344 Commits (cd00a87db732687d0d6a9ffdc1eb9f6f5ebc49b6)

Author	SHA1	Message	Date
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
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
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	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
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
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
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
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	8 months ago
mogith-pn	9e1ed17bfb	Community : Modified doc strings and example notebook for Clarifai (#15816) ... Community : Modified doc strings and example notebook for Clarifai Description: 1. Modified doc strings inside clarifai vectorstore class and embeddings. 2. Modified notebook examples. --------- Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>	8 months ago
Erick Friis	38523d7c57	together[minor]: add llm (#15853)	8 months ago
Erick Friis	ee708739c3	community[patch]: pinecone v3 support (#15849) ... Info in slack --------- Co-authored-by: Roie Schwaber-Cohen <roie.cohen@gmail.com>	8 months ago
Erick Friis	85a4594ed7	community[patch]: more deprecations (#15782)	8 months ago
NuODaniel	70b6315b23	community[patch]: fix qianfan chat stream calling caused exception (#13800) ... - **Description:** `QianfanChatEndpoint` extends `BaseChatModel` as a super class, which has a default stream implement might concat the MessageChunk with `__add__`. When call stream(), a ValueError for duplicated key will be raise. - **Issues:** * #13546 * #13548 * merge two single test file related to qianfan. - **Dependencies:** no - **Tag maintainer:** --------- Co-authored-by: root <liujun45@baidu.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	8 months ago
Bagatur	ee5bd986de	community[patch]: update oai deprecation message (#15681) ... addresses #15674	8 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') ```	8 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`.	8 months ago
Christophe Bornet	1f5f6381ec	Add doc for AstraDB document loader (#15703) ... <!-- Thank you for contributing to LangChain! Please title your PR "<package>: <description>", where <package> is whichever of langchain, community, core, experimental, etc. is being modified. Replace this entire comment with: - **Description:** a description of the change, - **Issue:** the issue # it fixes if applicable, - **Dependencies:** any dependencies required for this change, - **Twitter handle:** we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` from the root of the package you've modified to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://python.langchain.com/docs/contributing/ If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. --> See preview : https://langchain-git-fork-cbornet-astra-loader-doc-langchain.vercel.app/docs/integrations/document_loaders/astradb	8 months ago
Erick Friis	94911ae503	community[patch]: Support different Pinecone initializations depending on the version (#15717) ... Co-authored-by: DosticJelena <jelenadostic2@gmail.com>	8 months ago
Nuno Campos	7ce4cd0709	Do not issue beta or deprecation warnings on internal calls (#15641)	8 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.	8 months ago
chyroc	a17a3638b5	Docs: fix excel document loader typo (#15470)	8 months ago
chyroc	9ae901c5e6	Feat: add CHM file loader (#15519) ... fix https://github.com/langchain-ai/langchain/issues/15469	8 months ago
Nan LI	0b393315ce	community: Correct Input API Key Name in Notebook and Enhance Readability of Comments for ZhipuAI Chat Model (#15529) ... - **Description:** This update rectifies an error in the notebook by changing the input variable from `zhipu_api_key` to `api_key`. It also includes revisions to comments to improve program readability. - **Issue:** The input variable in the notebook example should be `api_key` instead of `zhipu_api_key`. - **Dependencies:** No additional dependencies are required for this change. To ensure quality and standards, we have performed extensive linting and testing. Commands such as make format, make lint, and make test have been run from the root of the modified package to ensure compliance with LangChain's coding standards.	8 months ago
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.	8 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.	8 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.	8 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.	8 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.	8 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>	8 months ago
Erick Friis	d136925c49	community[patch]: fix deprecation warnings on openai subclasses (#15621)	8 months ago
Bagatur	c5226d7a18	docs: update cohere chat integration (#15562) ... Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	8 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	8 months ago
Bagatur	a7d023aaf0	core[patch], community[patch]: mark runnable context, lc load as beta (#15603)	8 months ago
chyroc	f12b5c1222	Feat: support Milvus more params (#15447) ... fix https://github.com/langchain-ai/langchain/issues/15442	8 months ago
Bagatur	b2f15738dd	core[patch], langchain[patch], community[patch]: Revert #15326 (#15546)	8 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>	8 months ago
chyroc	b65e57971e	Patch: improve type hint (#15451)	8 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>	8 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>	8 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>	8 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>	8 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.	8 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>	8 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. -->	8 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>	8 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>	8 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>	8 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>	8 months ago
chyroc	37ad6ec248	Refactor: use SecretStr for tongyi chat-model (#15102)	8 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>	8 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>	8 months ago
chyroc	07d294b5ec	Fix: fix Bing Search empty result exception, fix #15384 (#15387) ... fix https://github.com/langchain-ai/langchain/issues/15384	8 months ago
Bagatur	1678d6ca17	langchain[patch], experimental[patch], docs: update tools imports (#15433)	8 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`	8 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 ```	8 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 ```	8 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>	8 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>	8 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	8 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	8 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>	8 months ago
Christophe Bornet	e2a8962ba6	Add AstraDB document loader (#14747) ... - **Description:** this adds the AstraDB document loader and an integration test - **Twitter handle:** cbornet_	8 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. -->	8 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>	8 months ago
chyroc	32e96a471c	Refactor: use SecretStr for llm_rails embeddings (#15090)	8 months ago
chyroc	b440f92d81	Refactor: use SecretStr for embaas embeddings (#15091)	8 months ago
chyroc	ea6cf0f1b1	Refactor: use SecretStr for edenai embeddings (#15092)	8 months ago
chyroc	32e6e9de13	Refactor: use SecretStr for palm chat-model (#15100)	8 months ago