langchain

Commit Graph

Author	SHA1	Message	Date
Sen Lin	eb7f07ae36	community[patch]: fix typo in ValueError message in load_local function (#21818 ) Description: Corrected an error in the `allow_dangerous_deserialization` message within the `load_local` functions	4 months ago
Jorge Piedrahita Ortiz	700b1c7212	community: sambaverse api update (#21816 ) - Description: fix sambaverse integration to make it compatible with sambaverse API update / minor changes in docs	4 months ago
maang-h	9f8d18c028	community[patch]: Fix unintended newline in print statement in exception for BaichuanTextEmbeddings (#21820 ) - Code: langchain_community/embeddings/baichuan.py:82 - Description: When I make an error using 'baichuan embeddings', the printed error message is wrapped (there is actually no need to wrap) ```python # example from langchain_community.embeddings import BaichuanTextEmbeddings # error key BAICHUAN_API_KEY = "sk-xxxxxxxxxxxxx" embeddings = BaichuanTextEmbeddings(baichuan_api_key=BAICHUAN_API_KEY) text_1 = "今天天气不错" query_result = embeddings.embed_query(text_1) ``` ![unintended newline](https://github.com/langchain-ai/langchain/assets/55082429/e1178ce8-62bb-405d-a4af-e3b28eabc158)	4 months ago
Bakar Tavadze	3b5ac44e03	langchain-robocorp[minor]: Enable passing additional headers to the action server. (#21809 ) Actions can optionally receive secrets via request headers. This PR enables this functionality.	4 months ago
Asaf Joseph Gardin	f3289b898c	partners: Revert AI21 Labs docs scan feature (#21699 ) Description: Reverted commit #21614 --------- Co-authored-by: Asaf Gardin <asafg@ai21.com> Co-authored-by: Erick Friis <erick@langchain.dev>	4 months ago
Eugene Yurtsev	8607735b80	langchain[patch],community[patch]: Move unit tests that depend on community to community (#21685 )	4 months ago
Marco Lamina	d0fae6cd54	community: Add token cost for GPT-4o model (#21771 ) Adding [token cost for the new GPT-4o model](https://openai.com/api/pricing/): * Input cost US$5.00 / 1M tokens * Output cost US$15.00 / 1M tokens	4 months ago
Massimiliano Pronesti	0c0db7c5db	feat(community): support semantic hybrid score threshold in Azure AI Search (#21527 ) Support semantic hybrid search with a score threshold -- similar to what we do for similarity search and for hybrid search (#20907).	4 months ago
Bagatur	6416d16d39	anthropic[patch]: Release 0.1.13, tool_choice support (#21773 )	4 months ago
Stefano Lottini	040597e832	community: init signature revision for Cassandra LLM cache classes + small maintenance (#17765 ) This PR improves on the `CassandraCache` and `CassandraSemanticCache` classes, mainly in the constructor signature, and also introduces several minor improvements around these classes. ### Init signature A (sigh) breaking change is tentatively introduced to the constructor. To me, the advantages outweigh the possible discomfort: the new syntax places the DB-connection objects `session` and `keyspace` later in the param list, so that they can be given a default value. This is what enables the pattern of _not_ specifying them, provided one has previously initialized the Cassandra connection through the versatile utility method `cassio.init(...)`. In this way, a much less unwieldy instantiation can be done, such as `CassandraCache()` and `CassandraSemanticCache(embedding=xyz)`, everything else falling back to defaults. A downside is that, compared to the earlier signature, this might turn out to be breaking for those doing positional instantiation. As a way to mitigate this problem, this PR typechecks its first argument trying to detect the legacy usage. (And to make this point less tricky in the future, most arguments are left to be keyword-only). If this is considered too harsh, I'd like guidance on how to further smoothen this transition. Our plan is to make the pattern of optional session/keyspace a standard across all Cassandra classes, so that a repeatable strategy would be ideal. A possibility would be to keep positional arguments for legacy reasons but issue a deprecation warning if any of them is actually used, to later remove them with 0.2 - please advise on this point. ### Other changes - class docstrings: enriched, completely moved to class level, added note on `cassio.init(...)` pattern, added tiny sample usage code. - semantic cache: revised terminology to never mention "distance" (it is in fact a similarity!). Kept the legacy constructor param with a deprecation warning if used. - `llm_caching` notebook: uniform flow with the Cassandra and Astra DB separate cases; better and Cassandra-first description; all imports made explicit and from community where appropriate. - cache integration tests moved to community (incl. the imported tools), env var bugfix for `CASSANDRA_CONTACT_POINTS`. --------- Co-authored-by: Erick Friis <erick@langchain.dev>	4 months ago
Kyle Cassidy	eca8c4bcc6	Standardized openai init params (#21739 ) ## Patch Summary community:openai[patch]: standardize init args ## Details I made changes to the OpenAI Chat API wrapper test in the Langchain open-source repository - File: `libs/community/tests/unit_tests/chat_models/test_openai.py` - Changes: - Updated `max_retries` with Pydantic Field - Updated the corresponding unit test - Related Issues: #20085 - Updated max_retries with Pydantic Field, updated the unit test. --------- Co-authored-by: JuHyung Son <sonju0427@gmail.com>	4 months ago
Ethan Yang	e44b448ec3	community: update openvino doc with streaming support (#21519 ) Co-authored-by: Chester Curme <chester.curme@gmail.com>	4 months ago
ccurme	19e6bf814b	community: fix CI (#21766 )	4 months ago
Mish Ushakov	d77e60a7f4	community: updated Browserbase loader (#21757 ) Thank you for contributing to LangChain! - [x] PR title: "community: updated Browserbase loader" - [x] PR message: Updates the Browserbase loader with more options and improved docs. - [x] Lint and test: Run `make format`, `make lint` and `make test` from the root of the package(s) you've modified. See contribution guidelines for more: https://python.langchain.com/docs/contributing/	4 months ago
Eugene Yurtsev	6ed0aa3239	core[major]: only use function description (#21622 ) Do not prefix function signature --- * Reason for this is that information is already present with tool calling models. * This will save on tokens for those models, and makes it more obvious what the description is! * The @tool can get more parameters to allow a user to re-introduce the the signature if we want	4 months ago
William FH	8498b41cda	Finish agent migration doc (#21731 )	4 months ago
Cheese	0ead09f84d	community: Implement `bind_tools` for ChatTongyi (#20725 ) ## Description Implement `bind_tools` in ChatTongyi. Usage example: ```py from langchain_core.tools import tool from langchain_community.chat_models.tongyi import ChatTongyi @tool def multiply(first_int: int, second_int: int) -> int: """Multiply two integers together.""" return first_int * second_int llm = ChatTongyi(model="qwen-turbo") llm_with_tools = llm.bind_tools([multiply]) msg = llm_with_tools.invoke("What's 5 times forty two") print(msg) ``` Streaming is also supported. ## Dependencies No Dependency is required for this change. --------- Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com> Co-authored-by: Chester Curme <chester.curme@gmail.com>	4 months ago
Bagatur	867adbf27b	docs: add aca-ds (#21746 )	4 months ago
Erick Friis	06110e20b9	pinecone: bump min core version (#21742 )	4 months ago
Erick Friis	bd3e7d50f3	fireworks: bump min core version (#21741 )	4 months ago
Erick Friis	f5c31078d7	airbyte[patch]: airbyte-cdk compatible pydantic versions (#21738 )	4 months ago
Erick Friis	3d33b89fa4	ibm[patch]: release 0.1.7 (#21737 )	4 months ago
Erick Friis	e41d801369	openai[patch]: fix embedding float precision issue (#21736 ) also clean up + comment some of the embedding batching code	4 months ago
JuHyung Son	38c297a025	upstage: Support batch input in embedding request. (#21730 ) Description: upstage embedding now supports batch input.	4 months ago
Harrison Chase	15be439719	Harrison/move flashrank rerank (#21448 ) third party integration, should be in community	4 months ago
Erick Friis	aca98fd150	multiple: releases with relaxed core dep (#21724 )	4 months ago
Bagatur	af284518bc	openai[patch]: Release 0.1.7, bump tiktoken 0.7.0 (#21723 )	4 months ago
William FH	ca768c8353	[Core] Check is async callable (#21714 ) To permit proper coercion of objects like the following: ```python class MyAsyncCallable: async def __call__(self, foo): return await ... class MyAsyncGenerator: async def __call__(self, foo): await ... yield ```	4 months ago
Eugene Yurtsev	5c2cfabec6	core[minor]: Add v2 implementation of astream events (#21638 ) This PR introduces a v2 implementation of astream events that removes intermediate abstractions and fixes some issues with v1 implementation. The v2 implementation significantly reduces relevant code that's associated with the astream events implementation together with overhead. After this PR, the astream events implementation: - Uses an async callback handler - No longer relies on BaseTracer - No longer relies on json patch As a result of this re-write, a number of issues were discovered with the existing implementation. ## Changes in V2 vs. V1 ### on_chat_model_end `output` The outputs associated with `on_chat_model_end` changed depending on whether it was within a chain or not. As a root level runnable the output was: ```python "data": {"output": AIMessageChunk(content="hello world!", id='some id')} ``` As part of a chain the output was: ``` "data": { "output": { "generations": [ [ { "generation_info": None, "message": AIMessageChunk( content="hello world!", id=AnyStr() ), "text": "hello world!", "type": "ChatGenerationChunk", } ] ], "llm_output": None, } }, ``` After this PR, we will always use the simpler representation: ```python "data": {"output": AIMessageChunk(content="hello world!", id='some id')} ``` NOTE Non chat models (i.e., regular LLMs) are still associated with the more verbose format. ### Remove some `_stream` events `on_retriever_stream` and `on_tool_stream` events were removed -- these were not real events, but created as an artifact of implementing on top of astream_log. The same information is already available in the `x_on_end` events. ### Propagating Names Names of runnables have been updated to be more consistent ```python model = GenericFakeChatModel(messages=infinite_cycle).configurable_fields( messages=ConfigurableField( id="messages", name="Messages", description="Messages return by the LLM", ) ) ``` Before: ```python "name": "RunnableConfigurableFields", ``` After: ```python "name": "GenericFakeChatModel", ``` ### on_retriever_end on_retriever_end will always return `output` which is a list of documents (rather than a dict containing a key called "documents") ### Retry events Removed the `on_retry` callback handler. It was incorrectly showing that the failed function being retried has invoked `on_chain_end` https://github.com/langchain-ai/langchain/pull/21638/files#diff-e512e3f84daf23029ebcceb11460f1c82056314653673e450a5831147d8cb84dL1394	4 months ago
Rajendra Kadam	54e003268e	langchain[minor]: Add PebbloRetrievalQA chain with Identity & Semantic Enforcement support (#20641 ) - Description: PebbloRetrievalQA chain introduces identity enforcement using vector-db metadata filtering - Dependencies: None - Issue: None - Documentation: Adding documentation for PebbloRetrievalQA chain in a separate PR(https://github.com/langchain-ai/langchain/pull/20746) - Unit tests: New unit-tests added --------- Co-authored-by: Eugene Yurtsev <eugene@langchain.dev>	4 months ago
Bagatur	241a6e43a5	docs: update structured how to (#21679 )	4 months ago
Jib	f369495fa0	mongodb: [performance] Increase DEFAULT_INSERT_BATCH_SIZE to 100,000 and introduce sizing constraints (#19608 )	4 months ago
Eugene Yurtsev	e69a9bedf8	core[patch]: Update mypy config (#21684 ) Update mypy config to ignore checking deps from numpy and pytest (which are optional in langsmith sdk)	4 months ago
Erick Friis	9973547aef	mongodb: release 0.1.4 (#21678 )	4 months ago
Jib	a97473c846	mongodb[patch]: Make ObjectId JSON-serializable on generation (#21394 )	4 months ago
Eugene Yurtsev	5c64c004cc	core[patch]: Add unit tests with some streaming scenarios (#21668 ) Add unit tests that show differences between sync / async versions when streaming. The inner on_chain_chunk event is missing if mixing sync and async functionality. Likely due to missing tap_output_iter implementation on the sync variant of `_transform_stream_with_config`	4 months ago
Eugene Yurtsev	2ac4d2960c	core[patch]: Add unit test to catch ordering (#21669 ) Add unit test to catch ordering issues	4 months ago
Zhao Blake	972d2071c6	core[patch]: Fix typo in VectorStoreExampleSelector doc-string (#21574 )	4 months ago
Erick Friis	2a984e8e3f	docs: huggingface package (#21645 )	4 months ago
Erick Friis	c77d2f2b06	multiple: core 0.2 nonbreaking dep, check_diff community->langchain dep (#21646 ) 0.2 is not a breaking release for core (but it is for langchain and community) To keep the core+langchain+community packages in sync at 0.2, we will relax deps throughout the ecosystem to tolerate `langchain-core` 0.2	4 months ago
Anush	edd68e4ad4	qdrant: init package (#21146 ) ## Description This PR introduces the new `langchain-qdrant` partner package, intending to deprecate the community package. ## Changes - Moved the Qdrant vector store implementation `/libs/partners/qdrant` with integration tests. - The conditional imports of the client library are now regular with minor implementation improvements. - Added a deprecation warning to `langchain_community.vectorstores.qdrant.Qdrant`. - Replaced references/imports from `langchain_community` with either `langchain_core` or by moving the definitions to the `langchain_qdrant` package itself. - Updated the Qdrant vector store documentation to reflect the changes. ## Testing - `QDRANT_URL` and [`QDRANT_API_KEY`](`583e36bf6b`) env values need to be set to [run integration tests](`d608c93d1f`) in the [cloud](https://cloud.qdrant.tech). - If a Qdrant instance is running at `http://localhost:6333`, the integration tests will use it too. - By default, tests use an [`in-memory`](https://github.com/qdrant/qdrant-client?tab=readme-ov-file#local-mode) instance(Not comprehensive). --------- Co-authored-by: Erick Friis <erick@langchain.dev> Co-authored-by: Erick Friis <erickfriis@gmail.com>	4 months ago
Prashanth Rao	63c3a0e56c	[community][graph]: Update KuzuQAChain and docs (#21218 ) This PR makes some small updates for `KuzuQAChain` for graph QA. - Updated Cypher generation prompt (we now support `WHERE EXISTS`) and generalize it more - Support different LLMs for Cypher generation and QA - Update docs and examples	4 months ago
Tomaz Bratanic	89ff6a3d3b	Add sentiment and confidence levels to diffbotgraphtransformer (#21590 ) Co-authored-by: Erick Friis <erickfriis@gmail.com> Co-authored-by: Erick Friis <erick@langchain.dev>	4 months ago
Erick Friis	9b51ca08bc	huggingface: fix community dep checking (#21628 )	4 months ago
Erick Friis	91a2ea5cd6	chroma, mongodb: fix docstrings (#21629 )	4 months ago
Jofthomas	afd85b60fc	huggingface: init package (#21097 ) First Pr for the langchain_huggingface partner Package - Moved some of the hugging face related class from `community` to the new `partner package` Still needed : - Documentation - Tests - Support for the new apply_chat_template in `ChatHuggingFace` - Confirm choice of class to support for embeddings witht he sentence-transformer team. cc : @efriis --------- Co-authored-by: Cyril Kondratenko <kkn1993@gmail.com> Co-authored-by: Erick Friis <erick@langchain.dev>	4 months ago
Tomaz Bratanic	9fce03e7db	community[patch]: Fix neo4j enhanced schema (#21582 )	4 months ago
Christophe Bornet	66a4da8ad0	community[patch]: Improve Cassandra VectorStore docsctrings (#21620 )	4 months ago
adreo00	40aff1eacc	core[major]: AsyncCallbackManagerForToolRun no longer casts return object to string (#20374 ) - Description: Stops `AsyncCallbackManagerForToolRun` from converting the output to str - Issue: #20372 - Dependencies: None	4 months ago
Eugene Yurtsev	25fbe356b4	community[patch]: upgrade to recent version of mypy (#21616 ) This PR upgrades community to a recent version of mypy. It inserts type: ignore on all existing failures.	4 months ago

1 2 3 4 5 ...

4219 Commits (4ca2149b7001c124c7c6a87d46f0f439b0f3785a)