langchain

Commit Graph

Author	SHA1	Message	Date
Erick Friis	4050d6ea2b	huggingface: remove text-generation dep (#22543 )	3 months ago
Erick Friis	a6fc74f379	ai21: fix core version (#22544 )	3 months ago
Asaf Joseph Gardin	75cba742e5	ai21: fix ai21 unittests (#22526 ) Co-authored-by: Asaf Gardin <asafg@ai21.com> Co-authored-by: Erick Friis <erick@langchain.dev>	3 months ago
Erick Friis	58192d617f	community: fix huggingface deprecations (#22522 )	3 months ago
Jacob Lee	1e748a6d40	docs[patch]: Adds links to deprecations page (#22514 ) @baskaryan	3 months ago
William FH	91fed3ace7	[Docs] Structured output Keywords (#22511 )	3 months ago
Christophe Bornet	8ba868d3b0	core[patch]: Add similarity_score_threshold to VectorStore search types (#22477 )	3 months ago
Eugene Yurtsev	9120cf5df2	core[patch]: Deduplicate of callback handlers in merge_configs (#22478 ) This PR adds deduplication of callback handlers in merge_configs. Fix for this issue: https://github.com/langchain-ai/langchain/issues/22227 The issue appears when the code is: 1) running python >=3.11 2) invokes a runnable from within a runnable 3) binds the callbacks to the child runnable from the parent runnable using with_config In this case, the same callbacks end up appearing twice: (1) the first time from with_config, (2) the second time with langchain automatically propagating them on behalf of the user. Prior to this PR this will emit duplicate events: ```python @tool async def get_items(question: str, callbacks: Callbacks): # <--- Accept callbacks """Ask question""" template = ChatPromptTemplate.from_messages( [ ( "human", "'{question}" ) ] ) chain = template \| chat_model.with_config( { "callbacks": callbacks, # <-- Propagate callbacks } ) return await chain.ainvoke({"question": question}) ``` Prior to this PR this will work work correctly (no duplicate events): ```python @tool async def get_items(question: str, callbacks: Callbacks): # <--- Accept callbacks """Ask question""" template = ChatPromptTemplate.from_messages( [ ( "human", "'{question}" ) ] ) chain = template \| chat_model return await chain.ainvoke({"question": question}, {"callbacks": callbacks}) ``` This will also work (as long as the user is using python >= 3.11) -- as langchain will automatically propagate callbacks ```python @tool async def get_items(question: str,): """Ask question""" template = ChatPromptTemplate.from_messages( [ ( "human", "'{question}" ) ] ) chain = template \| chat_model return await chain.ainvoke({"question": question}) ```	3 months ago
Jacob Lee	64dbc52cae	docs[patch]: Update quickstart tutorial (#22504 ) Mentions LCEL more, hopefully flags it to more people as a simple entrypoint @baskaryan @hwchase17	3 months ago
Ofer Mendelevitch	ad502e8d50	community[minor]: Vectara Integration Update - Streaming, FCS, Chat, updates to documentation and example notebooks (#21334 ) Thank you for contributing to LangChain! Description: update to the Vectara / Langchain integration to integrate new Vectara capabilities: - Full RAG implemented as a Runnable with as_rag() - Vectara chat supported with as_chat() - Both support streaming response - Updated documentation and example notebook to reflect all the changes - Updated Vectara templates Twitter handle: ofermend Add tests and docs: no new tests or docs, but updated both existing tests and existing docs	3 months ago
Bagatur	cb183a9bf1	docs: update anthropic chat model (#22483 ) Related to #22296 And update anthropic to accept base_url	3 months ago
Erick Friis	d700ce8545	robocorp: typo (#22509 )	3 months ago
Erick Friis	39fd44579a	robocorp: release 0.0.9.post1 (#22507 )	3 months ago
Erick Friis	339e3b7f55	ai21: release 0.1.6 (#22508 )	3 months ago
ccurme	3c53cea760	together, upstage: bump minimum langchain-openai version (#22505 )	3 months ago
Erick Friis	c438b5b78e	docs: fix api ref link generation (#22438 ) Co-authored-by: Bagatur <baskaryan@gmail.com>	3 months ago
Bagatur	efcb04f84b	mongodb[patch]: Release 0.1.6 (#22501 )	3 months ago
Bagatur	222b1ba112	groq[patch]: Release 0.1.5 (#22500 )	3 months ago
Bagatur	f021be510e	milvus[patch]: Release 0.1.1 (#22499 )	3 months ago
Bagatur	64d68c17cd	upstage[patch]: Release 0.1.6 (#22498 )	3 months ago
Bagatur	48fba40fce	experimental[patch]: Release 0.0.60 (#22497 )	3 months ago
Bagatur	e60f88ccdd	community[patch]: Release 0.2.2 (#22496 )	3 months ago
Bagatur	85aa218564	langchain[patch]: Release 0.2.2 (#22495 )	3 months ago
Bagatur	8e86080def	mistralai[patch]: Release 0.1.8 (#22494 )	3 months ago
Bagatur	e850de2422	huggingface[patch]: release 0.0.2 (#22493 )	3 months ago
Jacob Lee	593de8a913	docs[patch]: Add robots.txt and root sitemap (#22492 ) CC @efriis @baskaryan	3 months ago
Bagatur	99a3cad258	text-splitters[patch]: Release 0.2.1 (#22490 )	3 months ago
Bagatur	161b02a8be	core[patch]: Release 0.2.4 (#22489 )	3 months ago
Ragul Kachiappan	50258a7dda	docs: Update chroma docs link for collection reference (#22472 ) 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: - Description: Updated dead link referencing chroma docs in Chroma notebook under vectorstores	3 months ago
nareshnagpal06	9b45374118	docs: Added Semantic Cache Example with BedrockChat using Bedrock Embedding… (#22190 ) …s and Opensearch Semantic Cache Thank you for contributing to LangChain! - [ ] 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" - [ ] 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! - [ ] 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. - [ ] 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. --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	3 months ago
Joydeep Banik Roy	3796672c67	community, milvus, pinecone, qdrant, mongo: Broadcast operation failure while using simsimd beyond v3.7.7 (#22271 ) - [ ] Packages affected: - community: fix `cosine_similarity` to support simsimd beyond 3.7.7 - partners/milvus: fix `cosine_similarity` to support simsimd beyond 3.7.7 - partners/mongodb: fix `cosine_similarity` to support simsimd beyond 3.7.7 - partners/pinecone: fix `cosine_similarity` to support simsimd beyond 3.7.7 - partners/qdrant: fix `cosine_similarity` to support simsimd beyond 3.7.7 - [ ] Broadcast operation failure while using simsimd beyond v3.7.7: - Description: I was using simsimd 4.3.1 and the unsupported operand type issue popped up. When I checked out the repo and ran the tests, they failed as well (have attached a screenshot for that). Looks like it is a variant of https://github.com/langchain-ai/langchain/issues/18022 . Prior to 3.7.7, simd.cdist returned an ndarray but now it returns simsimd.DistancesTensor which is ineligible for a broadcast operation with numpy. With this change, it also remove the need to explicitly cast `Z` to numpy array - Issue: #19905 - Dependencies: No - Twitter handle: https://x.com/GetzJoydeep <img width="1622" alt="Screenshot 2024-05-29 at 2 50 00 PM" src="https://github.com/langchain-ai/langchain/assets/31132555/fb27b383-a9ae-4a6f-b355-6d503b72db56"> - [ ] Considerations: 1. I started with community but since similar changes were there in Milvus, MongoDB, Pinecone, and QDrant so I modified their files as well. If touching multiple packages in one PR is not the norm, then I can remove them from this PR and raise separate ones 2. I have run and verified that the tests work. Since, only MongoDB had tests, I ran theirs and verified it works as well. Screenshots attached : <img width="1573" alt="Screenshot 2024-05-29 at 2 52 13 PM" src="https://github.com/langchain-ai/langchain/assets/31132555/ce87d1ea-19b6-4900-9384-61fbc1a30de9"> <img width="1614" alt="Screenshot 2024-05-29 at 3 33 51 PM" src="https://github.com/langchain-ai/langchain/assets/31132555/6ce1d679-db4c-4291-8453-01028ab2dca5"> I have added a test for simsimd. I feel it may not go well with the CI/CD setup as installing simsimd is not a dependency requirement. I have just imported simsimd to ensure simsimd cosine similarity is invoked. However, its not a good approach. Suggestions are welcome and I can make the required changes on the PR. Please provide guidance on the same as I am new to the community. --------- Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	3 months ago
KyrianC	03178ee74f	community[minor]: Add tools calls to `ChatEdenAI` (#22320 ) ### Description Add tools implementation to `ChatEdenAI`: - `bind_tools()` - `with_structured_output()` ### Documentation Updated `docs/docs/integrations/chat/edenai.ipynb` ### Notes We don´t support stream with tools as of yet. If stream is called with tools we directly yield the whole message from `generate` (implemented the same way as Anthropic did).	3 months ago
pranavvuppala	9d4350e69a	docs : Update docstrings for OpenAI base.py (#22221 ) - [x] PR title: Update docstrings for OpenAI base.py -Description: Updated the docstring of few OpenAI functions for a better understanding of the function. - Issue: #21983 --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	3 months ago
Anindyadeep	7a197539aa	communty[patch]: Native RAG Support in Prem AI langchain (#22238 ) This PR adds native RAG support in langchain premai package. The same has been added in the docs too.	3 months ago
Rahul Triptahi	77ad857934	community[minor]: Enable retrieval api calls in PebbloRetrievalQA (#21958 ) Description: Enable app discovery and Prompt/Response apis in PebbloSafeRetrieval Documentation: NA Unit test: N/A --------- Signed-off-by: Rahul Tripathi <rauhl.psit.ec@gmail.com> Co-authored-by: Rahul Tripathi <rauhl.psit.ec@gmail.com>	3 months ago
liugz18	8fd231086e	experimental[patch]: Fix graph_transformers llms #21482 (#22417 ) Fix AttributeError on calling LLMGraphTransformer.convert_to_graph_documents #21482 since raw_schema is always a str @baskaryan	3 months ago
ccurme	6db25b4e31	core[patch]: bump langsmith (#22476 ) Noticing errors logged in some situations when tracing with Langsmith: ```python from langchain_core.pydantic_v1 import BaseModel from langchain_anthropic import ChatAnthropic class AnswerWithJustification(BaseModel): """An answer to the user question along with justification for the answer.""" answer: str justification: str llm = ChatAnthropic(model="claude-3-haiku-20240307") structured_llm = llm.with_structured_output(AnswerWithJustification) list(structured_llm.stream("What weighs more a pound of bricks or a pound of feathers")) ``` ``` Error in LangChainTracer.on_chain_end callback: AttributeError("'NoneType' object has no attribute 'append'") [AnswerWithJustification(answer='A pound of bricks and a pound of feathers weigh the same amount.', justification='This is because a pound is a unit of mass, not volume. By definition, a pound of any material, whether bricks or feathers, will weigh the same - one pound. The physical size or volume of the materials does not matter when measuring by mass. So a pound of bricks and a pound of feathers both weigh exactly one pound.')] ```	3 months ago
Bagatur	17c127531a	community[patch]: deprecate all HF classes (#22444 )	3 months ago
Nuno Campos	58b118544e	Use immutable sequence type for batch/batch_as_completed types (#22433 ) Thank you for contributing to LangChain! - [ ] 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" - [ ] 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! - [ ] 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. - [ ] 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
Christophe Bornet	9a8fe58ebe	community[minor]: Improve Cassandra VectorStore as_retriever (#22465 ) The Vectorstore's API `as_retriever` doesn't expose explicitly the parameters `search_type` and `search_kwargs` and so these are not well documented. This PR improves `as_retriever` for the Cassandra VectorStore by making these parameters explicit. NB: An alternative would have been to modify `as_retriever` in `Vectorstore`. But there's probably a good reason these were not exposed in the first place ? Is it because implementations may decide to not support them and have fixed values when creating the VectorStoreRetriever ?	3 months ago
Christophe Bornet	23bba18f92	core[patch]: Fix VectorStore's as_retriever mutating tags param (#22470 ) The current VectorStore `as_retriever` implementation mutates the `tags` param when it's passed in kwargs. This fix ensures that a copy is done.	3 months ago
Michal Gregor	98b2e7b195	huggingface[patch]: Support for HuggingFacePipeline in ChatHuggingFace. (#22194 ) - Description: Added support for using HuggingFacePipeline in ChatHuggingFace (previously it was only usable with API endpoints, probably by oversight). - Issue: #19997 - Dependencies: none - Twitter handle: none --------- Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	3 months ago
Fahreddin Özcan	0061ded002	community[patch]: Upstash Vector Store Namespace Support (#22251 ) This PR introduces namespace support for Upstash Vector Store, which would allow users to partition their data in the vector index. --------- Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	3 months ago
Isaac Francisco	25cf1a74d5	docs: rag tutorial small fixes (#22450 )	3 months ago
Jacob Lee	b0f014666d	docs[patch]: Adds search keywords for common queries (#22449 ) CC @baskaryan @efriis @ccurme	3 months ago
Guangdong Liu	bc7e32f315	core(patch):fix partial_variables not working with SystemMessagePromptTemplate (#20711 ) - Issue: close #17560 - @baskaryan, @eyurtsev	3 months ago
Martin Kolb	f2dd31b9e8	docs: Fix doc issue for HANA Cloud Vector Engine (#22260 ) - Description: This PR fixes a rendering issue in the docs (Python notebook) of HANA Cloud Vector Engine. - Issue: N/A - Dependencies: no new dependencies added File of the fixed notebook: `docs/docs/integrations/vectorstores/hanavector.ipynb`	3 months ago
Dristy Srivastava	ef3df45d9d	community[minor]: Updating payload for pebblo discover API (#22309 ) Description: Updating response for pebblo discover API. Also updating filed name case type Documentation: N/A Unit tests: N/A	3 months ago
Miroslav	cbd5720011	huggingface[patch]: Skip Login to HuggingFaceHub when token is not set (#22365 )	3 months ago
Stefano Lottini	f78ae1d932	docs: Astra DB vectorstore, add automatic-embedding example (#22350 ) Description: Adding an example showcasing the newly-introduced API-side embedding computation option for the Astra DB vector store	3 months ago

... 2 3 4 5 6 ...

9827 Commits (ada1e5cc64ac583fb86876a4ed68a7e7d3494342) All Branches Search

9827 Commits (ada1e5cc64ac583fb86876a4ed68a7e7d3494342)

All Branches