langchain

Commit Graph

Author	SHA1	Message	Date
Erick Friis	506f81563f	Update Deps in Experimental (#13029 )	10 months ago
Stefano Lottini	4f4b020582	Add "Astra DB" vector store integration (#12966 ) # Astra DB Vector store integration - Description: This PR adds a `VectorStore` implementation for DataStax Astra DB using its HTTP API - Issue: (no related issue) - Dependencies: A new required dependency is `astrapy` (`>=0.5.3`) which was added to pyptoject.toml, optional, as per guidelines - Tag maintainer: I recently mentioned to @baskaryan this integration was coming - Twitter handle: `@rsprrs` if you want to mention me This PR introduces the `AstraDB` vector store class, extensive integration test coverage, a reworking of the documentation which conflates Cassandra and Astra DB on a single "provider" page and a new, completely reworked vector-store example notebook (common to the Cassandra store, since parts of the flow is shared by the two APIs). I also took care in ensuring docs (and redirects therein) are behaving correctly. All style, linting, typechecks and tests pass as far as the `AstraDB` integration is concerned. I could build the documentation and check it all right (but ran into trouble with the `api_docs_build` makefile target which I could not verify: `Error: Unable to import module 'plan_and_execute.agent_executor' with error: No module named 'langchain_experimental'` was the first of many similar errors) Thank you for a review! Stefano --------- Co-authored-by: Erick Friis <erick@langchain.dev>	10 months ago
Yang, Bo	600caff03c	Add `Memorize` tool (#11722 ) - Description: Add `Memorize` tool - Tag maintainer: @hwchase17 This PR added a new tool `Memorize` so that an agent can use it to fine-tune itself. This tool requires `TrainableLLM` introduced in #11721 DEMO: `6a9003d5db` ![image](https://github.com/langchain-ai/langchain/assets/601530/d6f0cb45-54df-4dcf-b143-f8aefb1e76e3)	10 months ago
Bagatur	cf481c9418	bump exp 38 (#13016 )	10 months ago
Bagatur	57e19989f6	Bagatur/oai assistant (#13010 )	10 months ago
Erick Friis	74134dd7e1	cli pyproject updating (#12945 ) `langchain app add` and `langchain app remove` will now keep the dependencies list updated. --------- Co-authored-by: Nuno Campos <nuno@boringbits.io>	10 months ago
Bagatur	6175dc30aa	bump 331rc2 (#13006 )	10 months ago
Erick Friis	0c81cd923e	oai v1 embeddings (#12969 ) Initial PR to get OpenAIEmbeddings working with the new sdk fyi @rlancemartin Fixes #12943 --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	10 months ago
Bagatur	fdbb45d79e	bump 331rc1 (#12965 )	10 months ago
Bagatur	3bb8030a6e	fix max_tokens (#12964 )	10 months ago
Bagatur	a9002a82b8	bump 331rc0 (#12963 )	10 months ago
Harrison Chase	c27400efeb	Support multimodal messages (#11320 ) Co-authored-by: Bagatur <baskaryan@gmail.com>	10 months ago
Bagatur	4f7dff9d66	Record system fingerprint chat openai (#12960 )	10 months ago
Bagatur	8e0cb2eb84	ChatOpenAI and AzureChatOpenAI openai>=1 compatible (#12948 )	10 months ago
Kacper Łukawski	52d0055a91	Add support of Cohere Embed v3 (#12940 ) Cohere released the new embedding API (Embed v3: https://txt.cohere.com/introducing-embed-v3/) that treats document and query embeddings differently. This PR updated the `CohereEmbeddings` to use them appropriately. It also works with the old models.	10 months ago
Praveen Venkateswaran	8e0dcb37d2	Add SecretStr for Symbl.ai Nebula API (#12896 ) Description: This PR masks API key secrets for the Nebula model from Symbl.ai Issue: #12165 Maintainer: @eyurtsev --------- Co-authored-by: Praveen Venkateswaran <praveen.venkateswaran@ibm.com>	10 months ago
Vinzenz Klass	59d0bd2150	feat: acquire advisory lock before creating extension in pgvector (#12935 ) - Description: Acquire advisory lock before attempting to create extension on postgres server, preventing errors in concurrent executions. - Issue: #12933 - Dependencies: None --------- Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>	10 months ago
Eugene Yurtsev	b376854b26	Fix for anyscale chat model api key (#12938 ) * ChatAnyscale was missing coercion to SecretStr for anyscale api key * The model inherits from ChatOpenAI so it should not force the openai api key to be secret str until openai model has the same changes https://github.com/langchain-ai/langchain/issues/12841	10 months ago
hmasdev	622bf12c2e	fix regex pattern of structured output parser (#12929 ) - Description: fix the regex pattern of [StructuredChatOutputParser](https://github.com/langchain-ai/langchain/blob/master/libs/langchain/langchain/agents/structured_chat/output_parser.py#L18) and add unit tests for the code change. - Issue: #12158 #12922 - Dependencies: None - Tag maintainer: - Twitter handle: @hmdev3 - NOTE: This PR conflicts #7495 . After #7495 is merged, I am going to update PR.	10 months ago
wemysschen	8d7144e6a6	fix baiducloud directory loader import file loader (#12924 ) Issue: fix baiducloud BOS directory loader imports its file loader --------- Co-authored-by: wemysschen <root@icoding-cwx.bcc-szzj.baidu.com>	10 months ago
Kacper Łukawski	621419f71e	Fix normalizing the cosine distance in Qdrant (#12934 ) Qdrant was incorrectly calculating the cosine similarity and returning `0.0` for the best match, instead of `1.0`. Internally Qdrant returns a cosine score from `-1.0` (worst match) to `1.0` (best match), and the current formula reflects it.	10 months ago
Hech	8fe6bcc662	Fix return metadata when searching for DingoDB (#12937 )	10 months ago
Jakub Novák	ada3d2cbd1	Add possibility to pass on_artifacts for a specific conversation (#12687 ) Possibility to pass on_artifacts to a conversation. It can be then achieved by adding this way: ```python result = agent.run( input=message.text, metadata={ "on_artifact": CALLBACK_FUNCTION }, ) ```	10 months ago
Bagatur	53f453f01a	bump 331 (#12932 )	10 months ago
Erick Friis	5000c7308e	cli template gitignores (#12914 ) - ap gitignore - package	10 months ago
Harrison Chase	aba407f774	use keys not items (#12918 )	10 months ago
wemysschen	e14aa37d59	fix bes vector store search (#12828 ) Issue: fix search body in baidu cloud vectorsearch --------- Co-authored-by: wemysschen <root@icoding-cwx.bcc-szzj.baidu.com>	10 months ago
Lance Martin	ea1ab391d4	Open Clip multimodal embeddings (#12754 )	10 months ago
Bagatur	ebee616822	bump 330 (#12853 )	10 months ago
Erick Friis	6c237716c4	Update readmes with new cli install (#12847 ) Old command still works. Just simplifying. Merge after releasing CLI 0.0.15	10 months ago
Erick Friis	7db49d3842	Confirm sys.path includes current dir for app serve (#12851 ) - Make sure sys.path is set properly for langchain app serve - bump	11 months ago
Erick Friis	1bc35f61cb	CLI 0.0.14, Uvicorn update and no more [serve] (#12845 ) Calls uvicorn directly from cli: Reload works if you define app by import string instead of object. (was doing subprocess in order to get reloading) Version bump to 0.0.14 Remove the need for [serve] for simplicity. Readmes are updated in #12847 to avoid cluttering this PR	11 months ago
William FH	18005c6384	Disable trace_on_chain_group auto-tracing (#12807 ) Previously we treated trace_on_chain_group as a command to always start tracing. This is unintuitive (makes the function do 2 things), and makes it harder to toggle tracing	11 months ago
Erick Friis	0da75b9ebd	Autopopulate module name in cli init (#12814 )	11 months ago
William FH	98aff29fbd	Add Dataset Page to printout (#12816 )	11 months ago
Manuel Rech	2e2b9c76d9	Keep also original query - multi_query.py (#12696 ) When you use a MultiQuery it might be useful to use the original query as well as the newly generated ones to maximise the changes to retriever the correct document. I haven't created an issue, it seems a very small and easy thing. --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	11 months ago
Bagatur	658a3a8607	FEAT: Merge TileDB vecstore (#12811 )	11 months ago
Akio Nishimura	c04647bb4e	Correct number of elements in config list in `batch()` and `abatch()` of `BaseLLM` (#12713 ) - Description: Correct number of elements in config list in `batch()` and `abatch()` of `BaseLLM` in case `max_concurrency` is not None. - Issue: #12643 - Twitter handle: @akionux --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	11 months ago
James Braza	88b506b321	Adds missing `urllib.parse` for IDE warning of `PubMedAPIWrapper` (#12808 ) Resolves an IDE (PyCharm 2023.2.3 PE) warning around `urllib.parse.quote`, also enabling CTRL-click	11 months ago
Bagatur	a2bb0dd445	TileDB update import unit tests	11 months ago
Nikos Papailiou	2fdaa1e5fd	Add TileDB vectorstore implementation (#12624 ) - Description: Add [TileDB](https://tiledb.com) vectorstore implementation. TileDB offers ANN search capabilities using the [TileDB-Vector-Search](https://github.com/TileDB-Inc/TileDB-Vector-Search) module. It provides serverless execution of ANN queries and storage of vector indexes both on local disk and cloud object stores (i.e. AWS S3). More details in: - [Why TileDB as a Vector Database](https://tiledb.com/blog/why-tiledb-as-a-vector-database) - [TileDB 101: Vector Search](https://tiledb.com/blog/tiledb-101-vector-search) - Twitter handle: @tiledb	11 months ago
盐粒 Yanli	1b233798a0	feat: Supprt pgvecto.rs as a VectorStore (#12718 ) Supprt [pgvecto.rs](https://github.com/tensorchord/pgvecto.rs) as a new VectorStore type. This introduces a new dependency [pgvecto_rs](https://pypi.org/project/pgvecto_rs/) and upgrade SQLAlchemy to ^2. Relate to https://github.com/tensorchord/pgvecto.rs/issues/11 --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	11 months ago
Daniel Chalef	0cbdba6a9b	zep: VectorStore: Use Native MMR (#12690 ) - refactor to use Zep's native MMR; update example - @baskaryan @eyurtsev	11 months ago
Daniel Chalef	cc3d3920e3	Zep: Summary Search and Example (#12686 ) Zep now has the ability to search over chat history summaries. This PR adds support for doing so. More here: https://blog.getzep.com/zep-v0-17/ @baskaryan @eyurtsev	11 months ago
Bagatur	526313002c	add import tests to all modules (#12806 )	11 months ago
Harrison Chase	6609a6033f	fix vectorstore imports (#12804 ) Co-authored-by: Bagatur <baskaryan@gmail.com>	11 months ago
Nuno Campos	f66a9d2adf	Automatically add configurable key to config_schema if config_specs i… (#12798 ) …s present <!-- Thank you for contributing to LangChain! 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, - Tag maintainer: for a quicker response, tag the relevant maintainer (see below), - 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` to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md 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/extras` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. -->	11 months ago
Praveen Venkateswaran	21eeba075c	enable the device_map parameter in huggingface pipeline (#12731 ) ### Enabling `device_map` in HuggingFacePipeline For multi-gpu settings with large models, the [accelerate](https://huggingface.co/docs/accelerate/usage_guides/big_modeling#using--accelerate) library provides the `device_map` parameter to automatically distribute the model across GPUs / disk. The [Transformers pipeline](`3520e37e86/src/transformers/pipelines/__init__.py (L543)`) enables users to specify `device` (or) `device_map`, and handles cases (with warnings) when both are specified. However, Langchain's HuggingFacePipeline only supports specifying `device` when calling transformers which limits large models and multi-gpu use-cases. Additionally, the [default value](`8bd3ce59cd/libs/langchain/langchain/llms/huggingface_pipeline.py (L72)`) of `device` is initialized to `-1` , which is incompatible with the transformers pipeline when `device_map` is specified. This PR addresses the addition of `device_map` as a parameter , and solves the incompatibility of `device = -1` when `device_map` is also specified. An additional test has been added for this feature. Additionally, some existing tests no longer work since 1. `max_new_tokens` has to be specified under `pipeline_kwargs` and not `model_kwargs` 2. The GPT2 tokenizer raises a `ValueError: Pipeline with tokenizer without pad_token cannot do batching`, since the `tokenizer.pad_token` is `None` ([related issue](https://github.com/huggingface/transformers/issues/19853) on the transformers repo). This PR handles fixing these tests as well. Co-authored-by: Praveen Venkateswaran <praveen.venkateswaran@ibm.com>	11 months ago
Mark Bell	3276aa3e17	__getattr__ should rase AttributeError not ImportError on missing attributes (#12801 ) [The python spec](https://docs.python.org/3/reference/datamodel.html#object.__getattr__) requires that `__getattr__` throw `AttributeError` for missing attributes but there are several places throwing `ImportError` in the current code base. This causes a specific problem with `hasattr` since it calls `__getattr__` then looks only for `AttributeError` exceptions. At present, calling `hasattr` on any of these modules will raise an unexpected exception that most code will not handle as `hasattr` throwing exceptions is not expected. In our case this is triggered by an exception tracker (Airbrake) that attempts to collect the version of all installed modules with code that looks like: `if hasattr(mod, "__version__"):`. With `HEAD` this is causing our exception tracker to fail on all exceptions. I only changed instances of unknown attributes raising `ImportError` and left instances of known attributes raising `ImportError`. It feels a little weird but doesn't seem to break anything.	11 months ago
Illia	71d1a48b66	Use data from all Google search results in SerpApi.com wrapper (#12770 ) - Description: Use all Google search results data in SerpApi.com wrapper instead of the first one only - Tag maintainer: @hwchase17 _P.S. `libs/langchain/tests/integration_tests/utilities/test_serpapi.py` are not executed during the `make test`._	11 months ago

1 2 3 4 5 ...

1714 Commits (506f81563f07f28e27f05d27cc4cf40411c0c01f)