2466 Commits (f7706637a8844eea02d5f6826d7c86ff7029d524)

Author	SHA1	Message	Date
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:  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