langchain

Commit Graph

Author	SHA1	Message	Date
Erick Friis	89d32ffbbd	community[patch]: release 0.0.27 (#18708 )	7 months ago
Erick Friis	c09b520ce4	core[patch]: release 0.1.30 (#18706 )	7 months ago
Piyush Jain	2b234a4d96	Support for claude v3 models. (#18630 ) Fixes #18513. ## Description This PR attempts to fix the support for Anthropic Claude v3 models in BedrockChat LLM. The changes here has updated the payload to use the `messages` format instead of the formatted text prompt for all models; `messages` API is backwards compatible with all models in Anthropic, so this should not break the experience for any models. ## Notes The PR in the current form does not support the v3 models for the non-chat Bedrock LLM. This means, that with these changes, users won't be able to able to use the v3 models with the Bedrock LLM. I can open a separate PR to tackle this use-case, the intent here was to get this out quickly, so users can start using and test the chat LLM. The Bedrock LLM classes have also grown complex with a lot of conditions to support various providers and models, and is ripe for a refactor to make future changes more palatable. This refactor is likely to take longer, and requires more thorough testing from the community. Credit to PRs [18579](https://github.com/langchain-ai/langchain/pull/18579) and [18548](https://github.com/langchain-ai/langchain/pull/18548) for some of the code here. --------- Co-authored-by: Erick Friis <erick@langchain.dev>	7 months ago
Sam Khano	1b4dcf22f3	community[minor]: Add DocumentDBVectorSearch VectorStore (#17757 ) Description: - Added Amazon DocumentDB Vector Search integration (HNSW index) - Added integration tests - Updated AWS documentation with DocumentDB Vector Search instructions - Added notebook for DocumentDB integration with example usage --------- Co-authored-by: EC2 Default User <ec2-user@ip-172-31-95-226.ec2.internal>	7 months ago
Vittorio Rigamonti	51f3902bc4	community[minor]: Adding support for Infinispan as VectorStore (#17861 ) Description: This integrates Infinispan as a vectorstore. Infinispan is an open-source key-value data grid, it can work as single node as well as distributed. Vector search is supported since release 15.x For more: [Infinispan Home](https://infinispan.org) Integration tests are provided as well as a demo notebook	7 months ago
Max Jakob	cca0167917	elasticsearch[patch], community[patch]: update references, deprecate community classes (#18506 ) Follow up on https://github.com/langchain-ai/langchain/pull/17467. - Update all references to the Elasticsearch classes to use the partners package. - Deprecate community classes. --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	7 months ago
José Luis Di Biase	6041ec3dd1	templates: rag-multi-modal typo, replace serch with search (#18519 ) Thank you for contributing to LangChain! - [x] PR title: "templates: rag-multi-modal typo, replace serch with search " - Description: Two little typos in multi modal templates (replace serch string with search) Signed-off-by: José Luis Di Biase <josx@interorganic.com.ar>	7 months ago
Djordje	12b4a4d860	community[patch]: Opensearch delete method added - indexing supported (#18522 ) - Description: Added delete method for OpenSearchVectorSearch, therefore indexing supported - Issue: No - Dependencies: No - Twitter handle: stkbmf	7 months ago
Erick Friis	687d27567d	openai[patch]: unit test azure init (#18703 )	7 months ago
Christophe Bornet	db8db6faae	community: Implement lazy_load() for PlaywrightURLLoader (#18676 ) Integration tests: `tests/integration_tests/document_loaders/test_url_playwright.py`	7 months ago
Aaron Yi	c092db862e	community[patch]: make metadata and text optional as expected in DocArray (#18678 ) ValidationError: 2 validation errors for DocArrayDoc text Field required [type=missing, input_value={'embedding': [-0.0191128...9, 0.01005221541175212]}, input_type=dict] For further information visit https://errors.pydantic.dev/2.5/v/missing metadata Field required [type=missing, input_value={'embedding': [-0.0191128...9, 0.01005221541175212]}, input_type=dict] For further information visit https://errors.pydantic.dev/2.5/v/missing ``` In the `_get_doc_cls` method, the `DocArrayDoc` class is defined as follows: ```python class DocArrayDoc(BaseDoc): text: Optional[str] embedding: Optional[NdArray] = Field(**embeddings_params) metadata: Optional[dict] ```	7 months ago
Eugene Yurtsev	4c25b49229	community[major]: breaking change in some APIs to force users to opt-in for pickling (#18696 ) This is a PR that adds a dangerous load parameter to force users to opt in to use pickle. This is a PR that's meant to raise user awareness that the pickling module is involved.	7 months ago
Eugene Yurtsev	0e52961562	community[patch]: Patch tdidf retriever (CVE-2024-2057) (#18695 ) This is a patch for `CVE-2024-2057`: https://www.cve.org/CVERecord?id=CVE-2024-2057 This affects users that: * Use the `TFIDFRetriever` * Attempt to de-serialize it from an untrusted source that contains a malicious payload	7 months ago
Leonid Ganeline	81cbf0f2fd	docs: update import paths for callbacks to use langchain_community callbacks where applicable (#18691 ) Refactored imports from `langchain` to `langchain_community` whenever it is applicable	7 months ago
Erick Friis	2619420df1	mongodb[patch]: release 0.1.1 (#18692 )	7 months ago
Leonid Ganeline	fb686333ac	docs: fix `streamlit` provider (#18606 ) There is a wrong python package import. Fixed it.	7 months ago
Christophe Bornet	ea141511d8	core: Move document loader interfaces to core (#17723 ) This is needed to be able to move document loaders to partner packages. --------- Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>	7 months ago
aditya thomas	97de498d39	docs: update to the streaming tutorial notebook in the lcel documentation (#18378 ) Description: Update to the streaming tutorial notebook in the LCEL documentation Issue: Fixed an import and (minor) changes in documentation language Dependencies: None	7 months ago
Guangdong Liu	32db9e74e4	docs: Fix some issues with sparkllm use cases (#17674 )	7 months ago
Christophe Bornet	5985454269	Merge pull request #18539 * Implement lazy_load() for GitLoader	7 months ago
Christophe Bornet	9a6f7e213b	Merge pull request #18423 * Implement lazy_load() for BSHTMLLoader	7 months ago
Christophe Bornet	b3a0c44838	Merge pull request #18673 * Implement lazy_load() for PDFMinerPDFasHTMLLoader and PyMuPDFLoader	7 months ago
Christophe Bornet	68fc0cf909	Merge pull request #18674 * Implement lazy_load() for TextLoader	7 months ago
Christophe Bornet	5b92f962f1	Merge pull request #18671 * Implement lazy_load() for MastodonTootsLoader	7 months ago
Christophe Bornet	15b1770326	Merge pull request #18421 * Implement lazy_load() for AssemblyAIAudioTranscriptLoader	7 months ago
Christophe Bornet	bb284eebe4	Merge pull request #18436 * Implement lazy_load() for ConfluenceLoader	7 months ago
Christophe Bornet	691480f491	Merge pull request #18647 * Implement lazy_load() for UnstructuredBaseLoader	7 months ago
Christophe Bornet	52ac67c5d8	Merge pull request #18654 * Implement lazy_load() for ObsidianLoader	7 months ago
Christophe Bornet	b9c0cf9025	Merge pull request #18656 * Implement lazy_load() for PsychicLoader	7 months ago
Christophe Bornet	aa7ac57b67	community: Implement lazy_load() for TrelloLoader (#18658 ) Covered by `tests/unit_tests/document_loaders/test_trello.py`	7 months ago
Christophe Bornet	302985fea1	community: Implement lazy_load() for SlackDirectoryLoader (#18675 ) Integration tests: `tests/integration_tests/document_loaders/test_slack.py`	7 months ago
Christophe Bornet	ed36f9f604	community: Implement lazy_load() for WhatsAppChatLoader (#18677 ) Integration test: `tests/integration_tests/document_loaders/test_whatsapp_chat.py`	7 months ago
Christophe Bornet	f414f5cdb9	community[minor]: Implement lazy_load() for WikipediaLoader (#18680 ) Integration test: `tests/integration_tests/document_loaders/test_wikipedia.py`	7 months ago
Bagatur	4cbfeeb1c2	community[patch]: Release 0.0.26 (#18683 )	7 months ago
Eugene Yurtsev	b9f3c7a0c9	Use Case: Extraction set temperature to 0, qualify a statement (#18672 ) Minor changes: 1) Set temperature to 0 (important) 2) Better qualify one of the statements with confidence	7 months ago
Eugene Yurtsev	a4a6978224	Docs: Revamp Extraction Use Case (#18588 ) Revamp the extraction use case documentation --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	7 months ago
Christophe Bornet	1100f8de7a	community[minor]: Implement lazy_load() for ArxivLoader (#18664 ) Integration tests: `tests/integration_tests/utilities/test_arxiv.py` and `tests/integration_tests/document_loaders/test_arxiv.py`	7 months ago
Christophe Bornet	2d96803ddd	community[minor]: Implement lazy_load() for OutlookMessageLoader (#18668 ) Integration test: `tests/integration_tests/document_loaders/test_email.py`	7 months ago
Christophe Bornet	ae167fb5b2	community[minor]: Implement lazy_load() for SitemapLoader (#18667 ) Integration tests: `test_sitemap.py` and `test_docusaurus.py`	7 months ago
Christophe Bornet	623dfcc55c	community[minor]: Implement lazy_load() for FacebookChatLoader (#18669 ) Integration test: `tests/integration_tests/document_loaders/test_facebook_chat.py`	7 months ago
Christophe Bornet	20794bb889	community[minor]: Implement lazy_load() for GitbookLoader (#18670 ) Integration test: `tests/integration_tests/document_loaders/test_gitbook.py`	7 months ago
Liang Zhang	81985b31e6	community[patch]: Databricks SerDe uses cloudpickle instead of pickle (#18607 ) - Description: Databricks SerDe uses cloudpickle instead of pickle when serializing a user-defined function transform_input_fn since pickle does not support functions defined in `__main__`, and cloudpickle supports this. - Dependencies: cloudpickle>=2.0.0 Added a unit test.	7 months ago
Erick Friis	f3e28289f6	infra: reorder api docs build steps (#18618 )	7 months ago
Leonid Ganeline	114d64d4a7	docs: `providers` update (#18527 ) Added missed pages. Added links and descriptions. Foratted to the consistent form.	7 months ago
Christophe Bornet	7d6de96186	community[patch]: Implement lazy_load() for CubeSemanticLoader (#18535 ) Covered by `test_cube_semantic.py`	7 months ago
Christophe Bornet	a6b5d45e31	community[patch]: Implement lazy_load() for EverNoteLoader (#18538 ) Covered by `test_evernote_loader.py`	7 months ago
PSV	d7dd3cd248	docs: structured_output (#18608 ) - Description: Fixed some typos and copy errors in the Beta Structured Output docs - Issue: N/A - Dependencies: Docs only - Twitter handle: @psvann Co-authored-by: P.S. Vann <psvann@yahoo.com>	7 months ago
Bagatur	29f1619d61	docs: why lcel nit (#18616 )	7 months ago
Max Jakob	ee7a7954b9	elasticsearch: add `ElasticsearchRetriever` (#18587 ) Implement [Retriever](https://python.langchain.com/docs/modules/data_connection/retrievers/) interface for Elasticsearch. I opted to only expose the `body`, which gives you full flexibility, and none the other 68 arguments of the [search method](https://elasticsearch-py.readthedocs.io/en/v8.12.1/api/elasticsearch.html#elasticsearch.Elasticsearch.search). Added a user agent header for usage tracking in Elastic Cloud. --------- Co-authored-by: Erick Friis <erick@langchain.dev>	7 months ago
Jib	8bc347c5fc	mongodb[patch]: include LLM caches in toplevel library import (#18601 )	7 months ago

... 9 10 11 12 13 ...

8459 Commits (ec7a59c96c5303986f29e513d0eb64541cae359b) All Branches Search

8459 Commits (ec7a59c96c5303986f29e513d0eb64541cae359b)

All Branches