221 Commits (f3601b0aaff4a7e9a0945a4e7bc784e44f84a481)

Author	SHA1	Message	Date
William FH	f3601b0aaf	Community[Patch] Remove docs form bm25 repr (#16110) ... Resolves: https://github.com/langchain-ai/langsmith-sdk/issues/356	8 months ago
Erick Friis	52114bdfac	community[patch]: release 0.0.13 (#16087)	8 months ago
James Briggs	ca288d8f2c	community[patch]: add vector param to index query for pinecone vec store (#16054)	8 months ago
Antonio Morales	476fb328ee	community[patch]: implement adelete from VectorStore in Qdrant (#16005) ... **Description:** Implement `adelete` function from `VectorStore` in `Qdrant` to support other asynchronous flows such as async indexing (`aindex`) which requires `adelete` to be implemented. Since `Qdrant` can be passed an async qdrant client, this can be supported easily. --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	8 months ago
高远	061e63eef2	community[minor]: add vikingdb vecstore (#15155) ... --------- Co-authored-by: gaoyuan <gaoyuan.20001218@bytedance.com>	8 months ago
andrijdavid	d196646811	community[patch]: Refactor OpenAIWhisperParserLocal (#15150) ... This PR addresses an issue in OpenAIWhisperParserLocal where requesting CUDA without availability leads to an AttributeError #15143 Changes: - Refactored Logic for CUDA Availability: The initialization now includes a check for CUDA availability. If CUDA is not available, the code falls back to using the CPU. This ensures seamless operation without manual intervention. - Parameterizing Batch Size and Chunk Size: The batch_size and chunk_size are now configurable parameters, offering greater flexibility and optimization options based on the specific requirements of the use case. --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	8 months ago
Zhichao HAN	5cf06db3b3	community[minor]: add JsonRequestsWrapper tool (#15374) ... **Description:** This new feature enhances the flexibility of pipeline integration, particularly when working with RESTful APIs. ``JsonRequestsWrapper`` allows for the decoding of JSON output, instead of the only option for text output. --------- Co-authored-by: Zhichao HAN <hanzhichao2000@hotmail.com>	8 months ago
chyroc	d334efc848	community[patch]: fix top_p type hint (#15452) ... fix: https://github.com/langchain-ai/langchain/issues/15341 @efriis	8 months ago
Mateusz Szewczyk	251afda549	community[patch]: fix stop (stop_sequences) param on WatsonxLLM (#15541) ... - **Description:** Fix to IBM [watsonx.ai](https://www.ibm.com/products/watsonx-ai) LLM provider (stop (`stop_sequences`) param on watsonxLLM) - **Dependencies:** [ibm-watsonx-ai](https://pypi.org/project/ibm-watsonx-ai/),	8 months ago
Funkeke	7220124368	community[patch]: fix tongyi completion and params error (#15544) ... fix tongyi completion json parse error and prompt's params error --------- Co-authored-by: fangkeke <3339698829@qq.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	8 months ago
盐粒 Yanli	ddf4e7c633	community[minor]: Update pgvecto_rs to use its high level sdk (#15574) ... - **Description:** Update pgvecto_rs to use its high level sdk, - **Issue:** fix #15173	8 months ago
YHW	ce21392a21	community: add a flag that determines whether to load the milvus collection (#15693) ... fix https://github.com/langchain-ai/langchain/issues/15694 --------- Co-authored-by: hyungwookyang <hyungwookyang@worksmobile.com> Co-authored-by: Bagatur <baskaryan@gmail.com>	8 months ago
Mohammad Mohtashim	9e779ca846	community[patch]: Fixing the SlackGetChannel Tool Input Error (#15725) ... Fixed the issue mentioned in #15698 for SlackGetChannel Tool. @baskaryan. --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com> Co-authored-by: Bagatur <baskaryan@gmail.com>	8 months ago
axiangcoding	daa9ccae52	community[patch]: deprecate ErnieBotChat and ErnieEmbeddings classes (#15862) ... - **Description:** add deprecated warning for ErnieBotChat and ErnieEmbeddings. - These two classes **lack maintenance** and do not use the sdk provided by qianfan, which means hard to implement some key feature like streaming. - The alternative `langchain_community.chat_models.QianfanChatEndpoint` and `langchain_community.embeddings.QianfanEmbeddingsEndpoint` can completely replace these two classes, only need to change configuration items. - **Issue:** None, - **Dependencies:** None, - **Twitter handle:** None --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	8 months ago
JaguarDB	b11fd3bedc	community[patch]: jaguar vector store fix integer-element error when joining metadata values (#15939) ... - **Description:** some document loaders add integer-type metadata values which cause error - **Issue:** 15937 - **Dependencies:** none --------- Co-authored-by: JY <jyjy@jaguardb>	8 months ago
Neo Zhao	21e0df937f	community[patch]: fix a bug that mistakenly handle zip iterator in FAISS.from_embeddings (#16020) ... **Description**: `zip` is iterator that will only produce result once, so the previous code will cause the `embeddings` to be an empty list. **Issue**: I could not find a related issue. **Dependencies**: this PR does not introduce or affect dependencies. --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	8 months ago
Leonid Ganeline	fb676d8a9b	community[minor], langchain[minor]: refactor `output_parsers` Rail (#15852) ... Moved Rail parser to `community` package.	8 months ago
Massimiliano Pronesti	e80aab2275	docs(community): update Amadeus toolkit to langchain v0.1 (#15976) ... - **Description:** docs update following the changes introduced in #15879 <!-- Thank you for contributing to LangChain! Please title your PR "<package>: <description>", where <package> is whichever of langchain, community, core, experimental, etc. is being modified. Replace this entire comment with: - **Description:** a description of the change, - **Issue:** the issue # it fixes if applicable, - **Dependencies:** any dependencies required for this change, - **Twitter handle:** we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` from the root of the package you've modified to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://python.langchain.com/docs/contributing/ If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. -->	8 months ago
Ashley Xu	ce7723c1e5	community[minor]: add additional support for `BigQueryVectorSearch` (#15904) ... BigQuery vector search lets you use GoogleSQL to do semantic search, using vector indexes for fast but approximate results, or using brute force for exact results. This PR: 1. Add `metadata[_job_ib]` in Document returned by any similarity search 2. Add `explore_job_stats` to enable users to explore job statistics and better the debuggability 3. Set the minimum row limit for running create vector index.	8 months ago
Mohammed Naqi	8799b028a6	community[minor]: Adding asynchronous function implementation for Doctran (#15941) ... ## Description In this update, I addressed the missing implementation for atransform_document, which is the asynchronous counterpart of transform_document in Doctran. ### Usage Example: ```py # Instantiate DoctranPropertyExtractor with specified properties property_extractor = DoctranPropertyExtractor(properties=properties) # Asynchronously extract properties from a list of documents extracted_document = await property_extractor.atransform_documents( documents, properties=properties ) # Display metadata of the first extracted document print(json.dumps(extracted_document[0].metadata, indent=2)) ``` ## Issue - Pull request #14525 has caused a break in the aforementioned code. Instead of removing an asynchronous implementation of a function, consider implementing a synchronous version alongside it.	8 months ago
Raunak	c0773ab329	community[patch]: Fixed 'coroutine' object is not subscriptable error (#15986) ... - **Description:** Added parenthesis in return statement of aembed_query() funtion to fix 'coroutine' object is not subscriptable error. - **Dependencies:** NA Co-authored-by: H161961 <Raunak.Raunak@Honeywell.com>	8 months ago
Karim Lalani	14244bd7e5	community[minor]: Added document loader for SurrealDB (#15995) ... Added a simple document loader to work with SurrealDB.	8 months ago
Karim Lalani	768e5e33bc	community[minor]: Fix to match SurrealDB 0.3.2 SDK (#15996) ... New version of SurrealDB python sdk was causing the integration to break. This fix addresses that change.	8 months ago
shahrin014	86321a949f	community: Ollama - Parameter structure to follow official documentation (#16035) ... ## Feature - Follow parameter structure as per official documentation - top level parameters (e.g. model, system, template) will be passed as top level parameters - other parameters will be sent in options unless options is provided  ## Tests - Test if top level parameters handled properly - Test if parameters that are not top level parameters are handled as options - Test if options is provided, it will be passed as is	8 months ago
Nir Kopler	0fa06732b7	community: add new gpt-3.5-turbo-1106 finetuned for cost calculation (#16039) ... **Description:** Added the new gpt-3.5-turbo-1106 for **finetuned** cost calculation, **Issue:** no issue found open By the information in OpenAI the pricing is the same as the older model (0613)	8 months ago
Virat Singh	eb6e385dc5	community: Add PolygonAPIWrapper and get_last_quote endpoint (#15971) ... - **Description:** Added a `PolygonAPIWrapper` and an initial `get_last_quote` endpoint, which allows us to get the last price quote for a given `ticker`. Once merged, I can add a Polygon tool in `tools/` for agents to use. - **Twitter handle:** [@virattt](https://twitter.com/virattt) The Polygon.io Stocks API provides REST endpoints that let you query the latest market data from all US stock exchanges.	8 months ago
Erick Friis	74bac7bda1	community[patch]: core min 0.1.9 (#15974)	8 months ago
Erick Friis	845e407e08	community[patch]: release 0.0.12 (#15973)	8 months ago
Jonathan Algar	a74f3a4979	Batch update of alt text and title attributes for images in md/mdx files across repo (#15357) ... **Description:** Batch update of alt text and title attributes for images in `md` & `mdx` files across the repo using [alttexter](https://github.com/jonathanalgar/alttexter)/[alttexter-ghclient](https://github.com/jonathanalgar/alttexter-ghclient) (built using LangChain/LangSmith). **Limitation:** cannot update `ipynb` files because of [this issue](https://github.com/langchain-ai/langchain/pull/15357#issuecomment-1885037250). Can revisit when Docusaurus is bumped to v3. I checked all the generated alt texts and titles and didn't find any technical inaccuracies. That's not to say they're _perfect_, but a lot better than what's there currently. [Deployed](https://langchain-819yf1tbk-langchain.vercel.app/docs/modules/model_io/) image example:  You can see LangSmith traces for all the calls out to the LLM in the PRs merged into this one: * https://github.com/jonathanalgar/langchain/pull/6 * https://github.com/jonathanalgar/langchain/pull/4 * https://github.com/jonathanalgar/langchain/pull/3 I didn't add the following files to the PR as the images already have OK alt texts: * 27dca2d92f/docs/docs/integrations/providers/argilla.mdx (L3) * 27dca2d92f/docs/docs/integrations/providers/apify.mdx (L11) --------- Co-authored-by: github-actions <github-actions@github.com>	8 months ago
Varik Matevosyan	efe6cfafe2	community: Added Lantern as VectorStore (#12951) ... Support [Lantern](https://github.com/lanterndata/lantern) as a new VectorStore type. - Added Lantern as VectorStore. It will support 3 distance functions `l2 squared`, `cosine` and `hamming` and will use `HNSW` index. - Added tests - Added example notebook	8 months ago
Edwin Wenink	9fb09c1c30	community: fix the "page" mode in the AzureAIDocumentIntelligenceParser (bug) (#15958) ... **Description**: the "page" mode in the AzureAIDocumentIntelligenceParser is not accessible due to a wrong membership test. The mode argument can only be a string (also see the assertion in the `__init__`: `assert self.mode in ["single", "page", "object", "markdown"]`, so the check `elif self.mode == ["page"]:` always fails. As a result, effectively the "object" mode is used when selecting the "page" mode, which may lead to errors. The docstring of the `AzureAIDocumentIntelligenceLoader` also ommitted the `mode` parameter alltogether, so I added it. **Issue**: I could not find a related issue (this class is only 3 weeks old anyways) **Dependencies**: this PR does not introduce or affect dependencies. The current demo notebook and examples are not affected because they all use the default markdown mode.	8 months ago
Mahdi Setayesh	eb76f9c9fe	community: Fixing a performance issue with AzureSearch to perform batch embedding (#15594) ... - **Description:** Azure Cognitive Search vector DB store performs slow embedding as it does not utilize the batch embedding functionality. This PR provide a fix to improve the performance of Azure Search class when adding documents to the vector search, - **Issue:** #11313 , - **Dependencies:** any dependencies required for this change, - **Twitter handle:** we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` from the root of the package you've modified to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://python.langchain.com/docs/contributing/ If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. -->	8 months ago
ChengZi	d5808f786c	community: Support milvus partition key. (#15740) ... - **Description:** Milvus's partition key is an important feature. It can support multi-tenancy. We hope to introduce this feature. https://milvus.io/docs/partition_key.md - **Issue:** No - **Dependencies:** No - **Twitter handle:** No --------- Signed-off-by: ChengZi <chen.zhang@zilliz.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	8 months ago
ohbeep	9b3962fc25	community: Add support of "http" URI for Milvus (#12710) (#15683) ... - **Description:** Add support of HTTP URI for Milvus - **Issue:** #12710 - **Dependencies:** N/A,	8 months ago
Raunak	e26e1f8b37	community: Added functions to make async calls to HuggingFaceHub's embedding endpoint in HuggingFaceHubEmbeddings class (#15737) ... **Description:** Added aembed_documents() and aembed_query() async functions in HuggingFaceHubEmbeddings class in langchain_community\embeddings\huggingface_hub.py file. It will support to make async calls to HuggingFaceHub's embedding endpoint and generate embeddings asynchronously. Test Cases: Added test_huggingfacehub_embedding_async_documents() and test_huggingfacehub_embedding_async_query() functions in test_huggingface_hub.py file to test the two async functions created in HuggingFaceHubEmbeddings class. Documentation: Updated huggingfacehub.ipynb with steps to install huggingface_hub package and use HuggingFaceHubEmbeddings. **Dependencies:** None, **Twitter handle:** I do not have a Twitter account --------- Co-authored-by: H161961 <Raunak.Raunak@Honeywell.com>	8 months ago
Christophe Bornet	81d1ba05dc	Add a BaseStore backed by AstraDB (#15812) ... - **Description:** this change adds a `BaseStore` backed by AstraDB - **Twitter handle:** cbornet_	8 months ago
manishsahni2000	74d9fc2f9e	PR community:Removing knn beta content in mongodb atlas vectorstore (#15865) ... <!-- Thank you for contributing to LangChain! Please title your PR "<package>: <description>", where <package> is whichever of langchain, community, core, experimental, etc. is being modified. Replace this entire comment with: - **Description:** a description of the change, - **Issue:** the issue # it fixes if applicable, - **Dependencies:** any dependencies required for this change, - **Twitter handle:** we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` from the root of the package you've modified to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://python.langchain.com/docs/contributing/ If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. -->	8 months ago
shahrin014	bdd90ae2ee	community: Ollama - Pass headers to post request (#15881) ... ## Feature - Set additional headers in constructor - Headers will be sent in post request This feature is useful if deploying Ollama on a cloud service such as hugging face, which requires authentication tokens to be passed in the request header. ## Tests - Test if header is passed - Test if header is not passed	8 months ago
Xin Liu	5efec068c9	feat: Implement `stream` interface (#15875) ... <!-- Thank you for contributing to LangChain! Please title your PR "<package>: <description>", where <package> is whichever of langchain, community, core, experimental, etc. is being modified. Replace this entire comment with: - **Description:** a description of the change, - **Issue:** the issue # it fixes if applicable, - **Dependencies:** any dependencies required for this change, - **Twitter handle:** we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` from the root of the package you've modified to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://python.langchain.com/docs/contributing/ If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. --> Major changes: - Rename `wasm_chat.py` to `llama_edge.py` - Rename the `WasmChatService` class to `ChatService` - Implement the `stream` interface for `ChatService` - Add `test_chat_wasm_service_streaming` in the integration test - Update `llama_edge.ipynb` --------- Signed-off-by: Xin Liu <sam@secondstate.io>	8 months ago
Massimiliano Pronesti	ec4dab0449	feat(community): make Amadeus toolkit LLM-agnostic (#15879) ... - **Description:** `AmadeusToolkit` and `AmadeusClosestAirport` contained a hardcoded call to `ChatOpenAI`. This PR makes it LLM-independent, while guaranteeing backward compatibility. - **Issue:** #15847 - **Dependencies:** None @baskaryan <!-- Thank you for contributing to LangChain! Please title your PR "<package>: <description>", where <package> is whichever of langchain, community, core, experimental, etc. is being modified. Replace this entire comment with: - **Description:** a description of the change, - **Issue:** the issue # it fixes if applicable, - **Dependencies:** any dependencies required for this change, - **Twitter handle:** we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` from the root of the package you've modified to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://python.langchain.com/docs/contributing/ If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. -->	8 months ago
Yacine	782dd44be9	<langchain_community.vectorstores>:<Fix pinecone.py __init__ docsrting instruction> (#15922) ... - **Description:** The pinecone docstring instructs to pass the embedding query text causing the warning below. It should be the embeddings object. warning message: UserWarning: Passing in `embedding` as a Callable is deprecated. Please pass in an Embeddings object instead. - **Issue:** NA - **Dependencies:** None @baskaryan	8 months ago
Erick Friis	623f87c888	community[patch]: pinecone bug (#15905)	8 months ago
axiangcoding	d5aa277b94	community: add collection_properties parameter to Milvus (#15788) ... - **Description:** add collection_properties parameter to Milvus. See [pymilvus set_properties() description](https://milvus.io/api-reference/pymilvus/v2.3.x/Collection/set_properties().md) - **Issue:** None - **Dependencies:** None - **Twitter handle:** None	8 months ago
mogith-pn	9e1ed17bfb	Community : Modified doc strings and example notebook for Clarifai (#15816) ... Community : Modified doc strings and example notebook for Clarifai Description: 1. Modified doc strings inside clarifai vectorstore class and embeddings. 2. Modified notebook examples. --------- Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>	8 months ago
Erick Friis	38523d7c57	together[minor]: add llm (#15853)	8 months ago
Erick Friis	ee708739c3	community[patch]: pinecone v3 support (#15849) ... Info in slack --------- Co-authored-by: Roie Schwaber-Cohen <roie.cohen@gmail.com>	8 months ago
Erick Friis	85a4594ed7	community[patch]: more deprecations (#15782)	8 months ago
NuODaniel	70b6315b23	community[patch]: fix qianfan chat stream calling caused exception (#13800) ... - **Description:** `QianfanChatEndpoint` extends `BaseChatModel` as a super class, which has a default stream implement might concat the MessageChunk with `__add__`. When call stream(), a ValueError for duplicated key will be raise. - **Issues:** * #13546 * #13548 * merge two single test file related to qianfan. - **Dependencies:** no - **Tag maintainer:** --------- Co-authored-by: root <liujun45@baidu.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	8 months ago
Bagatur	ee5bd986de	community[patch]: update oai deprecation message (#15681) ... addresses #15674	8 months ago
Erick Friis	4ed3d17c47	community[patch]: release 0.0.11 (#15760)	8 months ago