2879 Commits (54dd8e52a8effadf0512e6d9a0e7731991e3dbda)

Author	SHA1	Message	Date
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