langchain

Commit Graph

Author	SHA1	Message	Date
Nuno Campos	226fe645f1	core[patch] Do not try to access attribute of None (#16321 )	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
Nicolò Boschi	a500527030	infra: google-vertexai relax types-requests deps range (#16264 ) - Description: At the moment it's not possible to include in the same project langchain-google-vertexai and boto3 (e.g. use bedrock and vertex in the same application) because of the dependency resolutions conflict. boto3 is still using urllib3 1.x, meanwhile langchain-google-vertexai -> types-requests depends on urllib3 2.x. [the last version of types-requests that allows urllib3 1.x is 2.31.0.6](https://pypi.org/project/types-requests/#description). In this PR I allow the vertexai package to get that version also. - Twitter handle: nicoloboschi	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
Chase VanSteenburg	1011b681dc	core[patch]: Fix f-string formatting in error message for configurable_fields (#16411 ) - Description: Simple fix to f-string formatting. Allows more informative ValueError output. - Issue: None needed. - Dependencies: None. - Twitter handle: @FlightP1an	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
James Braza	d511366dd3	infra: absolute `EXAMPLE_DIR` path in core unit tests (#16325 ) If you invoked testing from places besides `core/`, this `EXAMPLE_DIR` path won't work. This PR makes`EXAMPLE_DIR` robust against invocation location	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	35ec0bbd3b	cli[patch]: pypi fields (#16410 )	8 months ago
Erick Friis	2ac3a82d85	cli[patch]: new fields in integration template, release 0.0.21 (#16398 )	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
Piotr Mardziel	1b9001db47	core[patch]: preserve inspect.iscoroutinefunction with @deprecated decorator (#16295 ) Adjusted `deprecate` decorator to make sure decorated async functions are still recognized as "coroutinefunction" by `inspect`. Before change, functions such as `LLMChain.acall` which are decorated as deprecated are not recognized as coroutine functions. After the change, they are recognized: ```python import inspect from langchain import LLMChain # Is false before change but true after. inspect.iscoroutinefunction(LLMChain.acall) ```	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
y2noda	54f90fc6bc	langchain_google_vertexai:Enable the use of langchain's built-in tools in Gemini's function calling (#16341 ) - Issue: This is a PR about #16340 <!-- Thank you for contributing to LangChain! Please title your PR "<package>: <description>", where <package> is whichever of langchain, community, core, experimental, etc. is being modified. Replace this entire comment with: - Description: a description of the change, - Issue: the issue # it fixes if applicable, - Dependencies: any dependencies required for this change, - Twitter handle: we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` from the root of the package you've modified to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://python.langchain.com/docs/contributing/ If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. --> Co-authored-by: yuhei.tsunoda <yuhei.tsunoda@brainpad.co.jp>	8 months ago
Tom Jorquera	1445ac95e8	community[patch]: Enable streaming for GPT4all (#16392 ) `streaming` param was never passed to model	8 months ago
Bagatur	af9f1738ca	langchain[patch]: Release 0.1.2 (#16388 )	8 months ago
Bagatur	8779013847	community[patch]: Release 0.0.14 (#16384 )	8 months ago
Bagatur	9cf0f5eb78	core[patch]: Release 0.1.14 (#16382 )	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
Bob Lin	acc14802d1	Fix `conn` field definition in SQLiteEntityStore (#15440 )	8 months ago
James Braza	e1c59779ad	core[patch]: Remove `print` statement on missing `grandalf` dependency in favor of more explicit ImportError (#16326 ) After this PR an ImportError will be raised without a print if grandalf is missing when using grandalf related code for printing runnable graphs.	8 months ago
Nuno Campos	971a68d04f	Docs: Update README.md in core (#16329 ) Docs: Update README.md in core	8 months ago
Eugene Yurtsev	89372fca22	core[patch]: Update sys info information (#16297 ) Update information collected in sys info. python -m langchain_core.sys_info System Information ------------------ > OS: Linux > OS Version: #14~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Mon Nov 20 18:15:30 UTC 2 > Python Version: 3.11.4 (main, Sep 25 2023, 10:06:23) [GCC 11.4.0] Package Information ------------------- > langchain_core: 0.1.10 > langchain: 0.1.0 > langchain_community: 0.0.11 > langchain_cli: 0.0.20 > langchain_experimental: 0.0.36 > langchain_openai: 0.0.2 > langchainhub: 0.1.14 > langserve: 0.0.19 Packages not installed (Not Necessarily a Problem) -------------------------------------------------- The following packages were not found: > langgraph	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
Nuno Campos	ef75bb63ce	core[patch] Fix tracer output of streamed runs with non-addable output (#16324 ) - Used to be None, now is just the last chunk <!-- 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
Ryan French	3d23a5eb36	langchain[patch]: Allow OpenSearch Query Translator to correctly work with Date types (#16022 ) Description: Fixes an issue where the Date type in an OpenSearch Self Querying Retriever would fail to generate a valid query Issue: https://github.com/langchain-ai/langchain/issues/14225	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
Bagatur	1e29b676d5	core[patch]: simple fallback streaming (#16055 )	8 months ago
Eugene Yurtsev	4ef0ed4ddc	astream_events: Add version parameter while method is in beta (#16290 ) Add a version parameter while the method is in beta phase. The idea is to make it possible to minimize making breaking changes for users while we're iterating on schema. Once the API is stable we can assign a default version requirement.	8 months ago
Bagatur	91230ef5d1	openai[patch]: Release 0.0.3 (#16289 )	8 months ago
Hamza Kyamanywa	39b3c6d94c	langchain[patch]: Add konlpy based text splitting for Korean (#16003 ) - Description: Adds a text splitter based on [Konlpy](https://konlpy.org/en/latest/#start) which is a Python package for natural language processing (NLP) of the Korean language. (It is like Spacy or NLTK for Korean) - Dependencies: Konlpy would have to be installed before this splitter is used, - Twitter handle: @untilhamza	8 months ago
Bagatur	e3828bee43	core[patch]: Release 0.1.13 (#16287 )	8 months ago
Bagatur	2454fefc53	docs: agent prompt docs (#16105 )	8 months ago
Bagatur	84bf5787a7	core[patch], openai[patch]: Chat openai stream logprobs (#16218 )	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
Eugene Yurtsev	177af65dc4	core[minor]: RFC Add astream_events to Runnables (#16172 ) This PR adds `astream_events` method to Runnables to make it easier to stream data from arbitrary chains. * Streaming only works properly in async right now * One should use `astream()` with if mixing in imperative code as might be done with tool implementations * Astream_log has been modified with minimal additive changes, so no breaking changes are expected * Underlying callback code / tracing code should be refactored at some point to handle things more consistently (OK for now) - ~~[ ] verify event for on_retry~~ does not work until we implement streaming for retry - ~~[ ] Any rrenaming? Should we rename "event" to "hook"?~~ - [ ] Any other feedback from community? - [x] throw NotImplementedError for `RunnableEach` for now ## Example See this [Example Notebook](`dbbc7fa0d6/docs/docs/modules/agents/how_to/streaming_events.ipynb`) for an example with streaming in the context of an Agent ## Event Hooks Reference Here is a reference table that shows some events that might be emitted by the various Runnable objects. Definitions for some of the Runnable are included after the table. \| event \| name \| chunk \| input \| output \| \|----------------------\|------------------\|---------------------------------\|-----------------------------------------------\|-------------------------------------------------\| \| on_chat_model_start \| [model name] \| \| {"messages": [[SystemMessage, HumanMessage]]} \| \| \| on_chat_model_stream \| [model name] \| AIMessageChunk(content="hello") \| \| \| \| on_chat_model_end \| [model name] \| \| {"messages": [[SystemMessage, HumanMessage]]} \| {"generations": [...], "llm_output": None, ...} \| \| on_llm_start \| [model name] \| \| {'input': 'hello'} \| \| \| on_llm_stream \| [model name] \| 'Hello' \| \| \| \| on_llm_end \| [model name] \| \| 'Hello human!' \| \| on_chain_start \| format_docs \| \| \| \| \| on_chain_stream \| format_docs \| "hello world!, goodbye world!" \| \| \| \| on_chain_end \| format_docs \| \| [Document(...)] \| "hello world!, goodbye world!" \| \| on_tool_start \| some_tool \| \| {"x": 1, "y": "2"} \| \| \| on_tool_stream \| some_tool \| {"x": 1, "y": "2"} \| \| \| \| on_tool_end \| some_tool \| \| \| {"x": 1, "y": "2"} \| \| on_retriever_start \| [retriever name] \| \| {"query": "hello"} \| \| \| on_retriever_chunk \| [retriever name] \| {documents: [...]} \| \| \| \| on_retriever_end \| [retriever name] \| \| {"query": "hello"} \| {documents: [...]} \| \| on_prompt_start \| [template_name] \| \| {"question": "hello"} \| \| \| on_prompt_end \| [template_name] \| \| {"question": "hello"} \| ChatPromptValue(messages: [SystemMessage, ...]) \| Here are declarations associated with the events shown above: `format_docs`: ```python def format_docs(docs: List[Document]) -> str: '''Format the docs.''' return ", ".join([doc.page_content for doc in docs]) format_docs = RunnableLambda(format_docs) ``` `some_tool`: ```python @tool def some_tool(x: int, y: str) -> dict: '''Some_tool.''' return {"x": x, "y": y} ``` `prompt`: ```python template = ChatPromptTemplate.from_messages( [("system", "You are Cat Agent 007"), ("human", "{question}")] ).with_config({"run_name": "my_template", "tags": ["my_template"]}) ```	8 months ago
SN	f175bf7d7b	Use env for revision id if not passed in as param; use `git describe` as backup (#16227 ) Co-authored-by: William Fu-Hinthorn <13333726+hinthornw@users.noreply.github.com>	8 months ago
Erick Friis	b9495da92d	langchain[patch]: fix stuff documents chain api docs render (#16159 )	8 months ago
Erick Friis	0e76d84137	google-vertexai[patch]: more integration test fixes (#16234 )	8 months ago
Erick Friis	aa35b43bcd	docs, google-vertex[patch]: function docs (#16231 )	8 months ago
Harrison Chase	f60f59d69f	google-vertexai[patch]: Harrison/vertex function calling (#16223 ) Co-authored-by: Erick Friis <erick@langchain.dev>	8 months ago
Rajesh Thallam	6bc6d64a12	langchain_google_vertexai[patch]: Add support for SystemMessage for Gemini chat model (#15933 ) - Description: In Google Vertex AI, Gemini Chat models currently doesn't have a support for SystemMessage. This PR adds support for it only if a user provides additional convert_system_message_to_human flag during model initialization (in this case, SystemMessage would be prepended to the first HumanMessage). NOTE: The implementation is similar to #14824 - Twitter handle: rajesh_thallam --------- Co-authored-by: Erick Friis <erick@langchain.dev>	8 months ago
Erick Friis	65b231d40b	mistralai[patch]: async integration tests (#16214 )	8 months ago
Eugene Zapolsky	6b9e3ed9e9	google-vertexai[minor]: added safety_settings property to gemini wrapper (#15344 ) Description: Gemini model has quite annoying default safety_settings settings. In addition, current VertexAI class doesn't provide a property to override such settings. So, this PR aims to - add safety_settings property to VertexAI - fix issue with incorrect LLM output parsing when LLM responds with appropriate 'blocked' response - fix issue with incorrect parsing LLM output when Gemini API blocks prompt itself as inappropriate - add safety_settings related tests I'm not enough familiar with langchain code base and guidelines. So, any comments and/or suggestions are very welcome. Issue: it will likely fix #14841 --------- Co-authored-by: Erick Friis <erick@langchain.dev>	8 months ago
Eugene Yurtsev	ecd4f0a7ec	core[patch]: testing add chat model for unit-tests (#16209 ) This PR adds a fake chat model for testing purposes. Used in this PR: https://github.com/langchain-ai/langchain/pull/16172	8 months ago
SN	7d444724d7	Add revision identifier to run_on_dataset (#16167 ) Allow specifying revision identifier for better project versioning	8 months ago
Eugene Yurtsev	5d8c147332	docs: Document and test PydanticOutputFunctionsParser (#15759 ) This PR adds documentation and testing to `PydanticOutputFunctionsParser(OutputFunctionsParser)`.	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
Nuno Campos	ca014d5b04	Update readme (#16160 ) <!-- 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
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: ![image](https://github.com/langchain-ai/langchain/assets/60742358/540e274a-debc-4564-9027-046b91424df3) 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
Bagatur	679a3ae933	openai[patch]: clarify azure error (#16157 )	8 months ago
Bagatur	7ad9eba8f4	core[patch]: Release 0.1.12 (#16161 )	8 months ago
Leonid Kuligin	58f0ba306b	changed default params for gemini (#16044 ) Replace this entire comment with: - Description: changed default values for Vertex LLMs (to be handled on the SDK's side)	8 months ago
Bagatur	5c73fd5bba	core[patch]: support old core namespaces (#16155 )	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
Erick Friis	11327e6b64	google-vertexai[patch]: typing, release 0.0.2 (#16153 )	8 months ago
Leonid Ganeline	2709d3e5f2	langchain[patch]: updated imports for `langchain.callbacks` (#16060 ) Updated imports from 'langchain` to `core` where it is possible --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	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
Leonid Ganeline	49aff3ea5b	langchain[patch]: updated `agents` imports (#16061 ) Updated imports into `langchain` to `core` where it is possible --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	8 months ago
Leonid Ganeline	60b1bd02d7	langchain[patch]: updated imports for `output_parsers` (#16059 ) Updated imports from `langchain` to `core` where it is possible	8 months ago
Leonid Ganeline	9e9ad9b0e9	langchain[patch]: updated `retrievers` imports (#16062 ) Updated imports into `langchain` to `core` where it is possible --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	8 months ago
Leonid Ganeline	d350be959d	langchain[patch]: updated `chains` imports (#16064 ) Updated imports into `langchain` to `core` where it is possible --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	8 months ago
Fei Wang	d0e101e4e0	community[patch]: fix ollama astream (#16070 ) Update ollama.py	8 months ago
ChengZi	8597484195	langchain[patch]: support more comparators in Milvus self-querying retriever (#16076 ) - Description: Support IN and LIKE comparators in Milvus self-querying retriever, based on [Boolean Expression Rules](https://milvus.io/docs/boolean.md) - Issue: No - Dependencies: No - Twitter handle: No Signed-off-by: ChengZi <chen.zhang@zilliz.com>	8 months ago
Kapil Sachdeva	f406dc3872	docs: in RunnableRetry, correct the example snippet that uses with_retry method on Runnable (#16108 ) The example code snippet for with_retry is using incorrect argument names. This PR fixes that	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
Erick Friis	06fe2f4fb0	partners: add license field (#16117 ) - bumps package post versions for packages without current unreleased updates - will bump package version in release prs associated with packages that do have changes (mistral, vertex)	8 months ago
Erick Friis	ce10fe0c2f	mistralai[patch]: release 0.0.3 (#16116 ) embeddings	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
David	c323742f4f	mistralai[minor]: Add embeddings (#15282 ) - Description: Adds MistralAIEmbeddings class for embeddings, using the new official API. - Dependencies: mistralai - Tag maintainer: @efriis, @hwchase17 - Twitter handle: @LMS_David_RS Create `integrations/text_embedding/mistralai.ipynb`: an example notebook for MistralAIEmbeddings class Modify `embeddings/__init__.py`: Import the class Create `embeddings/mistralai.py`: The embedding class Create `integration_tests/embeddings/test_mistralai.py`: The test file. --------- Co-authored-by: Erick Friis <erick@langchain.dev>	8 months ago
Leonid Kuligin	4df14a61fc	google-vertexai[minor]: add function calling on VertexAI (#15822 ) Replace this entire comment with: - Description: Description: added support for tools on VertexAI - Issue: #15073 - Twitter handle: lkuligin --------- Co-authored-by: Erick Friis <erick@langchain.dev>	8 months ago
Bagatur	8840a8cc95	docs: tool-use use case (#15783 ) Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	8 months ago
Bagatur	3d34347a85	langchain[patch]: bump core dep to 0.1.9 (#16104 )	8 months ago
Bagatur	62a2e9ee19	langchain[patch]: Release 0.1.1 (#16103 )	8 months ago
Bagatur	076593382a	core[patch]: Release 0.1.11 (#16100 )	8 months ago
Bagatur	c5656a4905	core[patch]: pass exceptions to fallbacks (#16048 )	8 months ago
Nuno Campos	770f57196e	Add unit test for overridden lc_namespace (#16093 )	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
Bagatur	697a6f2c80	langchain[patch]: fix requests lint (#16049 )	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
Christophe Bornet	15c2b4a47e	community[minor]: Add AstraDB self query retriever (#15738 ) - Description: this change adds a self-query retriever for AstraDB - Twitter handle: cbornet_	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 ![image](https://github.com/langchain-ai/langchain/assets/17451563/d14715d9-9701-4ee3-b44b-89fffea62389) ## 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
Bagatur	bccb07f93e	core[patch]: simple prompt pretty printing (#15968 )	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: ![chrome_yZQ7BF2GTj](https://github.com/langchain-ai/langchain/assets/93204286/43a9a4d4-70fd-41c4-8978-b6240ff63ffa) 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
Harrison Chase	1afac77439	stop making copies of inputs (#15926 )	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
Bagatur	c697c89ca4	docs: add agent prompt creation examples (#15957 )	8 months ago
Erick Friis	69533c8628	multiple[patch]: .post releases and pyproject metadata (#15962 )	8 months ago
Erick Friis	95020637bc	openai[patch]: 0.0.2.post1, urls (#15961 )	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
enfeng	13b90232c1	langchain-google-genai[patch]: Add support for end_point and transport parameters to the Gemini API (#15532 ) Add support for end_point and transport parameters to the Gemini API --------- Co-authored-by: yangenfeng <yangenfeng@xiaoniangao.com> Co-authored-by: Erick Friis <erick@langchain.dev>	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
Tal	eb9b334a6b	Enable customizing the output parser of `OpenAIFunctionsAgent` (#15827 ) - Description: This PR defines the output parser of OpenAIFunctionsAgent as an attribute, enabling customization and subclassing of the parser logic. - Issue: Subclassing is currently impossible as the `OpenAIFunctionsAgentOutputParser` class is hard coded into the `plan` and `aplan` methods - Dependencies: None <!-- Thank you for contributing to LangChain! Please title your PR "<package>: <description>", where <package> is whichever of langchain, community, core, experimental, etc. is being modified. Replace this entire comment with: - Description: a description of the change, - Issue: the issue # it fixes if applicable, - Dependencies: any dependencies required for this change, - Twitter handle: we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` from the root of the package you've modified to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://python.langchain.com/docs/contributing/ If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. --> --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	8 months ago
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
JanHorcicka	f454e95461	langchain: fix OutputParserException (#15914 ) (#15916 ) Description: Fixes OutputParserException thrown by the output_parser when 'query' is 'Null'. Replace this entire comment with: - Description: Current implentation of output_parser throws OutputParserException if the response from the LLM contains `query: null`. This unfortunately happens for my use case. And since there is no way to modify the prompt used in SelfQueryRetriever, then we have to fix it here, so it doesn't crash. - Issue: https://github.com/langchain-ai/langchain/issues/15914 Didn't run tests. `make test` is not working. There is no `test` rule in the `Makefile`. Co-authored-by: Jan Horcicka <jhorcick@amazon.com>	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
Nuno Campos	112208baa5	Passthrough configurable primitive values as tracer metadata (#15915 ) <!-- 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
William FH	129552e3d6	Rm deprecated (#15920 ) Remove the usage of deprecated methods in the test runner.	8 months ago
Nuno Campos	438beb6c94	Pass config specs through ensemble retriever (#15917 ) <!-- Thank you for contributing to LangChain! Please title your PR "<package>: <description>", where <package> is whichever of langchain, community, core, experimental, etc. is being modified. Replace this entire comment with: - Description: a description of the change, - Issue: the issue # it fixes if applicable, - Dependencies: any dependencies required for this change, - Twitter handle: we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` from the root of the package you've modified to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://python.langchain.com/docs/contributing/ If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. --> --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	8 months ago
Erick Friis	ebb6ad4f7a	mistralai[patch]: release 0.0.2 (#15912 )	8 months ago
Erick Friis	437cebc955	core[patch]: release 0.1.10 (#15911 )	8 months ago
Harrison Chase	80d41a8da3	add old serializable mapping (#15906 )	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
Eugene Yurtsev	a06db53c37	Add unit tests to test openai tools agent (#15843 ) This PR adds unit testing to test openai tools agent.	8 months ago
Bagatur	79124fd71d	experimental[patch]: Release 0.0.49 (#15823 )	8 months ago
Harrison Chase	20abe24819	experimental[minor]: Add semantic chunker (#15799 )	8 months ago
Eugene Yurtsev	feb41c5e28	langchain[patch]: Improve stream_log with AgentExecutor and Runnable Agent (#15792 ) This PR fixes an issue where AgentExecutor with RunnableAgent does not allow users to see individual llm tokens if streaming=True is not set explicitly on the underlying chat model. The majority of this PR is testing code: 1. Create a test chat model that makes it easier to test streaming and supports AIMessages that include function invocation information. 2. Tests for the chat model 3. Tests for RunnableAgent (previously untested) 4. Tests for openai agent (previously untested)	8 months ago
Erick Friis	85a4594ed7	community[patch]: more deprecations (#15782 )	8 months ago
Erick Friis	33dccf0f66	core[patch]: release 0.1.9 (#15794 )	8 months ago
Erick Friis	0c95f3a981	mistralai[patch]: warn on stop token, fix on_llm_new_token (#15787 ) Fixes #15269 Addresses with warning. MistralAI API doesn't support stop token yet. --------- Co-authored-by: Niels Garve <info@nielsgarve.com>	8 months ago
Erick Friis	323941a90a	mistralai[patch]: persist async client (#15786 )	8 months ago
NuODaniel	70b6315b23	community[patch]: fix qianfan chat stream calling caused exception (#13800 ) - Description: `QianfanChatEndpoint` extends `BaseChatModel` as a super class, which has a default stream implement might concat the MessageChunk with `__add__`. When call stream(), a ValueError for duplicated key will be raise. - Issues: * #13546 * #13548 * merge two single test file related to qianfan. - Dependencies: no - Tag maintainer: --------- Co-authored-by: root <liujun45@baidu.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	8 months ago
Erick Friis	656e87beb9	core[patch]: add alternative_import to deprecated (#15781 )	8 months ago
Erick Friis	04a5a37e92	robocorp[patch]: fix readme, release 0.0.1.post1 (#15777 )	8 months ago
Erick Friis	91ec9da534	openai[patch]: unit test load (#15624 )	8 months ago
Erick Friis	7be72e1103	openai[patch], docs: readme (#15773 )	8 months ago
Bagatur	ee5bd986de	community[patch]: update oai deprecation message (#15681 ) addresses #15674	8 months ago
Erick Friis	7562f70c95	robocorp[minor]: Add robocorp action server toolkit (#15766 ) Co-authored-by: Rihards Gravis <rihards@gravis.lv> Co-authored-by: Mikko Korpela <mikko@robocorp.com>	8 months ago
Erick Friis	4ed3d17c47	community[patch]: release 0.0.11 (#15760 )	8 months ago
Bagatur	da395f3182	experimental[patch]: loosen core max version (#15763 )	8 months ago
William FH	04caf07dee	Make packages optional (#15727 ) So we don't have to instruct people to modify the Dockerfile every time they delete the packages directory. See: https://stackoverflow.com/questions/70096208/dockerfile-copy-folder-if-it-exists-conditional-copy/70096420#70096420 Tested on a new repo	8 months ago
Eugene Yurtsev	3a8ad90509	langchain(patch): Fix output type for pydantic output parser (#15714 ) This PR fixes the output type for the pydantic output parser. Fix for: https://github.com/langchain-ai/langserve/issues/301	8 months ago
Erick Friis	95a2c92e26	experimental[patch]: minimum version bump (#15724 ) - experimental: minimum version bump - actually 0.1.5 - actually 0.1.7	8 months ago
Erick Friis	6c9b7c2cec	experimental: minimum version bump (#15722 ) experimental relies on `from langchain_core.runnables.config import run_in_executor` which was introduced in core 0.1.5. Updated pyproject dependency as well as minimum version test.	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
Eugene Yurtsev	b508fcce65	core(minor): Add a way to print out system information for debugging purposes. (#15718 ) To use: ```bash python -m langchain_core.sys_info ```	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
Bagatur	4c47f39fcb	community[patch]: Release 0.0.10 (#15678 )	8 months ago
Bagatur	60f925d678	core[patch]: Release 0.1.8 (#15677 )	8 months ago
Nuno Campos	7ce4cd0709	Do not issue beta or deprecation warnings on internal calls (#15641 )	8 months ago
Nuno Campos	ef22559f1f	Populate streamed_output for all runs handled by atransform_stream_with_config (#15599 ) This means that users of astream_log() now get streamed output of virtually all requested runs, whereas before the only streamed output would be for the root run and raw llm runs <!-- 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
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	b1fa726377	docs: langchain-openai (#15513 ) Updates docs and cookbooks to import ChatOpenAI, OpenAI, and OpenAI Embeddings from `langchain_openai` There are likely more --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	8 months ago
Bagatur	14c5c15958	experimental[patch]: Release 0.0.48 (#15483 )	8 months ago
Erick Friis	d136925c49	community[patch]: fix deprecation warnings on openai subclasses (#15621 )	8 months ago
Bagatur	4ac61670b2	infra: fix langchain openai test dep (#15620 )	8 months ago

... 2 3 4 5 6 ...

2736 Commits (db6af2139592b0f21e72c6221bb445767e1a0c7d)