7562 Commits (8009be862ee2f3bd6728ce359ae78f9e58709d09)

 

All Branches   

Search

Author	SHA1	Message	Date
Alex Peplowski	70c296ae96	community[patch]: Expose Anthropic Retry Logic (#17069) ... **Description:** Expose Anthropic's retry logic, so that `max_retries` can be configured via langchain. Anthropic's retry logic is implemented in their Python SDK here: https://github.com/anthropics/anthropic-sdk-python?tab=readme-ov-file#retries --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	7 months ago
DanisJiang	de9a6cdf16	experimental[patch]: Enhance protection against arbitrary code execution in PALChain (#17091) ... - **Description:** Block some ways to trigger arbitrary code execution bug in PALChain. --------- Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>	7 months ago
Lyndsey	8562a1e7d4	community[patch]: support query filters for NotionDBLoader (#17217) ... - **Description:** Support filtering databases in the use case where devs do not want to query ALL entries within a DB, - **Issue:** N/A, - **Dependencies:** N/A, - **Twitter handle:** I don't have Twitter but feel free to tag my Github! --------- Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>	7 months ago
volodymyr-memsql	e36bc379f2	community[patch]: Add vector index support to SingleStoreDB VectorStore (#17308) ... This pull request introduces support for various Approximate Nearest Neighbor (ANN) vector index algorithms in the VectorStore class, starting from version 8.5 of SingleStore DB. Leveraging this enhancement enables users to harness the power of vector indexing, significantly boosting search speed, particularly when handling large sets of vectors. --------- Co-authored-by: Volodymyr Tkachuk <vtkachuk-ua@singlestore.com> Co-authored-by: Bagatur <baskaryan@gmail.com>	7 months ago
Kate Silverstein	0bc4a9b3fc	community[minor]: Adds Llamafile as an LLM (#17431) ... * **Description:** Adds a simple LLM implementation for interacting with [llamafile](https://github.com/Mozilla-Ocho/llamafile)-based models. * **Dependencies:** N/A * **Issue:** N/A **Detail** [llamafile](https://github.com/Mozilla-Ocho/llamafile) lets you run LLMs locally from a single file on most computers without installing any dependencies. To use the llamafile LLM implementation, the user needs to: 1. Download a llamafile e.g. https://huggingface.co/jartine/TinyLlama-1.1B-Chat-v1.0-GGUF/resolve/main/TinyLlama-1.1B-Chat-v1.0.Q5_K_M.llamafile?download=true 2. Make the file executable. 3. Run the llamafile in 'server mode'. (All llamafiles come packaged with a lightweight server; by default, the server listens at `http://localhost:8080`.) ```bash wget https://url/of/model.llamafile chmod +x model.llamafile ./model.llamafile --server --nobrowser ``` Now, the user can invoke the LLM via the LangChain client: ```python from langchain_community.llms.llamafile import Llamafile llm = Llamafile() llm.invoke("Tell me a joke.") ```	7 months ago
Rakib Hosen	5ce1827d31	community[patch]: fix import in language parser (#17538) ... - **Description:** Resolving import error in language_parser.py during "from langchain.langchain.text_splitter import Language - **Issue:** the issue #17536 - **Dependencies:** NO - **Twitter handle:** @iRakibHosen --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	7 months ago
Raunak	685d62b032	community[patch]: Added functions in NetworkxEntityGraph class (#17535) ... - **Description:** 1. Added _clear_edges()_ and _get_number_of_nodes()_ functions in NetworkxEntityGraph class. 2. Added the above two function in graph_networkx_qa.ipynb documentation.	7 months ago
Erick Friis	bfaa8c3048	anthropic[patch]: de-beta anthropic messages, release 0.0.2 (#17540)	7 months ago
Erick Friis	a99c667c22	partners: version constraints (#17492) ... Core should be ^0.1 by default Careful about 0.x.y and 0.0.z packages	7 months ago
Erick Friis	d7418acbe1	nomic[patch]: release 0.0.2, dimensionality (#17534) ... - nomic[patch]: release 0.0.2 - x	7 months ago
Bagatur	9e8a3fc4ff	infra: rm @ from pr template (#17507)	7 months ago
shibuiwilliam	c502736841	infra: add test for ensemble retriever to ensure multiple retrievers (#8401) ... Add tests to ensemble retriever to ensure it works with combination of multiple retrievers --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	7 months ago
Qihui Xie	5738143d4b	add mongodb_store (#13801) ... # Add MongoDB storage - **Description:** Add MongoDB Storage as an option for large doc store. Example usage: ```Python # Instantiate the MongodbStore with a MongoDB connection from langchain.storage import MongodbStore mongo_conn_str = "mongodb://localhost:27017/" mongodb_store = MongodbStore(mongo_conn_str, db_name="test-db", collection_name="test-collection") # Set values for keys doc1 = Document(page_content='test1') doc2 = Document(page_content='test2') mongodb_store.mset([("key1", doc1), ("key2", doc2)]) # Get values for keys values = mongodb_store.mget(["key1", "key2"]) # [doc1, doc2] # Iterate over keys for key in mongodb_store.yield_keys(): print(key) # Delete keys mongodb_store.mdelete(["key1", "key2"]) ``` - **Dependencies:** Use `mongomock` for integration test. --------- Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>	7 months ago
Mo Latif	50b48a8e6a	langchain[patch]: Invoke chain prep_inputs and prep_outputs inside try block to catch validation errors (#16644) ... - **Description:** Callback manager can't catch chain input or output validation errors because `prepare_input` and `prepare_output` are not part of the try/raise logic, this PR fixes that logic. - **Issue:** #15954	7 months ago
Christophe Bornet	a8f530bc4d	Add async methods to CacheBackedEmbeddings (#16873) ... Adds async methods to CacheBackedEmbeddings	7 months ago
Bagatur	dd68a8716e	infra: update rtd yaml (#17502)	7 months ago
Bagatur	1aeb52caac	infra: merge in master during api docs build (#17494)	7 months ago
Bagatur	54373fb384	infra: add api docs build GHA (#17493)	7 months ago
Bagatur	50de7a31f0	langchain[patch]: structured output chain nits (#17291)	7 months ago
Nat Noordanus	8a3b74fe1f	community[patch]: Fix pydantic ForwardRef error in BedrockBase (#17416) ... - **Description:** Fixes a type annotation issue in the definition of BedrockBase. This issue was that the annotation for the `config` attribute includes a ForwardRef to `botocore.client.Config` which is only imported when `TYPE_CHECKING`. This can cause pydantic to raise an error like `pydantic.errors.ConfigError: field "config" not yet prepared so type is still a ForwardRef, ...`. - **Issue:** N/A - **Dependencies:** N/A - **Twitter handle:** `@__nat_n__`	7 months ago
Bagatur	2c076bebc9	docs: fix self query redirect (#17490)	7 months ago
Ashley Xu	f746a73e26	Add the BQ job usage tracking from LangChain (#17123) ... - **Description:** Add the BQ job usage tracking from LangChain --------- Co-authored-by: Erick Friis <erick@langchain.dev>	7 months ago
Bagatur	5dca107621	docs: update providers (#17488)	7 months ago
JongRok BAEK	8d6cc90fc5	langchain.core : Use shallow copy for schema manipulation in JsonOutputParser.get_format_instructions (#17162) ... - **Description :** Fix: Use shallow copy for schema manipulation in get_format_instructions Prevents side effects on the original schema object by using a dictionary comprehension for a safer and more controlled manipulation of schema key-value pairs, enhancing code reliability. - **Issue:** #17161 - **Dependencies:** None - **Twitter handle:** None	7 months ago
Rave Harpaz	90f55e6bd1	Documentation/add update documentation for oci (#17473) ... Thank you for contributing to LangChain! Checklist: - **PR title**: docs: add & update docs for Oracle Cloud Infrastructure (OCI) integrations - **Description**: adding and updating documentation for two integrations - OCI Generative AI & OCI Data Science (1) adding integration page for OCI Generative AI embeddings (@baskaryan request, docs/docs/integrations/text_embedding/oci_generative_ai.ipynb) (2) updating integration page for OCI Generative AI llms (docs/docs/integrations/llms/oci_generative_ai.ipynb) (3) adding platform documentation for OCI (@baskaryan request, docs/docs/integrations/platforms/oci.mdx). this combines the integrations of OCI Generative AI & OCI Data Science (4) if possible, requesting to be added to 'Featured Community Providers' so supplying a modified docs/docs/integrations/platforms/index.mdx to reflect the addition - **Issue:** none - **Dependencies:** no new dependencies - **Twitter handle:** --------- Co-authored-by: MING KANG <ming.kang@oracle.com>	7 months ago
Bagatur	b5d3416563	experimental[patch]: Release 0.0.51 (#17484)	7 months ago
Bagatur	de7c4b277c	langchain[patch]: Release 0.1.7 (#17482)	7 months ago
Bagatur	39342d98d6	community[patch]: Release 0.0.20 (#17480)	7 months ago
Bagatur	89b765ec27	core[patch]: Release 0.1.23 (#17479)	7 months ago
Max Jakob	ab3d944667	community[patch]: ElasticsearchStore: preserve user headers (#16830) ... Users can provide an Elasticsearch connection with custom headers. This PR makes sure these headers are preserved when adding the langchain user agent header.	7 months ago
Erick Friis	112e10e933	infra: azure release integration testing secrets (#17476)	7 months ago
Erick Friis	9eb1b56e73	pinecone[patch]: release 0.0.2 (#17477)	7 months ago
Erick Friis	37678471c4	openai[patch]: relax tiktoken constraint, release 0.0.6 (#17472)	7 months ago
Wendy H. Chun	2df7387c91	langchain[patch]: Fix to avoid infinite loop during collapse chain in map reduce (#16253) ... - **Description:** Depending on `token_max` used in `load_summarize_chain`, it could cause an infinite loop when documents cannot collapse under `token_max`. This change would not affect the existing feature, but it also gives an option to users to avoid the situation. - **Issue:** https://github.com/langchain-ai/langchain/issues/16251 - **Dependencies:** None - **Twitter handle:** None --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	7 months ago
wulixuan	5d06797905	community[minor]: integrate chat models with Yuan2.0 (#16575) ... 1. integrate chat models with [`Yuan2.0`](https://github.com/IEIT-Yuan/Yuan-2.0/blob/main/README-EN.md) 2. add a new doc for [Yuan2.0 integration](docs/docs/integrations/llms/yuan2.ipynb) Yuan2.0 is a new generation Fundamental Large Language Model developed by IEIT System. We have published all three models, Yuan 2.0-102B, Yuan 2.0-51B, and Yuan 2.0-2B. --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	7 months ago
Taha Khabouss	15baffc484	langchain[patch]: Ensure that the Elasticsearch Query Translator functions accurately w… (#17044) ... Description: Addresses a problem where the Date type within an Elasticsearch SelfQueryRetriever would encounter difficulties in generating a valid query. Issue: #17042 --------- Co-authored-by: Max Jakob <max.jakob@elastic.co> Co-authored-by: Bagatur <baskaryan@gmail.com>	7 months ago
Erick Friis	e5c76f9dbd	pinecone[patch]: poetry update (#17471)	7 months ago
Erick Friis	10bdf2422c	pinecone[patch]: release 0.0.2rc0, remove simsimd dep (#17469)	7 months ago
Erick Friis	065cde69b1	google-genai[patch]: release 0.0.9, safety settings docs (#17432)	7 months ago
Sergey Kozlov	db6f266d97	core: improve None value processing in merge_dicts() (#17462) ... - **Description:** fix `None` and `0` merging in `merge_dicts()`, add tests. ```python from langchain_core.utils._merge import merge_dicts assert merge_dicts({"a": None}, {"a": 0}) == {"a": 0} ``` --------- Co-authored-by: Sergey Kozlov <sergey.kozlov@ludditelabs.io>	7 months ago
Ian Gregory	e5472b5eb8	Framework for supporting more languages in LanguageParser (#13318) ... ## Description I am submitting this for a school project as part of a team of 5. Other team members are @LeilaChr, @maazh10, @Megabear137, @jelalalamy. This PR also has contributions from community members @Harrolee and @Mario928. Initial context is in the issue we opened (#11229). This pull request adds: - Generic framework for expanding the languages that `LanguageParser` can handle, using the [tree-sitter](https://github.com/tree-sitter/py-tree-sitter#py-tree-sitter) parsing library and existing language-specific parsers written for it - Support for the following additional languages in `LanguageParser`: - C - C++ - C# - Go - Java (contributed by @Mario928 https://github.com/ThatsJustCheesy/langchain/pull/2) - Kotlin - Lua - Perl - Ruby - Rust - Scala - TypeScript (contributed by @Harrolee https://github.com/ThatsJustCheesy/langchain/pull/1) Here is the [design document](https://docs.google.com/document/d/17dB14cKCWAaiTeSeBtxHpoVPGKrsPye8W0o_WClz2kk) if curious, but no need to read it. ## Issues - Closes #11229 - Closes #10996 - Closes #8405 ## Dependencies `tree_sitter` and `tree_sitter_languages` on PyPI. We have tried to add these as optional dependencies. ## Documentation We have updated the list of supported languages, and also added a section to `source_code.ipynb` detailing how to add support for additional languages using our framework. ## Maintainer - @hwchase17 (previously reviewed https://github.com/langchain-ai/langchain/pull/6486) Thanks!! ## Git commits We will gladly squash any/all of our commits (esp merge commits) if necessary. Let us know if this is desirable, or if you will be squash-merging anyway. <!-- 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. --> --------- Co-authored-by: Maaz Hashmi <mhashmi373@gmail.com> Co-authored-by: LeilaChr <87657694+LeilaChr@users.noreply.github.com> Co-authored-by: Jeremy La <jeremylai511@gmail.com> Co-authored-by: Megabear137 <zubair.alnoor27@gmail.com> Co-authored-by: Lee Harrold <lhharrold@sep.com> Co-authored-by: Mario928 <88029051+Mario928@users.noreply.github.com> Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	7 months ago
merlin-quix	729c6d6827	docs: add use case for managing chat messages via Apache Kafka (#16771) ... Adding a new notebook that demonstrates how to use LangChain's standard chat features while passing the chat messages back and forth via Apache Kafka. This goal is to simulate an architecture where the chat front end and the LLM are running as separate services that need to communicate with one another over an internal nework. It's an alternative to typical pattern of requesting a reponse from the model via a REST API (there's more info on why you would want to do this at the end of the notebook). NOTE: Assuming "uses cases" is the right place for this but feel free to propose another location. --------- Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	7 months ago
Bagatur	3925071dd6	langchain[patch], templates[patch]: fix multi query retriever, web re… (#17434) ... …search retriever Fixes #17352	7 months ago
Bagatur	c0ce93236a	experimental[patch]: fix zero-shot pandas agent (#17442)	7 months ago
Abhishek Jain	37e1275f9e	community[patch]: Fixed the 'aembed' method of 'CohereEmbeddings'. (#16497) ... **Description:** - The existing code was trying to find a `.embeddings` property on the `Coroutine` returned by calling `cohere.async_client.embed`. - Instead, the `.embeddings` property is present on the value returned by the `Coroutine`. - Also, it seems that the original cohere client expects a value of `max_retries` to not be `None`. Hence, setting the default value of `max_retries` to `3`. --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	7 months ago
Sridhar Ramaswamy	9f1cbbc6ed	community[minor]: Add pebblo safe document loader (#16862) ... - **Description:** Pebblo opensource project enables developers to safely load data to their Gen AI apps. It identifies semantic topics and entities found in the loaded data and summarizes them in a developer-friendly report. - **Dependencies:** none - **Twitter handle:** srics @hwchase17	7 months ago
Preetam D'Souza	0834457f28	docs: Fix broken link in summarization use-case (#16554) ... - **Description:** Fix broken link to `StuffDocumentsChain` - **Issue:** N/A - **Dependencies:** None - **Twitter handle:** [@preetamdsouza](https://twitter.com/preetamdsouza)	7 months ago
Sheil Naik	d70a5bbf15	docs: Fix broken link in LLMs index.mdx (#16557) ... - **Description:** The [LLMs](https://python.langchain.com/docs/modules/model_io/llms/) page has a broken link. This fixes the link. - **Issue:** N/A - **Dependencies:** N/A - **Twitter handle:** @sheilnaik	7 months ago
mhavey	1bbb64d956	community[minor], langchian[minor]: Add Neptune Rdf graph and chain (#16650) ... **Description**: This PR adds a chain for Amazon Neptune graph database RDF format. It complements the existing Neptune Cypher chain. The PR also includes a Neptune RDF graph class to connect to, introspect, and query a Neptune RDF graph database from the chain. A sample notebook is provided under docs that demonstrates the overall effect: invoking the chain to make natural language queries against Neptune using an LLM. **Issue**: This is a new feature **Dependencies**: The RDF graph class depends on the AWS boto3 library if using IAM authentication to connect to the Neptune database. --------- Co-authored-by: Piyush Jain <piyushjain@duck.com> Co-authored-by: Bagatur <baskaryan@gmail.com>	7 months ago
Michael Feil	e1cfd0f3e7	community[patch]: infinity embeddings update incorrect default url (#16759) ... The default url has always been incorrect (7797 instead 7997). Here is a update to the correct url.	7 months ago