2987 Commits (f9f5626ca48d56d875444504e4745d2b059965fc)

Author	SHA1	Message	Date
Brian Burgin	148347e858	community[minor]: Add LiteLLM Router Integration (#15588) ... community: - **Description:** - Add new ChatLiteLLMRouter class that allows a client to use a LiteLLM Router as a LangChain chat model. - Note: The existing ChatLiteLLM integration did not cover the LiteLLM Router class. - Add tests and Jupyter notebook. - **Issue:** None - **Dependencies:** Relies on existing ChatLiteLLM integration - **Twitter handle:** @bburgin_0 --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	8 months ago
Bob Lin	35e60728b7	docs: Fix broken urls (#16559)	8 months ago
Bob Lin	6023953ea7	docs: Fix github link (#16560)	8 months ago
Erick Friis	adc008407e	exa: init pkg (#16553)	8 months ago
Rave Harpaz	c4e9c9ca29	community[minor]: Add OCI Generative AI integration (#16548) ... <!-- Thank you for contributing to LangChain! Please title your PR "<package>: <description>", where <package> is whichever of langchain, community, core, experimental, etc. is being modified. Replace this entire comment with: - **Description:** Adding Oracle Cloud Infrastructure Generative AI integration. Oracle Cloud Infrastructure (OCI) Generative AI is a fully managed service that provides a set of state-of-the-art, customizable large language models (LLMs) that cover a wide range of use cases, and which is available through a single API. Using the OCI Generative AI service you can access ready-to-use pretrained models, or create and host your own fine-tuned custom models based on your own data on dedicated AI clusters. https://docs.oracle.com/en-us/iaas/Content/generative-ai/home.htm - **Issue:** None, - **Dependencies:** OCI Python SDK, - **Twitter handle:** we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` from the root of the package you've modified to check this locally. Passed See contribution guidelines for more information on how to write/run tests, lint, etc: https://python.langchain.com/docs/contributing/ If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. we provide unit tests. However, we cannot provide integration tests due to Oracle policies that prohibit public sharing of api keys.   If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. --> --------- Co-authored-by: Arthur Cheng <arthur.cheng@oracle.com> Co-authored-by: Bagatur <baskaryan@gmail.com>	8 months ago
Leonid Ganeline	f6a05e964b	docs: `Hugging Face` update (#16490) ... - added missed integrations to the platform page - updated integration examples: added links and fixed formats	8 months ago
Harel Gal	a91181fe6d	community[minor]: add support for Guardrails for Amazon Bedrock (#15099) ... Added support for optionally supplying 'Guardrails for Amazon Bedrock' on both types of model invocations (batch/regular and streaming) and for all models supported by the Amazon Bedrock service. @baskaryan @hwchase17 ```python llm = Bedrock(model_id="<model_id>", client=bedrock, model_kwargs={}, guardrails={"id": " <guardrail_id>", "version": "<guardrail_version>", "trace": True}, callbacks=[BedrockAsyncCallbackHandler()]) class BedrockAsyncCallbackHandler(AsyncCallbackHandler): """Async callback handler that can be used to handle callbacks from langchain.""" async def on_llm_error( self, error: BaseException, **kwargs: Any, ) -> Any: reason = kwargs.get("reason") if reason == "GUARDRAIL_INTERVENED": # kwargs contains additional trace information sent by 'Guardrails for Bedrock' service. print(f"""Guardrails: {kwargs}""") # streaming llm = Bedrock(model_id="<model_id>", client=bedrock, model_kwargs={}, streaming=True, guardrails={"id": "<guardrail_id>", "version": "<guardrail_version>"}) ``` --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	8 months ago
Martin Kolb	04651f0248	community[minor]: VectorStore integration for SAP HANA Cloud Vector Engine (#16514) ... - **Description:** This PR adds a VectorStore integration for SAP HANA Cloud Vector Engine, which is an upcoming feature in the SAP HANA Cloud database (https://blogs.sap.com/2023/11/02/sap-hana-clouds-vector-engine-announcement/). - **Issue:** N/A - **Dependencies:** [SAP HANA Python Client](https://pypi.org/project/hdbcli/) - **Twitter handle:** @sapopensource Implementation of the integration: `libs/community/langchain_community/vectorstores/hanavector.py` Unit tests: `libs/community/tests/unit_tests/vectorstores/test_hanavector.py` Integration tests: `libs/community/tests/integration_tests/vectorstores/test_hanavector.py` Example notebook: `docs/docs/integrations/vectorstores/hanavector.ipynb` Access credentials for execution of the integration tests can be provided to the maintainers. --------- Co-authored-by: sascha <sascha.stoll@sap.com> Co-authored-by: Bagatur <baskaryan@gmail.com>	8 months ago
Bob Lin	54dd8e52a8	docs: Updated comments about `n_gpu_layers` in the Metal section (#16501) ... Ref: https://github.com/langchain-ai/langchain/issues/16502	8 months ago
Anastasiia Manokhina	ce595f0203	docs:Updated integration docs structure for chat/google_vertex_ai_palm (#16201) ... Description: - checked that the doc chat/google_vertex_ai_palm is using new functions: invoke, stream etc. - added Gemini example - fixed wrong output in Sanskrit example Issue: https://github.com/langchain-ai/langchain/issues/15664 Dependencies: None Twitter handle: None	8 months ago
Erick Friis	8d299645f9	docs: rm output (#16519)	8 months ago
Lance Martin	0b740ebd49	Update SQL agent toolkit docs (#16409)	8 months ago
Francisco Ingham	13cf4594f4	docs: added a few suggestions for sql docs (#16508)	8 months ago
Eugene Yurtsev	6004e9706f	Docs: Add streaming section (#16468) ... Adds a streaming section to LangChain documentation, explaining `stream`/`astream` API and `astream_events` API.	8 months ago
Tipwheal	66aafc0573	Docs: typo in tool use quick start page (#16494) ... Minor typo fix	8 months ago
BeatrixCohere	2b2285dac0	docs: Update cohere rerank and comparison docs (#16198) ... - **Description:** Update the cohere rerank docs to use cohere embeddings - **Issue:** n/a - **Dependencies:** n/a - **Twitter handle:** n/a	8 months ago
Raunak	476bf8b763	community[patch]: Load list of files using UnstructuredFileLoader (#16216) ... - **Description:** Updated `_get_elements()` function of `UnstructuredFileLoader `class to check if the argument self.file_path is a file or list of files. If it is a list of files then it iterates over the list of file paths, calls the partition function for each one, and appends the results to the elements list. If self.file_path is not a list, it calls the partition function as before. - **Issue:** Fixed #15607, - **Dependencies:** NA - **Twitter handle:** NA Co-authored-by: H161961 <Raunak.Raunak@Honeywell.com>	8 months ago
Xudong Sun	019b6ebe8d	community[minor]: Add iFlyTek Spark LLM chat model support (#13389) ... - **Description:** This PR enables LangChain to access the iFlyTek's Spark LLM via the chat_models wrapper. - **Dependencies:** websocket-client ^1.6.1 - **Tag maintainer:** @baskaryan ### SparkLLM chat model usage Get SparkLLM's app_id, api_key and api_secret from [iFlyTek SparkLLM API Console](https://console.xfyun.cn/services/bm3) (for more info, see [iFlyTek SparkLLM Intro](https://xinghuo.xfyun.cn/sparkapi) ), then set environment variables `IFLYTEK_SPARK_APP_ID`, `IFLYTEK_SPARK_API_KEY` and `IFLYTEK_SPARK_API_SECRET` or pass parameters when using it like the demo below: ```python3 from langchain.chat_models.sparkllm import ChatSparkLLM client = ChatSparkLLM( spark_app_id="<app_id>", spark_api_key="<api_key>", spark_api_secret="<api_secret>" ) ```	8 months ago
Eugene Yurtsev	d898d2f07b	docs: Fix version in which astream_events was released (#16481) ... Fix typo in version	8 months ago
bu2kx	ff3163297b	community[minor]: Add KDBAI vector store (#12797) ... Addition of KDBAI vector store (https://kdb.ai). Dependencies: `kdbai_client` v0.1.2 Python package. Sample notebook: `docs/docs/integrations/vectorstores/kdbai.ipynb` Tag maintainer: @bu2kx Twitter handle: @kxsystems	8 months ago
JongRok BAEK	4ec3fe4680	docs: Updated integration docs structure for chat/anthropic (#16268) ... Description: - Added output and environment variables - Updated the documentation for chat/anthropic, changing references from `langchain.schema` to `langchain_core.prompts`. Issue: https://github.com/langchain-ai/langchain/issues/15664 Dependencies: None Twitter handle: None Since this is my first open-source PR, please feel free to point out any mistakes, and I'll be eager to make corrections.	8 months ago
Shivani Modi	4e160540ff	community[minor]: Adding Konko Completion endpoint (#15570) ... This PR introduces update to Konko Integration with LangChain. 1. **New Endpoint Addition**: Integration of a new endpoint to utilize completion models hosted on Konko. 2. **Chat Model Updates for Backward Compatibility**: We have updated the chat models to ensure backward compatibility with previous OpenAI versions. 4. **Updated Documentation**: Comprehensive documentation has been updated to reflect these new changes, providing clear guidance on utilizing the new features and ensuring seamless integration. Thank you to the LangChain team for their exceptional work and for considering this PR. Please let me know if any additional information is needed. --------- Co-authored-by: Shivani Modi <shivanimodi@Shivanis-MacBook-Pro.local> Co-authored-by: Shivani Modi <shivanimodi@Shivanis-MBP.lan>	8 months ago
Facundo Santiago	92e6a641fd	feat: adding paygo api support for Azure ML / Azure AI Studio (#14560) ... - **Description:** Introducing support for LLMs and Chat models running in Azure AI studio and Azure ML using the new deployment mode pay-as-you-go (model as a service). - **Issue:** NA - **Dependencies:** None. - **Tag maintainer:** @prakharg-msft @gdyre - **Twitter handle:** @santiagofacundo Examples added: * [docs/docs/integrations/llms/azure_ml.ipynb](https://github.com/santiagxf/langchain/blob/santiagxf/azureml-endpoints-paygo-community/docs/docs/integrations/chat/azureml_endpoint.ipynb) * [docs/docs/integrations/chat/azureml_chat_endpoint.ipynb](https://github.com/santiagxf/langchain/blob/santiagxf/azureml-endpoints-paygo-community/docs/docs/integrations/chat/azureml_chat_endpoint.ipynb) --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	8 months ago
baichuan-assistant	20fcd49348	community: Fix Baichuan Chat. (#15207) ... - **Description:** Baichuan Chat (with both Baichuan-Turbo and Baichuan-Turbo-192K models) has updated their APIs. There are breaking changes. For example, BAICHUAN_SECRET_KEY is removed in the latest API but is still required in Langchain. Baichuan's Langchain integration needs to be updated to the latest version. - **Issue:** #15206 - **Dependencies:** None, - **Twitter handle:** None @hwchase17. Co-authored-by: BaiChuanHelper <wintergyc@WinterGYCs-MacBook-Pro.local>	8 months ago
gcheron	cfc225ecb3	community: SQLStrStore/SQLDocStore provide an easy SQL alternative to `InMemoryStore` to persist data remotely in a SQL storage (#15909) ... **Description:** - Implement `SQLStrStore` and `SQLDocStore` classes that inherits from `BaseStore` to allow to persist data remotely on a SQL server. - SQL is widely used and sometimes we do not want to install a caching solution like Redis. - Multiple issues/comments complain that there is no easy remote and persistent solution that are not in memory (users want to replace InMemoryStore), e.g., https://github.com/langchain-ai/langchain/issues/14267, https://github.com/langchain-ai/langchain/issues/15633, https://github.com/langchain-ai/langchain/issues/14643, https://stackoverflow.com/questions/77385587/persist-parentdocumentretriever-of-langchain - This is particularly painful when wanting to use `ParentDocumentRetriever ` - This implementation is particularly useful when: * it's expensive to construct an InMemoryDocstore/dict * you want to retrieve documents from remote sources * you just want to reuse existing objects - This implementation integrates well with PGVector, indeed, when using PGVector, you already have a SQL instance running. `SQLDocStore` is a convenient way of using this instance to store documents associated to vectors. An integration example with ParentDocumentRetriever and PGVector is provided in docs/docs/integrations/stores/sql.ipynb or [here](https://github.com/gcheron/langchain/blob/sql-store/docs/docs/integrations/stores/sql.ipynb). - It persists `str` and `Document` objects but can be easily extended. **Issue:** Provide an easy SQL alternative to `InMemoryStore`. --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	8 months ago
dudgeon	26b2ad6d5b	Fixed typo on quickstart.ipynb (#16482) ... - **Description:** Quick typo fix: `inpect` >> `inspect` - **Issue:** N/A - **Dependencies:** any dependencies required for this change, - **Twitter handle:** @geoffdudgeon	8 months ago
Eugene Yurtsev	39d1cbfecf	Docs: Document astream_events API (#16300) ... Document astream events API	8 months ago
Florian MOREL	4b7969efc5	community[minor]: New documents loader for visio files (with extension .vsdx) (#16171) ... **Description** : New documents loader for visio files (with extension .vsdx) A [visio file](https://fr.wikipedia.org/wiki/Microsoft_Visio) (with extension .vsdx) is associated with Microsoft Visio, a diagram creation software. It stores information about the structure, layout, and graphical elements of a diagram. This format facilitates the creation and sharing of visualizations in areas such as business, engineering, and computer science. A Visio file can contain multiple pages. Some of them may serve as the background for others, and this can occur across multiple layers. This loader extracts the textual content from each page and its associated pages, enabling the extraction of all visible text from each page, similar to what an OCR algorithm would do. **Dependencies** : xmltodict package	8 months ago
KhoPhi	fb41b68ea1	docs: Update with LCEL examples to Ollama & ChatOllama Integration notebook (#16194) ... - **Description:** Updated the Chat/Ollama docs notebook with LCEL chain examples - **Issue:** #15664 I'm a new contributor 😊 - **Dependencies:** No dependencies - **Twitter handle:** Comments: - How do I truncate the output of the stream in the notebook if and or when it goes on and on and on for even the basic of prompts? Edit: Looking forward to feedback @baskaryan --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	8 months ago
Michael Gorham	3b0226b2c6	docs: Update redis_chat_message_history.ipynb (#16344) ... ## Problem Spent several hours trying to figure out how to pass `RedisChatMessageHistory` as a `GetSessionHistoryCallable` with a different REDIS hostname. This example kept connecting to `redis://localhost:6379`, but I wanted to connect to a server not hosted locally. ## Cause Assumption the user knows how to implement `BaseChatMessageHistory` and `GetSessionHistoryCallable` ## Solution Update documentation to show how to explicitly set the REDIS hostname using a lambda function much like the MongoDB and SQLite examples.	8 months ago
Ian	c98994c3c9	docs: Improve notebook to show how to use tidb to store history messages (#16420) ... After merging [PR #16304](https://github.com/langchain-ai/langchain/pull/16304), I realized that our notebook example for integrating TiDB with LangChain was too basic. To make it more useful and user-friendly, I plan to create a detailed example. This will show how to use TiDB for saving history messages in LangChain, offering a clearer, more practical guide for our users	8 months ago
Eugene Yurtsev	c88750d54b	Docs: Agent streaming notebooks (#15858) ... Update information about streaming in the agents section. Show how to use astream_events to get token by token streaming.	8 months ago
Eugene Yurtsev	e5672bc944	docs: Re-write custom agent to show to write a tools agent (#15907) ... Shows how to write a tools agent rather than a functions agent.	8 months ago
Boris Feld	404abf139a	community: Add CometLLM tracing context var (#15765) ... I also added LANGCHAIN_COMET_TRACING to enable the CometLLM tracing integration similar to other tracing integrations. This is easier for end-users to enable it rather than importing the callback and pass it manually. (This is the same content as https://github.com/langchain-ai/langchain/pull/14650 but rebased and squashed as something seems to confuse Github Action).	8 months ago
Jennifer Melot	d6275e47f2	docs: Updated integration docs structure for tools/arxiv (#16091) (#16250) ... - **Description:** Updated docs for tools/arxiv to use `AgentExecutor` and `invoke` - **Issue:** #15664 - **Dependencies:** None - **Twitter handle:** None	8 months ago
ChengZi	a950fa0487	docs: add milvus multitenancy doc (#16177) ... - **Description:** add milvus multitenancy doc, it is an example for this [pr](https://github.com/langchain-ai/langchain/pull/15740) . - **Issue:** No, - **Dependencies:** No, - **Twitter handle:** No Signed-off-by: ChengZi <chen.zhang@zilliz.com>	8 months ago
parkererickson-tg	b26a22f307	community[minor]: add TigerGraph support (#16280) ... **Description:** Add support for querying TigerGraph databases through the InquiryAI service. **Issue**: N/A **Dependencies:** N/A **Twitter handle:** @TigerGraphDB	8 months ago
Christophe Bornet	8da34118bc	docs: Add documentation for Cassandra Document Loader (#16282)	8 months ago
Jonathan Algar	774e543e1f	docs: fix formatting issue in rockset.ipynb (#16328) ... **Description:** randomly discovered while working on another PR https://github.com/quarto-dev/quarto-cli/discussions/8131#discussioncomment-8027706 @anubhav94N ICYI	8 months ago
Ian	b9f5104e6c	communty[minor]: Store Message History to TiDB Database (#16304) ... This pull request integrates the TiDB database into LangChain for storing message history, marking one of several steps towards a comprehensive integration of TiDB with LangChain. A simple usage ```python from datetime import datetime from langchain_community.chat_message_histories import TiDBChatMessageHistory history = TiDBChatMessageHistory( connection_string="mysql+pymysql://<host>:<PASSWORD>@<host>:4000/<db>?ssl_ca=/etc/ssl/cert.pem&ssl_verify_cert=true&ssl_verify_identity=true", session_id="code_gen", earliest_time=datetime.utcnow(), # Optional to set earliest_time to load messages after this time point. ) history.add_user_message("hi! How's feature going?") history.add_ai_message("It's almot done") ```	8 months ago
Sarthak Chaure	dd5b8107b1	Docs: Updated callbacks/index.mdx (#16404) ... The callbacks get started demo code was updated , replacing the chain.run() command ( which is now depricated) ,with the updated chain.invoke() command. Solving the following issue : #16379 Twitter/X : @Hazxhx	8 months ago
Omar-aly	873de14cd8	docs: update vectorstores/llm_rails integration doc (#16199) ... Description: - Updated the docs for the vectorstores integration module llm_rails.ipynb Issue: - [Connected to Issue #15664](https://github.com/langchain-ai/langchain/issues/15664) Dependencies: - N/A Co-authored-by: omaraly23 <112936089+omaraly22@users.noreply.github.com>	8 months ago
Lance Martin	369e90d427	docs: Minor update to Robocorp toolkit docs (#16399)	8 months ago
Hadi	a1c0cf21c9	docs: Update import library for StreamlitCallbackHandler (#16401) ... - **Description:** Some code sources have been moved from `langchain` to `langchain_community` and so the documentation is not yet up-to-date. This is specifically true for `StreamlitCallbackHandler` which returns a `warning` message if not loaded from `langchain_community`., - **Issue:** I don't see a # issue that could address this problem but perhaps #10744, - **Dependencies:** Since it's a documentation change no dependencies are required	8 months ago
JaguarDB	7ecd2f22ac	community[patch]: update documentation on jaguar vector store (#16346) ... - **Description:** update documentation on jaguar vector store: Instruction for setting up jaguar server and usage of text_tag. - **Issue:** - **Dependencies:** - **Twitter handle:** --------- Co-authored-by: JY <jyjy@jaguardb>	8 months ago
Iskren Ivov Chernev	fc196cab12	community[minor]: DeepInfra support for chat models (#16380) ... Add deepinfra chat models support. This is https://github.com/langchain-ai/langchain/pull/14234 re-opened from my branch (so maintainers can edit).	8 months ago
Bagatur	eac91b60c9	docs: qa rag nit (#16400)	8 months ago
Bagatur	1dc6c1ce06	core[patch], community[patch], langchain[patch], docs: Update SQL chains/agents/docs (#16168) ... Revamp SQL use cases docs. In the process update SQL chains and agents.	8 months ago
Jatin Chawda	05162928c0	Docs: Fixed Urls of AsyncHtmlLoader, AsyncChromiumLoader and HTML2Text links in Web scraping Docs (#16365) ... Fixing links in documentation.	8 months ago
Christophe Bornet	f9be877ed7	Docs: Add self-querying retriever and store to AstraDB provider doc (#16362) ... Add self-querying retriever and store to AstraDB provider doc	8 months ago
Mateusz Szewczyk	076dbb1a8f	docs: IBM watsonx.ai Use `invoke` instead of `__call__` (#16371) ... - **Description:** Updating documentation of IBM [watsonx.ai](https://www.ibm.com/products/watsonx-ai) LLM with using `invoke` instead of `__call__` - **Dependencies:** [ibm-watsonx-ai](https://pypi.org/project/ibm-watsonx-ai/), - **Tag maintainer:** : Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` to check this locally. ✅ The following warning information show when i use `run` and `__call__` method: ``` LangChainDeprecationWarning: The function `__call__` was deprecated in LangChain 0.1.7 and will be removed in 0.2.0. Use invoke instead. warn_deprecated( ``` We need to update documentation for using `invoke` method	8 months ago
Bob Lin	c6bd7778b0	Use `invoke` instead of `__call__` (#16369) ... The following warning information will be displayed when i use `llm(PROMPT)`: ```python /Users/169/llama.cpp/venv/lib/python3.11/site-packages/langchain_core/_api/deprecation.py:117: LangChainDeprecationWarning: The function `__call__` was deprecated in LangChain 0.1.7 and will be removed in 0.2.0. Use invoke instead. warn_deprecated( ``` So I changed to standard usage.	8 months ago
Virat Singh	c2a614eddc	community: Add PolygonLastQuote Tool and Toolkit (#15990) ... **Description:** In this PR, I am adding a `PolygonLastQuote` Tool, which can be used to get the latest price quote for a given ticker / stock. Additionally, I've added a Polygon Toolkit, which we can use to encapsulate future tools that we build for Polygon. **Twitter handle:** [@virattt](https://twitter.com/virattt) --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	8 months ago
Bagatur	1e29b676d5	core[patch]: simple fallback streaming (#16055)	8 months ago
Hamza Kyamanywa	39b3c6d94c	langchain[patch]: Add konlpy based text splitting for Korean (#16003) ... - **Description:** Adds a text splitter based on [Konlpy](https://konlpy.org/en/latest/#start) which is a Python package for natural language processing (NLP) of the Korean language. (It is like Spacy or NLTK for Korean) - **Dependencies:** Konlpy would have to be installed before this splitter is used, - **Twitter handle:** @untilhamza	8 months ago
Hongyu Lin	9b0a531aa2	doc: Fix small typo in quickstart (#16164) ... - **Description:** fix small typo in quickstart --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	8 months ago
Lance Martin	881d1c3ec5	Update MultiON toolkit docs (#16286)	8 months ago
Bagatur	6f7a414955	docs: fix links (#16284)	8 months ago
Lance Martin	f63906a9c2	Test and update MultiON agent toolkit docs (#16235)	8 months ago
Ashley Xu	0f99646ca6	docs: add the enrollment form for`BigQueryVectorSearch` (#16240) ... This PR adds the enrollment form for BigQueryVectorSearch.	8 months ago
Eugene Yurtsev	177af65dc4	core[minor]: RFC Add astream_events to Runnables (#16172) ... This PR adds `astream_events` method to Runnables to make it easier to stream data from arbitrary chains. * Streaming only works properly in async right now * One should use `astream()` with if mixing in imperative code as might be done with tool implementations * Astream_log has been modified with minimal additive changes, so no breaking changes are expected * Underlying callback code / tracing code should be refactored at some point to handle things more consistently (OK for now) - ~~[ ] verify event for on_retry~~ does not work until we implement streaming for retry - ~~[ ] Any rrenaming? Should we rename "event" to "hook"?~~ - [ ] Any other feedback from community? - [x] throw NotImplementedError for `RunnableEach` for now ## Example See this [Example Notebook](dbbc7fa0d6/docs/docs/modules/agents/how_to/streaming_events.ipynb) for an example with streaming in the context of an Agent ## Event Hooks Reference Here is a reference table that shows some events that might be emitted by the various Runnable objects. Definitions for some of the Runnable are included after the table. | event | name | chunk | input | output | |----------------------|------------------|---------------------------------|-----------------------------------------------|-------------------------------------------------| | on_chat_model_start | [model name] | | {"messages": [[SystemMessage, HumanMessage]]} | | | on_chat_model_stream | [model name] | AIMessageChunk(content="hello") | | | | on_chat_model_end | [model name] | | {"messages": [[SystemMessage, HumanMessage]]} | {"generations": [...], "llm_output": None, ...} | | on_llm_start | [model name] | | {'input': 'hello'} | | | on_llm_stream | [model name] | 'Hello' | | | | on_llm_end | [model name] | | 'Hello human!' | | on_chain_start | format_docs | | | | | on_chain_stream | format_docs | "hello world!, goodbye world!" | | | | on_chain_end | format_docs | | [Document(...)] | "hello world!, goodbye world!" | | on_tool_start | some_tool | | {"x": 1, "y": "2"} | | | on_tool_stream | some_tool | {"x": 1, "y": "2"} | | | | on_tool_end | some_tool | | | {"x": 1, "y": "2"} | | on_retriever_start | [retriever name] | | {"query": "hello"} | | | on_retriever_chunk | [retriever name] | {documents: [...]} | | | | on_retriever_end | [retriever name] | | {"query": "hello"} | {documents: [...]} | | on_prompt_start | [template_name] | | {"question": "hello"} | | | on_prompt_end | [template_name] | | {"question": "hello"} | ChatPromptValue(messages: [SystemMessage, ...]) | Here are declarations associated with the events shown above: `format_docs`: ```python def format_docs(docs: List[Document]) -> str: '''Format the docs.''' return ", ".join([doc.page_content for doc in docs]) format_docs = RunnableLambda(format_docs) ``` `some_tool`: ```python @tool def some_tool(x: int, y: str) -> dict: '''Some_tool.''' return {"x": x, "y": y} ``` `prompt`: ```python template = ChatPromptTemplate.from_messages( [("system", "You are Cat Agent 007"), ("human", "{question}")] ).with_config({"run_name": "my_template", "tags": ["my_template"]}) ```	8 months ago
Erick Friis	aa35b43bcd	docs, google-vertex[patch]: function docs (#16231)	8 months ago
Erick Friis	f2b2d59e82	docs: transport and client options docs (#16226) ... <!-- Thank you for contributing to LangChain! Please title your PR "<package>: <description>", where <package> is whichever of langchain, community, core, experimental, etc. is being modified. Replace this entire comment with: - **Description:** a description of the change, - **Issue:** the issue # it fixes if applicable, - **Dependencies:** any dependencies required for this change, - **Twitter handle:** we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` from the root of the package you've modified to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://python.langchain.com/docs/contributing/ If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. -->	8 months ago
Rajesh Thallam	6bc6d64a12	langchain_google_vertexai[patch]: Add support for SystemMessage for Gemini chat model (#15933) ... - **Description:** In Google Vertex AI, Gemini Chat models currently doesn't have a support for SystemMessage. This PR adds support for it only if a user provides additional convert_system_message_to_human flag during model initialization (in this case, SystemMessage would be prepended to the first HumanMessage). **NOTE:** The implementation is similar to #14824 - **Twitter handle:** rajesh_thallam --------- Co-authored-by: Erick Friis <erick@langchain.dev>	8 months ago
jzaldi	ed118950fe	docs: Updated integration docs structure for llm/google_vertex_ai_palm (#16091) ... - **Description**: Updated doc for llm/google_vertex_ai_palm with new functions: `invoke`, `stream`... Changed structure of the document to match the required one. - **Issue**: #15664 - **Dependencies**: None - **Twitter handle**: None --------- Co-authored-by: Jorge Zaldívar <jzaldivar@google.com>	8 months ago
Bagatur	aa2e642ce3	docs: tool use nits (#16211)	8 months ago
Eugene Zapolsky	6b9e3ed9e9	google-vertexai[minor]: added safety_settings property to gemini wrapper (#15344) ... **Description:** Gemini model has quite annoying default safety_settings settings. In addition, current VertexAI class doesn't provide a property to override such settings. So, this PR aims to - add safety_settings property to VertexAI - fix issue with incorrect LLM output parsing when LLM responds with appropriate 'blocked' response - fix issue with incorrect parsing LLM output when Gemini API blocks prompt itself as inappropriate - add safety_settings related tests I'm not enough familiar with langchain code base and guidelines. So, any comments and/or suggestions are very welcome. **Issue:** it will likely fix #14841 --------- Co-authored-by: Erick Friis <erick@langchain.dev>	8 months ago
Bagatur	27ad65cc68	docs: add tool use diagrams (#16207)	8 months ago
Bagatur	27ed2673da	docs: model io order (#16163)	8 months ago
Bagatur	2af813c7eb	docs: bump sphinx>=5 (#16162)	8 months ago
David DeCaprio	ec9642d667	docs: Updated MongoDB Chat history example notebook to use LCEL format. (#15750) ... - **Description:** Updated the MongoDB example integration notebook to latest standards - **Issue:** [15664](https://github.com/langchain-ai/langchain/issues/15664) - **Dependencies:** None - **Twitter handle:** @davedecaprio --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	8 months ago
Bagatur	e7ddec1f2c	docs: change parallel doc name (#16152)	8 months ago
Joshua Carroll	bc0cb1148a	docs: Fix StreamlitChatMessageHistory docs to latest API (#16072) ... - **Description:** Update [this page](https://python.langchain.com/docs/integrations/memory/streamlit_chat_message_history) to use the latest API - **Issue:** https://github.com/langchain-ai/langchain/issues/13995 - **Dependencies:** None - **Twitter handle:** @OhSynap	8 months ago
David DeCaprio	9c2f1f07a0	docs: Updated SQLite example to use LCEL and SQLChatMessageHistory (#16094) ... - **Description:** Updated the SQLite example integration notebook to latest standards - **Issue:** [15664](https://github.com/langchain-ai/langchain/issues/15664) - **Dependencies:** None - **Twitter handle:** @davedecaprio	8 months ago
Abhinav	da96c511d1	docs: Replace azure_cosmos_db_vector_search with azure_cosmos_db in Cosmos DB Documentation (#16122) ... **Description**: This PR fixes an error in the documentation for Azure Cosmos DB Integration. **Issue**: The correct way to import `AzureCosmosDBVectorSearch` is ```python from langchain_community.vectorstores.azure_cosmos_db import ( AzureCosmosDBVectorSearch, ) ``` While the [documentation](https://python.langchain.com/docs/integrations/vectorstores/azure_cosmos_db) states it to be ```python from langchain_community.vectorstores.azure_cosmos_db_vector_search import ( AzureCosmosDBVectorSearch, CosmosDBSimilarityType, ) ``` As you can see in [azure_cosmos_db.py](c323742f4f/libs/langchain/langchain/vectorstores/azure_cosmos_db.py (L1C45-L2)) **Dependencies:**: None **Twitter handle**: None	8 months ago
purificant	3606c5d5e9	infra: update poetry 1.6.1 -> 1.7.1 (#15027)	8 months ago
Ikko Eltociear Ashimine	a35e5f19a8	docs: Update gradient.ipynb (#16149) ... Enviroment -> Environment	8 months ago
David	c323742f4f	mistralai[minor]: Add embeddings (#15282) ... - **Description:** Adds MistralAIEmbeddings class for embeddings, using the new official API. - **Dependencies:** mistralai - **Tag maintainer**: @efriis, @hwchase17 - **Twitter handle:** @LMS_David_RS Create `integrations/text_embedding/mistralai.ipynb`: an example notebook for MistralAIEmbeddings class Modify `embeddings/__init__.py`: Import the class Create `embeddings/mistralai.py`: The embedding class Create `integration_tests/embeddings/test_mistralai.py`: The test file. --------- Co-authored-by: Erick Friis <erick@langchain.dev>	8 months ago
Leonid Ganeline	f974eb5b8b	docs: updated `Anyscale` page (#16107) ... - added description - fixed broken links - added setting instructions - added the Chat model reference	8 months ago
Bagatur	8840a8cc95	docs: tool-use use case (#15783) ... Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	8 months ago
Christophe Bornet	6b6269441c	docs: Add page for AstraDB self retriever (#16077) ... Preview: https://langchain-git-fork-cbornet-astra-self-retriever-docs-langchain.vercel.app/docs/integrations/retrievers/self_query/astradb	8 months ago
Juan Bustos	5f057f24ac	docs: Update elasticsearch.ipynb (#16090) ... Fixed a typo, the parameter used for the Elasticsearch API key was called api_key, but the parameter is called es_api_key.	8 months ago
高远	061e63eef2	community[minor]: add vikingdb vecstore (#15155) ... --------- Co-authored-by: gaoyuan <gaoyuan.20001218@bytedance.com>	8 months ago
Zhichao HAN	5cf06db3b3	community[minor]: add JsonRequestsWrapper tool (#15374) ... **Description:** This new feature enhances the flexibility of pipeline integration, particularly when working with RESTful APIs. ``JsonRequestsWrapper`` allows for the decoding of JSON output, instead of the only option for text output. --------- Co-authored-by: Zhichao HAN <hanzhichao2000@hotmail.com>	8 months ago
Averi Kitsch	ee378a0f40	docs: add page for Firestore Chat Message History integration (#15554) ... - **Description:** Adds documentation for the `FirestoreChatMessageHistory` integration and lists integration in Google's documentation - **Issue:** NA - **Dependencies:** No --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	8 months ago
盐粒 Yanli	ddf4e7c633	community[minor]: Update pgvecto_rs to use its high level sdk (#15574) ... - **Description:** Update pgvecto_rs to use its high level sdk, - **Issue:** fix #15173	8 months ago
axiangcoding	daa9ccae52	community[patch]: deprecate ErnieBotChat and ErnieEmbeddings classes (#15862) ... - **Description:** add deprecated warning for ErnieBotChat and ErnieEmbeddings. - These two classes **lack maintenance** and do not use the sdk provided by qianfan, which means hard to implement some key feature like streaming. - The alternative `langchain_community.chat_models.QianfanChatEndpoint` and `langchain_community.embeddings.QianfanEmbeddingsEndpoint` can completely replace these two classes, only need to change configuration items. - **Issue:** None, - **Dependencies:** None, - **Twitter handle:** None --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	8 months ago
Eugene Yurtsev	7c57cfd8f0	docs: Update OpenAI functions agent (#15894) ... Add info and a tip explaining when to use this agent.	8 months ago
Eugene Yurtsev	beec7259c8	docs: Add info admonitions to a few agents (#15899) ... Add admonitions directly in the agent page to explain constraints and include a link to agent types.	8 months ago
Bigtable123	7306032dcf	docs: update baidu_qianfan_endpoint.ipynb doc (#15940) ... - **Description:** Updated the docs for the chat integration module baidu_qianfan_endpoint.ipynb - **Issue:** #15664 - **Dependencies:**N/A	8 months ago
Bhadresh Savani	6137c7608d	docs: Integration Documentation updated run to invoke for llms/ai21.ipynb (#15889) ... - **Description:** Updated Integration Documentation for [llms/ai21.ipynb](https://github.com/langchain-ai/langchain/blob/master/docs/docs/integrations/llms/ai21.ipynb) - **Issue:** #15664, - **Dependencies:** NA, - **Twitter handle:** @BhadreshSavani	8 months ago
Massimiliano Pronesti	e80aab2275	docs(community): update Amadeus toolkit to langchain v0.1 (#15976) ... - **Description:** docs update following the changes introduced in #15879 <!-- Thank you for contributing to LangChain! Please title your PR "<package>: <description>", where <package> is whichever of langchain, community, core, experimental, etc. is being modified. Replace this entire comment with: - **Description:** a description of the change, - **Issue:** the issue # it fixes if applicable, - **Dependencies:** any dependencies required for this change, - **Twitter handle:** we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` from the root of the package you've modified to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://python.langchain.com/docs/contributing/ If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. -->	8 months ago
Ashley Xu	ce7723c1e5	community[minor]: add additional support for `BigQueryVectorSearch` (#15904) ... BigQuery vector search lets you use GoogleSQL to do semantic search, using vector indexes for fast but approximate results, or using brute force for exact results. This PR: 1. Add `metadata[_job_ib]` in Document returned by any similarity search 2. Add `explore_job_stats` to enable users to explore job statistics and better the debuggability 3. Set the minimum row limit for running create vector index.	8 months ago
Antonio Mindov	fb7e66b809	docs: fix typo in inspect runnables docs (#15994) ... - **Description:** Fixing a typo related to prompts in the inspecting runnables docs	8 months ago
Karim Lalani	14244bd7e5	community[minor]: Added document loader for SurrealDB (#15995) ... Added a simple document loader to work with SurrealDB.	8 months ago
Karim Lalani	768e5e33bc	community[minor]: Fix to match SurrealDB 0.3.2 SDK (#15996) ... New version of SurrealDB python sdk was causing the integration to break. This fix addresses that change.	8 months ago
Bagatur	60d6a416e6	docs: fix self query diagram (#16043)	8 months ago
Mahad	f7706637a8	docs: fix documentation broken link in integrations chroma (#16041) ... - **Description:** Fixed broken link in the documentation for Chroma., - **Issue:** - **Dependencies:**	8 months ago
Erick Friis	7b084b4cc7	docs: more pip installs (#15771) ... - vertex chat - google - some pip openai - percent and openai - all percent - more - pip - fmt - docs: google vertex partner docs - fmt - docs: more pip installs	8 months ago
Bagatur	3f75fd41cc	docs: agent table fix (#15964)	8 months ago
Virat Singh	eb6e385dc5	community: Add PolygonAPIWrapper and get_last_quote endpoint (#15971) ... - **Description:** Added a `PolygonAPIWrapper` and an initial `get_last_quote` endpoint, which allows us to get the last price quote for a given `ticker`. Once merged, I can add a Polygon tool in `tools/` for agents to use. - **Twitter handle:** [@virattt](https://twitter.com/virattt) The Polygon.io Stocks API provides REST endpoints that let you query the latest market data from all US stock exchanges.	8 months ago
Jonathan Algar	a74f3a4979	Batch update of alt text and title attributes for images in md/mdx files across repo (#15357) ... **Description:** Batch update of alt text and title attributes for images in `md` & `mdx` files across the repo using [alttexter](https://github.com/jonathanalgar/alttexter)/[alttexter-ghclient](https://github.com/jonathanalgar/alttexter-ghclient) (built using LangChain/LangSmith). **Limitation:** cannot update `ipynb` files because of [this issue](https://github.com/langchain-ai/langchain/pull/15357#issuecomment-1885037250). Can revisit when Docusaurus is bumped to v3. I checked all the generated alt texts and titles and didn't find any technical inaccuracies. That's not to say they're _perfect_, but a lot better than what's there currently. [Deployed](https://langchain-819yf1tbk-langchain.vercel.app/docs/modules/model_io/) image example:  You can see LangSmith traces for all the calls out to the LLM in the PRs merged into this one: * https://github.com/jonathanalgar/langchain/pull/6 * https://github.com/jonathanalgar/langchain/pull/4 * https://github.com/jonathanalgar/langchain/pull/3 I didn't add the following files to the PR as the images already have OK alt texts: * 27dca2d92f/docs/docs/integrations/providers/argilla.mdx (L3) * 27dca2d92f/docs/docs/integrations/providers/apify.mdx (L11) --------- Co-authored-by: github-actions <github-actions@github.com>	8 months ago
Varik Matevosyan	efe6cfafe2	community: Added Lantern as VectorStore (#12951) ... Support [Lantern](https://github.com/lanterndata/lantern) as a new VectorStore type. - Added Lantern as VectorStore. It will support 3 distance functions `l2 squared`, `cosine` and `hamming` and will use `HNSW` index. - Added tests - Added example notebook	8 months ago
Christophe Bornet	bc60203d0f	Add documentation for AstraDBStore (#15953) ... Preview: https://langchain-git-fork-cbornet-astradb-store-doc-langchain.vercel.app/docs/integrations/stores/astradb	8 months ago
Bagatur	c697c89ca4	docs: add agent prompt creation examples (#15957)	8 months ago
Rihards Gravis	6a48ea43ec	docs: Update Robocorp Action Server installation instructions (#15943) ... **Description:** Remove section on how to install Action Server and direct the users t o the instructions on Robocorp repository. **Reason:** Robocorp Action Server has moved from a pip installation to a standalone cli application and is due for changes. Because of that, leaving only LangChain integration relevant part in the documentation.	8 months ago
Raunak	e26e1f8b37	community: Added functions to make async calls to HuggingFaceHub's embedding endpoint in HuggingFaceHubEmbeddings class (#15737) ... **Description:** Added aembed_documents() and aembed_query() async functions in HuggingFaceHubEmbeddings class in langchain_community\embeddings\huggingface_hub.py file. It will support to make async calls to HuggingFaceHub's embedding endpoint and generate embeddings asynchronously. Test Cases: Added test_huggingfacehub_embedding_async_documents() and test_huggingfacehub_embedding_async_query() functions in test_huggingface_hub.py file to test the two async functions created in HuggingFaceHubEmbeddings class. Documentation: Updated huggingfacehub.ipynb with steps to install huggingface_hub package and use HuggingFaceHubEmbeddings. **Dependencies:** None, **Twitter handle:** I do not have a Twitter account --------- Co-authored-by: H161961 <Raunak.Raunak@Honeywell.com>	8 months ago
Mu Xian Ming	560bb49c99	docs: redis_chat_message_history.ipynb integration doc (#15789) ... - **Description:** Updated the docs for the memory integration module redis_chat_message_history.ipynb - **Issue:** #15664 - **Dependencies:** N/A Co-authored-by: Mu Xianming <mu.xianming@lmwn.com>	8 months ago
Xin Liu	5efec068c9	feat: Implement `stream` interface (#15875) ... <!-- Thank you for contributing to LangChain! Please title your PR "<package>: <description>", where <package> is whichever of langchain, community, core, experimental, etc. is being modified. Replace this entire comment with: - **Description:** a description of the change, - **Issue:** the issue # it fixes if applicable, - **Dependencies:** any dependencies required for this change, - **Twitter handle:** we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` from the root of the package you've modified to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://python.langchain.com/docs/contributing/ If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. --> Major changes: - Rename `wasm_chat.py` to `llama_edge.py` - Rename the `WasmChatService` class to `ChatService` - Implement the `stream` interface for `ChatService` - Add `test_chat_wasm_service_streaming` in the integration test - Update `llama_edge.ipynb` --------- Signed-off-by: Xin Liu <sam@secondstate.io>	8 months ago
Nuno Campos	438beb6c94	Pass config specs through ensemble retriever (#15917) ... <!-- Thank you for contributing to LangChain! Please title your PR "<package>: <description>", where <package> is whichever of langchain, community, core, experimental, etc. is being modified. Replace this entire comment with: - **Description:** a description of the change, - **Issue:** the issue # it fixes if applicable, - **Dependencies:** any dependencies required for this change, - **Twitter handle:** we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` from the root of the package you've modified to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://python.langchain.com/docs/contributing/ If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. --> --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	8 months ago
Eugene Yurtsev	44101b6b0e	Docs[patch]: Update OpenAI tools agent description (#15896) ... Update OpenAI tools agent description.	8 months ago
Eugene Yurtsev	46b7a8d913	Docs[patch]: Update agent quick start for agents (#15892) ... Minor change: 1) Update tool invocation to use .invoke 2) Show hub prompt	8 months ago
Jacob Lee	c11dbefedc	docs[patch]: Fix bad headers in output parser docs (#15778) ... Currently looks like this: <img width="282" alt="Screenshot 2024-01-09 at 1 08 53 PM" src="https://github.com/langchain-ai/langchain/assets/6952323/58f3d368-6588-418e-8502-30d13757cb99"> CC @efriis @baskaryan	8 months ago
Christophe Bornet	c56060bb7d	Add document loader section to Astra provider doc page (#15882) ... See preview: https://langchain-git-fork-cbornet-provider-astra-doc-loader-langchain.vercel.app/docs/integrations/providers/astradb#ocument-loader	8 months ago
xvjixiang	611f18c944	Docs: Fix a typo in elasticsearch vectorstore notebook (#15807) ... <!-- Thank you for contributing to LangChain! Please title your PR "<package>: <description>", where <package> is whichever of langchain, community, core, experimental, etc. is being modified. Replace this entire comment with: - **Description:** a description of the change, - **Issue:** the issue # it fixes if applicable, - **Dependencies:** any dependencies required for this change, - **Twitter handle:** we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` from the root of the package you've modified to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://python.langchain.com/docs/contributing/ If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. -->	8 months ago
mogith-pn	9e1ed17bfb	Community : Modified doc strings and example notebook for Clarifai (#15816) ... Community : Modified doc strings and example notebook for Clarifai Description: 1. Modified doc strings inside clarifai vectorstore class and embeddings. 2. Modified notebook examples. --------- Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>	8 months ago
Harrison Chase	97411e998f	[docs] add beautiful soup dependency (#15860)	8 months ago
Daniel	6d299a55c0	docs: Update cohere.mdx, Text embedding had incorrect code snippet (#15840) ... text embedding code snippet was incorrect.	8 months ago
Erick Friis	38523d7c57	together[minor]: add llm (#15853)	8 months ago
William FH	2895ca87cf	Update Evals Notebook (#15851)	8 months ago
Bagatur	18411c379c	docs: fix links (#15848)	8 months ago
Harrison Chase	21a1538949	add raga reranker (#15838)	8 months ago
Harrison Chase	20abe24819	experimental[minor]: Add semantic chunker (#15799)	8 months ago
Harrison Chase	a1d7f2b3e1	add dspy notebook (#15798)	8 months ago
Bagatur	942071bf57	docs: collapse structured use case (#15791)	8 months ago
NuODaniel	70b6315b23	community[patch]: fix qianfan chat stream calling caused exception (#13800) ... - **Description:** `QianfanChatEndpoint` extends `BaseChatModel` as a super class, which has a default stream implement might concat the MessageChunk with `__add__`. When call stream(), a ValueError for duplicated key will be raise. - **Issues:** * #13546 * #13548 * merge two single test file related to qianfan. - **Dependencies:** no - **Tag maintainer:** --------- Co-authored-by: root <liujun45@baidu.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	8 months ago
Erick Friis	7be72e1103	openai[patch], docs: readme (#15773)	8 months ago
Erick Friis	7562f70c95	robocorp[minor]: Add robocorp action server toolkit (#15766) ... Co-authored-by: Rihards Gravis <rihards@gravis.lv> Co-authored-by: Mikko Korpela <mikko@robocorp.com>	8 months ago
Erick Friis	7bc100fd43	docs: integration package pip installs (#15762) ... More than 300 files - will fail check_diff. Will merge after Vercel deploy succeeds Still occurrences that need changing - will update more later	8 months ago
Bagatur	1b0db82dbe	docs: fix recognition (#15769)	8 months ago
Shoya SHIRAKI	123e01b9d8	docs: remove unnecessary description (#15752) ... | before | after | | ---- | ---- | |  |  | Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>	8 months ago
Kane Sweet	167a0ac5f5	docs: update aws_dynamodb integration doc (#15666) ... - **Description:** - Updated the docs for the memory integration module `aws_dynamodb.ipynb` - **Issue:** - #15664 - **Dependencies:** - N/A	8 months ago
Hamza Kyamanywa	fc3cb64dc3	langchain-docs: Correct the word "iteratively" in use-cases documentation (#15697) ... Replace this entire comment with: - **Description:** a description of the change, - **Issue:** the issue # it fixes if applicable, - **Dependencies:** any dependencies required for this change, - **Twitter handle:** we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! **Description:** Fixes the word "iteratively" in the use-cases documentation **Twitter handle:** @untilhamza	8 months ago
Christophe Bornet	1f5f6381ec	Add doc for AstraDB document loader (#15703) ... <!-- Thank you for contributing to LangChain! Please title your PR "<package>: <description>", where <package> is whichever of langchain, community, core, experimental, etc. is being modified. Replace this entire comment with: - **Description:** a description of the change, - **Issue:** the issue # it fixes if applicable, - **Dependencies:** any dependencies required for this change, - **Twitter handle:** we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` from the root of the package you've modified to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://python.langchain.com/docs/contributing/ If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. --> See preview : https://langchain-git-fork-cbornet-astra-loader-doc-langchain.vercel.app/docs/integrations/document_loaders/astradb	8 months ago
MING KANG	c3624b416d	docs: fix llm/chat_model tables (#15716) ... - **Description:** This PR aims to fix the documentation for langchain-commnuity. - **Issue:** The table In this page : [https://python.langchain.com/docs/integrations/llms/](https://urldefense.com/v3/__https://python.langchain.com/docs/integrations/llms/__;!!ACWV5N9M2RV99hQ!Jqw8gWnQrL1H6blPiGN10jrh1TDAzqGcKAaTAZv7TBy1X_m-03E7T-alOrWY5_71R8QUdONvF2wMRK54D50$) is built based on old module. The proposed fix is to modify the import from langchain-commnuity. - **Dependencies:** N/A - **Twitter handle:** N/A	8 months ago
Bagatur	c0eb2482c3	docs: add LangGraph (#15682)	8 months ago
Harrison Chase	3e7a590a43	dont use docarray (#15710) ... theres some issue with the integration currently so dont use it	8 months ago
abzachshan	7025fa23aa	Docs: Add missing import of 'ConfigurableField' in 'Full code comparison' example in LCEL (#15661) ... <!-- Thank you for contributing to LangChain! Please title your PR "<package>: <description>", where <package> is whichever of langchain, community, core, experimental, etc. is being modified. Replace this entire comment with: - **Description:** Add missing import of 'ConfigurableField' in 'Full code comparison' example in LCEL - **Issue:** Example code not running - **Dependencies:** None - **Twitter handle:** @heyyoshan	8 months ago
Harrison Chase	38ae4df3a1	update ragatouille integration (#15658)	8 months ago
Shaurya Rohatgi	1bfb1725a1	fix: Ollama import statements (#15493) ... <!-- Thank you for contributing to LangChain! Please title your PR "<package>: <description>", where <package> is whichever of langchain, community, core, experimental, etc. is being modified. Replace this entire comment with: - **Description:** a description of the change, - **Issue:** the issue # it fixes if applicable, - **Dependencies:** any dependencies required for this change, - **Twitter handle:** we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` from the root of the package you've modified to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://python.langchain.com/docs/contributing/ If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. -->	8 months ago
Nan LI	0b393315ce	community: Correct Input API Key Name in Notebook and Enhance Readability of Comments for ZhipuAI Chat Model (#15529) ... - **Description:** This update rectifies an error in the notebook by changing the input variable from `zhipu_api_key` to `api_key`. It also includes revisions to comments to improve program readability. - **Issue:** The input variable in the notebook example should be `api_key` instead of `zhipu_api_key`. - **Dependencies:** No additional dependencies are required for this change. To ensure quality and standards, we have performed extensive linting and testing. Commands such as make format, make lint, and make test have been run from the root of the modified package to ensure compliance with LangChain's coding standards.	8 months ago
V.Prasanna kumar	378d40f3ea	changed broken link for wandb tracing with agent (#15578) ... fix of #14905 <!-- Thank you for contributing to LangChain! Please title your PR "<package>: <description>", where <package> is whichever of langchain, community, core, experimental, etc. is being modified. Replace this entire comment with: - **Description:** a description of the change, - **Issue:** the issue # it fixes if applicable, - **Dependencies:** any dependencies required for this change, - **Twitter handle:** we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` from the root of the package you've modified to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://python.langchain.com/docs/contributing/ If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. --> --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	8 months ago
Ammar Azman	a37389ac59	Adding reading source for Curie model (#15569) ... Improving documentation <!-- Thank you for contributing to LangChain! Please title your PR "<package>: <description>", where <package> is whichever of langchain, community, core, experimental, etc. is being modified. Replace this entire comment with: - **Description:** Adding resource for Curie model - **Issue:** the issue # it fixes if applicable, - **Dependencies:** any dependencies required for this change, - **Twitter handle:** @mmarccode Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` from the root of the package you've modified to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://python.langchain.com/docs/contributing/ If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. -->	8 months ago
Bagatur	4759d10cf6	docs: add changelog (#15606) ... <!-- Thank you for contributing to LangChain! Please title your PR "<package>: <description>", where <package> is whichever of langchain, community, core, experimental, etc. is being modified. Replace this entire comment with: - **Description:** a description of the change, - **Issue:** the issue # it fixes if applicable, - **Dependencies:** any dependencies required for this change, - **Twitter handle:** we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` from the root of the package you've modified to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://python.langchain.com/docs/contributing/ If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. --> --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	8 months ago
Usama Shahid	f0128dbcde	Update openai_tools.ipynb (#15649) ... Description: Update openai_tools.ipynb Issue: The distinction between OpenAI function agents and OpenAI tools was not adequately emphasised.	8 months ago
Harrison Chase	472f70c54b	fix docs build (#15645)	8 months ago
Erick Friis	b1fa726377	docs: langchain-openai (#15513) ... Updates docs and cookbooks to import ChatOpenAI, OpenAI, and OpenAI Embeddings from `langchain_openai` There are likely more --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	8 months ago
Harrison Chase	be612f408e	move output parser table (#15637)	8 months ago
Bagatur	c5226d7a18	docs: update cohere chat integration (#15562) ... Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	8 months ago
Bagatur	75281af822	docs: Fix chain redirects (#15600)	8 months ago