329 Commits (849051102a6e315072e3a1d8dfdcee1527436c92)

Author	SHA1	Message	Date
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