516 Commits (e080281623597fb1bf5c7c8470b1fb48edb37a52)

Author	SHA1	Message	Date
thiswillbeyourgithub	1d082359ee	community: add support for callable filters in FAISS (#16190) ... - **Description:** Filtering in a FAISS vectorstores is very inflexible and doesn't allow that many use case. I think supporting callable like this enables a lot: regular expressions, condition on multiple keys etc. **Note** I had to manually alter a test. I don't understand if it was falty to begin with or if there is something funky going on. - **Issue:** None - **Dependencies:** None - **Twitter handle:** None Signed-off-by: thiswillbeyourgithub <26625900+thiswillbeyourgithub@users.noreply.github.com>	8 months ago
Killinsun - Ryota Takeuchi	52f4ad8216	community: Add new fields in metadata for qdrant vector store (#16608) ... ## Description The PR is to return the ID and collection name from qdrant client to metadata field in `Document` class. ## Issue The motivation is almost same to [11592](https://github.com/langchain-ai/langchain/issues/11592) Returning ID is useful to update existing records in a vector store, but we cannot know them if we use some retrievers. In order to avoid any conflicts, breaking changes, the new fields in metadata have a prefix `_` ## Dependencies N/A ## Twitter handle @kill_in_sun <!-- 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
hulitaitai	32cad38ec6	<langchain_community\llms\chatglm.py>: <Correcting "history"> (#16729) ... Use the real "history" provided by the original program instead of putting "None" in the history. - **Description:** I change one line in the code to make it return the "history" of the chat model. - **Issue:** At the moment it returns only the answers of the chat model. However the chat model himself provides a history more complet with the questions of the user. - **Dependencies:** no dependencies required for this change,	8 months ago
Bassem Yacoube	85e93e05ed	community[minor]: Update OctoAI LLM, Embedding and documentation (#16710) ... This PR includes updates for OctoAI integrations: - The LLM class was updated to fix a bug that occurs with multiple sequential calls - The Embedding class was updated to support the new GTE-Large endpoint released on OctoAI lately - The documentation jupyter notebook was updated to reflect using the new LLM sdk Thank you!	8 months ago
Volodymyr Machula	32c5be8b73	community[minor]: Connery Tool and Toolkit (#14506) ... ## Summary This PR implements the "Connery Action Tool" and "Connery Toolkit". Using them, you can integrate Connery actions into your LangChain agents and chains. Connery is an open-source plugin infrastructure for AI. With Connery, you can easily create a custom plugin with a set of actions and seamlessly integrate them into your LangChain agents and chains. Connery will handle the rest: runtime, authorization, secret management, access management, audit logs, and other vital features. Additionally, Connery and our community offer a wide range of ready-to-use open-source plugins for your convenience. Learn more about Connery: - GitHub: https://github.com/connery-io/connery-platform - Documentation: https://docs.connery.io - Twitter: https://twitter.com/connery_io ## TODOs - [x] API wrapper - [x] Integration tests - [x] Connery Action Tool - [x] Docs - [x] Example - [x] Integration tests - [x] Connery Toolkit - [x] Docs - [x] Example - [x] Formatting (`make format`) - [x] Linting (`make lint`) - [x] Testing (`make test`)	8 months ago
Harrison Chase	8457c31c04	community[patch]: activeloop ai tql deprecation (#14634) ... Co-authored-by: AdkSarsen <adilkhan@activeloop.ai>	8 months ago
Neli Hateva	c95facc293	langchain[minor], community[minor]: Implement Ontotext GraphDB QA Chain (#16019) ... - **Description:** Implement Ontotext GraphDB QA Chain - **Issue:** N/A - **Dependencies:** N/A - **Twitter handle:** @OntotextGraphDB	8 months ago
Elliot	39eb00d304	community[patch]: Adapt more parameters related to MemorySearchPayload for the search method of ZepChatMessageHistory (#15441) ... - **Description:** To adapt more parameters related to MemorySearchPayload for the search method of ZepChatMessageHistory, - **Issue:** None, - **Dependencies:** None, - **Twitter handle:** None	8 months ago
Jael Gu	a1aa3a657c	community[patch]: Milvus supports add & delete texts by ids (#16256) ... # Description To support [langchain indexing](https://python.langchain.com/docs/modules/data_connection/indexing) as requested by users, vectorstore Milvus needs to support: - document addition by id (`add_documents` method with `ids` argument) - delete by id (`delete` method with `ids` argument) Example usage: ```python from langchain.indexes import SQLRecordManager, index from langchain.schema import Document from langchain_community.vectorstores import Milvus from langchain_openai import OpenAIEmbeddings collection_name = "test_index" embedding = OpenAIEmbeddings() vectorstore = Milvus(embedding_function=embedding, collection_name=collection_name) namespace = f"milvus/{collection_name}" record_manager = SQLRecordManager( namespace, db_url="sqlite:///record_manager_cache.sql" ) record_manager.create_schema() doc1 = Document(page_content="kitty", metadata={"source": "kitty.txt"}) doc2 = Document(page_content="doggy", metadata={"source": "doggy.txt"}) index( [doc1, doc1, doc2], record_manager, vectorstore, cleanup="incremental", # None, "incremental", or "full" source_id_key="source", ) ``` # Fix issues Fix https://github.com/milvus-io/milvus/issues/30112 --------- Signed-off-by: Jael Gu <mengjia.gu@zilliz.com> Co-authored-by: Bagatur <baskaryan@gmail.com>	8 months ago
Michard Hugo	e9d3527b79	community[patch]: Add missing async similarity_distance_threshold handling in RedisVectorStoreRetriever (#16359) ... Add missing async similarity_distance_threshold handling in RedisVectorStoreRetriever - **Description:** added method `_aget_relevant_documents` to `RedisVectorStoreRetriever` that overrides parent method to add support of `similarity_distance_threshold` in async mode (as for sync mode) - **Issue:** #16099 - **Dependencies:** N/A - **Twitter handle:** N/A	8 months ago
Anthony Bernabeu	2db79ab111	community[patch]: Implement TTL for DynamoDBChatMessageHistory (#15478) ... - **Description:** Implement TTL for DynamoDBChatMessageHistory, - **Issue:** see #15477, - **Dependencies:** N/A, --------- Co-authored-by: Piyush Jain <piyushjain@duck.com>	8 months ago
taimo	d3d9244fee	langchain-community: fix unicode escaping issue with SlackToolkit (#16616) ... - **Description:** fix unicode escaping issue with SlackToolkit - **Issue:** #16610	8 months ago
Benito Geordie	f3fdc5c5da	community: Added integrations for ThirdAI's NeuralDB with Retriever and VectorStore frameworks (#15280) ... **Description:** Adds ThirdAI NeuralDB retriever and vectorstore integration. NeuralDB is a CPU-friendly and fine-tunable text retrieval engine.	8 months ago
Pashva Mehta	22d90800c8	community: Fixed schema discrepancy in from_texts function for weaviate vectorstore (#16693) ... * Description: Fixed schema discrepancy in **from_texts** function for weaviate vectorstore which created a redundant property "key" inside a class. * Issue: Fixed: https://github.com/langchain-ai/langchain/issues/16692 * Twitter handle: @pashvamehta1	8 months ago
Daniel Erenrich	0600998f38	community: Wikidata tool support (#16691) ... - **Description:** Adds Wikidata support to langchain. Can read out documents from Wikidata. - **Issue:** N/A - **Dependencies:** Adds implicit dependencies for `wikibase-rest-api-client` (for turning items into docs) and `mediawikiapi` (for hitting the search endpoint) - **Twitter handle:** @derenrich You can see an example of this tool used in a chain [here](https://nbviewer.org/urls/d.erenrich.net/upload/Wikidata_Langchain.ipynb) or [here](https://nbviewer.org/urls/d.erenrich.net/upload/Wikidata_Lars_Kai_Hansen.ipynb) <!-- Thank you for contributing to LangChain! 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
Christophe Bornet	2e3af04080	Use Postponed Evaluation of Annotations in Astra and Cassandra doc loaders (#16694) ... Minor/cosmetic change	8 months ago
Christophe Bornet	36e432672a	community[minor]: Add async methods to AstraDBLoader (#16652)	8 months ago
Rashedul Hasan Rijul	481493dbce	community[patch]: apply embedding functions during query if defined (#16646) ... **Description:** This update ensures that the user-defined embedding function specified during vector store creation is applied during queries. Previously, even if a custom embedding function was defined at the time of store creation, Bagel DB would default to using the standard embedding function during query execution. This pull request addresses this issue by consistently using the user-defined embedding function for queries if one has been specified earlier.	8 months ago
Serena Ruan	f01fb47597	community[patch]: MLflowCallbackHandler -- Move textstat and spacy as optional dependency (#16657) ... Signed-off-by: Serena Ruan <serena.rxy@gmail.com>	8 months ago
Zhuoyun(John) Xu	508bde7f40	community[patch]: Ollama - Pass headers to post request in async method (#16660) ... # Description A previous PR (https://github.com/langchain-ai/langchain/pull/15881) added option to pass headers to ollama endpoint, but headers are not pass to the async method.	8 months ago
João Carlos Ferra de Almeida	3e87b67a3c	community[patch]: Add Cookie Support to Fetch Method (#16673) ... - **Description:** This change allows the `_fetch` method in the `WebBaseLoader` class to utilize cookies from an existing `requests.Session`. It ensures that when the `fetch` method is used, any cookies in the provided session are included in the request. This enhancement maintains compatibility with existing functionality while extending the utility of the `fetch` method for scenarios where cookie persistence is necessary. - **Issue:** Not applicable (new feature), - **Dependencies:** Requires `aiohttp` and `requests` libraries (no new dependencies introduced), - **Twitter handle:** N/A Co-authored-by: Joao Almeida <joao.almeida@mercedes-benz.io>	8 months ago
Harrison Chase	27665e3546	[community] fix anthropic streaming (#16682)	8 months ago
Christophe Bornet	4915c3cd86	[Fix] Fix Cassandra Document loader default page content mapper (#16273) ... We can't use `json.dumps` by default as many types returned by the cassandra driver are not serializable. It's safer to use `str` and let users define their own custom `page_content_mapper` if needed.	8 months ago
Pasha	4e189cd89a	community[patch]: youtube loader transcript format (#16625) ... - **Description**: YoutubeLoader right now returns one document that contains the entire transcript. I think it would be useful to add an option to return multiple documents, where each document would contain one line of transcript with the start time and duration in the metadata. For example, [AssemblyAIAudioTranscriptLoader](https://github.com/langchain-ai/langchain/blob/master/libs/community/langchain_community/document_loaders/assemblyai.py) is implemented in a similar way, it allows you to choose between the format to use for the document loader.	8 months ago
yin1991	a936472512	docs: Update documentation to use 'model_id' rather than 'model_name' to match actual API (#16615) ... - **Description:** Replace 'model_name' with 'model_id' for accuracy - **Issue:** [link-to-issue](https://github.com/langchain-ai/langchain/issues/16577) - **Dependencies:** - **Twitter handle:**	8 months ago
Micah Parker	6543e585a5	community[patch]: Added support for Ollama's num_predict option in ChatOllama (#16633) ... Just a simple default addition to the options payload for a ollama generate call to support a max_new_tokens parameter. Should fix issue: https://github.com/langchain-ai/langchain/issues/14715	8 months ago
baichuan-assistant	70ff54eace	community[minor]: Add Baichuan Text Embedding Model and Baichuan Inc introduction (#16568) ... - **Description:** Adding Baichuan Text Embedding Model and Baichuan Inc introduction. Baichuan Text Embedding ranks #1 in C-MTEB leaderboard: https://huggingface.co/spaces/mteb/leaderboard Co-authored-by: BaiChuanHelper <wintergyc@WinterGYCs-MacBook-Pro.local>	8 months ago
Ghani	e30c6662df	Langchain-community : EdenAI chat integration. (#16377) ... - **Description:** This PR adds [EdenAI](https://edenai.co/) for the chat model (already available in LLM & Embeddings). It supports all [ChatModel] functionality: generate, async generate, stream, astream and batch. A detailed notebook was added. - **Dependencies**: No dependencies are added as we call a rest API. --------- Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>	8 months ago
Jatin Chawda	a79345f199	community[patch]: Fixed tool names snake_case (#16397) ... #16396 Fixed 1. golden_query 2. google_lens 3. memorize 4. merriam_webster 5. open_weather_map 6. pub_med 7. stack_exchange 8. generate_image 9. wikipedia	8 months ago
Bagatur	61e876aad8	openai[patch]: Explicitly support embedding dimensions (#16596)	8 months ago
Bagatur	5df8ab574e	infra: move indexing documentation test (#16595)	8 months ago
Bagatur	61b200947f	community[patch]: Release 0.0.16 (#16591)	8 months ago
Bagatur	ef42d9d559	core[patch], community[patch], openai[patch]: consolidate openai tool… (#16485) ... … converters One way to convert anything to an OAI function: convert_to_openai_function One way to convert anything to an OAI tool: convert_to_openai_tool Corresponding bind functions on OAI models: bind_functions, bind_tools	8 months ago
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
Dmitry Tyumentsev	e86e66bad7	community[patch]: YandexGPT models - add sleep_interval (#16566) ... Added sleep between requests to prevent errors associated with simultaneous requests.	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
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
Unai Garay Maestre	fdbfa6b2c8	Adds progress bar to VertexAIEmbeddings (#14542) ... - **Description:** Adds progress bar to VertexAIEmbeddings - **Issue:** related issue https://github.com/langchain-ai/langchain/issues/13637 Signed-off-by: ugm2 <unaigaraymaestre@gmail.com> --------- Signed-off-by: ugm2 <unaigaraymaestre@gmail.com>	8 months ago
Jeremi Joslin	9e95699277	community[patch]: Fix error message when litellm is not installed (#16316) ... The error message was mentioning the wrong package. I updated it to the correct one.	8 months ago
bachr	b3ed98dec0	community[patch]: avoid KeyError when language not in LANGUAGE_SEGMENTERS (#15212) ... **Description:** Handle unsupported languages in same way as when none is provided **Issue:** The following line will throw a KeyError if the language is not supported. ```python self.Segmenter = LANGUAGE_SEGMENTERS[language] ``` E.g. when using `Language.CPP` we would get `KeyError: <Language.CPP: 'cpp'>` --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	8 months ago
chyroc	61da2ff24c	community[patch]: use SecretStr for yandex model secrets (#15463)	8 months ago
Alessio Serra	d628a80a5d	community[patch]: added 'conversational' as a valid task for hugginface endopoint models (#15761) ... - **Description:** added the conversational task to hugginFace endpoint in order to use models designed for chatbot programming. - **Dependencies:** None --------- Co-authored-by: Alessio Serra (ext.) <alessio.serra@partner.bmw.de> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com> Co-authored-by: Bagatur <baskaryan@gmail.com>	8 months ago
Karim Lalani	4c7755778d	community[patch]: SurrealDB fix for asyncio (#16092) ... Code fix for asyncio	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
Serena Ruan	5c6e123757	community[patch]: Fix MlflowCallback with none artifacts_dir (#16487)	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
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
Noah Stapp	e135e5257c	community[patch]: Include scores in MongoDB Atlas QA chain results (#14666) ... Adds the ability to return similarity scores when using `RetrievalQA.from_chain_type` with `MongoDBAtlasVectorSearch`. Requires that `return_source_documents=True` is set. Example use: ``` vector_search = MongoDBAtlasVectorSearch.from_documents(...) qa = RetrievalQA.from_chain_type( llm=OpenAI(), chain_type="stuff", retriever=vector_search.as_retriever(search_kwargs={"additional": ["similarity_score"]}), return_source_documents=True ) ... docs = qa({"query": "..."}) docs["source_documents"][0].metadata["score"] # score will be here ``` I've tested this feature locally, using a MongoDB Atlas Cluster with a vector search index.	8 months ago
Serena Ruan	90f5a1c40e	community[minor]: Improve mlflow callback (#15691) ... - **Description:** Allow passing run_id to MLflowCallbackHandler to resume a run instead of creating a new run. Support recording retriever relevant metrics. Refactor the code to fix some bugs. --------- Signed-off-by: Serena Ruan <serena.rxy@gmail.com>	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
Davide Menini	9ce177580a	community: normalize bedrock embeddings (#15103) ... In this PR I added a post-processing function to normalize the embeddings. This happens only if the new `normalize` flag is `True`. --------- Co-authored-by: taamedag <Davide.Menini@swisscom.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
Massimiliano Pronesti	e529939c54	feat(llms): support more tasks in HuggingFaceHub LLM and remove deprecated dep (#14406) ... - **Description:** this PR upgrades the `HuggingFaceHub` LLM: * support more tasks (`translation` and `conversational`) * replaced the deprecated `InferenceApi` with `InferenceClient` * adjusted the overall logic to use the "recommended" model for each task when no model is provided, and vice-versa. - **Tag mainter(s)**: @baskaryan @hwchase17	8 months ago
Bagatur	54149292f8	community[patch]: Release 0.0.15 (#16474)	8 months ago
Tomaz Bratanic	d0a8082188	Fix neo4j sanitize (#16439) ... Fix the sanitization bug and add an integration test	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
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
DL	b9e7f6f38a	community[minor]: Bedrock async methods (#12477) ... Description: Added support for asynchronous streaming in the Bedrock class and corresponding tests. Primarily: async def aprepare_output_stream async def _aprepare_input_and_invoke_stream async def _astream async def _acall I've ensured that the code adheres to the project's linting and formatting standards by running make format, make lint, and make test. Issue: #12054, #11589 Dependencies: None Tag maintainer: @baskaryan Twitter handle: @dominic_lovric --------- Co-authored-by: Piyush Jain <piyushjain@duck.com>	8 months ago
Frank995	5694728816	community[patch]: Implement vector length definition at init time in PGVector for indexing (#16133) ... Replace this entire comment with: - **Description:** allow user to define tVector length in PGVector when creating the embedding store, this allows for later indexing - **Issue:** #16132 - **Dependencies:** None	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
Alireza Kashani	d1b4ead87c	community[patch]: Update grobid.py (#16298) ... there is a case where "coords" does not exist in the "sentence" therefore, the "split(";")" will lead to error. we can fix that by adding "if sentence.get("coords") is not None:" the resulting empty "sbboxes" from this scenario will raise error at "sbboxes[0]["page"]" because sbboxes are empty. the PDF from https://pubmed.ncbi.nlm.nih.gov/23970373/ can replicate those errors.	8 months ago
s-g-1	fbe592a5ce	community[patch]: fix typo in pgvecto_rs debug msg (#16318) ... fixes typo in pip install message for the pgvecto_rs community vector store no issues found mentioning this no dependents changed	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
Erick Friis	cfe95ab085	multiple: update langsmith dep (#16407)	8 months ago
Eli Lucherini	6b2a57161a	community[patch]: allow additional kwargs in MlflowEmbeddings for compatibility with Cohere API (#15242) ... - **Description:** add support for kwargs in`MlflowEmbeddings` `embed_document()` and `embed_query()` so that all the arguments required by Cohere API (and others?) can be passed down to the server. - **Issue:** #15234 - **Dependencies:** MLflow with MLflow Deployments (`pip install mlflow[genai]`) **Tests** Now this code [adapted from the docs](https://python.langchain.com/docs/integrations/providers/mlflow#embeddings-example) for the Cohere API works locally. ```python """ Setup ----- export COHERE_API_KEY=... mlflow deployments start-server --config-path examples/deployments/cohere/config.yaml Run --- python /path/to/this/file.py """ embeddings = MlflowCohereEmbeddings(target_uri="http://127.0.0.1:5000", endpoint="embeddings") print(embeddings.embed_query("hello")[:3]) print(embeddings.embed_documents(["hello", "world"])[0][:3]) ``` Output ``` [0.060455322, 0.028793335, -0.025848389] [0.031707764, 0.021057129, -0.009361267] ```	8 months ago
Guillem Orellana Trullols	aad2aa7188	community[patch]: BedrockChat -> Support Titan express as chat model (#15408) ... Titan Express model was not supported as a chat model because LangChain messages were not "translated" to a text prompt. Co-authored-by: Guillem Orellana Trullols <guillem.orellana_trullols@siemens.com>	8 months ago
Katarina Supe	01c2f27ffa	community[patch]: Update Memgraph support (#16360) ... - **Description:** I removed two queries to the database and left just one whose results were formatted afterward into other type of schema (avoided two calls to DB) - **Issue:** / - **Dependencies:** / - **Twitter handle:** @supe_katarina	8 months ago
Max Jakob	8569b8f680	community[patch]: ElasticsearchStore enable max inner product (#16393) ... Enable max inner product for approximate retrieval strategy. For exact strategy we lack the necessary `maxInnerProduct` function in the Painless scripting language, this is why we do not add it there. Similarity docs: https://www.elastic.co/guide/en/elasticsearch/reference/current/dense-vector.html#dense-vector-params --------- Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com> Co-authored-by: Joe McElroy <joseph.mcelroy@elastic.co>	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	85e8423312	community[patch]: Update bing results tool name (#16395) ... Make BingSearchResults tool name OpenAI functions compatible (can't have spaces). Fixes #16368	8 months ago
Max Jakob	de209af533	community[patch]: ElasticsearchStore: add relevance function selector (#16378) ... Implement similarity function selector for ElasticsearchStore. The scores coming back from Elasticsearch are already similarities (not distances) and they are already normalized (see [docs](https://www.elastic.co/guide/en/elasticsearch/reference/current/dense-vector.html#dense-vector-params)). Hence we leave the scores untouched and just forward them. This fixes #11539. However, in hybrid mode (when keyword search and vector search are involved) Elasticsearch currently returns no scores. This PR adds an error message around this fact. We need to think a bit more to come up with a solution for this case. This PR also corrects a small error in the Elasticsearch integration test. --------- Co-authored-by: Erick Friis <erick@langchain.dev>	8 months ago
Tom Jorquera	1445ac95e8	community[patch]: Enable streaming for GPT4all (#16392) ... `streaming` param was never passed to model	8 months ago
Bagatur	8779013847	community[patch]: Release 0.0.14 (#16384)	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
Luke	5396604ef4	community: Handling missing key in Google Trends API response. (#15864) ... - **Description:** Handing response where _interest_over_time_ is missing. - **Issue:** #15859 - **Dependencies:** None	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
Ofer Mendelevitch	ffae98d371	template: Update Vectara templates (#15363) ... fixed multi-query template for Vectara added self-query template for Vectara Also added prompt_name parameter to summarization CC @efriis **Twitter handle:** @ofermend	8 months ago
Carey	021b0484a8	community[patch]: add skipped test for inner product normalization (#14989) ... --------- Co-authored-by: Erick Friis <erick@langchain.dev>	8 months ago
Christophe Bornet	3ccbe11363	community[minor]: Add Cassandra document loader (#16215) ... - **Description:** document loader for Apache Cassandra - **Twitter handle:** cbornet_	8 months ago
mikeFore4	9d32af72ce	community[patch]: huggingface hub character removal bug fix (#16233) ... - **Description:** Some text-generation models on huggingface repeat the prompt in their generated response, but not all do! The tests use "gpt2" which DOES repeat the prompt and as such, the HuggingFaceHub class is hardcoded to remove the first few characters of the response (to match the len(prompt)). However, if you are using a model (such as the very popular "meta-llama/Llama-2-7b-chat-hf") that DOES NOT repeat the prompt in it's generated text, then the beginning of the generated text will be cut off. This code change fixes that bug by first checking whether the prompt is repeated in the generated response and removing it conditionally. - **Issue:** #16232 - **Dependencies:** N/A - **Twitter handle:** N/A	8 months ago
Andreas Motl	3613d8a2ad	community[patch]: Use SQLAlchemy's `bulk_save_objects` method to improve insert performance (#16244) ... - **Description:** Improve [pgvector vector store adapter](https://github.com/langchain-ai/langchain/blob/v0.1.1/libs/community/langchain_community/vectorstores/pgvector.py) to save embeddings in batches, to improve its performance. - **Issue:** NA - **Dependencies:** NA - **References:** https://github.com/crate-workbench/langchain/pull/1 Hi again from the CrateDB team, following up on GH-16243, this is another minor patch to the pgvector vector store adapter. Inserting embeddings in batches, using [SQLAlchemy's `bulk_save_objects`](https://docs.sqlalchemy.org/en/20/orm/session_api.html#sqlalchemy.orm.Session.bulk_save_objects) method, can deliver substantial performance gains. With kind regards, Andreas. NB: As I am seeing just now that this method is a legacy feature of SA 2.0, it will need to be reworked on a future iteration. However, it is not deprecated yet, and I haven't been able to come up with a different implementation, yet.	8 months ago
Christophe Bornet	3502a407d9	infra: Use dotenv in langchain-community's integration tests (#16137) ... * Removed some env vars not used in langchain package IT * Added Astra DB env vars in langchain package, used for cache tests * Added conftest.py to load env vars in langchain_community IT * Added .env.example in langchain_community IT	8 months ago
Tomaz Bratanic	1e80113ac9	community[patch]: Add neo4j timeout and value sanitization option (#16138) ... The timeout function comes in handy when you want to kill longrunning queries. The value sanitization removes all lists that are larger than 128 elements. The idea here is to remove embedding properties from results.	8 months ago
Krishna Shedbalkar	f238217cea	community[patch]: Basic Logging and Human input to ShellTool (#15932) ... - **Description:** As Shell tool is very versatile, while integrating it into applications as openai functions, developers have no clue about what command is being executed using the ShellTool. All one can see is:  Summarising my feature request: 1. There's no visibility about what command was executed. 2. There's no mechanism to prevent a command to be executed using ShellTool, like a y/n human input which can be accepted from user to proceed with executing the command., - **Issue:** the issue #15931 it fixes if applicable, - **Dependencies:** There isn't any dependancy, - **Twitter handle:** @krishnashed	8 months ago
Christophe Bornet	fb940d11df	community[patch]: Use newer MetadataVectorCassandraTable in Cassandra vector store (#15987) ... as VectorTable is deprecated Tested manually with `test_cassandra.py` vector store integration test.	8 months ago
Mohammad Mohtashim	1fa056c324	community[patch]: Don't set search path for unknown SQL dialects (#16047) ... - **Description:** Made a small fix for the `SQLDatabase` highlighted in an issue. The issue pertains to switching schema for different SQL engines. - **Issue:** #16023 @baskaryan	8 months ago
Leonid Ganeline	c5f6b828ad	langchain[patch], community[minor]: move `output_parsers.ernie_functions` (#16057) ... `output_parsers.ernie_functions` moved into `community`	8 months ago
Fei Wang	d0e101e4e0	community[patch]: fix ollama astream (#16070) ... Update ollama.py	8 months ago
BeatrixCohere	b0c3e3db2b	community[patch]: Handle when documents are not provided in the Cohere response (#16144) ... - **Description:** This handles the cohere response when documents aren't included in the response - **Issue:** N/A - **Dependencies:** N/A - **Twitter handle:** N/A	8 months ago
Felix Krones	d91126fc64	community[patch]: missing unpack operator for or_clause in pgvector document filter (#16148) ... - Fix for #16146 - Adding unpack operation to "or" and "and" filter for pgvector retriever. #	8 months ago
William FH	e5cf1e2414	Community[patch]use secret str in Tavily and HuggingFaceInferenceEmbeddings (#16109) ... So the api keys don't show up in repr's Still need to do tests	8 months ago
William FH	f3601b0aaf	Community[Patch] Remove docs form bm25 repr (#16110) ... Resolves: https://github.com/langchain-ai/langsmith-sdk/issues/356	8 months ago
Erick Friis	52114bdfac	community[patch]: release 0.0.13 (#16087)	8 months ago
James Briggs	ca288d8f2c	community[patch]: add vector param to index query for pinecone vec store (#16054)	8 months ago
Antonio Morales	476fb328ee	community[patch]: implement adelete from VectorStore in Qdrant (#16005) ... **Description:** Implement `adelete` function from `VectorStore` in `Qdrant` to support other asynchronous flows such as async indexing (`aindex`) which requires `adelete` to be implemented. Since `Qdrant` can be passed an async qdrant client, this can be supported easily. --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	8 months ago
高远	061e63eef2	community[minor]: add vikingdb vecstore (#15155) ... --------- Co-authored-by: gaoyuan <gaoyuan.20001218@bytedance.com>	8 months ago
andrijdavid	d196646811	community[patch]: Refactor OpenAIWhisperParserLocal (#15150) ... This PR addresses an issue in OpenAIWhisperParserLocal where requesting CUDA without availability leads to an AttributeError #15143 Changes: - Refactored Logic for CUDA Availability: The initialization now includes a check for CUDA availability. If CUDA is not available, the code falls back to using the CPU. This ensures seamless operation without manual intervention. - Parameterizing Batch Size and Chunk Size: The batch_size and chunk_size are now configurable parameters, offering greater flexibility and optimization options based on the specific requirements of the use case. --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.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
chyroc	d334efc848	community[patch]: fix top_p type hint (#15452) ... fix: https://github.com/langchain-ai/langchain/issues/15341 @efriis	8 months ago
Mateusz Szewczyk	251afda549	community[patch]: fix stop (stop_sequences) param on WatsonxLLM (#15541) ... - **Description:** Fix to IBM [watsonx.ai](https://www.ibm.com/products/watsonx-ai) LLM provider (stop (`stop_sequences`) param on watsonxLLM) - **Dependencies:** [ibm-watsonx-ai](https://pypi.org/project/ibm-watsonx-ai/),	8 months ago
Funkeke	7220124368	community[patch]: fix tongyi completion and params error (#15544) ... fix tongyi completion json parse error and prompt's params error --------- Co-authored-by: fangkeke <3339698829@qq.com> 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
YHW	ce21392a21	community: add a flag that determines whether to load the milvus collection (#15693) ... fix https://github.com/langchain-ai/langchain/issues/15694 --------- Co-authored-by: hyungwookyang <hyungwookyang@worksmobile.com> Co-authored-by: Bagatur <baskaryan@gmail.com>	8 months ago
Mohammad Mohtashim	9e779ca846	community[patch]: Fixing the SlackGetChannel Tool Input Error (#15725) ... Fixed the issue mentioned in #15698 for SlackGetChannel Tool. @baskaryan. --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com> Co-authored-by: Bagatur <baskaryan@gmail.com>	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
JaguarDB	b11fd3bedc	community[patch]: jaguar vector store fix integer-element error when joining metadata values (#15939) ... - **Description:** some document loaders add integer-type metadata values which cause error - **Issue:** 15937 - **Dependencies:** none --------- Co-authored-by: JY <jyjy@jaguardb>	8 months ago
Neo Zhao	21e0df937f	community[patch]: fix a bug that mistakenly handle zip iterator in FAISS.from_embeddings (#16020) ... **Description**: `zip` is iterator that will only produce result once, so the previous code will cause the `embeddings` to be an empty list. **Issue**: I could not find a related issue. **Dependencies**: this PR does not introduce or affect dependencies. --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	8 months ago
Leonid Ganeline	fb676d8a9b	community[minor], langchain[minor]: refactor `output_parsers` Rail (#15852) ... Moved Rail parser to `community` package.	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
Mohammed Naqi	8799b028a6	community[minor]: Adding asynchronous function implementation for Doctran (#15941) ... ## Description In this update, I addressed the missing implementation for atransform_document, which is the asynchronous counterpart of transform_document in Doctran. ### Usage Example: ```py # Instantiate DoctranPropertyExtractor with specified properties property_extractor = DoctranPropertyExtractor(properties=properties) # Asynchronously extract properties from a list of documents extracted_document = await property_extractor.atransform_documents( documents, properties=properties ) # Display metadata of the first extracted document print(json.dumps(extracted_document[0].metadata, indent=2)) ``` ## Issue - Pull request #14525 has caused a break in the aforementioned code. Instead of removing an asynchronous implementation of a function, consider implementing a synchronous version alongside it.	8 months ago
Raunak	c0773ab329	community[patch]: Fixed 'coroutine' object is not subscriptable error (#15986) ... - **Description:** Added parenthesis in return statement of aembed_query() funtion to fix 'coroutine' object is not subscriptable error. - **Dependencies:** NA Co-authored-by: H161961 <Raunak.Raunak@Honeywell.com>	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
shahrin014	86321a949f	community: Ollama - Parameter structure to follow official documentation (#16035) ... ## Feature - Follow parameter structure as per official documentation - top level parameters (e.g. model, system, template) will be passed as top level parameters - other parameters will be sent in options unless options is provided  ## Tests - Test if top level parameters handled properly - Test if parameters that are not top level parameters are handled as options - Test if options is provided, it will be passed as is	8 months ago
Nir Kopler	0fa06732b7	community: add new gpt-3.5-turbo-1106 finetuned for cost calculation (#16039) ... **Description:** Added the new gpt-3.5-turbo-1106 for **finetuned** cost calculation, **Issue:** no issue found open By the information in OpenAI the pricing is the same as the older model (0613)	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
Erick Friis	74bac7bda1	community[patch]: core min 0.1.9 (#15974)	8 months ago
Erick Friis	845e407e08	community[patch]: release 0.0.12 (#15973)	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
Edwin Wenink	9fb09c1c30	community: fix the "page" mode in the AzureAIDocumentIntelligenceParser (bug) (#15958) ... **Description**: the "page" mode in the AzureAIDocumentIntelligenceParser is not accessible due to a wrong membership test. The mode argument can only be a string (also see the assertion in the `__init__`: `assert self.mode in ["single", "page", "object", "markdown"]`, so the check `elif self.mode == ["page"]:` always fails. As a result, effectively the "object" mode is used when selecting the "page" mode, which may lead to errors. The docstring of the `AzureAIDocumentIntelligenceLoader` also ommitted the `mode` parameter alltogether, so I added it. **Issue**: I could not find a related issue (this class is only 3 weeks old anyways) **Dependencies**: this PR does not introduce or affect dependencies. The current demo notebook and examples are not affected because they all use the default markdown mode.	8 months ago
Mahdi Setayesh	eb76f9c9fe	community: Fixing a performance issue with AzureSearch to perform batch embedding (#15594) ... - **Description:** Azure Cognitive Search vector DB store performs slow embedding as it does not utilize the batch embedding functionality. This PR provide a fix to improve the performance of Azure Search class when adding documents to the vector search, - **Issue:** #11313 , - **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
ChengZi	d5808f786c	community: Support milvus partition key. (#15740) ... - **Description:** Milvus's partition key is an important feature. It can support multi-tenancy. We hope to introduce this feature. https://milvus.io/docs/partition_key.md - **Issue:** No - **Dependencies:** No - **Twitter handle:** No --------- Signed-off-by: ChengZi <chen.zhang@zilliz.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	8 months ago
ohbeep	9b3962fc25	community: Add support of "http" URI for Milvus (#12710) (#15683) ... - **Description:** Add support of HTTP URI for Milvus - **Issue:** #12710 - **Dependencies:** N/A,	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
Christophe Bornet	81d1ba05dc	Add a BaseStore backed by AstraDB (#15812) ... - **Description:** this change adds a `BaseStore` backed by AstraDB - **Twitter handle:** cbornet_	8 months ago
manishsahni2000	74d9fc2f9e	PR community:Removing knn beta content in mongodb atlas vectorstore (#15865) ... <!-- 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
shahrin014	bdd90ae2ee	community: Ollama - Pass headers to post request (#15881) ... ## Feature - Set additional headers in constructor - Headers will be sent in post request This feature is useful if deploying Ollama on a cloud service such as hugging face, which requires authentication tokens to be passed in the request header. ## Tests - Test if header is passed - Test if header is not passed	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
Massimiliano Pronesti	ec4dab0449	feat(community): make Amadeus toolkit LLM-agnostic (#15879) ... - **Description:** `AmadeusToolkit` and `AmadeusClosestAirport` contained a hardcoded call to `ChatOpenAI`. This PR makes it LLM-independent, while guaranteeing backward compatibility. - **Issue:** #15847 - **Dependencies:** None @baskaryan <!-- 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
Yacine	782dd44be9	<langchain_community.vectorstores>:<Fix pinecone.py __init__ docsrting instruction> (#15922) ... - **Description:** The pinecone docstring instructs to pass the embedding query text causing the warning below. It should be the embeddings object. warning message: UserWarning: Passing in `embedding` as a Callable is deprecated. Please pass in an Embeddings object instead. - **Issue:** NA - **Dependencies:** None @baskaryan	8 months ago
Erick Friis	623f87c888	community[patch]: pinecone bug (#15905)	8 months ago
axiangcoding	d5aa277b94	community: add collection_properties parameter to Milvus (#15788) ... - **Description:** add collection_properties parameter to Milvus. See [pymilvus set_properties() description](https://milvus.io/api-reference/pymilvus/v2.3.x/Collection/set_properties().md) - **Issue:** None - **Dependencies:** None - **Twitter handle:** None	9 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>	9 months ago
Erick Friis	38523d7c57	together[minor]: add llm (#15853)	9 months ago
Erick Friis	ee708739c3	community[patch]: pinecone v3 support (#15849) ... Info in slack --------- Co-authored-by: Roie Schwaber-Cohen <roie.cohen@gmail.com>	9 months ago
Erick Friis	85a4594ed7	community[patch]: more deprecations (#15782)	9 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>	9 months ago
Bagatur	ee5bd986de	community[patch]: update oai deprecation message (#15681) ... addresses #15674	9 months ago
Erick Friis	4ed3d17c47	community[patch]: release 0.0.11 (#15760)	9 months ago
Ian	32ec56194b	community: fix myscale delete function bug (#15675) ... Now the SQL used to delete vector doc from myscale is as follow: ```sql DELETE FROM collection WHERE id = '1' AND id = '2' AND id = '3' ``` But the expected one should be ```sql DELETE FROM collection WHERE id IN ('1', '2', '3') ```	9 months ago
Christophe Bornet	a466f79ac9	Fix AstraDB logical operator filtering (#15699) ... <!-- 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. --> This change fixes the AstraDB logical operator filtering (`$and,` `$or`). The `metadata` prefix must not be added if the key is `$and` or `$or`.	9 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	9 months ago
Erick Friis	94911ae503	community[patch]: Support different Pinecone initializations depending on the version (#15717) ... Co-authored-by: DosticJelena <jelenadostic2@gmail.com>	9 months ago
Bagatur	4c47f39fcb	community[patch]: Release 0.0.10 (#15678)	9 months ago
Nuno Campos	7ce4cd0709	Do not issue beta or deprecation warnings on internal calls (#15641)	9 months ago
Earlee	98c6c9603e	community: fix: should flush after inserting data on milvus (#15568) ... The inserted data cannot take effect immediately. We should flush after inserting data on milvus.	9 months ago
chyroc	a17a3638b5	Docs: fix excel document loader typo (#15470)	9 months ago
chyroc	9ae901c5e6	Feat: add CHM file loader (#15519) ... fix https://github.com/langchain-ai/langchain/issues/15469	9 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.	9 months ago
kursathalat	9ea28ee464	fix: Fix DEFAULT_API_KEY for ArgillaCallbackHandler (#15534) ... - ArgillaCallbackHandler does not properly set the default values while initializing. This PR corrects the line. - Issue: #15531 - Dependencies: Argilla - Also corrected some dead links.	9 months ago
Chad Norvell	d1bfb70bc4	community: Allow deleting by ID and collection in `pgvector` (#15627) ... - **Description:** The `delete_collection` method deletes an entire collection regardless of custom ID. The `delete` method deletes everything with the provided custom IDs regardless of collection. It can be useful to restrict deletion to both the collection and a set of custom IDs. This change adds support for that by allowing you to optionally specify that `delete` should be restricted to the collection defined on the `PGVector` instance.	9 months ago
Chad Norvell	f6226d464e	community: Include PDF ID in MathPix metadata (#15629) ... - **Description:** Includes the PDF ID in the MathPix document metadata. This is useful in case you need to re-request a processed PDF from the MathPix API later.	9 months ago
Chad Norvell	d2a686b165	community: Provide more actionable errors in the MathPix PDF loader (#15630) ... - **Description:** The `error_info['id']` can be cross-referenced with the MathPix API documentation to get very specific information about why an error occurred.	9 months ago
Kai	5d05df4bce	community: Fixed bug of "system message check" in chat_models/tongyi. (#15631) ... - **Description:** This PR is to fix a bug of "system message check" in langchain_community/ chat_models/tongyi.py - **Issue:** In term of current logic, if there's no system message in the chat messages, an error of "System message can only be the first message." will be wrongly raised. - **Dependencies:** No. - **Twitter handle:** I don't have a Twitter account.	9 months ago
Raunak	64f5968a81	community: Replaced hardcoded "metadata" with FIELDS_METADATA variable in semantic_hybrid_search_with_score_and_rerank (#15642) ... - **Description:** This PR is to fix a bug in semantic_hybrid_search_with_score_and_rerank() function in langchain_community/vectorstores/azuresearch.py. The hardcoded "metadata" name is replaced with FIELDS_METADATA variable with an if block to check if the metadata column exists or not. - **Issue:** Fixed #15581 - **Dependencies:** No - **Twitter handle:** None Co-authored-by: H161961 <Raunak.Raunak@Honeywell.com>	9 months ago
Erick Friis	d136925c49	community[patch]: fix deprecation warnings on openai subclasses (#15621)	9 months ago
Bagatur	c5226d7a18	docs: update cohere chat integration (#15562) ... Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	9 months ago
Bagatur	dbb582d227	infra: community bump min core version (#15617)	9 months ago
Bagatur	1e4b8f0453	community[patch]: Release 0.0.9 (#15615)	9 months ago
Erick Friis	ebc75c5ca7	openai[minor]: implement langchain-openai package (#15503) ... Todo - [x] copy over integration tests - [x] update docs with new instructions in #15513 - [x] add linear ticket to bump core -> community, community->langchain, and core->openai deps - [ ] (optional): add `pip install langchain-openai` command to each notebook using it - [x] Update docstrings to not need `openai` install - [x] Add serialization - [x] deprecate old models Contributor steps: - [x] Add secret names to manual integrations workflow in .github/workflows/_integration_test.yml - [x] Add secrets to release workflow (for pre-release testing) in .github/workflows/_release.yml Maintainer steps (Contributors should not do these): - [x] set up pypi and test pypi projects - [x] add credential secrets to Github Actions - [ ] add package to conda-forge Functional changes to existing classes: - now relies on openai client v1 (1.6.1) via concrete dep in langchain-openai package Codebase organization - some function calling stuff moved to `langchain_core.utils.function_calling` in order to be used in both community and langchain-openai	9 months ago
Bagatur	a7d023aaf0	core[patch], community[patch]: mark runnable context, lc load as beta (#15603)	9 months ago
chyroc	f12b5c1222	Feat: support Milvus more params (#15447) ... fix https://github.com/langchain-ai/langchain/issues/15442	9 months ago
Bagatur	b2f15738dd	core[patch], langchain[patch], community[patch]: Revert #15326 (#15546)	9 months ago
Bagatur	0b579dc623	infra: update community test min reqs (#15490)	9 months ago
Bagatur	266db0efc8	community[patch]: bump core version >=0.1.5,<0.2 (#15488)	9 months ago
Bagatur	a2324ee533	community[patch]: Release 0.0.8 (#15481)	9 months ago
Bagatur	54b58c03db	infra: add minimum deps pre release check (#15485)	9 months ago
Bagatur	baeac236b6	langchain[patch], experimental[patch]: update utilities imports (#15438)	9 months ago
Harutaka Kawamura	73da8f863c	Remove unused `Params` (#14385) ... <!-- Thank you for contributing to LangChain! 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, - **Tag maintainer:** for a quicker response, tag the relevant maintainer (see below), - **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` to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md 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/extras` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. --> Removes unused `Params` in `libs/langchain/langchain/llms/mlflow.py`. Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	9 months ago
chyroc	b65e57971e	Patch: improve type hint (#15451)	9 months ago
Harutaka Kawamura	8ebf55ebbf	Fix `llms.Mlflow` example (#14386) ... <!-- Thank you for contributing to LangChain! 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, - **Tag maintainer:** for a quicker response, tag the relevant maintainer (see below), - **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` to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md 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/extras` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. --> The example code for `llms.Mlflow` is outdated. Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	9 months ago
Xin Liu	0a7d360ba4	feat: new integration `wasm_chat` (#14787) ... <!-- Thank you for contributing to LangChain! 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, - **Tag maintainer:** for a quicker response, tag the relevant maintainer (see below), - **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` to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md 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/extras` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. --> Adds `WasmChat` integration. `WasmChat` runs GGUF models locally or via chat service in lightweight and secure WebAssembly containers. In this PR, `WasmChatService` is introduced as the first step of the integration. `WasmChatService` is driven by [llama-api-server](https://github.com/second-state/llama-utils) and [WasmEdge Runtime](https://wasmedge.org/). --------- Signed-off-by: Xin Liu <sam@secondstate.io>	9 months ago
Anush	58cc7878e9	refactor: Qdrant async improvements (#14492) ... Follow up on https://github.com/langchain-ai/langchain/pull/13048. This PR intends to simplify the Qdrant async implementation by replacing the internal GRPC methods with the `QdrantAsyncClient` methods. This is a backward compatible change with no additional steps required after merge. --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	9 months ago
JuR-0	4dab37741a	Fix Bedrock broad error catching (#14398) ... Fixes #14347 <!-- Thank you for contributing to LangChain! Replace this entire comment with: - **Description:** Added the traceback of the previous error to keep the initial error type, - **Issue:** #14347 , - **Dependencies:** None, - **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. See contribution guidelines for more information on how to write/run tests, lint, etc: https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md 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/extras` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. --> --------- Co-authored-by: Julien Raffy <julien.raffy@emeria.eu> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	9 months ago
Bob Lin	e93be14c11	Improvement: Allow passing parameters to the underlying es_client. Closes: #14403 (#14435) ... ### Description In https://github.com/langchain-ai/langchain/issues/14403, the user mentioned that he hopes not to verify ssl and needs to pass more parameters I found that the `Elasticsearch` class [has very many parameters](98f2af2134/elasticsearch/_sync/client/__init__.py (L131-L191) ): <img width="1097" alt="Screenshot 2023-12-08 at 4 24 39 PM" src="https://github.com/langchain-ai/langchain/assets/10000925/f2201554-b41a-4388-a8e8-c14a2d0466d4"> In order to adapt to more situations, I want to add the kwargs parameter so that users can enter more `Elasticsearch` parameters. Like [redis](https://github.com/langchain-ai/langchain/blob/master/libs/langchain/langchain/vectorstores/redis/base.py#L253), [tair](https://github.com/langchain-ai/langchain/blob/master/libs/langchain/langchain/vectorstores/tair.py#L32), [myscale](https://github.com/langchain-ai/langchain/blob/master/libs/langchain/langchain/vectorstores/myscale.py#L112) and so on.	9 months ago
codehound42	8aa921d3a4	Support `score_threshold` in SupabaseVectorStore similarity search (#14439) ... Description: Add support for setting the `score_threshold` for similarity search in SupabaseVectoreStore. This pull request addresses issue #14438 Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	9 months ago
YISH	eecfa81918	Add the collection_description parameter to Milvus (#14524) ... Because Milvus' collection_name doesn't support UFT8 characters in other languages, I want the `collection_descriotion`. <!-- Thank you for contributing to LangChain! 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, - **Tag maintainer:** for a quicker response, tag the relevant maintainer (see below), - **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` to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md 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/extras` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. -->	9 months ago
Evgenii Molov	b4ec340fb3	Fix failing serpapi response processing for Google Maps API (#14817) ... **Description:** Fix for processing for serpapi response for Google Maps API **Issue:** Due to the fact corresponding [api](https://serpapi.com/google-maps-api) returns 'local_results' as list, and old version requested `res["local_results"].keys()` of the list. As the result we got exception: ```AttributeError: 'list' object has no attribute 'keys'```. Way to reproduce wrong behaviour: ``` params = { "engine": "google_maps", "type": "search", "google_domain": "google.de", "ll": "@51.1917,10.525,14z", "hl": "de", "gl": "de", } search = SerpAPIWrapper(params=params) results = search.run("cafe") ``` --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com> Co-authored-by: Ran <rccalman@gmail.com>	9 months ago
YISH	da0f750a0b	Milvus allows to store metadata as json field (#14636) ... Because Milvus doesn't support nullable fields, but document metadata is very rich, so it makes more sense to store it as json. https://github.com/milvus-io/pymilvus/issues/1705#issuecomment-1731112372 <!-- Thank you for contributing to LangChain! 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, - **Tag maintainer:** for a quicker response, tag the relevant maintainer (see below), - **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` to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md 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/extras` 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>	9 months ago
Ashley Xu	0ce7858529	feat: add Google BigQueryVectorSearch in vectorstore (#14829) ... 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 integrates LangChain vectorstore with BigQuery Vector Search. <!-- Thank you for contributing to LangChain! 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, - **Tag maintainer:** for a quicker response, tag the relevant maintainer (see below), - **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` 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/extras` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. --> --------- Co-authored-by: Vlad Kolesnikov <vladkol@google.com>	9 months ago
JaguarDB	02f59c2035	Use args option in jaguar so it takes more options in similarity search (#15080) ... - **Description:** replace score_threshold with args - **Issue:** needs a way to pass more options to similarity search - **Dependencies:** None - **Twitter handle:** @workbot --------- Co-authored-by: JY <jyjy@jaguardb>	9 months ago
chyroc	37ad6ec248	Refactor: use SecretStr for tongyi chat-model (#15102)	9 months ago
Shaurya Rohatgi	e1c2cd7a28	community: Semanticscholar tool to search 200M+ scientific articles (#15151) ... - **Description:** Tool now supports querying over 200 million scientific articles, vastly expanding its reach beyond the 2 million articles accessible through Arxiv. This update significantly broadens access to the entire scope of scientific literature. - **Dependencies:** semantischolar https://github.com/danielnsilva/semanticscholar - **Twitter handle:** @shauryr --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	9 months ago
dudub12	7e6b0056b8	SQLDatabase drop the column names in the result. (#15361) ... Fix for the following bug: https://github.com/langchain-ai/langchain/issues/15360 --------- Co-authored-by: dudu butbul <100126964+dudu-upstream@users.noreply.github.com>	9 months ago
chyroc	07d294b5ec	Fix: fix Bing Search empty result exception, fix #15384 (#15387) ... fix https://github.com/langchain-ai/langchain/issues/15384	9 months ago
Bagatur	1678d6ca17	langchain[patch], experimental[patch], docs: update tools imports (#15433)	9 months ago
Leonid Ganeline	b8c6ebf647	refactor `utils` (#15432) ... The `langchain` [still holds several artifacts](https://api.python.langchain.com/en/latest/langchain_api_reference.html#module-langchain.utils) that belongs to `community`. If they moved then `langchain.utils` namespace would be removed completely. - moved `ernie_functions` artifacts to `community`	9 months ago
Bagatur	fa5d49f2c1	docs, experimental[patch], langchain[patch], community[patch]: update storage imports (#15429) ... ran ```bash g grep -l "langchain.vectorstores" | xargs -L 1 sed -i '' "s/langchain\.vectorstores/langchain_community.vectorstores/g" g grep -l "langchain.document_loaders" | xargs -L 1 sed -i '' "s/langchain\.document_loaders/langchain_community.document_loaders/g" g grep -l "langchain.chat_loaders" | xargs -L 1 sed -i '' "s/langchain\.chat_loaders/langchain_community.chat_loaders/g" g grep -l "langchain.document_transformers" | xargs -L 1 sed -i '' "s/langchain\.document_transformers/langchain_community.document_transformers/g" g grep -l "langchain\.graphs" | xargs -L 1 sed -i '' "s/langchain\.graphs/langchain_community.graphs/g" g grep -l "langchain\.memory\.chat_message_histories" | xargs -L 1 sed -i '' "s/langchain\.memory\.chat_message_histories/langchain_community.chat_message_histories/g" gco master libs/langchain/tests/unit_tests/*/test_imports.py gco master libs/langchain/tests/unit_tests/**/test_public_api.py ```	9 months ago
Bagatur	480626dc99	docs, community[patch], experimental[patch], langchain[patch], cli[pa… (#15412) ... …tch]: import models from community ran ```bash git grep -l 'from langchain\.chat_models' | xargs -L 1 sed -i '' "s/from\ langchain\.chat_models/from\ langchain_community.chat_models/g" git grep -l 'from langchain\.llms' | xargs -L 1 sed -i '' "s/from\ langchain\.llms/from\ langchain_community.llms/g" git grep -l 'from langchain\.embeddings' | xargs -L 1 sed -i '' "s/from\ langchain\.embeddings/from\ langchain_community.embeddings/g" git checkout master libs/langchain/tests/unit_tests/llms git checkout master libs/langchain/tests/unit_tests/chat_models git checkout master libs/langchain/tests/unit_tests/embeddings/test_imports.py make format cd libs/langchain; make format cd ../experimental; make format cd ../core; make format ```	9 months ago
Mohammad Mohtashim	b6c57d38fa	Langchain_community: Small Fix when loading facebook messages (#15358) ... - **Description:** SingleFileFacebookMessengerChatLoader did not handle the case for when messages had stickers and/or photos so fixed that. - **Issue:** #15356 --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	9 months ago
Mateusz Szewczyk	cbfaccc424	WatsonxLLM updates/enhancements (#14598) ... - **Description:** updates/enhancements to IBM [watsonx.ai](https://www.ibm.com/products/watsonx-ai) LLM provider (prompt tuned models and prompt templates deployments support) - **Dependencies:** [ibm-watsonx-ai](https://pypi.org/project/ibm-watsonx-ai/), - **Tag maintainer:** : @hwchase17 , @eyurtsev , @baskaryan - **Twitter handle:** details in comment below. Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` to check this locally. ✅ --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	9 months ago
Manjunath Janardhan	7a0feba9f7	GITLAB_URL should take default https://gitlab.com instead of error (#14638) ... The fix #14221 has broken default gitlab url which is forcing the users to specify GITLAB_URL for default one. With this fix if GITLAB_URL is not set, the default gitlab url will be taken. - **Description:** Add the GITHUB URL instead of None - **Issue:** the issue #14221 has broken the default github URL - **Dependencies:** None - **Tag maintainer:** @hwchase17 - **Twitter handle:** manjunath_shiva	9 months ago
David	dcf047c48f	add api_base to _client_params (community version of #14393) (#14644) ... - **Description:** This PR adds `api_base` to `_client_params` in the `chat_model` of LiteLLM to ensure it's included in API calls. Previously, `api_base` was set on the client but was not included in the parameters passed to the completion function. This change ensures that `api_base` is correctly passed to all API calls. - **Issue:** #14338 - **Tag maintainer:** @hwchase17 @agola11 - **Twitter handle:** @LMS_David_RS	9 months ago
xuxiang	dd1d818a82	Fixing the Issue with DashScopeEmbeddings Handling More than 25 Rows of Data (#14662) ... <!-- Thank you for contributing to LangChain! 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, - **Tag maintainer:** for a quicker response, tag the relevant maintainer (see below), - **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` to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md 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/extras` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. --> This change addresses the issue where DashScopeEmbeddingAPI limits requests to 25 lines of data, and DashScopeEmbeddings did not handle cases with more than 25 lines, leading to errors. I have implemented a fix to manage data exceeding this limit efficiently. --------- Co-authored-by: xuxiang <xuxiang@aliyun.com>	9 months ago
Christophe Bornet	e2a8962ba6	Add AstraDB document loader (#14747) ... - **Description:** this adds the AstraDB document loader and an integration test - **Twitter handle:** cbornet_	9 months ago
Igor Dvorkin	76923e5743	Restore self message sent before OSX 12 Monterey (#14818) ... <!-- Thank you for contributing to LangChain! 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, - **Tag maintainer:** for a quicker response, tag the relevant maintainer (see below), - **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` to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md 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/extras` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. -->	9 months ago
savoiepe	d006be60ec	Added more filtering options to pgvector vectorstore (#14852) ... - **Description:** Using PGVector vector store, it was only possible to filter for values equals, in or not in metadata. Extended this feature to work with the following keywords : IN, NIN, BETWEEN, GT, LT, NE, EQ, LIKE, CONTAINS, OR, AND --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	9 months ago
chyroc	32e96a471c	Refactor: use SecretStr for llm_rails embeddings (#15090)	9 months ago
chyroc	b440f92d81	Refactor: use SecretStr for embaas embeddings (#15091)	9 months ago
chyroc	ea6cf0f1b1	Refactor: use SecretStr for edenai embeddings (#15092)	9 months ago
chyroc	32e6e9de13	Refactor: use SecretStr for palm chat-model (#15100)	9 months ago
chyroc	b6952d41e5	Refactor: use SecretStr for GPTRouter chat-model (#15101)	9 months ago
Nan LI	f506b4cfd2	community: Integration of New Chat Model Based on ChatGLM3 via ZhipuAI API (#15105) ... - **Description:** - This PR introduces a significant enhancement to the LangChain project by integrating a new chat model powered by the third-generation base large model, ChatGLM3, via the zhipuai API. - This advanced model supports functionalities like function calls, code interpretation, and intelligent Agent capabilities. - The additions include the chat model itself, comprehensive documentation in the form of Python notebook docs, and thorough testing with both unit and integrated tests. - **Dependencies:** This update relies on the ZhipuAI package as a key dependency. - **Twitter handle:** If this PR receives spotlight attention, we would be honored to receive a mention for our integration of the advanced ChatGLM3 model via the ZhipuAI API. Kindly tag us at @kaiwu. 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. TO DO: Continue refining and enhancing both the unit tests and integrated tests. --------- Co-authored-by: jing <jingguo92@gmail.com> Co-authored-by: hyy1987 <779003812@qq.com> Co-authored-by: jianchuanqi <qijianchuan@hotmail.com> Co-authored-by: lirq <whuclarence@gmail.com> Co-authored-by: whucalrence <81530213+whucalrence@users.noreply.github.com> Co-authored-by: Jing Guo <48378126+JaneCrystall@users.noreply.github.com>	9 months ago
Hin	2cf1e73d12	Feat add volcano embedding (#14693) ... Description: Volcano Ark is an enterprise-grade large-model service platform for developers, providing a full range of functions and services such as model training, inference, evaluation, fine-tuning. You can visit its homepage at https://www.volcengine.com/docs/82379/1099455 for details. This change could help developers use the platform for embedding. Issue: None Dependencies: volcengine Tag maintainer: @baskaryan Twitter handle: @hinnnnnnnnnnnns --------- Co-authored-by: lujingxuansc <lujingxuansc@bytedance.com>	9 months ago
David Křístek	a010f29013	fix: call correct stream method in ollama (#15104) ... Co-authored-by: David Kristek <david@David--MacBook-Pro.local>	9 months ago
Christian Janiake	be578f32be	community:Lazy load wikipedia dump file (#15111) ... **Description:** the MWDumpLoader implementation currently does not support the lazy_load method, and the files are usually very large. We are proposing refactoring the load function, extracting two private functions with the functionality of loading the dump file and parsing a single page, to reuse the code in the lazy_load implementation.	9 months ago
chyroc	a4ae4bc361	feat: mask api_key for konko (#14010) ... for https://github.com/langchain-ai/langchain/issues/12165	9 months ago
joel-teratis	62d32bd214	fix(minor): added missing **kwargs parameter to chroma query function (#14919) ... **Description:** This PR adds the `**kwargs` parameter to six calls in the `chroma.py` package. All functions already were able to receive `kwargs` but they were discarded before. **Issue:** When passing `kwargs` to functions in the `chroma.py` package they are being ignored. For example: ``` chroma_instance.similarity_search_with_score( query, k=100, include=["metadatas", "documents", "distances", "embeddings"], # this parameter gets ignored ) ``` The `include` parameter does not get passed on to the next function and does not have any effect. **Dependencies:** None	9 months ago
NuODaniel	7773943a51	community:qianfan endpoint support init params & remove useless params definietion (#15381) ... - **Description:** - support custom kwargs in object initialization. For instantance, QPS differs from multiple object(chat/completion/embedding with diverse models), for which global env is not a good choice for configuration. - **Issue:** no - **Dependencies:** no - **Twitter handle:** no @baskaryan PTAL	9 months ago
Nuno Campos	99000c612e	Propagate context vars in all classes/methods (#15329) ... - Any direct usage of ThreadPoolExecutor or asyncio.run_in_executor needs manual handling of context vars <!-- 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. -->	9 months ago
Ankush Gola	7eec8f2487	Delete V1 tracer and refactor tracer tests to core (#15326)	9 months ago
chyroc	7ce338201c	Patch: improve check openai version (#15301)	9 months ago
Nuno Campos	eb5e250188	Propagate context vars in all classes/methods ... - Any direct usage of ThreadPoolExecutor or asyncio.run_in_executor needs manual handling of context vars	9 months ago
Shuai Liu	4b53440e70	Upgrades the Tongyi LLM and ChatTongyi Model (#14793) ... - **Description:** fixes and upgrades for the Tongyi LLM and ChatTongyi Model - Fixed typos; it should be `Tongyi`, not `OpenAI`. - Fixed a bug in `stream_generate_with_retry`; it's a real stream generator now. - Fixed a bug in `validate_environment`; the `dashscope_api_key` should be properly handled when set by environment variables or initialization parameters. - Changed the `dashscope` response to incremental output by setting the parameter `incremental_output`, which eliminates the need for the prefix-removal trick. - Removed some unused parameters, like `n`, `prefix_messages`. - Added `_stream` method. - Added async methods support, such as `_astream`, `_agenerate`, `_abatch`. - **Dependencies:** No new dependencies. - **Tag maintainer:** @hwchase17 > PS: Some may be confused about the terms `dashscope`, `tongyi`, and `Qwen`: > - `dashscope`: A platform to deploy LLMs and provide APIs to invoke the LLM. > - `tongyi`: A brand name or overall term about Alibaba Cloud's LLM/AI. > - `Qwen`: An LLM that is open-sourced and deployed in `dashscope`. > > We use the `dashscope` SDK to interact with the `tongyi`-`Qwen` LLM. --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	9 months ago
Bagatur	8bfac1a319	community[patch]: Release 0.0.7 (#15320)	9 months ago
Diego Rani Mazine	ec72225265	refactor: enable connection pool usage in PGVector (#11514) ... - **Description:** `PGVector` refactored to use connection pool. - **Issue:** #11433, - **Tag maintainer:** @hwchase17 @eyurtsev, --------- Co-authored-by: Diego Rani Mazine <diego.mazine@mercadolivre.com> Co-authored-by: Nuno Campos <nuno@langchain.dev>	9 months ago
joshy-deshaw	bf5385592e	core, community: propagate context between threads (#15171) ... While using `chain.batch`, the default implementation uses a `ThreadPoolExecutor` and run the chains in separate threads. An issue with this approach is that that [the token counting callback](https://python.langchain.com/docs/modules/callbacks/token_counting) fails to work as a consequence of the context not being propagated between threads. This PR adds context propagation to the new threads and adds some thread synchronization in the OpenAI callback. With this change, the token counting callback works as intended. Having the context propagation change would be highly beneficial for those implementing custom callbacks for similar functionalities as well. --------- Co-authored-by: Nuno Campos <nuno@langchain.dev>	9 months ago
shroominic	694bbb14cd	community: fix typo in async ollama chat (#15276) ... Made a stupid typo in the last PR which got already merged😅	9 months ago
triThirty	fea4888e72	community: Enhance Github error prompt (#15248) ... - **Description:** The Github error prompt is confused because of JWT enctrypt to somebody not familiar with Github connection method. This PR is to add some useful error prompt to help users troubleshooting. - **Issue:** https://github.com/langchain-ai/langchain/issues/14550#issuecomment-1867445049 - **Dependencies:** None, - **Twitter handle:** None	9 months ago
Bob Lin	a464eb4394	community: Make doctran synchronous (#15264) ... ### Description I found that the methods in [the doctran library](https://github.com/psychic-api/doctran) have been restructured into [synchronized versions](14944a59f7), And [the example ipynb](https://github.com/psychic-api/doctran/blob/main/examples.ipynb) also shows that the code is synchronized, but the README has not been updated yet. so we need to modify the code and update the documentation. ### Issue https://github.com/langchain-ai/langchain/issues/14645	9 months ago
chyroc	6fb3cc6f27	Fix: Use `Union` instead of `|` to improve compatibility, fix #15244 (#15245)	9 months ago
chyroc	1abcf441ae	Refactor: use SecretStr for Predibase llms (#15119)	9 months ago
chyroc	0a9a73a9c9	Refactor: use SecretStr for PipelineAI llms (#15120)	9 months ago
chyroc	d63ceb65b3	Refactor: use SecretStr for StochasticAI llms (#15118)	9 months ago
chyroc	674fde87d2	Refactor: use SecretStr for VolcEngineMaas llms (#15117)	9 months ago
chyroc	3cc1da2b38	Refactor: use SecretStr for Petals llms (#15121)	9 months ago
shroominic	e6f0cee896	community: Async Ollama + ChatOllama (#15169) ... **Description:** Adding async methods to booth OllamaLLM and ChatOllama to enable async streaming and async .on_llm_new_token callbacks. **Issue:** ChatOllama is not working in combination with an AsyncCallbackManager because the .on_llm_new_token method is not awaited.	9 months ago
Phill Zarfos	35896faab7	community: correct spelling mistakes of "Suffle" and "reporoducibility" (#15172) ... - **Description:** Correct spelling mistakes of "Suffle" and "reporoducibility" in `DirectoryLoader` class - **Issue:** N/A - **Dependencies:** N/A - **Twitter handle:** N/A	9 months ago
chyroc	3a3f880e5a	Patch: improve ollama 404 api error message, fix #15147 (#15156) ... Make this issue more clearly exposed to developers	9 months ago
Ivan	59d4b80a92	[community]: Elasticsearch chat history encoding (#15055) ... - Added ensure_ascii property to ElasticsearchChatMessageHistory <!-- 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: Ivan Chetverikov <ivan.chetverikov@raftds.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	9 months ago
Corey Brown	9e492620d4	Don't reassign chunk_type (#14923) ... **Description**: The parameter chunk_type was being hard coded to "extractive_answers", so that when "snippet" was being passed, it was being ignored. This change simply doesn't do that.	9 months ago
Takuya Igei	6da2246215	Add support Vertex AI Gemini uses a public image URL (#14949) ... ## What Since `langchain_google_genai.ChatGoogleGenerativeAI` supported A public image URL, we add to support it in `langchain.chat_models.ChatVertexAI` as well. ### Example ```py from langchain.chat_models.vertexai import ChatVertexAI from langchain_core.messages import HumanMessage llm = ChatVertexAI(model_name="gemini-pro-vision") image_message = { "type": "image_url", "image_url": { "url": "https://python.langchain.com/assets/images/cell-18-output-1-0c7fb8b94ff032d51bfe1880d8370104.png", }, } text_message = { "type": "text", "text": "What is shown in this image?", } message = HumanMessage(content=[text_message, image_message]) output = llm([message]) print(output.content) ``` ## Refs - https://python.langchain.com/docs/integrations/llms/google_vertex_ai_palm - https://python.langchain.com/docs/integrations/chat/google_generative_ai	9 months ago
Archan Ghosh	affa3e755a	Update arxiv.py with get_summaries_as_docs inside of Arxivloader (#14953) ... Added the call function get_summaries_as_docs inside of Arxivloader - **Description:** Added a function that returns the documents from get_summaries_as_docs, as the call signature is present in the parent file but never used from Arxivloader, this can be used from Arxivloader itself just like .load() as both the signatures are same. - **Issue:** Reduces time to load papers as no pdf is processed only metadata is pulled from Arxiv allowing users for faster load times on bulk loads. Users can then choose one or more paper and use ID directly with .load() to load pdf thereby loading all the contents of the paper.	9 months ago
ccurme	f2782f4c86	community: add args_schema to GmailSendMessage (#14973) ... - **Description:** `tools.gmail.send_message` implements a `SendMessageSchema` that is not used anywhere. `GmailSendMessage` also does not have an `args_schema` attribute (this led to issues when invoking the tool with an OpenAI functions agent, at least for me). Here we add the missing attribute and a minimal test for the tool. - **Issue:** N/A - **Dependencies:** N/A - **Twitter handle:** N/A --------- Co-authored-by: Chester Curme <chestercurme@microsoft.com>	9 months ago
Philip Kiely - Baseten	6342da333a	community: refactor Baseten integration with new API endpoints & docs (#15017) ... - **Description:** In response to user feedback, this PR refactors the Baseten integration with updated model endpoints, as well as updates relevant documentation. This PR has been tested by end users in production and works as expected. - **Issue:** N/A - **Dependencies:** This PR actually removes the dependency on the `baseten` package! - **Twitter handle:** https://twitter.com/basetenco	9 months ago
Blane Honeycutt	3fc1b3553b	Community: Adds ability to pass a Config to the boto3 client used by Bedrock (#15029) ... # Description This PR adds the ability to pass a `botocore.config.Config` instance to the boto3 client instantiated by the Bedrock LLM. Currently, the Bedrock LLM doesn't support a way to pass a Config, which means that some settings (e.g., timeouts and retry configuration) require instantiating a new boto3 client with a Config and then replacing the LLM's client: ```python llm = Bedrock( region_name='us-west-2', model_id="anthropic.claude-v2", model_kwargs={'max_tokens_to_sample': 4096, 'temperature': 0}, ) llm.client = boto_client('bedrock-runtime', region_name='us-west-2', config=Config({'read_timeout': 300})) ``` # Issue N/A # Dependencies N/A	9 months ago
Grzegorz Sajko	dc71fcfabf	corrected outdated link (#15053) ... <!-- 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. -->	9 months ago
Ran	c3f8733aef	fix: correct spelling mistakes of "seperate, intialise, pre-defined" (#14647) ... fix spellings **seperate -> separate**: found more occurrences, see https://github.com/langchain-ai/langchain/pull/14602 **initialise -> intialize**: the latter is more common in the repo **pre-defined > predefined**: adding a comma after a prefix is a delicate matter, but this is a generally accepted word also, another word that appears in the repo is "fs" (stands for filesystem), e.g., in `libs/core/langchain_core/prompts/loading.py` ` """Unified method for loading a prompt from LangChainHub or local fs."""` Isn't "filesystem" better?	9 months ago
Harrison Chase	2e159931ac	add defaults for tavily (#15075)	9 months ago
chyroc	4440ec5ab3	Refactor: use SecretStr for minimax embeddings (#15067)	9 months ago
chyroc	aa19ca9723	Refactor: use SecretStr for jina embeddings (#15068) ... <!-- 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. -->	9 months ago
Michael Goin	501cc8311d	community[patch]: Fix generation_config not setting properly for DeepSparse (#15036) ... - **Description:** Tiny but important bugfix to use a more stable interface for specifying generation_config parameters for DeepSparse LLM	9 months ago
QIAN Zifei	2460f977c5	community[minor]: Azure DocumentIntelligenceLoader/Parser support update with latest SDK (#14389) ... - **Description:** Add DocumentIntelligenceLoader & DocumentIntelligenceParser implementation using the latest Azure Document Intelligence SDK with markdown support. The core logic resides in DocumentIntelligenceParser and DocumentIntelligenceLoader is a mere wrapper of the parser. The parser will takes api_endpoint and api_key and creates DocumentIntelligenceClient for the user. 4 parsing modes are supported: 1. Markdown (default) 2. Single 3. Page 4. Object UT and notebook are also updated accordingly. - **Dependencies:** Azure Document Intelligence SDK: azure-ai-documentintelligence [azure-sdk-for-python/sdk/documentintelligence/azure-ai-documentintelligence at 7c42462ac662522a6fd21b17d2a20f4cd40d0356 · Azure/azure-sdk-for-python (github.com)](https://nam06.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2FAzure%2Fazure-sdk-for-python%2Ftree%2F7c42462ac662522a6fd21b17d2a20f4cd40d0356%2Fsdk%2Fdocumentintelligence%2Fazure-ai-documentintelligence&data=05%7C01%7CZifei.Qian%40microsoft.com%7C298225aa3e31468a863108dbf07374ff%7C72f988bf86f141af91ab2d7cd011db47%7C1%7C0%7C638368150928704292%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=oE0Sl4HERnMKdbkV9KgBV46Z2xytcQAShdTWf7ZNl%2Bs%3D&reserved=0). --------- Co-authored-by: Erick Friis <erick@langchain.dev>	9 months ago
Ran	129a929d69	infra: Fix test filesystem paths incompatible with windows (#14388) ... - **Description:** This PR fixes test failures on Windows caused by path handling differences and unescaped special characters in regex. The failing tests are: ``` FAILED tests/unit_tests/storage/test_filesystem.py::test_yield_keys - AssertionError: assert ['key1', 'subdir\\key2'] == ['key1', 'subdir/key2'] FAILED tests/unit_tests/test_imports.py::test_importable_all - ModuleNotFoundError: No module named 'langchain_community.langchain_community\\adapters' FAILED tests/unit_tests/tools/file_management/test_utils.py::test_get_validated_relative_path_errs_on_absolute - re.error: incomplete escape \U at position 53 FAILED tests/unit_tests/tools/file_management/test_utils.py::test_get_validated_relative_path_errs_on_parent_dir - re.error: incomplete escape \U at position 69 FAILED tests/unit_tests/tools/file_management/test_utils.py::test_get_validated_relative_path_errs_for_symlink_outside_root - re.error: incomplete escape \U at position 64 ``` - **Issue:** fixes https://github.com/langchain-ai/langchain/issues/11775 (partially) - **Dependencies:** none	9 months ago