langchain

Commit Graph

Author	SHA1	Message	Date
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
Bagatur	81810cec2e	langchain[minor]: Release 0.1.0 (#15619 )	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	1bc6b19ea7	openai[patch]: v0.0.2 (#15618 )	8 months ago
Bagatur	46446a100d	core[patch]: deprecate v1 tracer (#15608 )	8 months ago
Bagatur	dbb582d227	infra: community bump min core version (#15617 )	8 months ago
Bagatur	1e4b8f0453	community[patch]: Release 0.0.9 (#15615 )	8 months ago
Erick Friis	7f8baa030b	openai: core version, rc1 (#15614 )	8 months ago
Erick Friis	5ac3a06378	google-vertexai: release 0.0.1 (#15613 )	8 months ago
Bagatur	96b47e18e0	core[patch]: Release 0.1.7 (#15610 )	8 months ago
Erick Friis	b257c7d0ea	google-vertexai, openai: release candidate version (#15611 )	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
Leonid Kuligin	f73bf4ee54	google-vertexai: added langchain_google_vertexai package (#15218 ) added langchain_google_vertexai package --------- Co-authored-by: Erick Friis <erick@langchain.dev>	8 months ago
Bagatur	e1fc4d5b95	core[patch]: add beta decorator (#15589 )	8 months ago
Bagatur	68eb3053e7	langchain[patch]: deprecate old agent classes and methods (#15558 )	8 months ago
Harrison Chase	9b9449750c	update chain docs (#15495 ) Co-authored-by: Bagatur <baskaryan@gmail.com>	8 months ago
Bagatur	00dfbd2a99	core[minor], langchain[minor]: deprecate old Chain and LLM methods (#15499 )	8 months ago
chyroc	f12b5c1222	Feat: support Milvus more params (#15447 ) fix https://github.com/langchain-ai/langchain/issues/15442	8 months ago
Bagatur	f5e4f0b30b	langchain[minor]: add warnings when importing integrations (#15505 ) Should be imported from community directly	8 months ago
Eugene Yurtsev	bf0b3cc0b5	core[patch]: Further restrict recursive URL loader (#15559 ) Includes code from this PR: https://github.com/langchain-ai/langchain/compare/HEAD...m0kr4n3:security/fix_ssrf with additional fixes Unit tests cover new test cases	8 months ago
Bagatur	817b84de9e	core[patch]: Release 0.1.6 (#15547 )	8 months ago
Bagatur	b2f15738dd	core[patch], langchain[patch], community[patch]: Revert #15326 (#15546 )	8 months ago
Bagatur	6e90b7a91b	langchain[patch]: bump community >=0.0.8,<0.1 (#15492 )	8 months ago
Bagatur	8b7d6531a5	langchain[patch]: Release 0.0.354 (#15482 )	8 months ago
Bagatur	0b579dc623	infra: update community test min reqs (#15490 )	8 months ago
Bagatur	266db0efc8	community[patch]: bump core version >=0.1.5,<0.2 (#15488 )	8 months ago
Bagatur	a2324ee533	community[patch]: Release 0.0.8 (#15481 )	8 months ago
Bagatur	54b58c03db	infra: add minimum deps pre release check (#15485 )	8 months ago
Bagatur	b317ad2472	core[patch]: Release 0.1.5 (#15480 )	8 months ago
Bagatur	baeac236b6	langchain[patch], experimental[patch]: update utilities imports (#15438 )	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
Nolan	6c4b5a4eff	Add option to preserve headers in MarkdownHeaderTextSplitter (#14433 ) - Description: `MarkdownHeaderTextSplitter` currently strips header lines from chunked content. Many applications require these header lines are preserved. This adds an optional parameter to preserve those headers in the chunked content. - Issue: #2836 (relevant) - Dependencies: - - Tag maintainer: @baskaryan - Twitter handle: @finnless Unit tests and new examples in notebook included. cc @rlancemartin --------- 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
Leonid Ganeline	2bbee894bb	fixed a dependency duplicate (#15444 ) BaseModel is derived twice. Left only one.	8 months ago
William FH	65afc13b8b	[Improvement] Evals: Add git info (#15446 )	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
Li-Lun Lin	cda68d717c	core[patch]: update LanguageModelInput from List to Sequence (#14405 ) Co-authored-by: Erick Friis <erick@langchain.dev>	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
amaleki2	413a56b8f1	adding vectorstore_kwarg attribute to search_similarity function (#14604 ) - Description: the ability to add all extra parameter of vectorstore and using them SemanticSimilarityExampleSelector. - Issue: #14583 - Dependencies: no dependensies - Tag maintainer: - Twitter handle: @AmirMalekiz --------- Co-authored-by: Amir Maleki <amaleki@fb.com> 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
Antonio Pisani	d4a98e4e04	core: update json output parser (#15079 ) - Description: changed json.py to handle additional cases of partial json string to be parsed, basically by dropping the last character in the string until a valid json string is found or the string is empty. Also added additional test cases. - Issue: function parse_partial_json could not parse cases where the key is present but the value is not. --------- Co-authored-by: Nuno Campos <nuno@langchain.dev>	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
Bagatur	93e924ec96	langchain[patch], docs: update agent toolkit imports (#15434 )	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
Bob Lin	e57e50b213	Remove unused `_get_python_repl` (#15389 ) This part of the code can also be safely cleaned up.	8 months ago
Dariusz Kajtoch	15b6c049d4	core:adds tests for partial_variables (#15427 ) Description: Added small tests to test partial_variables in PromptTemplate. It was missing.	8 months ago
suhas-kotaki	73a628de9a	added fix for key error: doc_id (#15428 ) <!-- 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
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
Harrison Chase	a33d92306c	add get prompts method (#15425 )	8 months ago
Nuno Campos	6810b4b0bc	Use tz-aware utc datetimes in tracer (#15187 ) <!-- 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
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
Nuno Campos	9cbf14dec2	Fetch runnable config from context var inside runnable lambda and runnable generator (#15334 ) - easier to write custom logic/loops with automatic tracing - if you don't want to streaming support write a regular function and pass to RunnableLambda - if you do want streaming write a generator and pass it to RunnableGenerator ```py import json from typing import AsyncIterator from langchain_core.messages import BaseMessage, FunctionMessage, HumanMessage from langchain_core.agents import AgentAction, AgentFinish from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder from langchain_core.runnables import Runnable, RunnableGenerator, RunnablePassthrough from langchain_core.tools import BaseTool from langchain.agents.output_parsers import OpenAIFunctionsAgentOutputParser from langchain.chat_models import ChatOpenAI from langchain.tools.render import format_tool_to_openai_function def _get_tavily(): from langchain.tools.tavily_search import TavilySearchResults from langchain.utilities.tavily_search import TavilySearchAPIWrapper tavily_search = TavilySearchAPIWrapper() return TavilySearchResults(api_wrapper=tavily_search) async def _agent_executor_generator( input: AsyncIterator[list[BaseMessage]], *, max_iterations: int = 10, tools: dict[str, BaseTool], agent: Runnable[list[BaseMessage], BaseMessage], parser: Runnable[BaseMessage, AgentAction \| AgentFinish], ) -> AsyncIterator[BaseMessage]: messages = [m async for mm in input for m in mm] for _ in range(max_iterations): next_message = await agent.ainvoke(messages) yield next_message messages.append(next_message) parsed = await parser.ainvoke(next_message) if isinstance(parsed, AgentAction): result = await tools[parsed.tool].ainvoke(parsed.tool_input) next_message = FunctionMessage(name=parsed.tool, content=json.dumps(result)) yield next_message messages.append(next_message) elif isinstance(parsed, AgentFinish): return def get_agent_executor(tools: list[BaseTool], system_message: str): llm = ChatOpenAI(model="gpt-4-1106-preview", temperature=0, streaming=True) prompt = ChatPromptTemplate.from_messages( [ ("system", system_message), MessagesPlaceholder(variable_name="messages"), ] ) llm_with_tools = llm.bind( functions=[format_tool_to_openai_function(t) for t in tools] ) agent = {"messages": RunnablePassthrough()} \| prompt \| llm_with_tools parser = OpenAIFunctionsAgentOutputParser() executor = RunnableGenerator(_agent_executor_generator) return executor.bind( tools={tool.name for tool in tools}, agent=agent, parser=parser ) agent = get_agent_executor([_get_tavily()], "You are a very nice agent!") async def main(): async for message in agent.astream( [HumanMessage(content="whats the weather in sf tomorrow?")] ): print(message) if __name__ == "__main__": import asyncio asyncio.run(main()) ``` results in this trace https://smith.langchain.com/public/fa17f05d-9724-4d08-8fa1-750f8fcd051b/r	8 months ago
Bagatur	8e0d5813c2	langchain[patch], experimental[patch]: replace langchain.schema imports (#15410 ) Import from core instead. Ran: ```bash git grep -l 'from langchain.schema\.output_parser' \| xargs -L 1 sed -i '' "s/from\ langchain\.schema\.output_parser/from\ langchain_core.output_parsers/g" git grep -l 'from langchain.schema\.messages' \| xargs -L 1 sed -i '' "s/from\ langchain\.schema\.messages/from\ langchain_core.messages/g" git grep -l 'from langchain.schema\.document' \| xargs -L 1 sed -i '' "s/from\ langchain\.schema\.document/from\ langchain_core.documents/g" git grep -l 'from langchain.schema\.runnable' \| xargs -L 1 sed -i '' "s/from\ langchain\.schema\.runnable/from\ langchain_core.runnables/g" git grep -l 'from langchain.schema\.vectorstore' \| xargs -L 1 sed -i '' "s/from\ langchain\.schema\.vectorstore/from\ langchain_core.vectorstores/g" git grep -l 'from langchain.schema\.language_model' \| xargs -L 1 sed -i '' "s/from\ langchain\.schema\.language_model/from\ langchain_core.language_models/g" git grep -l 'from langchain.schema\.embeddings' \| xargs -L 1 sed -i '' "s/from\ langchain\.schema\.embeddings/from\ langchain_core.embeddings/g" git grep -l 'from langchain.schema\.storage' \| xargs -L 1 sed -i '' "s/from\ langchain\.schema\.storage/from\ langchain_core.stores/g" git checkout master libs/langchain/tests/unit_tests/schema/ make format cd libs/experimental make format cd ../langchain make format ```	8 months ago
Ankush Gola	f50dba12ff	Calculate trace_id and dotted_order client side (#15351 ) <!-- 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
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
Lucca Zenóbio	3bd0a15506	Fix for openai multi tools input format. (#14653 ) Sometimes, the tool_schema is like: ` {'action_name': 'search_items', 'action': {'term': 'pizza'}}` sometimes, specially with gpt3.5 it comes like: `{'action_name': 'search_items', 'term': 'pizza'}` and it fails. This PR is a way to make it work in both scenarios. issues releated: #6624 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: Lucca Zenobio <lucca.zenobio@ifood.com.br>	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
Thomas B	9d8468a576	Enhancement on feature/yaml output parser (#14674 ) Adding to my previously, already merged PR I made some further improvements: * Added documentation to the existing Pydantic Parser notebook, with an example using LCEL and `with_retry()` on `OutputParserException`. * Added an additional output example to the prompt * More lenient parser in terms of LLM output format * Amended unit test FYI @hwchase17 --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	8 months ago
Zeeland	ff10f30149	fix: syntax error in function docs (#14641 ) fix syntax error in function docs	8 months ago
Paresh Chiramel	9be08a1956	Update _retrieve_ref inside json_schema.py to include an isdigit() check (#14745 ) - Description: Update _retrieve_ref inside json_schema.py to include an isdigit() check - Issue: This library is used inside dereference_refs inside langchain_community.agent_toolkits.openapi.spec. When I read in a yaml file which has references for "400", "401" etc; the line "out = out[component]" causes a KeyError. The isdigit() check ensures that if it is an integer like "400" or "401"; it converts it into integer before using it as a key to prevent the error. - Dependencies: No dependencies - Tag maintainer: @baskaryan --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.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
Rajesh Sharma	dfd7b9edda	Update regex in output parser (#15082 ) The regex used to match "Action" and "Action Input" in the output parser has been updated. Previously, the regex did not correctly handle multi-line inputs for "Action Input". The updated code uses the 're.DOTALL' flag to ensure multi-line inputs are correctly captured. <!-- 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
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
chyroc	b6952d41e5	Refactor: use SecretStr for GPTRouter chat-model (#15101 )	8 months ago
Nan LI	f506b4cfd2	community: Integration of New Chat Model Based on ChatGLM3 via ZhipuAI API (#15105 ) - Description: - This PR introduces a significant enhancement to the LangChain project by integrating a new chat model powered by the third-generation base large model, ChatGLM3, via the zhipuai API. - This advanced model supports functionalities like function calls, code interpretation, and intelligent Agent capabilities. - The additions include the chat model itself, comprehensive documentation in the form of Python notebook docs, and thorough testing with both unit and integrated tests. - Dependencies: This update relies on the ZhipuAI package as a key dependency. - Twitter handle: If this PR receives spotlight attention, we would be honored to receive a mention for our integration of the advanced ChatGLM3 model via the ZhipuAI API. Kindly tag us at @kaiwu. To ensure quality and standards, we have performed extensive linting and testing. Commands such as make format, make lint, and make test have been run from the root of the modified package to ensure compliance with LangChain's coding standards. TO DO: Continue refining and enhancing both the unit tests and integrated tests. --------- Co-authored-by: jing <jingguo92@gmail.com> Co-authored-by: hyy1987 <779003812@qq.com> Co-authored-by: jianchuanqi <qijianchuan@hotmail.com> Co-authored-by: lirq <whuclarence@gmail.com> Co-authored-by: whucalrence <81530213+whucalrence@users.noreply.github.com> Co-authored-by: Jing Guo <48378126+JaneCrystall@users.noreply.github.com>	8 months ago
Hin	2cf1e73d12	Feat add volcano embedding (#14693 ) Description: Volcano Ark is an enterprise-grade large-model service platform for developers, providing a full range of functions and services such as model training, inference, evaluation, fine-tuning. You can visit its homepage at https://www.volcengine.com/docs/82379/1099455 for details. This change could help developers use the platform for embedding. Issue: None Dependencies: volcengine Tag maintainer: @baskaryan Twitter handle: @hinnnnnnnnnnnns --------- Co-authored-by: lujingxuansc <lujingxuansc@bytedance.com>	8 months ago
David Křístek	a010f29013	fix: call correct stream method in ollama (#15104 ) Co-authored-by: David Kristek <david@David--MacBook-Pro.local>	8 months ago
Christian Janiake	be578f32be	community:Lazy load wikipedia dump file (#15111 ) Description: the MWDumpLoader implementation currently does not support the lazy_load method, and the files are usually very large. We are proposing refactoring the load function, extracting two private functions with the functionality of loading the dump file and parsing a single page, to reuse the code in the lazy_load implementation.	8 months ago
chyroc	a4ae4bc361	feat: mask api_key for konko (#14010 ) for https://github.com/langchain-ai/langchain/issues/12165	8 months ago
joel-teratis	62d32bd214	fix(minor): added missing kwargs parameter to chroma query function (#14919 ) Description: This PR adds the `kwargs` parameter to six calls in the `chroma.py` package. All functions already were able to receive `kwargs` but they were discarded before. Issue: When passing `kwargs` to functions in the `chroma.py` package they are being ignored. For example: ``` chroma_instance.similarity_search_with_score( query, k=100, include=["metadatas", "documents", "distances", "embeddings"], # this parameter gets ignored ) ``` The `include` parameter does not get passed on to the next function and does not have any effect. Dependencies: None	8 months ago
chyroc	0665a7da19	Docs: add param comment for `tracing_v2_enabled` (#15308 ) Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	8 months ago
NuODaniel	7773943a51	community:qianfan endpoint support init params & remove useless params definietion (#15381 ) - Description: - support custom kwargs in object initialization. For instantance, QPS differs from multiple object(chat/completion/embedding with diverse models), for which global env is not a good choice for configuration. - Issue: no - Dependencies: no - Twitter handle: no @baskaryan PTAL	8 months ago
Nuno Campos	b9636e5c98	Catch type errors in dumps/dumpd (#15336 ) These can happen for edge cases not covered by `default` handler (eg. "strange" keys in dicts) <!-- Thank you for contributing to LangChain! Please title your PR "<package>: <description>", where <package> is whichever of langchain, community, core, experimental, etc. is being modified. Replace this entire comment with: - Description: a description of the change, - Issue: the issue # it fixes if applicable, - Dependencies: any dependencies required for this change, - Twitter handle: we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` from the root of the package you've modified to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://python.langchain.com/docs/contributing/ If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. -->	9 months ago
Nuno Campos	99000c612e	Propagate context vars in all classes/methods (#15329 ) - Any direct usage of ThreadPoolExecutor or asyncio.run_in_executor needs manual handling of context vars <!-- Thank you for contributing to LangChain! Please title your PR "<package>: <description>", where <package> is whichever of langchain, community, core, experimental, etc. is being modified. Replace this entire comment with: - Description: a description of the change, - Issue: the issue # it fixes if applicable, - Dependencies: any dependencies required for this change, - Twitter handle: we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` from the root of the package you've modified to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://python.langchain.com/docs/contributing/ If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. -->	9 months ago
Ankush Gola	7eec8f2487	Delete V1 tracer and refactor tracer tests to core (#15326 )	9 months ago
Nuno Campos	4e4b119614	Fix executor	9 months ago
chyroc	7ce338201c	Patch: improve check openai version (#15301 )	9 months ago
Jon Nolen	27ee61645d	core: Update messages/__init__.py to account for AIMessageChunk which breaks message history runnable. (#15327 ) - Description: fix parse issue for AIMessageChunk when using - Issue: https://github.com/langchain-ai/langchain/issues/14511 - Dependencies: none - Twitter handle: none Taken from this fix: https://github.com/gpt-engineer-org/gpt-engineer/issues/804#issuecomment-1769853850 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>	9 months ago
Nuno Campos	9bb1fbcadf	Lint	9 months ago
Nuno Campos	f7313adf2a	old py compat	9 months ago

... 3 4 5 6 7 ...

2736 Commits (db6af2139592b0f21e72c6221bb445767e1a0c7d)