langchain

Commit Graph

Author	SHA1	Message	Date
Eugene Yurtsev	4f1821db3e	core[minor]: Add get_by_ids to vectorstore interface (#23594 ) This PR adds a part of the indexing API proposed in this RFC https://github.com/langchain-ai/langchain/pull/23544/files. It allows rolling out `get_by_ids` which should be uncontroversial to existing vectorstores without introducing new abstractions. The semantics for this method depend on the ability of identifying returned documents using the new optional ID field on documents: https://github.com/langchain-ai/langchain/pull/23411 Alternatives are: 1. Relax the sequence requirement ```python def get_by_ids(self, ids: Iterable[str], /) -> Iterable[Document]: ``` Rejected: - implementations are more likley to start batching with bad defaults - users would need to call list() or we'd need to introduce another convenience method 2. Support more kwargs ```python def get_by_ids(self, ids: Sequence[str], /, **kwargs) -> List[Document]: ... ``` Rejected: - No need for `batch` parameter since IDs is a sequence - Output cannot be customized since `Document` is fixed. (e.g., parameters could be useful to grab extra metadata like the vector that was indexed with the Document or to project a part of the document)	3 months ago
Valentin	bf402f902e	community: Fix LanceDB similarity search bug (#23591 ) Description: LanceDB didn't allow querying the database using similarity score thresholds because the metrics value was missing. This PR simply fixes that bug. Issue: not applicable Dependencies: none Twitter handle: not available --------- Co-authored-by: ccurme <chester.curme@gmail.com>	3 months ago
Bagatur	389a568f9a	standard-tests[patch]: add anthropic format integration test (#23717 )	3 months ago
Rafael Pereira	4b9517db85	Jira: Allow Jira access using only the token (#23708 ) - Description: At the moment the Jira wrapper only accepts the the usage of the Username and Password/Token at the same time. However Jira allows the connection using only is useful for enterprise context. Co-authored-by: rpereira <rafael.pereira@criticalsoftware.com>	3 months ago
Francesco Kruk	7538f3df58	Update jina embedding notebook to show multimodal capability more clearly (#23702 ) After merging the [PR #22594 to include Jina AI multimodal capabilities in the Langchain documentation](https://github.com/langchain-ai/langchain/pull/22594), we updated the notebook to showcase the difference between text and multimodal capabilities more clearly.	3 months ago
Tim Van Wassenhove	24916c6703	community: Register pandas df in duckdb when creating vector_store (#23690 ) - Description: Register pandas df in duckdb when creating vector_store - Issue: Resolves #23308 - Dependencies: None - Twitter handle: @timvw Co-authored-by: Tim Van Wassenhove <tim.van.wassenhove@telenetgroup.be>	3 months ago
Sourav Biswal	b60df8bb4f	Update chatbot.ipynb (#23688 ) DOC: missing parenthesis #23687 Thank you for contributing to LangChain! - [x] PR title: "package: description" - Where "package" is whichever of langchain, community, core, experimental, etc. is being modified. Use "docs: ..." for purely docs changes, "templates: ..." for template changes, "infra: ..." for CI changes. - Example: "community: add foobar LLM" - [x] PR message: *Delete this entire checklist* and replace with - Description: a description of the change - Issue: the issue # it fixes, if applicable - Dependencies: any dependencies required for this change - Twitter handle: if your PR gets announced, and you'd like a mention, we'll gladly shout you out! - [x] Add tests and docs: 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. - [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/ Additional guidelines: - Make sure optional dependencies are imported within a function. - Please do not add dependencies to pyproject.toml files (even optional ones) unless they are required for unit tests. - Most PRs should not touch more than one package. - Changes should be backwards compatible. - If you are adding something to community, do not re-import it in langchain. If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.	3 months ago
Jacob Lee	9604cb833b	ci[patch]: Update people PR CI permissions (#23696 ) CC @agola11	3 months ago
Bagatur	29aa9d6750	groq[patch]: Release 0.1.6 (#23655 )	3 months ago
Bagatur	f2d0c13a15	fireworks[patch]: Release 0.1.4 (#23654 )	3 months ago
Bagatur	9a5e35d1ba	mistralai[patch]: Release 0.1.9 (#23653 )	3 months ago
Bagatur	74321e546d	infra: update release permissions (#23662 )	3 months ago
Mateusz Szewczyk	a78ccb993c	ibm: Add support for Chat Models (#22979 )	3 months ago
Jacob Lee	16c59118eb	docs[patch]: Adds short tracing how-tos and conceptual guide (#23657 ) CC @agola11	3 months ago
Jacob Lee	c0bb26e85b	docs[patch]: Typo fix (#23652 )	3 months ago
Jacob Lee	72175c57bd	docs[patch]: Fix docs bugs in response to feedback (#23649 ) - Update Meta Llama 3 cookbook link - Add prereq section and information on `messages_modifier` to LangGraph migration guide - Update `PydanticToolsParser` explanation and entrypoint in tool calling guide - Add more obvious warning to `OllamaFunctions` - Fix Wikidata tool install flow - Update Bedrock LLM initialization @baskaryan can you add a bit of information on how to authenticate into the `ChatBedrock` and `BedrockLLM` models? I wasn't able to figure it out :(	3 months ago
Bagatur	af2c05e5f3	openai[patch]: Release 0.1.13 (#23651 )	3 months ago
Bagatur	b63c7f10bc	anthropic[patch]: Release 0.1.17 (#23650 )	3 months ago
Bagatur	fc8fd49328	openai, anthropic, ...: with_structured_output to pass in explicit tool choice (#23645 ) ...community, mistralai, groq, fireworks part of #23644	3 months ago
Bagatur	c5f35a72da	docs: vllm pkg nit (#23648 )	3 months ago
Bagatur	81064017a9	docs: azure openai docstring (#23643 ) part of #22296	3 months ago
Bagatur	381aedcc61	docs: standardize azure openai page (#23642 ) part of #22296	3 months ago
Vadym Barda	e8d77002ea	core: add RemoveMessage (#23636 ) This change adds a new message type `RemoveMessage`. This will enable `langgraph` users to manually modify graph state (or have the graph nodes modify the state) to remove messages by `id` Examples: * allow users to delete messages from state by calling ```python graph.update_state(config, values=[RemoveMessage(id=state.values[-1].id)]) ``` * allow nodes to delete messages ```python graph.add_node("delete_messages", lambda state: [RemoveMessage(id=state[-1].id)]) ```	3 months ago
ccurme	8fce8c6771	community: fix extended tests (#23640 )	3 months ago
ccurme	5d93916665	openai[patch]: release 0.1.12 (#23641 )	3 months ago
Jacob Lee	a032583b17	docs[patch]: Update diagrams (#23613 )	3 months ago
ccurme	390ee8d971	standard-tests: add test for structured output (#23631 ) - add test for structured output - fix bug with structured output for Azure - better testing on Groq (break out Mixtral + Llama3 and add xfails where needed)	3 months ago
Eugene Yurtsev	6c1ba9731d	docs: Resurface some methods in API reference and clarify note at top of Reference (#23633 ) This PR modifies the API Reference in the following way: 1. Relist standard methods: invoke, ainvoke, batch, abatch, batch_as_completed, abatch_as_completed, stream, astream, astream_events. These are the main entry points for a lot of runnables, so we'll keep them for each runnable. 2. Relist methods from Runnable Serializable: to_json, configurable_fields, configurable_alternatives. 3. Expand the note in the API reference documentation to explain that additional methods are available.	3 months ago
Brace Sproul	800b0ff3b9	docs[minor]: Hide langserve pages (#23618 )	3 months ago
j pradhan	5f21eab491	community:perplexity[patch]: standardize init args (#21794 ) updated request_timeout default alias value per related docstring. Related to [20085](https://github.com/langchain-ai/langchain/issues/20085) Thank you for contributing to LangChain! --------- Co-authored-by: ccurme <chester.curme@gmail.com>	3 months ago
mackong	11483b0fb8	community[patch]: set tool name for tongyi&qianfan llm (#22889 ) - Description: The name of ToolMessage is default to None, which makes tool message send to LLM likes ```json {"role": "tool", "tool_call_id": "", "content": "{\"time\": \"12:12\"}", "name": null} ``` But the name seems essential for some LLMs like TongYi Qwen. so we need to set the name use agent_action's tool value. - Issue: N/A - Dependencies: N/A	3 months ago
Leonid Ganeline	e4caa41aa9	community: docstrings `toolkits` (#23616 ) Added missed docstrings. Formatted docstrings to the consistent form.	3 months ago
clement.l	19eb82e68b	docs: Fix link in LLMChain tutorial (#23620 ) Co-authored-by: Bagatur <baskaryan@gmail.com>	3 months ago
Bagatur	bd68a38723	docs: update chatmodel.with_structured_output feat in table (#23610 )	3 months ago
ccurme	adf2dc13de	community: fix lint (#23611 )	3 months ago
Bagatur	ef0593db58	docs: tool call run model (#23609 )	3 months ago
Leonid Ganeline	75a44fe951	core: `chat_*` docstrings (#23412 ) Added missed docstrings. Formatted docstrings to the consistent form.	3 months ago
Bagatur	3b1fcb2a65	chroma[patch]: Release 0.1.2 (#23604 )	3 months ago
Eugene Yurtsev	68f348357e	community[patch]: Test InMemoryVectorStore with RWAPI test suite (#23603 ) Add standard test suite to InMemoryVectorStore implementation.	3 months ago
Eugene Yurtsev	da7beb1c38	core[patch]: Add unit test when catching generator exit (#23402 ) This pr adds a unit test for: https://github.com/langchain-ai/langchain/pull/22662 And narrows the scope where the exception is caught.	3 months ago
NG Sai Prasanth	5e6d23f27d	community: Standardise tool import for arxiv & semantic scholar (#23578 ) - Description: Fixing the way users have to import Arxiv and Semantic Scholar - Issue: Changed to use `from langchain_community.tools.arxiv import ArxivQueryRun` instead of `from langchain_community.tools.arxiv.tool import ArxivQueryRun` - Dependencies: None - Twitter handle: Nope	3 months ago
ccurme	d04f657424	langchain[patch]: deprecate ConversationChain (#23504 ) Would like some feedback on how to best incorporate legacy memory objects into `RunnableWithMessageHistory`.	3 months ago
Ayo Ayibiowu	c6f700b7cb	fix(community): allow support for disabling max_tokens args (#21534 ) This PR fixes an issue with not able to use unlimited/infinity tokens from the respective provider for the LiteLLM provider. This is an issue when working in an agent environment that the token usage can drastically increase beyond the initial value set causing unexpected behavior.	3 months ago
WU LIFU	2a0d6788f7	docs[patch]: extraction_examples fix the examples given to the llm (#23393 ) Descriptions: currently in the [doc](https://python.langchain.com/v0.2/docs/how_to/extraction_examples/) it sets "Data" as the LLM's structured output schema, however its examples given to the LLM output's "Person", which causes the LLM to be confused and might occasionally return "Person" as the function to call issue: #23383 Co-authored-by: Lifu Wu <lifu@nextbillion.ai>	3 months ago
Leonid Ganeline	c0fdbaac85	langchain: docstrings in `agents` root (#23561 ) Added missed docstrings. Formatted docstrings to the consistent form.	3 months ago
Leonid Ganeline	b64c4b4750	langchain: docstrings `agents` nested (#23598 ) Added missed docstrings. Formatted docstrings to the consistent form. --------- Co-authored-by: ccurme <chester.curme@gmail.com>	3 months ago
mackong	70834cd741	community[patch]: support convert FunctionMessage for Tongyi (#23569 ) Description: For function call agent with Tongyi, cause the AgentAction will be converted to FunctionMessage by `47f69fe0d8/libs/core/langchain_core/agents.py (L188)` But now Tongyi's convert_message_to_dict doesn't support FunctionMessage `47f69fe0d8/libs/community/langchain_community/chat_models/tongyi.py (L184-L207)` Then next round conversation will be failed by the TypeError exception. This patch adds the support to convert FunctionMessage for Tongyi. Issue: N/A Dependencies: N/A	3 months ago
Bagatur	d45ece0e58	chroma[patch]: loosen py req (#23599 ) currently causes issues if you try adding to a project that supports py<4	3 months ago
Mohammad Mohtashim	4796b7eb15	[Community [HuggingFace]]: Small Fix for ChatHuggingFace. (#22925 ) - Description: A small fix where I moved the `available_endpoints` in order to avoid the token error in the below issue. Also I have added conftest file and updated the `scripy`,`numpy` versions to support newer python versions in poetry files. - Issue: #22804 --------- Co-authored-by: Erick Friis <erick@langchain.dev> Co-authored-by: ccurme <chester.curme@gmail.com>	3 months ago
Jacob Lee	644723adda	docs[patch]: Add search keyword, update contribution guide (#23602 ) CC @vbarda @hinthornw	3 months ago

1 2 3 4 5 ...

10142 Commits (4f1821db3e6019dfbe144375a68c08e6b4f6b7e4) All Branches Search

10142 Commits (4f1821db3e6019dfbe144375a68c08e6b4f6b7e4)

All Branches