7061 Commits (226fe645f15980410306f934b5c8966d30685ef6)

 

All Branches   

Search

Author	SHA1	Message	Date
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>	6 months ago
Mu Xian Ming	560bb49c99	docs: redis_chat_message_history.ipynb integration doc (#15789) ... - **Description:** Updated the docs for the memory integration module redis_chat_message_history.ipynb - **Issue:** #15664 - **Dependencies:** N/A Co-authored-by: Mu Xianming <mu.xianming@lmwn.com>	6 months ago
Christophe Bornet	81d1ba05dc	Add a BaseStore backed by AstraDB (#15812) ... - **Description:** this change adds a `BaseStore` backed by AstraDB - **Twitter handle:** cbornet_	6 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. -->	6 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	6 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>	6 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. -->	6 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>	6 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	6 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. -->	6 months ago
William FH	129552e3d6	Rm deprecated (#15920) ... Remove the usage of deprecated methods in the test runner.	6 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>	6 months ago
Erick Friis	ebb6ad4f7a	mistralai[patch]: release 0.0.2 (#15912)	6 months ago
Erick Friis	437cebc955	core[patch]: release 0.1.10 (#15911)	6 months ago
Harrison Chase	80d41a8da3	add old serializable mapping (#15906)	6 months ago
Erick Friis	623f87c888	community[patch]: pinecone bug (#15905)	6 months ago
Eugene Yurtsev	44101b6b0e	Docs[patch]: Update OpenAI tools agent description (#15896) ... Update OpenAI tools agent description.	6 months ago
Eugene Yurtsev	46b7a8d913	Docs[patch]: Update agent quick start for agents (#15892) ... Minor change: 1) Update tool invocation to use .invoke 2) Show hub prompt	6 months ago
Jacob Lee	c11dbefedc	docs[patch]: Fix bad headers in output parser docs (#15778) ... Currently looks like this: <img width="282" alt="Screenshot 2024-01-09 at 1 08 53 PM" src="https://github.com/langchain-ai/langchain/assets/6952323/58f3d368-6588-418e-8502-30d13757cb99"> CC @efriis @baskaryan	6 months ago
Christophe Bornet	c56060bb7d	Add document loader section to Astra provider doc page (#15882) ... See preview: https://langchain-git-fork-cbornet-provider-astra-doc-loader-langchain.vercel.app/docs/integrations/providers/astradb#ocument-loader	6 months ago
xvjixiang	611f18c944	Docs: Fix a typo in elasticsearch vectorstore notebook (#15807) ... <!-- 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. -->	6 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	6 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>	6 months ago
Harrison Chase	97411e998f	[docs] add beautiful soup dependency (#15860)	6 months ago
Daniel	6d299a55c0	docs: Update cohere.mdx, Text embedding had incorrect code snippet (#15840) ... text embedding code snippet was incorrect.	6 months ago
Sagar B Manjunath	e6240fecab	templates: Add NVIDIA Canonical RAG example chain (#15758) ... - **Description:** Adds a RAG template that uses NVIDIA AI playground and embedding models, along with Milvus vector store - **Dependencies:** This template depends on the AI playground service in NVIDIA NGC. API keys with a significant trial compute are available (10k queries at the time of writing). This template also depends on the Milvus Vector store which is publicly available. Note: [A quick link to get a key](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/ai-foundation/models/codellama-13b/api) when you have an NGC account. Generate Key button at the top right of the code window. --------- Co-authored-by: Sagar B Manjunath <sbogadimanju@nvidia.com> Co-authored-by: Erick Friis <erick@langchain.dev>	6 months ago
Erick Friis	38523d7c57	together[minor]: add llm (#15853)	6 months ago
William FH	2895ca87cf	Update Evals Notebook (#15851)	6 months ago
Erick Friis	ee708739c3	community[patch]: pinecone v3 support (#15849) ... Info in slack --------- Co-authored-by: Roie Schwaber-Cohen <roie.cohen@gmail.com>	6 months ago
Bagatur	18411c379c	docs: fix links (#15848)	6 months ago
Lance Martin	9c871f427b	TogetherAI RAG (#15846)	6 months ago
Eugene Yurtsev	a06db53c37	Add unit tests to test openai tools agent (#15843) ... This PR adds unit testing to test openai tools agent.	6 months ago
Harrison Chase	21a1538949	add raga reranker (#15838)	6 months ago
Eugene Yurtsev	45f49ca439	infra: fix issue preview (#15836) ... Fixing the placeholder for the code example. GitHub collapses newlines when trying to use the text area, which is super confusing.	6 months ago
Eugene Yurtsev	c425e6f740	More updates to issue template (#15833) ... More update to issue template	6 months ago
Eugene Yurtsev	65980c22b8	Infra: Fix syntax error in BUG REPORT template (#15831) ... Fix syntax error in issue template	6 months ago
Eugene Yurtsev	e182d630f7	ISSUE_TEMPLATE: Update issue template (#15757) ... Drop some fields, re-order, start directing folks towards QA. --------- Co-authored-by: Erick Friis <erick@langchain.dev>	6 months ago
Bagatur	6432494f9d	infra: explicitly specify py path (#15826)	6 months ago
Bagatur	79124fd71d	experimental[patch]: Release 0.0.49 (#15823)	6 months ago
Harrison Chase	20abe24819	experimental[minor]: Add semantic chunker (#15799)	6 months ago
Harrison Chase	a1d7f2b3e1	add dspy notebook (#15798)	6 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)	6 months ago
Erick Friis	85a4594ed7	community[patch]: more deprecations (#15782)	6 months ago
Erick Friis	33dccf0f66	core[patch]: release 0.1.9 (#15794)	6 months ago
Bagatur	942071bf57	docs: collapse structured use case (#15791)	6 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>	6 months ago
Erick Friis	323941a90a	mistralai[patch]: persist async client (#15786)	6 months ago
Tomaz Bratanic	3e0cd11f51	templates: Add neo4j semantic layer template (#15652) ... Co-authored-by: Tomaz Bratanic <tomazbratanic@Tomazs-MacBook-Pro.local> Co-authored-by: Erick Friis <erick@langchain.dev>	6 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>	6 months ago
Erick Friis	656e87beb9	core[patch]: add alternative_import to deprecated (#15781)	6 months ago