass\n",
+    "KAY_API_KEY = getpass()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "id": "b4d4d386-2a6b-4942-863e-9202f5a9f1d6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.retrievers import KayAiRetriever\n",
+    "import os\n",
+    "from kay.rag.retrievers import KayRetriever\n",
+    "os.environ[\"KAY_API_KEY\"] = KAY_API_KEY\n",
+    "retriever = KayAiRetriever.create(dataset_id=\"company\", data_types=[\"10-K\", \"10-Q\", \"PressRelease\"], num_contexts=3)\n",
+    "docs = retriever.get_relevant_documents(\"What were the biggest strategy changes and partnerships made by Roku in 2023??\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "04ee2d6b-c2ab-4e15-8a8b-afaf6ef8c0f6",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[Document(page_content='Company Name: ROKU INC\\nCompany Industry: CABLE & OTHER PAY TELEVISION SERVICES\\nArticle Title: Roku and FreeWheel Announce Strategic Partnership to Bring Roku’s Leading Ad Tech to FreeWheel Customers\\nText: Additionally, eMarketer Link: https://cts.businesswire.com/ct/CT?id=smartlink&url=https%3A%2F%2Fwww.insiderintelligence.com%2Finsights%2Favod-more-than-50-percent-of-us-digital-video-viewers%2F&esheet=53451144&newsitemid=20230712907788&lan=en-US&anchor=eMarketer&index=4&md5=b64dea72bcf6b6379474462602781d83 projects 57% of U.S. digital video users will stream an advertising-based video on demand (AVOD) service this year.\\nHaving solutions aimed at driving greater interoperability and automation will help accelerate this growth.\\nKey highlights of this collaboration include:\\nStreamlined Integration: Roku has now integrated its demand application programming interface (dAPI) with FreeWheel s TV platform. Roku s demand API gives publishers direct, automatic and real-time access to more advertiser demand. This enhanced integration allows for streamlined ad operation workflows and better inventory quality control, both of which will improve publisher yield and revenue.\\nSeamless Data Targeting: Publishers can now use Roku platform signals to enable advertisers to target audiences and measure campaign performance without relying on cookies. Additionally, FreeWheel and Roku will rely on data clean room technology to enable the activation of additional data sets providing better measurement and monetization to publishers and agencies.', metadata={'_additional': {'id': '962b79e0-f9d1-43ae-9f7a-8a9b42bc7a9a'}, 'chunk_type': 'text', 'chunk_years_mentioned': [], 'company_name': 'ROKU INC', 'company_sic_code_description': 'CABLE & OTHER PAY TELEVISION SERVICES', 'data_source': 'PressRelease', 'data_source_link': 'https://www.nasdaq.com/press-release/roku-and-freewheel-announce-strategic-partnership-to-bring-rokus-leading-ad-tech-to', 'data_source_publish_date': '2023-07-12T00:00:00Z', 'data_source_uid': 'a46f309c-705d-3946-96db-87aa4e73261f', 'title': 'ROKU INC |  Roku and FreeWheel Announce Strategic Partnership to Bring Roku’s Leading Ad Tech to FreeWheel Customers'}),\n",
+       " Document(page_content='Company Name: ROKU INC \\n Company Industry: CABLE & OTHER PAY TELEVISION SERVICES \\n Form Title: 10-K 2022-FY \\n Form Section: Risk Factors \\n Text: nd the Note Regarding Forward Looking Statements.This section of this Annual Report generally discusses fiscal years 2022 and 2021 and year to year comparisons between those years.Discussions of fiscal year 2020 and year to year comparisons between fiscal years 2021 and 2020 that are not included in this Annual Report can be found in Management\\'s Discussion and Analysis of Financial Condition and Results of Operations in Part II, Item 7 of our Annual Report for the fiscal year ended December 31, 2021 filed with the SEC on February 18, 2022.Overview Effective as of the fourth quarter of fiscal 2022, we reorganized our reportable segments to better align with management\\'s reporting of information reviewed by the Chief Operating Decision Maker (\"CODM\") for each segment.We renamed our \"player\" segment to \"devices\" which now includes our licensing arrangements with service operators and licensed Roku TV partners in addition to sales of our streaming players, audio products, smart home products and Roku branded TVs that will be designed, made, and sold by us in 2023.Our historical segment information is recast to conform to our new presentation in our financial statements and accompanying notes included in Item 8 of this Annual Report.Our two reportable segments are the platform segment and the devices segment.', metadata={'_additional': {'id': 'a76c5fed-5d63-45a7-b63a-2c30e05140fc'}, 'chunk_type': 'text', 'chunk_years_mentioned': [2020, 2021, 2022, 2023], 'company_name': 'ROKU INC', 'company_sic_code_description': 'CABLE & OTHER PAY TELEVISION SERVICES', 'data_source': '10-K', 'data_source_link': 'https://www.sec.gov/Archives/edgar/data/1428439/000142843923000007', 'data_source_publish_date': '2022-01-01T00:00:00Z', 'data_source_uid': '0001428439-23-000007', 'title': 'ROKU INC |  10-K 2022-FY '}),\n",
+       " Document(page_content='Company Name: ROKU INC \\n Company Industry: CABLE & OTHER PAY TELEVISION SERVICES \\n Form Title: 10-Q 2023-Q1 \\n Form Section: Risk Factors \\n Text: Our current and potential partners include TV brands, cable and satellite companies, and telecommunication providers.Under these license arrangements, we generally have limited or no control over the amount and timing of resources these entities dedicate to the relationship.In the past, our licensed Roku TV partners have failed to meet their forecasts and anticipated market launch dates for distributing Roku TV models, and they may fail to meet their forecasts or such launches in the future.If our licensed Roku TV partners or service operator partners fail to meet their forecasts or such launches for distributing licensed streaming devices or choose to deploy competing streaming solutions within their product lines, our business may be harmed.We depend on a small number of content publishers for a majority of our streaming hours, and if we fail to maintain these relationships, our business could be harmed.*Historically, a small number of content publishers have accounted for a significant portion of the hours streamed on our platform.In the three months ended March 31, 2023, the top three streaming services represented over 50% of all hours streamed in the period.If, for any reason, we cease distributing channels that have historically streamed a large percentage of the aggregate streaming hours on our platform, our streaming hours, our active accounts, or Roku streaming device sales may be adversely affected, and our business may be harmed.', metadata={'_additional': {'id': '2a92b2bb-02a0-4e15-8b64-d7e04078a205'}, 'chunk_type': 'text', 'chunk_years_mentioned': [2023], 'company_name': 'ROKU INC', 'company_sic_code_description': 'CABLE & OTHER PAY TELEVISION SERVICES', 'data_source': '10-Q', 'data_source_link': 'https://www.sec.gov/Archives/edgar/data/1428439/000142843923000017', 'data_source_publish_date': '2023-01-01T00:00:00Z', 'data_source_uid': '0001428439-23-000017', 'title': 'ROKU INC |  10-Q 2023-Q1 '})]"
+      ]
+     },
+     "execution_count": 21,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "docs"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "21f6e9e5-478c-4b2c-9d61-f7a84f4d2f8f",
+   "metadata": {},
+   "source": [
+    "Usage in a chain\n",
+    "-"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "d1cba716-ab8d-4518-9196-43f17eb189dc",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdin",
+     "output_type": "stream",
+     "text": [
+      " ········\n"
+     ]
+    }
+   ],
+   "source": [
+    "OPENAI_API_KEY = getpass()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "79441f1f-fa06-452c-bcd6-160ad0debc6a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "os.environ[\"OPENAI_API_KEY\"] = OPENAI_API_KEY"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "0c504bcd-f6e0-4028-a797-b31fb4b6d027",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.chat_models import ChatOpenAI\n",
+    "from langchain.chains import ConversationalRetrievalChain\n",
+    "\n",
+    "model = ChatOpenAI(model_name=\"gpt-3.5-turbo\")\n",
+    "qa = ConversationalRetrievalChain.from_llm(model, retriever=retriever)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "977f158b-38d3-4b5f-9379-7cdd09436327",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "-> **Question**: What were the biggest strategy changes and partnerships made by Roku in 2023? \n",
+      "\n",
+      "**Answer**: In 2023, Roku made a strategic partnership with FreeWheel to bring Roku's leading ad tech to FreeWheel customers. This partnership aimed to drive greater interoperability and automation in the advertising-based video on demand (AVOD) space. Key highlights of this collaboration include streamlined integration of Roku's demand application programming interface (dAPI) with FreeWheel's TV platform, allowing for better inventory quality control and improved publisher yield and revenue. Additionally, publishers can now use Roku platform signals to enable advertisers to target audiences and measure campaign performance without relying on cookies. This partnership also involves the use of data clean room technology to enable the activation of additional data sets for better measurement and monetization for publishers and agencies. These partnerships and strategies aim to support Roku's growth in the AVOD market. \n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "questions = [\n",
+    "    \"What were the biggest strategy changes and partnerships made by Roku in 2023?\"\n",
+    "    # \"Where is Wex making the most money in 2023?\",\n",
+    "]\n",
+    "chat_history = []\n",
+    "\n",
+    "for question in questions:\n",
+    "    result = qa({\"question\": question, \"chat_history\": chat_history})\n",
+    "    chat_history.append((question, result[\"answer\"]))\n",
+    "    print(f\"-> **Question**: {question} \\n\")\n",
+    "    print(f\"**Answer**: {result['answer']} \\n\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.18"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/extras/integrations/retrievers/pubmed.ipynb

@@ -81,7 +81,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.12"
+   "version": "3.9.18"
   }
  },
  "nbformat": 4,

docs/extras/integrations/retrievers/sec_filings.ipynb

@@ -0,0 +1,165 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "263f914c-9d67-4316-8b3d-03c3b99ba9d8",
+   "metadata": {},
+   "source": [
+    "SEC filings data\n",
+    "=\n",
+    "\n",
+    "SEC filings data powered by [Kay.ai](https://kay.ai) and [Cybersyn](https://www.cybersyn.com/).\n",
+    "\n",
+    ">The SEC filing is a financial statement or other formal document submitted to the U.S. Securities and Exchange Commission (SEC). Public companies, certain insiders, and broker-dealers are required to make regular SEC filings. Investors and financial professionals rely on these filings for information about companies they are evaluating for investment purposes."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "fc507b8e-ea51-417c-93da-42bf998a1195",
+   "metadata": {},
+   "source": [
+    "Setup\n",
+    "=\n",
+    "\n",
+    "First you will need to install the `kay` package. You will also need an API key: you can get one for free at [https://kay.ai](https://kay.ai/). Once you have an API key, you must set it as an environment variable `KAY_API_KEY`.\n",
+    "\n",
+    "In this example we're going to use the `KayAiRetriever`. Take a look at the [kay notebook](/docs/integrations/retrievers/kay) for more detailed information for the parmeters that it accepts.`"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c923bea0-585a-4f62-8662-efc167e8d793",
+   "metadata": {},
+   "source": [
+    "Examples\n",
+    "=\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "f7b8c99c-0341-4f3c-912f-a11e98f7de71",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdin",
+     "output_type": "stream",
+     "text": [
+      " ········\n",
+      " ········\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Setup API keys for Kay and OpenAI\n",
+    "from getpass import getpass\n",
+    "KAY_API_KEY = getpass()\n",
+    "OPENAI_API_KEY = getpass()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "04ee2d6b-c2ab-4e15-8a8b-afaf6ef8c0f6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "os.environ[\"KAY_API_KEY\"] = KAY_API_KEY\n",
+    "os.environ[\"OPENAI_API_KEY\"] = OPENAI_API_KEY"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "0c504bcd-f6e0-4028-a797-b31fb4b6d027",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.chains import ConversationalRetrievalChain\n",
+    "from langchain.chat_models import ChatOpenAI\n",
+    "from langchain.retrievers import KayAiRetriever\n",
+    "\n",
+    "model = ChatOpenAI(model_name=\"gpt-3.5-turbo\")\n",
+    "retriever = KayAiRetriever.create(dataset_id=\"company\", data_types=[\"10-K\", \"10-Q\"], num_contexts=6)\n",
+    "qa = ConversationalRetrievalChain.from_llm(model, retriever=retriever)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "977f158b-38d3-4b5f-9379-7cdd09436327",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "-> **Question**: What are patterns in Nvidia's spend over the past three quarters? \n",
+      "\n",
+      "**Answer**: Based on the provided information, here are the patterns in NVIDIA's spend over the past three quarters:\n",
+      "\n",
+      "1. Research and Development Expenses:\n",
+      "   - Q3 2022: Increased by 34% compared to Q3 2021.\n",
+      "   - Q1 2023: Increased by 40% compared to Q1 2022.\n",
+      "   - Q2 2022: Increased by 25% compared to Q2 2021.\n",
+      "   \n",
+      "   Overall, research and development expenses have been consistently increasing over the past three quarters.\n",
+      "\n",
+      "2. Sales, General and Administrative Expenses:\n",
+      "   - Q3 2022: Increased by 8% compared to Q3 2021.\n",
+      "   - Q1 2023: Increased by 14% compared to Q1 2022.\n",
+      "   - Q2 2022: Decreased by 16% compared to Q2 2021.\n",
+      "   \n",
+      "   The pattern for sales, general and administrative expenses is not as consistent, with some quarters showing an increase and others showing a decrease.\n",
+      "\n",
+      "3. Total Operating Expenses:\n",
+      "   - Q3 2022: Increased by 25% compared to Q3 2021.\n",
+      "   - Q1 2023: Increased by 113% compared to Q1 2022.\n",
+      "   - Q2 2022: Increased by 9% compared to Q2 2021.\n",
+      "   \n",
+      "   Total operating expenses have generally been increasing over the past three quarters, with a significant increase in Q1 2023.\n",
+      "\n",
+      "Overall, the pattern indicates a consistent increase in research and development expenses and total operating expenses, while sales, general and administrative expenses show some fluctuations. \n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "questions = [\n",
+    "    \"What are patterns in Nvidia's spend over the past three quarters?\",\n",
+    "    #\"What are some recent challenges faced by the renewable energy sector?\",\n",
+    "]\n",
+    "chat_history = []\n",
+    "\n",
+    "for question in questions:\n",
+    "    result = qa({\"question\": question, \"chat_history\": chat_history})\n",
+    "    chat_history.append((question, result[\"answer\"]))\n",
+    "    print(f\"-> **Question**: {question} \\n\")\n",
+    "    print(f\"**Answer**: {result['answer']} \\n\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.18"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/extras/integrations/text_embedding/gradient.ipynb

@@ -0,0 +1,150 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Gradient\n",
+    "\n",
+    "`Gradient` allows to create `Embeddings` as well fine tune and get completions on LLMs with a simple web API.\n",
+    "\n",
+    "This notebook goes over how to use Langchain with Embeddings of [Gradient](https://gradient.ai/).\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Imports"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.embeddings import GradientEmbeddings"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Set the Environment API Key\n",
+    "Make sure to get your API key from Gradient AI. You are given $10 in free credits to test and fine-tune different models."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from getpass import getpass\n",
+    "import os\n",
+    "\n",
+    "if not os.environ.get(\"GRADIENT_ACCESS_TOKEN\",None):\n",
+    "    # Access token under https://auth.gradient.ai/select-workspace\n",
+    "    os.environ[\"GRADIENT_ACCESS_TOKEN\"] = getpass(\"gradient.ai access token:\")\n",
+    "if not os.environ.get(\"GRADIENT_WORKSPACE_ID\",None):\n",
+    "    # `ID` listed in `$ gradient workspace list`\n",
+    "    # also displayed after login at at https://auth.gradient.ai/select-workspace\n",
+    "    os.environ[\"GRADIENT_WORKSPACE_ID\"] = getpass(\"gradient.ai workspace id:\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Optional: Validate your Enviroment variables ```GRADIENT_ACCESS_TOKEN``` and ```GRADIENT_WORKSPACE_ID``` to get currently deployed models. Using the `gradientai` Python package."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install gradientai"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create the Gradient instance"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "documents = [\"Pizza is a dish.\",\"Paris is the capital of France\", \"numpy is a lib for linear algebra\"]\n",
+    "query = \"Where is Paris?\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "embeddings = GradientEmbeddings(\n",
+    "    model=\"bge-large\"\n",
+    ")\n",
+    "\n",
+    "documents_embedded = embeddings.embed_documents(documents)\n",
+    "query_result = embeddings.embed_query(query)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# (demo) compute similarity\n",
+    "import numpy as np\n",
+    "\n",
+    "scores = np.array(documents_embedded) @ np.array(query_result).T\n",
+    "dict(zip(documents, scores))"
+   ]
+  },
+  {
+   "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": "3.10.6"
+  },
+  "vscode": {
+   "interpreter": {
+    "hash": "a0a0263b650d907a3bfe41c0f8d6a63a071b884df3cfdc1579f00cdc1aed6b03"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

docs/extras/integrations/text_embedding/llm_rails.ipynb

@@ -0,0 +1,133 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "278b6c63",
+   "metadata": {},
+   "source": [
+    "# LLMRails\n",
+    "\n",
+    "Let's load the LLMRails Embeddings class.\n",
+    "\n",
+    "To use LLMRails embedding you need to pass api key by argument or set it in environment with `LLM_RAILS_API_KEY` key.\n",
+    "To gey API Key you need to sign up in https://console.llmrails.com/signup and then go to https://console.llmrails.com/api-keys and copy key from there after creating one key in platform."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "0be1af71",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.embeddings import LLMRailsEmbeddings"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "2c66e5da",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "embeddings = LLMRailsEmbeddings(model='embedding-english-v1') # or embedding-multi-v1"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "01370375",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "text = \"This is a test document.\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a42e4035",
+   "metadata": {},
+   "source": [
+    "To generate embeddings, you can either query an invidivual text, or you can query a list of texts."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "91bc875d-829b-4c3d-8e6f-fc2dda30a3bd",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[-0.09996652603149414,\n",
+       " 0.015568195842206478,\n",
+       " 0.17670190334320068,\n",
+       " 0.16521021723747253,\n",
+       " 0.21193109452724457]"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "query_result = embeddings.embed_query(text)\n",
+    "query_result[:5]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "a4b0d49e-0c73-44b6-aed5-5b426564e085",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[-0.04242777079343796,\n",
+       " 0.016536075621843338,\n",
+       " 0.10052520781755447,\n",
+       " 0.18272875249385834,\n",
+       " 0.2079043835401535]"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "doc_result = embeddings.embed_documents([text])\n",
+    "doc_result[0][:5]"
+   ]
+  }
+ ],
+ "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": "3.11.5"
+  },
+  "vscode": {
+   "interpreter": {
+    "hash": "e971737741ff4ec9aff7dc6155a1060a59a8a6d52c757dbbe66bf8ee389494b1"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/extras/integrations/vectorstores/elasticsearch.ipynb

@@ -44,7 +44,7 @@
    "source": [
     "There are two main ways to setup an Elasticsearch instance for use with:\n",
     "\n",
-    "1. Elastic Cloud: Elastic Cloud is a managed Elasticsearch service. Signup for a [free trial](https://cloud.elastic.co/registration?storm=langchain-notebook).\n",
+    "1. Elastic Cloud: Elastic Cloud is a managed Elasticsearch service. Signup for a [free trial](https://cloud.elastic.co/registration?utm_source=langchain&utm_content=documentation).\n",
     "\n",
     "To connect to an Elasticsearch instance that does not require\n",
     "login credentials (starting the docker instance with security enabled), pass the Elasticsearch URL and index name along with the\n",
@@ -662,7 +662,7 @@
    "id": "0960fa0a",
    "metadata": {},
    "source": [
-    "# Customise the Query\n",
+    "## Customise the Query\n",
     "With `custom_query` parameter at search, you are able to adjust the query that is used to retrieve documents from Elasticsearch. This is useful if you want to want to use a more complex query, to support linear boosting of fields."
    ]
   },
@@ -720,6 +720,35 @@
     "print(results[0])"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "3242fd42",
+   "metadata": {},
+   "source": [
+    "# FAQ\n",
+    "\n",
+    "## Question: Im getting timeout errors when indexing documents into Elasticsearch. How do I fix this?\n",
+    "One possible issue is your documents might take longer to index into Elasticsearch. ElasticsearchStore uses the Elasticsearch bulk API which has a few defaults that you can adjust to reduce the chance of timeout errors.\n",
+    "\n",
+    "This is also a good idea when you're using SparseVectorRetrievalStrategy.\n",
+    "\n",
+    "The defaults are:\n",
+    "- `chunk_size`: 500\n",
+    "- `max_chunk_bytes`: 100MB\n",
+    "\n",
+    "To adjust these, you can pass in the `chunk_size` and `max_chunk_bytes` parameters to the ElasticsearchStore `add_texts` method.\n",
+    "\n",
+    "```python\n",
+    "    vector_store.add_texts(\n",
+    "        texts,\n",
+    "        bulk_kwargs={\n",
+    "            \"chunk_size\": 50,\n",
+    "            \"max_chunk_bytes\": 200000000\n",
+    "        }\n",
+    "    )\n",
+    "```"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "604c66ea",

docs/extras/integrations/vectorstores/supabase.ipynb

@@ -92,7 +92,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 15,
    "id": "19846a7b-99bc-47a7-8e1c-f13c2497f1ae",
    "metadata": {},
    "outputs": [],
@@ -105,7 +105,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 16,
    "id": "c71c3901-d44b-4d09-92c5-3018628c28fa",
    "metadata": {},
    "outputs": [],
@@ -115,7 +115,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 17,
    "id": "8b91ecfa-f61b-489a-a337-dff1f12f6ab2",
    "metadata": {},
    "outputs": [],
@@ -138,51 +138,66 @@
     "load_dotenv()"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "924d4df5",
+   "metadata": {},
+   "source": [
+    "First we'll create a Supabase client and instantiate a OpenAI embeddings class."
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 19,
    "id": "5ce44f7c",
    "metadata": {},
    "outputs": [],
    "source": [
     "import os\n",
     "from supabase.client import Client, create_client\n",
+    "from langchain.embeddings.openai import OpenAIEmbeddings\n",
+    "from langchain.vectorstores import SupabaseVectorStore\n",
     "\n",
     "supabase_url = os.environ.get(\"SUPABASE_URL\")\n",
     "supabase_key = os.environ.get(\"SUPABASE_SERVICE_KEY\")\n",
-    "supabase: Client = create_client(supabase_url, supabase_key)"
+    "supabase: Client = create_client(supabase_url, supabase_key)\n",
+    "\n",
+    "embeddings = OpenAIEmbeddings()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0c707d4c",
+   "metadata": {},
+   "source": [
+    "Next we'll load and parse some data for our vector store (skip if you already have documents with embeddings stored in your DB)."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 20,
    "id": "aac9563e",
    "metadata": {
     "tags": []
    },
    "outputs": [],
    "source": [
-    "from langchain.embeddings.openai import OpenAIEmbeddings\n",
+    "\n",
     "from langchain.text_splitter import CharacterTextSplitter\n",
-    "from langchain.vectorstores import SupabaseVectorStore\n",
-    "from langchain.document_loaders import TextLoader"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "a3c3999a",
-   "metadata": {},
-   "outputs": [],
-   "source": [
     "from langchain.document_loaders import TextLoader\n",
     "\n",
     "loader = TextLoader(\"../../../state_of_the_union.txt\")\n",
     "documents = loader.load()\n",
     "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
-    "docs = text_splitter.split_documents(documents)\n",
-    "\n",
-    "embeddings = OpenAIEmbeddings()"
+    "docs = text_splitter.split_documents(documents)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "5abb9b93",
+   "metadata": {},
+   "source": [
+    "Insert the above documents into the database. Embeddings will automatically be generated for each document."
    ]
   },
   {
@@ -192,13 +207,39 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# We're using the default `documents` table here. You can modify this by passing in a `table_name` argument to the `from_documents` method.\n",
-    "vector_store = SupabaseVectorStore.from_documents(docs, embeddings, client=supabase)"
+    "\n",
+    "vector_store = SupabaseVectorStore.from_documents(docs, embeddings, client=supabase, table_name=\"documents\", query_name=\"match_documents\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e169345d",
+   "metadata": {},
+   "source": [
+    "Alternatively if you already have documents with embeddings in your database, simply instantiate a new `SupabaseVectorStore` directly:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 10,
+   "id": "397e3e7d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "vector_store = SupabaseVectorStore(embedding=embeddings, client=supabase, table_name=\"documents\", query_name=\"match_documents\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e28ce092",
+   "metadata": {},
+   "source": [
+    "Finally, test it out by performing a similarity search:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
    "id": "5eabdb75",
    "metadata": {},
    "outputs": [],
@@ -209,7 +250,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": null,
    "id": "4b172de8",
    "metadata": {},
    "outputs": [
@@ -431,7 +472,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.12"
+   "version": "3.11.5"
   }
  },
  "nbformat": 4,

docs/extras/modules/agents/how_to/agent_structured.ipynb

@@ -0,0 +1,358 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "fb69907a",
+   "metadata": {},
+   "source": [
+    "# Returning Structured Output\n",
+    "\n",
+    "This notebook covers how to have an agent return a structured output.\n",
+    "By default, most of the agents return a single string.\n",
+    "It can often be useful to have an agent return something with more structure.\n",
+    "\n",
+    "\n",
+    "A good example of this is an agent tasked with doing question-answering over some sources.\n",
+    "Let's say we want the agent to respond not only with the answer, but also a list of the sources used.\n",
+    "We then want our output to roughly follow the schema below:\n",
+    "\n",
+    "```python\n",
+    "class Response(BaseModel):\n",
+    "    \"\"\"Final response to the question being asked\"\"\"\n",
+    "    answer: str = Field(description = \"The final answer to respond to the user\")\n",
+    "    sources: List[int] = Field(description=\"List of page chunks that contain answer to the question. Only include a page chunk if it contains relevant information\")\n",
+    "```\n",
+    "\n",
+    "In this notebook we will go over an agent that has a retriever tool and responds in the correct format."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4fc33ba5",
+   "metadata": {},
+   "source": [
+    "## Create the Retriever\n",
+    "\n",
+    "In this section we will do some setup work to create our retriever over some mock data containing the \"State of the Union\" address. Importantly, we will add a \"page_chunk\" tag to the metadata of each document. This is just some fake data intended to simulate a source field. In practice, this would more likely be the URL or path of a document."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "4ea20467",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.embeddings.openai import OpenAIEmbeddings\n",
+    "from langchain.vectorstores import Chroma\n",
+    "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
+    "from langchain.document_loaders import TextLoader"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "e3002ed7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Load in document to retrieve over\n",
+    "loader = TextLoader('../../state_of_the_union.txt')\n",
+    "documents = loader.load()\n",
+    "\n",
+    "# Split document into chunks\n",
+    "text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
+    "texts = text_splitter.split_documents(documents)\n",
+    "\n",
+    "# Here is where we add in the fake source information\n",
+    "for i, doc in enumerate(texts):\n",
+    "    doc.metadata['page_chunk'] = i\n",
+    "\n",
+    "# Create our retriever\n",
+    "embeddings = OpenAIEmbeddings()\n",
+    "vectorstore = Chroma.from_documents(texts, embeddings, collection_name=\"state-of-union\")\n",
+    "retriever = vectorstore.as_retriever()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6ec1c106",
+   "metadata": {},
+   "source": [
+    "## Create the tools\n",
+    "\n",
+    "We will now create the tools we want to give to the agent. In this case, it is just one - a tool that wraps our retriever."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "204ef7ca",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.agents.agent_toolkits.conversational_retrieval.tool import create_retriever_tool\n",
+    "\n",
+    "retriever_tool = create_retriever_tool(\n",
+    "    retriever,\n",
+    "    \"state-of-union-retriever\",\n",
+    "    \"Query a retriever to get information about state of the union address\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9af5b61b",
+   "metadata": {},
+   "source": [
+    "## Create response schema\n",
+    "\n",
+    "Here is where we will define the response schema. In this case, we want the final answer to have two fields: one for the `answer`, and then another that is a list of `sources`"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "2df91723",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from pydantic import BaseModel, Field\n",
+    "from typing import List\n",
+    "from langchain.utils.openai_functions import convert_pydantic_to_openai_function\n",
+    "\n",
+    "class Response(BaseModel):\n",
+    "    \"\"\"Final response to the question being asked\"\"\"\n",
+    "    answer: str = Field(description = \"The final answer to respond to the user\")\n",
+    "    sources: List[int] = Field(description=\"List of page chunks that contain answer to the question. Only include a page chunk if it contains relevant information\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2cd181df",
+   "metadata": {},
+   "source": [
+    "## Create the custom parsing logic\n",
+    "\n",
+    "We now create some custom parsing logic.\n",
+    "How this works is that we will pass the `Response` schema to the OpenAI LLM via their `functions` parameter.\n",
+    "This is similar to how we pass tools for the agent to use.\n",
+    "\n",
+    "When the `Response` function is called by OpenAI, we want to use that as a signal to return to the user.\n",
+    "When any other function is called by OpenAI, we treat that as a tool invocation.\n",
+    "\n",
+    "Therefor, our parsing logic has the following blocks:\n",
+    "\n",
+    "- If no function is called, assume that we should use the response to respond to the user, and therefor return `AgentFinish`\n",
+    "- If the `Response` function is called, respond to the user with the inputs to that function (our structured output), and therefor return `AgentFinish`\n",
+    "- If any other function is called, treat that as a tool invocation, and therefor return `AgentActionMessageLog`\n",
+    "\n",
+    "Note that we are using `AgentActionMessageLog` rather than `AgentAction` because it lets us attach a log of messages that we can use in the future to pass back into the agent prompt."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "dfb73fe3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.schema.agent import AgentActionMessageLog, AgentFinish\n",
+    "import json"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "5b46cdb2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def parse(output):\n",
+    "    # If no function was invoked, return to user\n",
+    "    if \"function_call\" not in output.additional_kwargs:\n",
+    "        return AgentFinish(return_values={\"output\": output.content}, log=output.content)\n",
+    "    \n",
+    "    # Parse out the function call\n",
+    "    function_call = output.additional_kwargs[\"function_call\"]\n",
+    "    name = function_call['name']\n",
+    "    inputs = json.loads(function_call['arguments'])\n",
+    "    \n",
+    "    # If the Response function was invoked, return to the user with the function inputs\n",
+    "    if name == \"Response\":\n",
+    "        return AgentFinish(return_values=inputs, log=str(function_call))\n",
+    "    # Otherwise, return an agent action\n",
+    "    else:\n",
+    "        return AgentActionMessageLog(tool=name, tool_input=inputs, log=\"\", message_log=[output])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6d7401a1",
+   "metadata": {},
+   "source": [
+    "## Create the Agent\n",
+    "\n",
+    "We can now put this all together! The components of this agent are:\n",
+    "\n",
+    "- prompt: a simple prompt with placeholders for the user's question and then the `agent_scratchpad` (any intermediate steps)\n",
+    "- tools: we can attach the tools and `Response` format to the LLM as functions\n",
+    "- format scratchpad: in order to format the `agent_scratchpad` from intermediate steps, we will use the standard `format_to_openai_functions`. This takes intermediate steps and formats them as AIMessages and FunctionMessages.\n",
+    "- output parser: we will use our custom parser above to parse the response of the LLM\n",
+    "- AgentExecutor: we will use the standard AgentExecutor to run the loop of agent-tool-agent-tool..."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "73c785f9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.prompts import ChatPromptTemplate, MessagesPlaceholder\n",
+    "from langchain.chat_models import ChatOpenAI\n",
+    "from langchain.tools.render import format_tool_to_openai_function\n",
+    "from langchain.agents.format_scratchpad import format_to_openai_functions\n",
+    "from langchain.agents import AgentExecutor"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "e1feaeda",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prompt = ChatPromptTemplate.from_messages([\n",
+    "    (\"system\", \"You are a helpful assistant\"),\n",
+    "    (\"user\", \"{input}\"),\n",
+    "    MessagesPlaceholder(variable_name=\"agent_scratchpad\"),\n",
+    "])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "d27dc3a8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm = ChatOpenAI(temperature=0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "7bab4af2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm_with_tools = llm.bind(\n",
+    "    functions=[\n",
+    "        # The retriever tool\n",
+    "        format_tool_to_openai_function(retriever_tool), \n",
+    "        # Response schema\n",
+    "        convert_pydantic_to_openai_function(Response)\n",
+    "    ]\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "b886416c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "agent = {\n",
+    "    \"input\": lambda x: x[\"input\"],\n",
+    "    # Format agent scratchpad from intermediate steps\n",
+    "    \"agent_scratchpad\": lambda x: format_to_openai_functions(x['intermediate_steps'])\n",
+    "} | prompt | llm_with_tools | parse"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "2cfd783e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "agent_executor = AgentExecutor(tools=[retriever_tool], agent=agent, verbose=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9f114fec",
+   "metadata": {},
+   "source": [
+    "## Run the agent\n",
+    "\n",
+    "We can now run the agent! Notice how it responds with a dictionary with two keys: `answer` and `sources`"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "2667c9a4",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3m\u001b[0m\u001b[36;1m\u001b[1;3m[Document(page_content='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\\nTonight, 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\\nOne of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \\n\\nAnd 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.', metadata={'page_chunk': 31, 'source': '../../state_of_the_union.txt'}), Document(page_content='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\\nWhen they came home, many of the world’s fittest and best trained warriors were never the same. \\n\\nHeadaches. Numbness. Dizziness. \\n\\nA cancer that would put them in a flag-draped coffin. \\n\\nI know. \\n\\nOne of those soldiers was my son Major Beau Biden. \\n\\nWe 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\\nBut I’m committed to finding out everything we can. \\n\\nCommitted to military families like Danielle Robinson from Ohio. \\n\\nThe widow of Sergeant First Class Heath Robinson.  \\n\\nHe was born a soldier. Army National Guard. Combat medic in Kosovo and Iraq. \\n\\nStationed near Baghdad, just yards from burn pits the size of football fields. \\n\\nHeath’s widow Danielle is here with us tonight. They loved going to Ohio State football games. He loved building Legos with their daughter.', metadata={'page_chunk': 37, 'source': '../../state_of_the_union.txt'}), Document(page_content='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\\nAnd if we are to advance liberty and justice, we need to secure the Border and fix the immigration system. \\n\\nWe can do both. At our border, we’ve installed new technology like cutting-edge scanners to better detect drug smuggling.  \\n\\nWe’ve set up joint patrols with Mexico and Guatemala to catch more human traffickers.  \\n\\nWe’re putting in place dedicated immigration judges so families fleeing persecution and violence can have their cases heard faster. \\n\\nWe’re securing commitments and supporting partners in South and Central America to host more refugees and secure their own borders.', metadata={'page_chunk': 32, 'source': '../../state_of_the_union.txt'}), Document(page_content='But cancer from prolonged exposure to burn pits ravaged Heath’s lungs and body. \\n\\nDanielle says Heath was a fighter to the very end. \\n\\nHe didn’t know how to stop fighting, and neither did she. \\n\\nThrough her pain she found purpose to demand we do better. \\n\\nTonight, Danielle—we are. \\n\\nThe VA is pioneering new ways of linking toxic exposures to diseases, already helping more veterans get benefits. \\n\\nAnd tonight, I’m announcing we’re expanding eligibility to veterans suffering from nine respiratory cancers. \\n\\nI’m also calling on Congress: pass a law to make sure veterans devastated by toxic exposures in Iraq and Afghanistan finally get the benefits and comprehensive health care they deserve. \\n\\nAnd fourth, let’s end cancer as we know it. \\n\\nThis is personal to me and Jill, to Kamala, and to so many of you. \\n\\nCancer is the #2 cause of death in America–second only to heart disease.', metadata={'page_chunk': 38, 'source': '../../state_of_the_union.txt'})]\u001b[0m\u001b[32;1m\u001b[1;3m{'name': 'Response', 'arguments': '{\\n  \"answer\": \"President mentioned Ketanji Brown Jackson as a nominee for the United States Supreme Court and praised her as one of the nation\\'s top legal minds.\",\\n  \"sources\": [31]\\n}'}\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "{'answer': \"President mentioned Ketanji Brown Jackson as a nominee for the United States Supreme Court and praised her as one of the nation's top legal minds.\",\n",
+       " 'sources': [31]}"
+      ]
+     },
+     "execution_count": 18,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "agent_executor.invoke({\"input\": \"what did the president say about kentaji brown jackson\"}, return_only_outputs=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b355665e",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/extras/modules/agents/how_to/intermediate_steps.ipynb

@@ -166,9 +166,9 @@
     }
    ],
    "source": [
-    "import json\n",
+    "from langchain.load.dump import dumps\n",
     "\n",
-    "print(json.dumps(response[\"intermediate_steps\"], indent=2))"
+    "print(dumps(response[\"intermediate_steps\"], pretty=True))"
    ]
   },
   {

docs/extras/modules/data_connection/indexing.ipynb

@@ -603,7 +603,7 @@
    "id": "4002a4ac-02dd-4599-9b23-9b59f54237c8",
    "metadata": {},
    "source": [
-    "The metadata attribute contains a filed called `source`. This source should be pointing at the *ultimate* provenance associated with the given document.\n",
+    "The metadata attribute contains a field called `source`. This source should be pointing at the *ultimate* provenance associated with the given document.\n",
     "\n",
     "For example, if these documents are representing chunks of some parent document, the `source` for both documents should be the same and reference the parent document.\n",
     "\n",

docs/extras/use_cases/more/agents/autonomous_agents/baby_agi.ipynb

@@ -36,7 +36,7 @@
     "from langchain.chains import LLMChain\nfrom langchain.llms import OpenAI\nfrom langchain.prompts import PromptTemplate\n",
     "from langchain.embeddings import OpenAIEmbeddings\n",
     "from langchain.llms import BaseLLM\n",
-    "from langchain.vectorstores.base import VectorStore\n",
+    "from langchain.schema.vectorstore import VectorStore\n",
     "from pydantic import BaseModel, Field\n",
     "from langchain.chains.base import Chain\n",
     "from langchain_experimental.autonomous_agents import BabyAGI"

docs/extras/use_cases/more/agents/autonomous_agents/baby_agi_with_agent.ipynb

@@ -32,7 +32,7 @@
     "from langchain.chains import LLMChain\nfrom langchain.llms import OpenAI\nfrom langchain.prompts import PromptTemplate\n",
     "from langchain.embeddings import OpenAIEmbeddings\n",
     "from langchain.llms import BaseLLM\n",
-    "from langchain.vectorstores.base import VectorStore\n",
+    "from langchain.schema.vectorstore import VectorStore\n",
     "from pydantic import BaseModel, Field\n",
     "from langchain.chains.base import Chain\n",
     "from langchain_experimental.autonomous_agents import BabyAGI"

docs/extras/use_cases/more/graph/graph_cypher_qa.ipynb

@@ -135,7 +135,7 @@
     }
    ],
    "source": [
-    "print(graph.get_schema)"
+    "print(graph.schema)"
    ]
   },
   {
@@ -510,13 +510,54 @@
     "chain.run(\"Who played in Top Gun?\")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "eefea16b-508f-4552-8942-9d5063ed7d37",
+   "metadata": {},
+   "source": [
+    "# Ignore specified node and relationship types\n",
+    "You can use `include_types` or `exclude_types` to ignore parts of the graph schema when generating Cypher statements."
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "id": "48ff7cf8-18a3-43d7-8cb1-c1b91744608d",
+   "execution_count": 18,
+   "id": "a20fa21e-fb85-41c4-aac0-53fb25e34604",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "chain = GraphCypherQAChain.from_llm(\n",
+    "     graph=graph,\n",
+    "     cypher_llm=ChatOpenAI(temperature=0, model=\"gpt-3.5-turbo\"),\n",
+    "     qa_llm=ChatOpenAI(temperature=0, model=\"gpt-3.5-turbo-16k\"),\n",
+    "     verbose=True,\n",
+    "     exclude_types=['Movie']\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "3ad7f6b8-543e-46e4-a3b2-40fa3e66e895",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Node properties are the following: \n",
+      " {'Actor': [{'property': 'name', 'type': 'STRING'}]}\n",
+      "Relationships properties are the following: \n",
+      " {}\n",
+      "Relationships are: \n",
+      "[]\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Inspect graph schema\n",
+    "print(chain.graph_schema)"
+   ]
   }
  ],
  "metadata": {

docs/extras/use_cases/more/graph/graph_memgraph_qa.ipynb

@@ -187,7 +187,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "print(graph.get_schema)"
+    "print(graph.schema)"
    ]
   },
   {
@@ -687,7 +687,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.13"
+   "version": "3.8.8"
   }
  },
  "nbformat": 4,

libs/experimental/README.md

@@ -13,4 +13,4 @@ Some of the code here may be marked with security notices. However,
 given the exploratory and experimental nature of the code in this package,
 the lack of a security notice on a piece of code does not mean that
 the code in question does not require additional security considerations
-in order to be safe to use.
+in order to be safe to use.

libs/experimental/langchain_experimental/autonomous_agents/autogpt/agent.py

@@ -10,9 +10,9 @@ from langchain.schema import (
     Document,
 )
 from langchain.schema.messages import AIMessage, HumanMessage, SystemMessage
+from langchain.schema.vectorstore import VectorStoreRetriever
 from langchain.tools.base import BaseTool
 from langchain.tools.human.tool import HumanInputRun
-from langchain.vectorstores.base import VectorStoreRetriever
 
 from langchain_experimental.autonomous_agents.autogpt.output_parser import (
     AutoGPTOutputParser,

libs/experimental/langchain_experimental/autonomous_agents/autogpt/memory.py

@@ -1,7 +1,7 @@
 from typing import Any, Dict, List
 
 from langchain.memory.chat_memory import BaseChatMemory, get_prompt_input_key
-from langchain.vectorstores.base import VectorStoreRetriever
+from langchain.schema.vectorstore import VectorStoreRetriever
 
 from langchain_experimental.pydantic_v1 import Field
 

libs/experimental/langchain_experimental/autonomous_agents/autogpt/prompt.py

@@ -5,8 +5,8 @@ from langchain.prompts.chat import (
     BaseChatPromptTemplate,
 )
 from langchain.schema.messages import BaseMessage, HumanMessage, SystemMessage
+from langchain.schema.vectorstore import VectorStoreRetriever
 from langchain.tools.base import BaseTool
-from langchain.vectorstores.base import VectorStoreRetriever
 
 from langchain_experimental.autonomous_agents.autogpt.prompt_generator import get_prompt
 from langchain_experimental.pydantic_v1 import BaseModel

libs/experimental/langchain_experimental/autonomous_agents/baby_agi/baby_agi.py

@@ -5,7 +5,7 @@ from typing import Any, Dict, List, Optional
 from langchain.callbacks.manager import CallbackManagerForChainRun
 from langchain.chains.base import Chain
 from langchain.schema.language_model import BaseLanguageModel
-from langchain.vectorstores.base import VectorStore
+from langchain.schema.vectorstore import VectorStore
 
 from langchain_experimental.autonomous_agents.baby_agi.task_creation import (
     TaskCreationChain,

libs/experimental/langchain_experimental/sql/vector_sql.py

@@ -8,7 +8,7 @@ from langchain.chains.llm import LLMChain
 from langchain.chains.sql_database.prompt import PROMPT, SQL_PROMPTS
 from langchain.prompts.prompt import PromptTemplate
 from langchain.schema import BaseOutputParser, BasePromptTemplate
-from langchain.schema.base import Embeddings
+from langchain.schema.embeddings import Embeddings
 from langchain.schema.language_model import BaseLanguageModel
 from langchain.tools.sql_database.prompt import QUERY_CHECKER
 from langchain.utilities.sql_database import SQLDatabase
@@ -76,23 +76,11 @@ class VectorSQLRetrieveAllOutputParser(VectorSQLOutputParser):
         return super().parse(text)
 
 
-def _try_eval(x: Any) -> Any:
-    try:
-        return eval(x)
-    except Exception:
-        return x
-
-
 def get_result_from_sqldb(
     db: SQLDatabase, cmd: str
 ) -> Union[str, List[Dict[str, Any]], Dict[str, Any]]:
     result = db._execute(cmd, fetch="all")  # type: ignore
-    if isinstance(result, list):
-        return [{k: _try_eval(v) for k, v in dict(d._asdict()).items()} for d in result]
-    else:
-        return {
-            k: _try_eval(v) for k, v in dict(result._asdict()).items()  # type: ignore
-        }
+    return result
 
 
 class VectorSQLDatabaseChain(SQLDatabaseChain):

libs/experimental/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "langchain-experimental"
-version = "0.0.20"
+version = "0.0.22"
 description = "Building applications with LLMs through composability"
 authors = []
 license = "MIT"

libs/langchain/Makefile

@@ -7,47 +7,18 @@ all: help
 # TESTING AND COVERAGE
 ######################
 
+# Define a variable for the test file path.
+TEST_FILE ?= tests/unit_tests/
+
 # Run unit tests and generate a coverage report.
 coverage:
 	poetry run pytest --cov \
 		--cov-config=.coveragerc \
 		--cov-report xml \
-		--cov-report term-missing:skip-covered
+		--cov-report term-missing:skip-covered \
+		$(TEST_FILE)
 
-######################
-# DOCUMENTATION
-######################
-
-clean: docs_clean api_docs_clean
-
-
-docs_build:
-	docs/.local_build.sh
-
-docs_clean:
-	rm -r docs/_dist
-
-docs_linkcheck:
-	poetry run linkchecker docs/_dist/docs_skeleton/ --ignore-url node_modules
-
-api_docs_build:
-	poetry run python docs/api_reference/create_api_rst.py
-	cd docs/api_reference && poetry run make html
-
-api_docs_clean:
-	rm -f docs/api_reference/api_reference.rst
-	cd docs/api_reference && poetry run make clean
-
-api_docs_linkcheck:
-	poetry run linkchecker docs/api_reference/_build/html/index.html
-
-# Define a variable for the test file path.
-TEST_FILE ?= tests/unit_tests/
-
-test:
-	poetry run pytest --disable-socket --allow-unix-socket $(TEST_FILE)
-
-tests: 
+test tests:
 	poetry run pytest --disable-socket --allow-unix-socket $(TEST_FILE)
 
 extended_tests:
@@ -98,7 +69,6 @@ spell_fix:
 
 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'
@@ -120,3 +90,4 @@ help:
 	@echo 'test_watch                   - run unit tests in watch mode'
 	@echo 'integration_tests            - run integration tests'
 	@echo 'docker_tests                 - run unit tests in docker'
+	@echo '-- DOCUMENTATION tasks are from the top-level Makefile --'

libs/langchain/README.md

@@ -92,4 +92,4 @@ For more information on these concepts, please see our [full documentation](http
 
 As an open-source project in a rapidly developing field, we are extremely open to contributions, whether it be in the form of a new feature, improved infrastructure, or better documentation.
 
-For detailed information on how to contribute, see [here](.github/CONTRIBUTING.md).
+For detailed information on how to contribute, see [here](../../.github/CONTRIBUTING.md).

libs/langchain/langchain/__init__.py

@@ -1,57 +1,14 @@
 # ruff: noqa: E402
 """Main entrypoint into package."""
+import warnings
 from importlib import metadata
-from typing import Optional
+from typing import TYPE_CHECKING, Any, Optional
+
+from langchain._api.deprecation import surface_langchain_deprecation_warnings
+
+if TYPE_CHECKING:
+    from langchain.schema import BaseCache
 
-from langchain.agents import MRKLChain, ReActChain, SelfAskWithSearchChain
-from langchain.chains import (
-    ConversationChain,
-    LLMBashChain,
-    LLMChain,
-    LLMCheckerChain,
-    LLMMathChain,
-    QAWithSourcesChain,
-    VectorDBQA,
-    VectorDBQAWithSourcesChain,
-)
-from langchain.docstore import InMemoryDocstore, Wikipedia
-from langchain.llms import (
-    Anthropic,
-    Banana,
-    CerebriumAI,
-    Cohere,
-    ForefrontAI,
-    GooseAI,
-    HuggingFaceHub,
-    HuggingFaceTextGenInference,
-    LlamaCpp,
-    Modal,
-    OpenAI,
-    Petals,
-    PipelineAI,
-    SagemakerEndpoint,
-    StochasticAI,
-    Writer,
-)
-from langchain.llms.huggingface_pipeline import HuggingFacePipeline
-from langchain.prompts import (
-    FewShotPromptTemplate,
-    Prompt,
-    PromptTemplate,
-)
-from langchain.schema.cache import BaseCache
-from langchain.schema.prompt_template import BasePromptTemplate
-from langchain.utilities.arxiv import ArxivAPIWrapper
-from langchain.utilities.golden_query import GoldenQueryAPIWrapper
-from langchain.utilities.google_search import GoogleSearchAPIWrapper
-from langchain.utilities.google_serper import GoogleSerperAPIWrapper
-from langchain.utilities.powerbi import PowerBIDataset
-from langchain.utilities.searx_search import SearxSearchWrapper
-from langchain.utilities.serpapi import SerpAPIWrapper
-from langchain.utilities.sql_database import SQLDatabase
-from langchain.utilities.wikipedia import WikipediaAPIWrapper
-from langchain.utilities.wolfram_alpha import WolframAlphaAPIWrapper
-from langchain.vectorstores import FAISS, ElasticVectorSearch
 
 try:
     __version__ = metadata.version(__package__)
@@ -62,10 +19,299 @@ del metadata  # optional, avoids polluting the results of dir(__package__)
 
 verbose: bool = False
 debug: bool = False
-llm_cache: Optional[BaseCache] = None
+llm_cache: Optional["BaseCache"] = None
 
-# For backwards compatibility
-SerpAPIChain = SerpAPIWrapper
+
+def _warn_on_import(name: str) -> None:
+    warnings.warn(
+        f"Importing {name} from langchain root module is no longer supported."
+    )
+
+
+# Surfaces Deprecation and Pending Deprecation warnings from langchain.
+surface_langchain_deprecation_warnings()
+
+
+def __getattr__(name: str) -> Any:
+    if name == "MRKLChain":
+        from langchain.agents import MRKLChain
+
+        _warn_on_import(name)
+
+        return MRKLChain
+    elif name == "ReActChain":
+        from langchain.agents import ReActChain
+
+        _warn_on_import(name)
+
+        return ReActChain
+    elif name == "SelfAskWithSearchChain":
+        from langchain.agents import SelfAskWithSearchChain
+
+        _warn_on_import(name)
+
+        return SelfAskWithSearchChain
+    elif name == "ConversationChain":
+        from langchain.chains import ConversationChain
+
+        _warn_on_import(name)
+
+        return ConversationChain
+    elif name == "LLMBashChain":
+        from langchain.chains import LLMBashChain
+
+        _warn_on_import(name)
+
+        return LLMBashChain
+    elif name == "LLMChain":
+        from langchain.chains import LLMChain
+
+        _warn_on_import(name)
+
+        return LLMChain
+    elif name == "LLMCheckerChain":
+        from langchain.chains import LLMCheckerChain
+
+        _warn_on_import(name)
+
+        return LLMCheckerChain
+    elif name == "LLMMathChain":
+        from langchain.chains import LLMMathChain
+
+        _warn_on_import(name)
+
+        return LLMMathChain
+    elif name == "QAWithSourcesChain":
+        from langchain.chains import QAWithSourcesChain
+
+        _warn_on_import(name)
+
+        return QAWithSourcesChain
+    elif name == "VectorDBQA":
+        from langchain.chains import VectorDBQA
+
+        _warn_on_import(name)
+
+        return VectorDBQA
+    elif name == "VectorDBQAWithSourcesChain":
+        from langchain.chains import VectorDBQAWithSourcesChain
+
+        _warn_on_import(name)
+
+        return VectorDBQAWithSourcesChain
+    elif name == "InMemoryDocstore":
+        from langchain.docstore import InMemoryDocstore
+
+        _warn_on_import(name)
+
+        return InMemoryDocstore
+    elif name == "Wikipedia":
+        from langchain.docstore import Wikipedia
+
+        _warn_on_import(name)
+
+        return Wikipedia
+    elif name == "Anthropic":
+        from langchain.llms import Anthropic
+
+        _warn_on_import(name)
+
+        return Anthropic
+    elif name == "Banana":
+        from langchain.llms import Banana
+
+        _warn_on_import(name)
+
+        return Banana
+    elif name == "CerebriumAI":
+        from langchain.llms import CerebriumAI
+
+        _warn_on_import(name)
+
+        return CerebriumAI
+    elif name == "Cohere":
+        from langchain.llms import Cohere
+
+        _warn_on_import(name)
+
+        return Cohere
+    elif name == "ForefrontAI":
+        from langchain.llms import ForefrontAI
+
+        _warn_on_import(name)
+
+        return ForefrontAI
+    elif name == "GooseAI":
+        from langchain.llms import GooseAI
+
+        _warn_on_import(name)
+
+        return GooseAI
+    elif name == "HuggingFaceHub":
+        from langchain.llms import HuggingFaceHub
+
+        _warn_on_import(name)
+
+        return HuggingFaceHub
+    elif name == "HuggingFaceTextGenInference":
+        from langchain.llms import HuggingFaceTextGenInference
+
+        _warn_on_import(name)
+
+        return HuggingFaceTextGenInference
+    elif name == "LlamaCpp":
+        from langchain.llms import LlamaCpp
+
+        _warn_on_import(name)
+
+        return LlamaCpp
+    elif name == "Modal":
+        from langchain.llms import Modal
+
+        _warn_on_import(name)
+
+        return Modal
+    elif name == "OpenAI":
+        from langchain.llms import OpenAI
+
+        _warn_on_import(name)
+
+        return OpenAI
+    elif name == "Petals":
+        from langchain.llms import Petals
+
+        _warn_on_import(name)
+
+        return Petals
+    elif name == "PipelineAI":
+        from langchain.llms import PipelineAI
+
+        _warn_on_import(name)
+
+        return PipelineAI
+    elif name == "SagemakerEndpoint":
+        from langchain.llms import SagemakerEndpoint
+
+        _warn_on_import(name)
+
+        return SagemakerEndpoint
+    elif name == "StochasticAI":
+        from langchain.llms import StochasticAI
+
+        _warn_on_import(name)
+
+        return StochasticAI
+    elif name == "Writer":
+        from langchain.llms import Writer
+
+        _warn_on_import(name)
+
+        return Writer
+    elif name == "HuggingFacePipeline":
+        from langchain.llms.huggingface_pipeline import HuggingFacePipeline
+
+        _warn_on_import(name)
+
+        return HuggingFacePipeline
+    elif name == "FewShotPromptTemplate":
+        from langchain.prompts import FewShotPromptTemplate
+
+        _warn_on_import(name)
+
+        return FewShotPromptTemplate
+    elif name == "Prompt":
+        from langchain.prompts import Prompt
+
+        _warn_on_import(name)
+
+        return Prompt
+    elif name == "PromptTemplate":
+        from langchain.prompts import PromptTemplate
+
+        _warn_on_import(name)
+
+        return PromptTemplate
+    elif name == "BasePromptTemplate":
+        from langchain.schema.prompt_template import BasePromptTemplate
+
+        _warn_on_import(name)
+
+        return BasePromptTemplate
+    elif name == "ArxivAPIWrapper":
+        from langchain.utilities import ArxivAPIWrapper
+
+        _warn_on_import(name)
+
+        return ArxivAPIWrapper
+    elif name == "GoldenQueryAPIWrapper":
+        from langchain.utilities import GoldenQueryAPIWrapper
+
+        _warn_on_import(name)
+
+        return GoldenQueryAPIWrapper
+    elif name == "GoogleSearchAPIWrapper":
+        from langchain.utilities import GoogleSearchAPIWrapper
+
+        _warn_on_import(name)
+
+        return GoogleSearchAPIWrapper
+    elif name == "GoogleSerperAPIWrapper":
+        from langchain.utilities import GoogleSerperAPIWrapper
+
+        _warn_on_import(name)
+
+        return GoogleSerperAPIWrapper
+    elif name == "PowerBIDataset":
+        from langchain.utilities import PowerBIDataset
+
+        _warn_on_import(name)
+
+        return PowerBIDataset
+    elif name == "SearxSearchWrapper":
+        from langchain.utilities import SearxSearchWrapper
+
+        _warn_on_import(name)
+
+        return SearxSearchWrapper
+    elif name == "WikipediaAPIWrapper":
+        from langchain.utilities import WikipediaAPIWrapper
+
+        _warn_on_import(name)
+
+        return WikipediaAPIWrapper
+    elif name == "WolframAlphaAPIWrapper":
+        from langchain.utilities import WolframAlphaAPIWrapper
+
+        _warn_on_import(name)
+
+        return WolframAlphaAPIWrapper
+    elif name == "SQLDatabase":
+        from langchain.utilities import SQLDatabase
+
+        _warn_on_import(name)
+
+        return SQLDatabase
+    elif name == "FAISS":
+        from langchain.vectorstores import FAISS
+
+        _warn_on_import(name)
+
+        return FAISS
+    elif name == "ElasticVectorSearch":
+        from langchain.vectorstores import ElasticVectorSearch
+
+        _warn_on_import(name)
+
+        return ElasticVectorSearch
+    # For backwards compatibility
+    elif name == "SerpAPIChain" or name == "SerpAPIWrapper":
+        from langchain.utilities import SerpAPIWrapper
+
+        _warn_on_import(name)
+
+        return SerpAPIWrapper
+    else:
+        raise AttributeError(f"Could not find: {name}")
 
 
 __all__ = [

libs/langchain/langchain/_api/__init__.py

@@ -13,10 +13,14 @@ from .deprecation import (
     LangChainDeprecationWarning,
     deprecated,
     suppress_langchain_deprecation_warning,
+    surface_langchain_deprecation_warnings,
+    warn_deprecated,
 )
 
 __all__ = [
     "deprecated",
     "LangChainDeprecationWarning",
     "suppress_langchain_deprecation_warning",
+    "surface_langchain_deprecation_warnings",
+    "warn_deprecated",
 ]

libs/langchain/langchain/_api/deprecation.py

@@ -21,84 +21,8 @@ class LangChainDeprecationWarning(DeprecationWarning):
     """A class for issuing deprecation warnings for LangChain users."""
 
 
-def _warn_deprecated(
-    since: str,
-    *,
-    message: str = "",
-    name: str = "",
-    alternative: str = "",
-    pending: bool = False,
-    obj_type: str = "",
-    addendum: str = "",
-    removal: str = "",
-) -> None:
-    """Display a standardized deprecation.
-
-    Arguments:
-        since : str
-            The release at which this API became deprecated.
-        message : str, optional
-            Override the default deprecation message. The %(since)s,
-            %(name)s, %(alternative)s, %(obj_type)s, %(addendum)s,
-            and %(removal)s format specifiers will be replaced by the
-            values of the respective arguments passed to this function.
-        name : str, optional
-            The name of the deprecated object.
-        alternative : str, optional
-            An alternative API that the user may use in place of the
-            deprecated API. The deprecation warning will tell the user
-            about this alternative if provided.
-        pending : bool, optional
-            If True, uses a PendingDeprecationWarning instead of a
-            DeprecationWarning. Cannot be used together with removal.
-        obj_type : str, optional
-            The object type being deprecated.
-        addendum : str, optional
-            Additional text appended directly to the final message.
-        removal : str, optional
-            The expected removal version. With the default (an empty
-            string), a removal version is automatically computed from
-            since. Set to other Falsy values to not schedule a removal
-            date. Cannot be used together with pending.
-    """
-    if pending and removal:
-        raise ValueError("A pending deprecation cannot have a scheduled removal")
-
-    if not pending:
-        if not removal:
-            removal = f"in {removal}" if removal else "within ?? minor releases"
-            raise NotImplementedError(
-                f"Need to determine which default deprecation schedule to use. "
-                f"{removal}"
-            )
-        else:
-            removal = f"in {removal}"
-
-    if not message:
-        message = ""
-
-        if obj_type:
-            message += f"The {obj_type} `{name}`"
-        else:
-            message += f"`{name}`"
-
-        if pending:
-            message += " will be deprecated in a future version"
-        else:
-            message += f" was deprecated in LangChain {since}"
-
-            if removal:
-                message += f" and will be removed {removal}"
-
-        if alternative:
-            message += f". Use {alternative} instead."
-
-        if addendum:
-            message += f" {addendum}"
-
-    warning_cls = PendingDeprecationWarning if pending else LangChainDeprecationWarning
-    warning = warning_cls(message)
-    warnings.warn(warning, category=LangChainDeprecationWarning, stacklevel=2)
+class LangChainPendingDeprecationWarning(PendingDeprecationWarning):
+    """A class for issuing deprecation warnings for LangChain users."""
 
 
 # PUBLIC API
@@ -262,7 +186,7 @@ def deprecated(
 
         def emit_warning() -> None:
             """Emit the warning."""
-            _warn_deprecated(
+            warn_deprecated(
                 since,
                 message=_message,
                 name=_name,
@@ -318,4 +242,100 @@ def suppress_langchain_deprecation_warning() -> Generator[None, None, None]:
     """Context manager to suppress LangChainDeprecationWarning."""
     with warnings.catch_warnings():
         warnings.simplefilter("ignore", LangChainDeprecationWarning)
+        warnings.simplefilter("ignore", LangChainPendingDeprecationWarning)
         yield
+
+
+def warn_deprecated(
+    since: str,
+    *,
+    message: str = "",
+    name: str = "",
+    alternative: str = "",
+    pending: bool = False,
+    obj_type: str = "",
+    addendum: str = "",
+    removal: str = "",
+) -> None:
+    """Display a standardized deprecation.
+
+    Arguments:
+        since : str
+            The release at which this API became deprecated.
+        message : str, optional
+            Override the default deprecation message. The %(since)s,
+            %(name)s, %(alternative)s, %(obj_type)s, %(addendum)s,
+            and %(removal)s format specifiers will be replaced by the
+            values of the respective arguments passed to this function.
+        name : str, optional
+            The name of the deprecated object.
+        alternative : str, optional
+            An alternative API that the user may use in place of the
+            deprecated API. The deprecation warning will tell the user
+            about this alternative if provided.
+        pending : bool, optional
+            If True, uses a PendingDeprecationWarning instead of a
+            DeprecationWarning. Cannot be used together with removal.
+        obj_type : str, optional
+            The object type being deprecated.
+        addendum : str, optional
+            Additional text appended directly to the final message.
+        removal : str, optional
+            The expected removal version. With the default (an empty
+            string), a removal version is automatically computed from
+            since. Set to other Falsy values to not schedule a removal
+            date. Cannot be used together with pending.
+    """
+    if pending and removal:
+        raise ValueError("A pending deprecation cannot have a scheduled removal")
+
+    if not pending:
+        if not removal:
+            removal = f"in {removal}" if removal else "within ?? minor releases"
+            raise NotImplementedError(
+                f"Need to determine which default deprecation schedule to use. "
+                f"{removal}"
+            )
+        else:
+            removal = f"in {removal}"
+
+    if not message:
+        message = ""
+
+        if obj_type:
+            message += f"The {obj_type} `{name}`"
+        else:
+            message += f"`{name}`"
+
+        if pending:
+            message += " will be deprecated in a future version"
+        else:
+            message += f" was deprecated in LangChain {since}"
+
+            if removal:
+                message += f" and will be removed {removal}"
+
+        if alternative:
+            message += f". Use {alternative} instead."
+
+        if addendum:
+            message += f" {addendum}"
+
+    warning_cls = (
+        LangChainPendingDeprecationWarning if pending else LangChainDeprecationWarning
+    )
+    warning = warning_cls(message)
+    warnings.warn(warning, category=LangChainDeprecationWarning, stacklevel=2)
+
+
+def surface_langchain_deprecation_warnings() -> None:
+    """Unmute LangChain deprecation warnings."""
+    warnings.filterwarnings(
+        "default",
+        category=LangChainPendingDeprecationWarning,
+    )
+
+    warnings.filterwarnings(
+        "default",
+        category=LangChainDeprecationWarning,
+    )

libs/langchain/langchain/adapters/openai.py

@@ -15,7 +15,7 @@ from typing import (
 
 from typing_extensions import Literal
 
-from langchain.chat_loaders.base import ChatSession
+from langchain.schema.chat import ChatSession
 from langchain.schema.messages import (
     AIMessage,
     AIMessageChunk,

libs/langchain/langchain/agents/agent.py

@@ -330,6 +330,11 @@ class RunnableAgent(BaseSingleActionAgent):
 
         arbitrary_types_allowed = True
 
+    @property
+    def return_values(self) -> List[str]:
+        """Return values of the agent."""
+        return []
+
     @property
     def input_keys(self) -> List[str]:
         """Return the input keys.

libs/langchain/langchain/agents/agent_toolkits/pandas/base.py

@@ -1,5 +1,5 @@
 """Agent for working with pandas objects."""
-from typing import Any, Dict, List, Optional, Tuple
+from typing import Any, Dict, List, Optional, Sequence, Tuple
 
 from langchain.agents.agent import AgentExecutor, BaseSingleActionAgent
 from langchain.agents.agent_toolkits.pandas.prompt import (
@@ -21,6 +21,7 @@ from langchain.chains.llm import LLMChain
 from langchain.schema import BasePromptTemplate
 from langchain.schema.language_model import BaseLanguageModel
 from langchain.schema.messages import SystemMessage
+from langchain.tools import BaseTool
 from langchain.tools.python.tool import PythonAstREPLTool
 
 
@@ -280,12 +281,13 @@ def create_pandas_dataframe_agent(
     agent_executor_kwargs: Optional[Dict[str, Any]] = None,
     include_df_in_prompt: Optional[bool] = True,
     number_of_head_rows: int = 5,
+    extra_tools: Sequence[BaseTool] = (),
     **kwargs: Dict[str, Any],
 ) -> AgentExecutor:
     """Construct a pandas agent from an LLM and dataframe."""
     agent: BaseSingleActionAgent
     if agent_type == AgentType.ZERO_SHOT_REACT_DESCRIPTION:
-        prompt, tools = _get_prompt_and_tools(
+        prompt, base_tools = _get_prompt_and_tools(
             df,
             prefix=prefix,
             suffix=suffix,
@@ -293,6 +295,7 @@ def create_pandas_dataframe_agent(
             include_df_in_prompt=include_df_in_prompt,
             number_of_head_rows=number_of_head_rows,
         )
+        tools = base_tools + list(extra_tools)
         llm_chain = LLMChain(
             llm=llm,
             prompt=prompt,
@@ -306,7 +309,7 @@ def create_pandas_dataframe_agent(
             **kwargs,
         )
     elif agent_type == AgentType.OPENAI_FUNCTIONS:
-        _prompt, tools = _get_functions_prompt_and_tools(
+        _prompt, base_tools = _get_functions_prompt_and_tools(
             df,
             prefix=prefix,
             suffix=suffix,
@@ -314,6 +317,7 @@ def create_pandas_dataframe_agent(
             include_df_in_prompt=include_df_in_prompt,
             number_of_head_rows=number_of_head_rows,
         )
+        tools = base_tools + list(extra_tools)
         agent = OpenAIFunctionsAgent(
             llm=llm,
             prompt=_prompt,

libs/langchain/langchain/agents/agent_toolkits/vectorstore/toolkit.py

@@ -5,12 +5,12 @@ from langchain.agents.agent_toolkits.base import BaseToolkit
 from langchain.llms.openai import OpenAI
 from langchain.pydantic_v1 import BaseModel, Field
 from langchain.schema.language_model import BaseLanguageModel
+from langchain.schema.vectorstore import VectorStore
 from langchain.tools import BaseTool
 from langchain.tools.vectorstore.tool import (
     VectorStoreQATool,
     VectorStoreQAWithSourcesTool,
 )
-from langchain.vectorstores.base import VectorStore
 
 
 class VectorStoreInfo(BaseModel):

libs/langchain/langchain/callbacks/tracers/base.py

@@ -102,6 +102,7 @@ class BaseTracer(BaseCallbackHandler, ABC):
         tags: Optional[List[str]] = None,
         parent_run_id: Optional[UUID] = None,
         metadata: Optional[Dict[str, Any]] = None,
+        name: Optional[str] = None,
         **kwargs: Any,
     ) -> Run:
         """Start a trace for an LLM run."""
@@ -122,6 +123,7 @@ class BaseTracer(BaseCallbackHandler, ABC):
             child_execution_order=execution_order,
             run_type="llm",
             tags=tags or [],
+            name=name,
         )
         self._start_trace(llm_run)
         self._on_llm_start(llm_run)
@@ -335,6 +337,7 @@ class BaseTracer(BaseCallbackHandler, ABC):
         tags: Optional[List[str]] = None,
         parent_run_id: Optional[UUID] = None,
         metadata: Optional[Dict[str, Any]] = None,
+        name: Optional[str] = None,
         **kwargs: Any,
     ) -> Run:
         """Start a trace for a tool run."""
@@ -356,6 +359,7 @@ class BaseTracer(BaseCallbackHandler, ABC):
             child_runs=[],
             run_type="tool",
             tags=tags or [],
+            name=name,
         )
         self._start_trace(tool_run)
         self._on_tool_start(tool_run)
@@ -406,6 +410,7 @@ class BaseTracer(BaseCallbackHandler, ABC):
         parent_run_id: Optional[UUID] = None,
         tags: Optional[List[str]] = None,
         metadata: Optional[Dict[str, Any]] = None,
+        name: Optional[str] = None,
         **kwargs: Any,
     ) -> Run:
         """Run when Retriever starts running."""
@@ -416,7 +421,7 @@ class BaseTracer(BaseCallbackHandler, ABC):
             kwargs.update({"metadata": metadata})
         retrieval_run = Run(
             id=run_id,
-            name="Retriever",
+            name=name or "Retriever",
             parent_run_id=parent_run_id,
             serialized=serialized,
             inputs={"query": query},

libs/langchain/langchain/callbacks/tracers/langchain.py

@@ -98,6 +98,7 @@ class LangChainTracer(BaseTracer):
         tags: Optional[List[str]] = None,
         parent_run_id: Optional[UUID] = None,
         metadata: Optional[Dict[str, Any]] = None,
+        name: Optional[str] = None,
         **kwargs: Any,
     ) -> None:
         """Start a trace for an LLM run."""
@@ -118,6 +119,7 @@ class LangChainTracer(BaseTracer):
             child_execution_order=execution_order,
             run_type="llm",
             tags=tags,
+            name=name,
         )
         self._start_trace(chat_model_run)
         self._on_chat_model_start(chat_model_run)

libs/langchain/langchain/callbacks/tracers/log_stream.py

@@ -193,7 +193,7 @@ class LogStreamCallbackHandler(BaseTracer):
                         "op": "replace",
                         "path": "",
                         "value": RunState(
-                            id=run.id,
+                            id=str(run.id),
                             streamed_output=[],
                             final_output=None,
                             logs=[],

libs/langchain/langchain/chains/conversational_retrieval/base.py

@@ -22,7 +22,7 @@ from langchain.pydantic_v1 import Extra, Field, root_validator
 from langchain.schema import BasePromptTemplate, BaseRetriever, Document
 from langchain.schema.language_model import BaseLanguageModel
 from langchain.schema.messages import BaseMessage
-from langchain.vectorstores.base import VectorStore
+from langchain.schema.vectorstore import VectorStore
 
 # Depending on the memory type and configuration, the chat history format may differ.
 # This needs to be consolidated.

libs/langchain/langchain/chains/graph_qa/cypher.py

@@ -34,12 +34,54 @@ def extract_cypher(text: str) -> str:
     return matches[0] if matches else text
 
 
+def construct_schema(
+    structured_schema: Dict[str, Any],
+    include_types: List[str],
+    exclude_types: List[str],
+) -> str:
+    """Filter the schema based on included or excluded types"""
+
+    def filter_func(x: str) -> bool:
+        return x in include_types if include_types else x not in exclude_types
+
+    filtered_schema = {
+        "node_props": {
+            k: v
+            for k, v in structured_schema.get("node_props", {}).items()
+            if filter_func(k)
+        },
+        "rel_props": {
+            k: v
+            for k, v in structured_schema.get("rel_props", {}).items()
+            if filter_func(k)
+        },
+        "relationships": [
+            r
+            for r in structured_schema.get("relationships", [])
+            if all(filter_func(r[t]) for t in ["start", "end", "type"])
+        ],
+    }
+
+    return (
+        f"Node properties are the following: \n {filtered_schema['node_props']}\n"
+        f"Relationships properties are the following: \n {filtered_schema['rel_props']}"
+        "\nRelationships are: \n"
+        + str(
+            [
+                f"(:{el['start']})-[:{el['type']}]->(:{el['end']})"
+                for el in filtered_schema["relationships"]
+            ]
+        )
+    )
+
+
 class GraphCypherQAChain(Chain):
     """Chain for question-answering against a graph by generating Cypher statements."""
 
     graph: Neo4jGraph = Field(exclude=True)
     cypher_generation_chain: LLMChain
     qa_chain: LLMChain
+    graph_schema: str
     input_key: str = "query"  #: :meta private:
     output_key: str = "result"  #: :meta private:
     top_k: int = 10
@@ -79,6 +121,8 @@ class GraphCypherQAChain(Chain):
         cypher_prompt: BasePromptTemplate = CYPHER_GENERATION_PROMPT,
         cypher_llm: Optional[BaseLanguageModel] = None,
         qa_llm: Optional[BaseLanguageModel] = None,
+        exclude_types: List[str] = [],
+        include_types: List[str] = [],
         **kwargs: Any,
     ) -> GraphCypherQAChain:
         """Initialize from LLM."""
@@ -96,7 +140,18 @@ class GraphCypherQAChain(Chain):
         qa_chain = LLMChain(llm=qa_llm or llm, prompt=qa_prompt)
         cypher_generation_chain = LLMChain(llm=cypher_llm or llm, prompt=cypher_prompt)
 
+        if exclude_types and include_types:
+            raise ValueError(
+                "Either `exclude_types` or `include_types` "
+                "can be provided, but not both"
+            )
+
+        graph_schema = construct_schema(
+            kwargs["graph"].structured_schema, include_types, exclude_types
+        )
+
         return cls(
+            graph_schema=graph_schema,
             qa_chain=qa_chain,
             cypher_generation_chain=cypher_generation_chain,
             **kwargs,
@@ -115,7 +170,7 @@ class GraphCypherQAChain(Chain):
         intermediate_steps: List = []
 
         generated_cypher = self.cypher_generation_chain.run(
-            {"question": question, "schema": self.graph.get_schema}, callbacks=callbacks
+            {"question": question, "schema": self.graph_schema}, callbacks=callbacks
         )
 
         # Extract Cypher code if it is wrapped in backticks

libs/langchain/langchain/chains/graph_qa/neptune_cypher.py

@@ -68,7 +68,7 @@ def use_simple_prompt(llm: BaseLanguageModel) -> bool:
         return True
 
     # Bedrock anthropic
-    if llm.model_id and "anthropic" in llm.model_id:  # type: ignore
+    if hasattr(llm, "model_id") and "anthropic" in llm.model_id:  # type: ignore
         return True
 
     return False

libs/langchain/langchain/chains/llm.py

@@ -42,8 +42,8 @@ class LLMChain(Chain):
             llm = LLMChain(llm=OpenAI(), prompt=prompt)
     """
 
-    @property
-    def lc_serializable(self) -> bool:
+    @classmethod
+    def is_lc_serializable(self) -> bool:
         return True
 
     prompt: BasePromptTemplate

libs/langchain/langchain/chains/llm_symbolic_math/__init__.py

@@ -2,3 +2,13 @@
 
 Heavily borrowed from llm_math, wrapper for SymPy
 """
+from langchain._api import warn_deprecated
+
+warn_deprecated(
+    since="0.0.304",
+    message=(
+        "On 2023-10-06 this module will be moved to langchain-experimental as "
+        "it relies on sympify https://github.com/sympy/sympy/issues/10805"
+    ),
+    pending=True,
+)

libs/langchain/langchain/chains/qa_with_sources/vector_db.py

@@ -11,7 +11,7 @@ from langchain.chains.combine_documents.stuff import StuffDocumentsChain
 from langchain.chains.qa_with_sources.base import BaseQAWithSourcesChain
 from langchain.docstore.document import Document
 from langchain.pydantic_v1 import Field, root_validator
-from langchain.vectorstores.base import VectorStore
+from langchain.schema.vectorstore import VectorStore
 
 
 class VectorDBQAWithSourcesChain(BaseQAWithSourcesChain):

libs/langchain/langchain/chains/question_answering/refine_prompts.py

@@ -33,7 +33,7 @@ refine_template = (
     "If the context isn't useful, return the original answer."
 )
 CHAT_REFINE_PROMPT = ChatPromptTemplate.from_messages(
-    [("human", "{question}"), ("ai", "{existing_answer}"), ("human", "refine_template")]
+    [("human", "{question}"), ("ai", "{existing_answer}"), ("human", refine_template)]
 )
 REFINE_PROMPT_SELECTOR = ConditionalPromptSelector(
     default_prompt=DEFAULT_REFINE_PROMPT,

libs/langchain/langchain/chains/retrieval_qa/base.py

@@ -21,7 +21,7 @@ from langchain.prompts import PromptTemplate
 from langchain.pydantic_v1 import Extra, Field, root_validator
 from langchain.schema import BaseRetriever, Document
 from langchain.schema.language_model import BaseLanguageModel
-from langchain.vectorstores.base import VectorStore
+from langchain.schema.vectorstore import VectorStore
 
 
 class BaseRetrievalQA(Chain):
@@ -197,8 +197,8 @@ class RetrievalQA(BaseRetrievalQA):
 
             from langchain.llms import OpenAI
             from langchain.chains import RetrievalQA
-            from langchain.faiss import FAISS
-            from langchain.vectorstores.base import VectorStoreRetriever
+            from langchain.vectorstores import FAISS
+            from langchain.schema.vectorstore import VectorStoreRetriever
             retriever = VectorStoreRetriever(vectorstore=FAISS(...))
             retrievalQA = RetrievalQA.from_llm(llm=OpenAI(), retriever=retriever)
 

libs/langchain/langchain/chains/router/embedding_router.py

@@ -7,7 +7,7 @@ from langchain.chains.router.base import RouterChain
 from langchain.docstore.document import Document
 from langchain.pydantic_v1 import Extra
 from langchain.schema.embeddings import Embeddings
-from langchain.vectorstores.base import VectorStore
+from langchain.schema.vectorstore import VectorStore
 
 
 class EmbeddingRouterChain(RouterChain):

libs/langchain/langchain/chat_loaders/base.py

@@ -1,15 +1,7 @@
 from abc import ABC, abstractmethod
-from typing import Iterator, List, Sequence, TypedDict
+from typing import Iterator, List
 
-from langchain.schema.messages import BaseMessage
-
-
-class ChatSession(TypedDict):
-    """Chat Session represents a single
-    conversation, channel, or other group of messages."""
-
-    messages: Sequence[BaseMessage]
-    """The LangChain chat messages loaded from the source."""
+from langchain.schema.chat import ChatSession
 
 
 class BaseChatLoader(ABC):

libs/langchain/langchain/chat_loaders/facebook_messenger.py

@@ -3,7 +3,8 @@ import logging
 from pathlib import Path
 from typing import Iterator, Union
 
-from langchain.chat_loaders.base import BaseChatLoader, ChatSession
+from langchain.chat_loaders.base import BaseChatLoader
+from langchain.schema.chat import ChatSession
 from langchain.schema.messages import HumanMessage
 
 logger = logging.getLogger(__file__)

libs/langchain/langchain/chat_loaders/gmail.py

@@ -2,7 +2,8 @@ import base64
 import re
 from typing import Any, Iterator
 
-from langchain.chat_loaders.base import BaseChatLoader, ChatSession
+from langchain.chat_loaders.base import BaseChatLoader
+from langchain.schema.chat import ChatSession
 from langchain.schema.messages import HumanMessage
 
 

libs/langchain/langchain/chat_loaders/imessage.py

@@ -3,8 +3,9 @@ from __future__ import annotations
 from pathlib import Path
 from typing import TYPE_CHECKING, Iterator, List, Optional, Union
 
-from langchain.chat_loaders.base import BaseChatLoader, ChatSession
+from langchain.chat_loaders.base import BaseChatLoader
 from langchain.schema import HumanMessage
+from langchain.schema.chat import ChatSession
 
 if TYPE_CHECKING:
     import sqlite3

libs/langchain/langchain/chat_loaders/slack.py

@@ -5,8 +5,9 @@ import zipfile
 from pathlib import Path
 from typing import Dict, Iterator, List, Union
 
-from langchain.chat_loaders.base import BaseChatLoader, ChatSession
+from langchain.chat_loaders.base import BaseChatLoader
 from langchain.schema import AIMessage, HumanMessage
+from langchain.schema.chat import ChatSession
 
 logger = logging.getLogger(__name__)
 

libs/langchain/langchain/chat_loaders/telegram.py

@@ -6,8 +6,9 @@ import zipfile
 from pathlib import Path
 from typing import Iterator, List, Union
 
-from langchain.chat_loaders.base import BaseChatLoader, ChatSession
+from langchain.chat_loaders.base import BaseChatLoader
 from langchain.schema import AIMessage, BaseMessage, HumanMessage
+from langchain.schema.chat import ChatSession
 
 logger = logging.getLogger(__name__)
 

libs/langchain/langchain/chat_loaders/utils.py

@@ -2,7 +2,7 @@
 from copy import deepcopy
 from typing import Iterable, Iterator, List
 
-from langchain.chat_loaders.base import ChatSession
+from langchain.schema.chat import ChatSession
 from langchain.schema.messages import AIMessage, BaseMessage
 
 

libs/langchain/langchain/chat_loaders/whatsapp.py

@@ -4,8 +4,9 @@ import re
 import zipfile
 from typing import Iterator, List, Union
 
-from langchain.chat_loaders.base import BaseChatLoader, ChatSession
+from langchain.chat_loaders.base import BaseChatLoader
 from langchain.schema import AIMessage, HumanMessage
+from langchain.schema.chat import ChatSession
 
 logger = logging.getLogger(__name__)
 

libs/langchain/langchain/chat_models/__init__.py

@@ -24,6 +24,7 @@ from langchain.chat_models.baidu_qianfan_endpoint import QianfanChatEndpoint
 from langchain.chat_models.bedrock import BedrockChat
 from langchain.chat_models.ernie import ErnieBotChat
 from langchain.chat_models.fake import FakeListChatModel
+from langchain.chat_models.fireworks import ChatFireworks
 from langchain.chat_models.google_palm import ChatGooglePalm
 from langchain.chat_models.human import HumanInputChatModel
 from langchain.chat_models.javelin_ai_gateway import ChatJavelinAIGateway
@@ -57,4 +58,5 @@ __all__ = [
     "ChatJavelinAIGateway",
     "ChatKonko",
     "QianfanChatEndpoint",
+    "ChatFireworks",
 ]

libs/langchain/langchain/chat_models/anthropic.py

@@ -99,8 +99,9 @@ class ChatAnthropic(BaseChatModel, _AnthropicCommon):
         """Return type of chat model."""
         return "anthropic-chat"
 
-    @property
-    def lc_serializable(self) -> bool:
+    @classmethod
+    def is_lc_serializable(cls) -> bool:
+        """Return whether this model can be serialized by Langchain."""
         return True
 
     def _convert_messages_to_prompt(self, messages: List[BaseMessage]) -> str:

libs/langchain/langchain/chat_models/anyscale.py

@@ -4,7 +4,7 @@ from __future__ import annotations
 import logging
 import os
 import sys
-from typing import TYPE_CHECKING, Optional, Set
+from typing import TYPE_CHECKING, Dict, Optional, Set
 
 import requests
 
@@ -50,7 +50,7 @@ class ChatAnyscale(ChatOpenAI):
         return "anyscale-chat"
 
     @property
-    def lc_secrets(self) -> dict[str, str]:
+    def lc_secrets(self) -> Dict[str, str]:
         return {"anyscale_api_key": "ANYSCALE_API_KEY"}
 
     anyscale_api_key: Optional[str] = None

libs/langchain/langchain/chat_models/base.py

@@ -139,6 +139,7 @@ class BaseChatModel(BaseLanguageModel[BaseMessageChunk], ABC):
                     callbacks=config.get("callbacks"),
                     tags=config.get("tags"),
                     metadata=config.get("metadata"),
+                    run_name=config.get("run_name"),
                     **kwargs,
                 ).generations[0][0],
             ).message,
@@ -165,6 +166,7 @@ class BaseChatModel(BaseLanguageModel[BaseMessageChunk], ABC):
             callbacks=config.get("callbacks"),
             tags=config.get("tags"),
             metadata=config.get("metadata"),
+            run_name=config.get("run_name"),
             **kwargs,
         )
         return cast(
@@ -197,7 +199,11 @@ class BaseChatModel(BaseLanguageModel[BaseMessageChunk], ABC):
                 self.metadata,
             )
             (run_manager,) = callback_manager.on_chat_model_start(
-                dumpd(self), [messages], invocation_params=params, options=options
+                dumpd(self),
+                [messages],
+                invocation_params=params,
+                options=options,
+                name=config.get("run_name"),
             )
             try:
                 generation: Optional[ChatGenerationChunk] = None
@@ -244,7 +250,11 @@ class BaseChatModel(BaseLanguageModel[BaseMessageChunk], ABC):
                 self.metadata,
             )
             (run_manager,) = await callback_manager.on_chat_model_start(
-                dumpd(self), [messages], invocation_params=params, options=options
+                dumpd(self),
+                [messages],
+                invocation_params=params,
+                options=options,
+                name=config.get("run_name"),
             )
             try:
                 generation: Optional[ChatGenerationChunk] = None
@@ -280,7 +290,7 @@ class BaseChatModel(BaseLanguageModel[BaseMessageChunk], ABC):
         return {**params, **kwargs}
 
     def _get_llm_string(self, stop: Optional[List[str]] = None, **kwargs: Any) -> str:
-        if self.lc_serializable:
+        if self.is_lc_serializable():
             params = {**kwargs, **{"stop": stop}}
             param_string = str(sorted([(k, v) for k, v in params.items()]))
             llm_string = dumps(self)
@@ -298,6 +308,7 @@ class BaseChatModel(BaseLanguageModel[BaseMessageChunk], ABC):
         *,
         tags: Optional[List[str]] = None,
         metadata: Optional[Dict[str, Any]] = None,
+        run_name: Optional[str] = None,
         **kwargs: Any,
     ) -> LLMResult:
         """Top Level call"""
@@ -314,7 +325,11 @@ class BaseChatModel(BaseLanguageModel[BaseMessageChunk], ABC):
             self.metadata,
         )
         run_managers = callback_manager.on_chat_model_start(
-            dumpd(self), messages, invocation_params=params, options=options
+            dumpd(self),
+            messages,
+            invocation_params=params,
+            options=options,
+            name=run_name,
         )
         results = []
         for i, m in enumerate(messages):
@@ -354,6 +369,7 @@ class BaseChatModel(BaseLanguageModel[BaseMessageChunk], ABC):
         *,
         tags: Optional[List[str]] = None,
         metadata: Optional[Dict[str, Any]] = None,
+        run_name: Optional[str] = None,
         **kwargs: Any,
     ) -> LLMResult:
         """Top Level call"""
@@ -371,7 +387,11 @@ class BaseChatModel(BaseLanguageModel[BaseMessageChunk], ABC):
         )
 
         run_managers = await callback_manager.on_chat_model_start(
-            dumpd(self), messages, invocation_params=params, options=options
+            dumpd(self),
+            messages,
+            invocation_params=params,
+            options=options,
+            name=run_name,
         )
 
         results = await asyncio.gather(

libs/langchain/langchain/chat_models/bedrock.py

@@ -1,7 +1,6 @@
-from typing import Any, AsyncIterator, Dict, Iterator, List, Optional
+from typing import Any, Dict, Iterator, List, Optional
 
 from langchain.callbacks.manager import (
-    AsyncCallbackManagerForLLMRun,
     CallbackManagerForLLMRun,
 )
 from langchain.chat_models.anthropic import convert_messages_to_prompt_anthropic
@@ -59,17 +58,6 @@ class BedrockChat(BaseChatModel, BedrockBase):
             delta = chunk.text
             yield ChatGenerationChunk(message=AIMessageChunk(content=delta))
 
-    def _astream(
-        self,
-        messages: List[BaseMessage],
-        stop: Optional[List[str]] = None,
-        run_manager: Optional[AsyncCallbackManagerForLLMRun] = None,
-        **kwargs: Any,
-    ) -> AsyncIterator[ChatGenerationChunk]:
-        raise NotImplementedError(
-            """Bedrock doesn't support async requests at the moment."""
-        )
-
     def _generate(
         self,
         messages: List[BaseMessage],
@@ -98,14 +86,3 @@ class BedrockChat(BaseChatModel, BedrockBase):
 
         message = AIMessage(content=completion)
         return ChatResult(generations=[ChatGeneration(message=message)])
-
-    async def _agenerate(
-        self,
-        messages: List[BaseMessage],
-        stop: Optional[List[str]] = None,
-        run_manager: Optional[AsyncCallbackManagerForLLMRun] = None,
-        **kwargs: Any,
-    ) -> ChatResult:
-        raise NotImplementedError(
-            """Bedrock doesn't support async stream requests at the moment."""
-        )

libs/langchain/langchain/chat_models/fireworks.py

@@ -0,0 +1,292 @@
+from typing import (
+    Any,
+    AsyncIterator,
+    Callable,
+    Dict,
+    Iterator,
+    List,
+    Optional,
+    Type,
+    Union,
+)
+
+from langchain.adapters.openai import convert_message_to_dict
+from langchain.callbacks.manager import (
+    AsyncCallbackManagerForLLMRun,
+    CallbackManagerForLLMRun,
+)
+from langchain.chat_models.base import BaseChatModel
+from langchain.llms.base import create_base_retry_decorator
+from langchain.pydantic_v1 import Field, root_validator
+from langchain.schema.messages import (
+    AIMessage,
+    AIMessageChunk,
+    BaseMessage,
+    BaseMessageChunk,
+    ChatMessage,
+    ChatMessageChunk,
+    FunctionMessage,
+    FunctionMessageChunk,
+    HumanMessage,
+    HumanMessageChunk,
+    SystemMessage,
+    SystemMessageChunk,
+)
+from langchain.schema.output import ChatGeneration, ChatGenerationChunk, ChatResult
+from langchain.utils.env import get_from_dict_or_env
+
+
+def _convert_delta_to_message_chunk(
+    _dict: Any, default_class: Type[BaseMessageChunk]
+) -> BaseMessageChunk:
+    """Convert a delta response to a message chunk."""
+    role = _dict.role
+    content = _dict.content or ""
+    additional_kwargs: Dict = {}
+
+    if role == "user" or default_class == HumanMessageChunk:
+        return HumanMessageChunk(content=content)
+    elif role == "assistant" or default_class == AIMessageChunk:
+        return AIMessageChunk(content=content, additional_kwargs=additional_kwargs)
+    elif role == "system" or default_class == SystemMessageChunk:
+        return SystemMessageChunk(content=content)
+    elif role == "function" or default_class == FunctionMessageChunk:
+        return FunctionMessageChunk(content=content, name=_dict.name)
+    elif role or default_class == ChatMessageChunk:
+        return ChatMessageChunk(content=content, role=role)
+    else:
+        return default_class(content=content)
+
+
+def convert_dict_to_message(_dict: Any) -> BaseMessage:
+    """Convert a dict response to a message."""
+    role = _dict.role
+    content = _dict.content or ""
+    if role == "user":
+        return HumanMessage(content=content)
+    elif role == "assistant":
+        content = _dict.content
+        additional_kwargs: Dict = {}
+        return AIMessage(content=content, additional_kwargs=additional_kwargs)
+    elif role == "system":
+        return SystemMessage(content=content)
+    elif role == "function":
+        return FunctionMessage(content=content, name=_dict.name)
+    else:
+        return ChatMessage(content=content, role=role)
+
+
+class ChatFireworks(BaseChatModel):
+    """Fireworks Chat models."""
+
+    model: str = "accounts/fireworks/models/llama-v2-7b-chat"
+    model_kwargs: dict = Field(
+        default_factory=lambda: {
+            "temperature": 0.7,
+            "max_tokens": 512,
+            "top_p": 1,
+        }.copy()
+    )
+    fireworks_api_key: Optional[str] = None
+    max_retries: int = 20
+
+    @root_validator()
+    def validate_environment(cls, values: Dict) -> Dict:
+        """Validate that api key in environment."""
+        try:
+            import fireworks.client
+        except ImportError as e:
+            raise ImportError("") from e
+        fireworks_api_key = get_from_dict_or_env(
+            values, "fireworks_api_key", "FIREWORKS_API_KEY"
+        )
+        fireworks.client.api_key = fireworks_api_key
+        return values
+
+    @property
+    def _llm_type(self) -> str:
+        """Return type of llm."""
+        return "fireworks-chat"
+
+    def _generate(
+        self,
+        messages: List[BaseMessage],
+        stop: Optional[List[str]] = None,
+        run_manager: Optional[CallbackManagerForLLMRun] = None,
+        **kwargs: Any,
+    ) -> ChatResult:
+        message_dicts = self._create_message_dicts(messages, stop)
+
+        params = {
+            "model": self.model,
+            "messages": message_dicts,
+            **self.model_kwargs,
+        }
+        response = completion_with_retry(self, run_manager=run_manager, **params)
+        return self._create_chat_result(response)
+
+    async def _agenerate(
+        self,
+        messages: List[BaseMessage],
+        stop: Optional[List[str]] = None,
+        run_manager: Optional[AsyncCallbackManagerForLLMRun] = None,
+        **kwargs: Any,
+    ) -> ChatResult:
+        message_dicts = self._create_message_dicts(messages, stop)
+        params = {
+            "model": self.model,
+            "messages": message_dicts,
+            **self.model_kwargs,
+        }
+        response = await acompletion_with_retry(self, run_manager=run_manager, **params)
+        return self._create_chat_result(response)
+
+    def _combine_llm_outputs(self, llm_outputs: List[Optional[dict]]) -> dict:
+        if llm_outputs[0] is None:
+            return {}
+        return llm_outputs[0]
+
+    def _create_chat_result(self, response: Any) -> ChatResult:
+        generations = []
+        for res in response.choices:
+            message = convert_dict_to_message(res.message)
+            gen = ChatGeneration(
+                message=message,
+                generation_info=dict(finish_reason=res.finish_reason),
+            )
+            generations.append(gen)
+        llm_output = {"model": self.model}
+        return ChatResult(generations=generations, llm_output=llm_output)
+
+    def _create_message_dicts(
+        self, messages: List[BaseMessage], stop: Optional[List[str]]
+    ) -> List[Dict[str, Any]]:
+        message_dicts = [convert_message_to_dict(m) for m in messages]
+        return message_dicts
+
+    def _stream(
+        self,
+        messages: List[BaseMessage],
+        stop: Optional[List[str]] = None,
+        run_manager: Optional[CallbackManagerForLLMRun] = None,
+        **kwargs: Any,
+    ) -> Iterator[ChatGenerationChunk]:
+        message_dicts = self._create_message_dicts(messages, stop)
+        default_chunk_class = AIMessageChunk
+        params = {
+            "model": self.model,
+            "messages": message_dicts,
+            "stream": True,
+            **self.model_kwargs,
+        }
+        for chunk in completion_with_retry(self, run_manager=run_manager, **params):
+            choice = chunk.choices[0]
+            chunk = _convert_delta_to_message_chunk(choice.delta, default_chunk_class)
+            finish_reason = choice.finish_reason
+            generation_info = (
+                dict(finish_reason=finish_reason) if finish_reason is not None else None
+            )
+            default_chunk_class = chunk.__class__
+            yield ChatGenerationChunk(message=chunk, generation_info=generation_info)
+
+    async def _astream(
+        self,
+        messages: List[BaseMessage],
+        stop: Optional[List[str]] = None,
+        run_manager: Optional[AsyncCallbackManagerForLLMRun] = None,
+        **kwargs: Any,
+    ) -> AsyncIterator[ChatGenerationChunk]:
+        message_dicts = self._create_message_dicts(messages, stop)
+        default_chunk_class = AIMessageChunk
+        params = {
+            "model": self.model,
+            "messages": message_dicts,
+            "stream": True,
+            **self.model_kwargs,
+        }
+        async for chunk in await acompletion_with_retry_streaming(
+            self, run_manager=run_manager, **params
+        ):
+            choice = chunk.choices[0]
+            chunk = _convert_delta_to_message_chunk(choice.delta, default_chunk_class)
+            finish_reason = choice.finish_reason
+            generation_info = (
+                dict(finish_reason=finish_reason) if finish_reason is not None else None
+            )
+            default_chunk_class = chunk.__class__
+            yield ChatGenerationChunk(message=chunk, generation_info=generation_info)
+
+
+def completion_with_retry(
+    llm: ChatFireworks,
+    run_manager: Optional[CallbackManagerForLLMRun] = None,
+    **kwargs: Any,
+) -> Any:
+    """Use tenacity to retry the completion call."""
+    import fireworks.client
+
+    retry_decorator = _create_retry_decorator(llm, run_manager=run_manager)
+
+    @retry_decorator
+    def _completion_with_retry(**kwargs: Any) -> Any:
+        return fireworks.client.ChatCompletion.create(
+            **kwargs,
+        )
+
+    return _completion_with_retry(**kwargs)
+
+
+async def acompletion_with_retry(
+    llm: ChatFireworks,
+    run_manager: Optional[AsyncCallbackManagerForLLMRun] = None,
+    **kwargs: Any,
+) -> Any:
+    """Use tenacity to retry the async completion call."""
+    import fireworks.client
+
+    retry_decorator = _create_retry_decorator(llm, run_manager=run_manager)
+
+    @retry_decorator
+    async def _completion_with_retry(**kwargs: Any) -> Any:
+        return await fireworks.client.ChatCompletion.acreate(
+            **kwargs,
+        )
+
+    return await _completion_with_retry(**kwargs)
+
+
+async def acompletion_with_retry_streaming(
+    llm: ChatFireworks,
+    run_manager: Optional[AsyncCallbackManagerForLLMRun] = None,
+    **kwargs: Any,
+) -> Any:
+    """Use tenacity to retry the completion call for streaming."""
+    import fireworks.client
+
+    retry_decorator = _create_retry_decorator(llm, run_manager=run_manager)
+
+    @retry_decorator
+    async def _completion_with_retry(**kwargs: Any) -> Any:
+        return fireworks.client.ChatCompletion.acreate(
+            **kwargs,
+        )
+
+    return await _completion_with_retry(**kwargs)
+
+
+def _create_retry_decorator(
+    llm: ChatFireworks,
+    run_manager: Optional[
+        Union[AsyncCallbackManagerForLLMRun, CallbackManagerForLLMRun]
+    ] = None,
+) -> Callable[[Any], Any]:
+    """Define retry mechanism."""
+    import fireworks.client
+
+    errors = [
+        fireworks.client.error.RateLimitError,
+        fireworks.client.error.ServiceUnavailableError,
+    ]
+    return create_base_retry_decorator(
+        error_types=errors, max_retries=llm.max_retries, run_manager=run_manager
+    )

libs/langchain/langchain/chat_models/jinachat.py

@@ -12,6 +12,7 @@ from typing import (
     Mapping,
     Optional,
     Tuple,
+    Type,
     Union,
 )
 
@@ -91,7 +92,7 @@ async def acompletion_with_retry(llm: JinaChat, **kwargs: Any) -> Any:
 
 
 def _convert_delta_to_message_chunk(
-    _dict: Mapping[str, Any], default_class: type[BaseMessageChunk]
+    _dict: Mapping[str, Any], default_class: Type[BaseMessageChunk]
 ) -> BaseMessageChunk:
     role = _dict.get("role")
     content = _dict.get("content") or ""
@@ -164,8 +165,9 @@ class JinaChat(BaseChatModel):
     def lc_secrets(self) -> Dict[str, str]:
         return {"jinachat_api_key": "JINACHAT_API_KEY"}
 
-    @property
-    def lc_serializable(self) -> bool:
+    @classmethod
+    def is_lc_serializable(cls) -> bool:
+        """Return whether this model can be serialized by Langchain."""
         return True
 
     client: Any  #: :meta private:

libs/langchain/langchain/chat_models/konko.py

@@ -55,8 +55,9 @@ class ChatKonko(ChatOpenAI):
     def lc_secrets(self) -> Dict[str, str]:
         return {"konko_api_key": "KONKO_API_KEY", "openai_api_key": "OPENAI_API_KEY"}
 
-    @property
-    def lc_serializable(self) -> bool:
+    @classmethod
+    def is_lc_serializable(cls) -> bool:
+        """Return whether this model can be serialized by Langchain."""
         return True
 
     client: Any = None  #: :meta private: