4616 Commits (386ef1e6549c115eb10898e4526d6529f393679a)

 

All Branches   

Search

Author	SHA1	Message	Date
Harrison Chase	386ef1e654	add agent output parsers (#10790)	1 year ago
Mukit Momin	67c5950df3	Amazon Bedrock Support Streaming (#10393) ... ### Description - Add support for streaming with `Bedrock` LLM and `BedrockChat` Chat Model. - Bedrock as of now supports streaming for the `anthropic.claude-*` and `amazon.titan-*` models only, hence support for those have been built. - Also increased the default `max_token_to_sample` for Bedrock `anthropic` model provider to `256` from `50` to keep in line with the `Anthropic` defaults. - Added examples for streaming responses to the bedrock example notebooks. **_NOTE:_**: This PR fixes the issues mentioned in #9897 and makes that PR redundant.	1 year ago
Bagatur	0749a642f5	Stream refac and vertex streaming (#10470) ... --------- Co-authored-by: Terry Cruz Melo <tcruz@vozy.co> Co-authored-by: Terry Cruz Melo <33166112+TerryCM@users.noreply.github.com>	1 year ago
William FH	f421af8b80	Criteria Parser Improvements (#10824)	1 year ago
Bagatur	095f300bf6	add lcel how to index (#10850)	1 year ago
Bagatur	46aa90062b	bump exp 19 (#10851)	1 year ago
Bagatur	775f3edffd	bump 296 (#10842)	1 year ago
Bagatur	96a9c27116	fix recursive loader (#10752) ... maintain same base url throughout recursion, yield initial page, fixing recursion depth tracking	1 year ago
Nuno Campos	276125a33b	Use shallow copy on runnable locals (#10825) ... - deep copy prevents storing complex objects in locals	1 year ago
DanielZzz	ebe08412ad	fix: chat_models Qianfan not compatiable with SystemMessage (#10642) ... - **Description:** QianfanEndpoint bugs for SystemMessages. When the `SystemMessage` is input as the messages to `chat_models.QianfanEndpoint`. A `TypeError` will be raised. - **Issue:** #10643 - **Dependencies:** - **Tag maintainer:** @baskaryan - **Twitter handle:** no	1 year ago
Massimiliano Pronesti	f0198354d9	fix(embeddings): number of texts in Azure OpenAIEmbeddings batch (#10707) ... This PR addresses the limitation of Azure OpenAI embeddings, which can handle at maximum 16 texts in a batch. This can be solved setting `chunk_size=16`. However, I'd love to have this automated, not to force the user to figure where the issue comes from and how to solve it. Closes #4575. @baskaryan --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	1 year ago
Aashish Saini	7395c28455	corrected spelling (#62) (#10816)	1 year ago
zhanghexian	0abe996409	add clustered vearch in langchain (#10771) ... --------- Co-authored-by: zhanghexian1 <zhanghexian1@jd.com> Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	1 year ago
HeTaoPKU	f505320a73	Add Minimax chat model (#10776) ... resolve the merging issues for https://github.com/langchain-ai/langchain/pull/6757 --------- Co-authored-by: 何涛 <taohe@bytedance.com>	1 year ago
Anar	c656a6b966	LLMRails (#10796) ... ### LLMRails Integration This PR provides integration with LLMRails. Implemented here are: langchain/vectorstore/llm_rails.py tests/integration_tests/vectorstores/test_llm_rails.py docs/extras/integrations/vectorstores/llm-rails.ipynb --------- Co-authored-by: Anar Aliyev <aaliyev@mgmt.cloudnet.services> Co-authored-by: Bagatur <baskaryan@gmail.com>	1 year ago
mateai	900dbd1cbe	Substring support for similarity_search_with_score (#10746) ... **Description:** Possible to filter with substrings in similarity_search_with_score, for example: filter={'user_id': {'substring': 'user'}} --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	1 year ago
Ansil M B	740eafe41d	Updated return parameter of YouTubeSearchTool (#10743) ... **Description:** changed return parameter of YouTubeSearchTool 1. changed the returning links of youtube videos by adding prefix "https://www.youtube.com", now this will return the exact links to the videos 2. updated the returning type from 'string' to 'list', which will be more suited for further processings **Issue:** Fixes #10742 **Dependencies:** None <!-- Thank you for contributing to LangChain! Replace this entire comment with: - **Description:** changed return parameter of YouTubeSearchTool - **Issue:** the issue # it fixes (if applicable), - **Dependencies:** None - **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/hwchase17/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: Harrison Chase <hw.chase.17@gmail.com>	1 year ago
Harrison Chase	1dae3c383e	Harrison/add submodule to docs (#10803)	1 year ago
Henry (Hezheng) Yin	c15bbaac31	misc: add gpt-3.5-turbo-instruct to model_token_mapping (#10808) ... A one-line fix to get`max_tokens=-1` working `OpenAI` class for `gpt-3.5-turbo-instruct` model. Closes https://github.com/langchain-ai/langchain/issues/10806	1 year ago
Harrison Chase	5d0493f652	improve notebook (#10804)	1 year ago
Harrison Chase	d2bee34d4c	Harrison/add vald (#10807) ... Co-authored-by: datelier <57349093+datelier@users.noreply.github.com>	1 year ago
Jacob Lee	bbc3fe259b	Start RunnableBranch callback tags with 1 instead of 0 (#10755) ... Changes to match `RunnableSequences` @eyurtsev	1 year ago
Ziyang Liu	931b292126	Add support for HTTP PUT in the open api agent prompt (#10763) ... **Description:** This PR adds HTTP PUT support for the langchain openapi agent toolkit by leveraging existing structure and HTTP put request wrapper. The PUT method is almost identical to HTTP POST but should be idempotent and therefore tighter than POST which is not idempotent. Some APIs may consider to use PUT instead of POST which is unfortunately not supported with the current toolkit yet.	1 year ago
Mateusz Wosinski	a29cd89923	Synthetic data generation (#9759) ... ### Description Implements synthetic data generation with the fields and preferences given by the user. Adds showcase notebook. Corresponding prompt was proposed for langchain-hub. ### Example ``` output = chain({"fields": {"colors": ["blue", "yellow"]}, "preferences": {"style": "Make it in a style of a weather forecast."}}) print(output) # {'fields': {'colors': ['blue', 'yellow']}, 'preferences': {'style': 'Make it in a style of a weather forecast.'}, 'text': "Good morning! Today's weather forecast brings a beautiful combination of colors to the sky, with hues of blue and yellow gently blending together like a mesmerizing painting."} ``` ### Twitter handle @deepsense_ai @matt_wosinski --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	1 year ago
Bagatur	c4a6de3fc9	Revert "Add ChatGLM for llm and chat_model by using ChatGLM API (#9797)" (#10805) ... @etveritas reverting for now until this is resolved https://github.com/langchain-ai/langchain/pull/9797/files#r1330795585, apologies for merging too eagerly!	1 year ago
Mickaël	c86a1a6710	chore: allow using dataclasses_json dependency v0.6.0 (#10775) ... **Description:** upgrade the `dataclasses_json` dependency to its latest version ([no real breaking change](https://github.com/lidatong/dataclasses-json/releases/tag/v0.6.0) if used correctly), while allowing previous version to not break other users' setup **Issue:** I need to use the latest version of that dependency in my project, but `langchain` prevents it. Note: it looks like running `poetry lock --no-update` did some changes to the lockfiles as it was the first time it was with the `macosx_11_0_arm64` architecture 🤷 --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	1 year ago
Bagatur	76dd7480e6	Add batch_size param to Weaviate vector store (#9890) ... cc @mcantillon21 @hsm207 @cs0lar	1 year ago
Mateusz Wosinski	720f6dbaac	Add XMLOutputParser (#10051) ... **Description** Adds new output parser, this time enabling the output of LLM to be of an XML format. Seems to be particularly useful together with Claude model. Addresses [issue 9820](https://github.com/langchain-ai/langchain/issues/9820). **Twitter handle** @deepsense_ai @matt_wosinski	1 year ago
etVERITAS	d6df288380	Add ChatGLM for llm and chat_model by using ChatGLM API (#9797) ... using sample: ``` endpoint_url = API URL ChatGLM_llm = ChatGLM( endpoint_url=endpoint_url, api_key=Your API Key by ChatGLM ) print(ChatGLM_llm("hello")) ``` ``` model = ChatChatGLM( chatglm_api_key="api_key", chatglm_api_base="api_base_url", model_name="model_name" ) chain = LLMChain(llm=model) ``` Description: The call of ChatGLM has been adapted. Issue: The call of ChatGLM has been adapted. Dependencies: Need python package `zhipuai` and `aiostream` Tag maintainer: @baskaryan Twitter handle: None I remove the compatibility test for pydantic version 2, because pydantic v2 can't not pickle classmethod,but BaseModel use @root_validator is a classmethod decorator. --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	1 year ago
Harrison Chase	d60145229b	make agent action serializable (#10797) ... Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>	1 year ago
Maxime Bourliatoux	21b236e5e4	Fixing _InactiveRpcError in MatchingEngine vectorstore (#10056) ... - Description: There was an issue with the MatchingEngine VectorStore, preventing from using it with a public endpoint. In the Google Cloud library there are two similar methods for private or public endpoints : `match()` and `find_neighbors()`. - Issue: Fixes #8378 - This uses the `google.cloud.aiplatform` library : https://github.com/googleapis/python-aiplatform/blob/main/google/cloud/aiplatform/matching_engine/matching_engine_index_endpoint.py	1 year ago
Sam Chou	4f19ba3065	Azure Search: Remove select field restrictions and expand metadata to other fields, also expose kwargs to searches (#9894) ... Description: If metadata field returned in results, previous behavior unchanged. If metadata field does not exist in results, expand metadata to any fields returned outside of content field. There's precedence for this as well, see the retriever: https://github.com/langchain-ai/langchain/blob/master/libs/langchain/langchain/retrievers/azure_cognitive_search.py#L96C46-L96C46 Issue: #9765 - Ameliorates hard-coding in case you already indexed to cognitive search without a metadata field but rather placed metadata in separate fields. @hwchase17	1 year ago
Piyush Jain	94cf71ecfa	Updated Neptune graph to use boto (#10121) ... ## Description This PR updates the `NeptuneGraph` class to start using the boto API for connecting to the Neptune service. With boto integration, the graph class now supports authenticating requests using Sigv4; this is encapsulated with the boto API, and users only have to ensure they have the correct AWS credentials setup in their workspace to work with the graph class. This PR also introduces a conditional prompt that uses a simpler prompt when using the `Anthropic` model provider. A simpler prompt have seemed to work better for generating cypher queries in our testing. **Note**: This version will require boto3 version 1.28.38 or greater to work.	1 year ago
Aashish Saini	33781ac4a2	Update sequential_chains.mdx (#64) (#10793) ... Fixed some more grammatical issues @baskaryan Co-authored-by: ManpreetShorthillsAI <142380984+ManpreetShorthillsAI@users.noreply.github.com> Co-authored-by: Aashish Saini <141953346+AashishSainiShorthillsAI@users.noreply.github.com> Co-authored-by: AryamanJaiswalShorthillsAI <142397527+AryamanJaiswalShorthillsAI@users.noreply.github.com> Co-authored-by: Adarsh Shrivastav <142413097+AdarshKumarShorthillsAI@users.noreply.github.com> Co-authored-by: Vishal <141389263+VishalYadavShorthillsAI@users.noreply.github.com> Co-authored-by: ChetnaGuptaShorthillsAI <142381084+ChetnaGuptaShorthillsAI@users.noreply.github.com> Co-authored-by: PankajKumarShorthillsAI <142473460+PankajKumarShorthillsAI@users.noreply.github.com> Co-authored-by: AbhishekYadavShorthillsAI <142393903+AbhishekYadavShorthillsAI@users.noreply.github.com> Co-authored-by: AmitSinghShorthillsAI <142410046+AmitSinghShorthillsAI@users.noreply.github.com> Co-authored-by: Md Nazish Arman <142379599+MdNazishArmanShorthillsAI@users.noreply.github.com> Co-authored-by: KamalSharmaShorthillsAI <142474019+KamalSharmaShorthillsAI@users.noreply.github.com> Co-authored-by: Lakshya <lakshyagupta87@yahoo.com> Co-authored-by: Aayush <142384656+AayushShorthillsAI@users.noreply.github.com> Co-authored-by: AnujMauryaShorthillsAI <142393269+AnujMauryaShorthillsAI@users.noreply.github.com> Co-authored-by: Saransh Sharma <142397365+SaranshSharmaShorthillsAI@users.noreply.github.com> Co-authored-by: GhayurHamzaShorthillsAI <136243850+GhayurHamzaShorthillsAI@users.noreply.github.com> Co-authored-by: Puneet Dhiman <142409038+PuneetDhimanShorthillsAI@users.noreply.github.com> Co-authored-by: Riya Rana <142411643+RiyaRanaShorthillsAI@users.noreply.github.com>	1 year ago
Douglas Monsky	d5f1969d55	Introducing Enhanced Functionality to WeaviateHybridSearchRetriever: Accepting Additional Keyword Arguments (#10802) ... **Description:** This commit enriches the `WeaviateHybridSearchRetriever` class by introducing a new parameter, `hybrid_search_kwargs`, within the `_get_relevant_documents` method. This parameter accommodates arbitrary keyword arguments (`**kwargs`) which can be channeled to the inherited public method, `get_relevant_documents`, originating from the `BaseRetriever` class. This modification facilitates more intricate querying capabilities, allowing users to convey supplementary arguments to the `.with_hybrid()` method. This expansion not only makes it possible to perform a more nuanced search targeting specific properties but also grants the ability to boost the weight of searched properties, to carry out a search with a custom vector, and to apply the Fusion ranking method. The documentation has been updated accordingly to delineate these new possibilities in detail. In light of the layered approach in which this search operates, initiating with `query.get()` and then transitioning to `.with_hybrid()`, several advantageous opportunities are unlocked for the hybrid component that were previously unattainable. Here’s a representative example showcasing a query structure that was formerly unfeasible: [Specific Properties Only](https://weaviate.io/developers/weaviate/search/hybrid#selected-properties-only) "The example below illustrates a BM25 search targeting the keyword 'food' exclusively within the 'question' property, integrated with vector search results corresponding to 'food'." ```python response = ( client.query .get("JeopardyQuestion", ["question", "answer"]) .with_hybrid( query="food", properties=["question"], # Will now be possible moving forward alpha=0.25 ) .with_limit(3) .do() ) ``` This functionality is now accessible through my alterations, by conveying `hybrid_search_kwargs={"properties": ["question", "answer"]}` as an argument to `WeaviateHybridSearchRetriever.get_relevant_documents()`. For example: ```python import os from weaviate import Client from langchain.retrievers import WeaviateHybridSearchRetriever client = Client( url=os.getenv("WEAVIATE_CLIENT_URL"), additional_headers={ "X-OpenAI-Api-Key": os.getenv("OPENAI_API_KEY"), "Authorization": f"Bearer {os.getenv('WEAVIATE_API_KEY')}", }, ) index_name = "Document" text_key = "content" attributes = ["title", "summary", "header", "url"] retriever = ExtendedWeaviateHybridSearchRetriever( client=client, index_name=index_name, text_key=text_key, attributes=attributes, ) # Warning: to utilize properties in this way, each use property must also be in the list `attributes + [text_key]`. hybrid_search_kwargs = {"properties": ["summary^2", "content"]} query_text = "Some Query Text" relevant_docs = retriever.get_relevant_documents( query=query_text, hybrid_search_kwargs=hybrid_search_kwargs ) ``` In my experience working with the `weaviate-client` library, I have found that these supplementary options stand as vital tools for refining/finetuning searches, notably within multifaceted datasets. As a final note, this implementation supports both backwards and forward (within reason) compatiblity. It accommodates any future additional parameters Weaviate may add to `.with_hybrid()`, without necessitating further alterations. **Additional Documentation:** For a more comprehensive understanding and to explore a myriad of useful options that are now accessible, please refer to the Weaviate documentation: - [Fusion Ranking Method](https://weaviate.io/developers/weaviate/search/hybrid#fusion-ranking-method) - [Selected Properties Only](https://weaviate.io/developers/weaviate/search/hybrid#selected-properties-only) - [Weight Boost Searched Properties](https://weaviate.io/developers/weaviate/search/hybrid#weight-boost-searched-properties) - [With a Custom Vector](https://weaviate.io/developers/weaviate/search/hybrid#with-a-custom-vector) **Tag Maintainer:** @hwchase17 - I have tagged you based on your frequent contributions to the pertinent file, `/retrievers/weaviate_hybrid_search.py`. My apologies if this was not the appropriate choice. Thank you for considering my contribution, I look forward to your feedback, and to future collaboration.	1 year ago
Jacob Lee	61cecf8b1b	Fix for versioned OpenAI instruct models (#10788) ... Versioned OpenAI instruct models may end with numbers, e.g. `gpt-3.5-turbo-instruct-0914`. Fixes https://github.com/langchain-ai/langchainjs/issues/2669 in Python	1 year ago
Bagatur	73afd72e1d	fix qa structured link (#10799) ... redirect not working for some reason	1 year ago
Cory Zue	62603f2664	make auto-setting the encodings optional, alow explicitly setting it (#10774) ... I was trying to use web loaders on some spanish documentation (e.g. [this site](https://www.fromdoppler.com/es/mailing-tendencias/), but the auto-encoding introduced in https://github.com/langchain-ai/langchain/pull/3602 was detected as "MacRoman" instead of the (correct) "UTF-8". To address this, I've added the ability to disable the auto-encoding, as well as the ability to explicitly tell the loader what encoding to use. - **Description:** Makes auto-setting the encoding optional in `WebBaseLoader`, and introduces an `encoding` option to explicitly set it. - **Dependencies:** N/A - **Tag maintainer:** @hwchase17 - **Twitter handle:** @czue	1 year ago
Harrison Chase	c68be4eb2b	tool rendering (#10786)	1 year ago
Aashish Saini	1b050b98f5	Corrected some spelling mistakes and grammatical errors (#10791) ... Corrected some spelling mistakes and grammatical errors CC: @baskaryan, @eyurtsev, @hwchase17. --------- Co-authored-by: Ishita Chauhan <136303787+IshitaChauhanShortHillsAI@users.noreply.github.com> Co-authored-by: Aashish Saini <141953346+AashishSainiShorthillsAI@users.noreply.github.com> Co-authored-by: ManpreetShorthillsAI <142380984+ManpreetShorthillsAI@users.noreply.github.com> Co-authored-by: AryamanJaiswalShorthillsAI <142397527+AryamanJaiswalShorthillsAI@users.noreply.github.com> Co-authored-by: Adarsh Shrivastav <142413097+AdarshKumarShorthillsAI@users.noreply.github.com> Co-authored-by: Vishal <141389263+VishalYadavShorthillsAI@users.noreply.github.com> Co-authored-by: ChetnaGuptaShorthillsAI <142381084+ChetnaGuptaShorthillsAI@users.noreply.github.com> Co-authored-by: PankajKumarShorthillsAI <142473460+PankajKumarShorthillsAI@users.noreply.github.com> Co-authored-by: AbhishekYadavShorthillsAI <142393903+AbhishekYadavShorthillsAI@users.noreply.github.com> Co-authored-by: AmitSinghShorthillsAI <142410046+AmitSinghShorthillsAI@users.noreply.github.com> Co-authored-by: Md Nazish Arman <142379599+MdNazishArmanShorthillsAI@users.noreply.github.com> Co-authored-by: KamalSharmaShorthillsAI <142474019+KamalSharmaShorthillsAI@users.noreply.github.com> Co-authored-by: Lakshya <lakshyagupta87@yahoo.com> Co-authored-by: Aayush <142384656+AayushShorthillsAI@users.noreply.github.com> Co-authored-by: AnujMauryaShorthillsAI <142393269+AnujMauryaShorthillsAI@users.noreply.github.com> Co-authored-by: ishita <chauhanishita5356@gmail.com>	1 year ago
Ahmad Bunni	5272e42b0d	Add namespace to pinecone hybrid search (#10677) ... **Description:** Pinecone hybrid search is now limited to default namespace. There is no option for the user to provide a namespace to partition an index, which is one of the most important features of pinecone. **Resource:** https://docs.pinecone.io/docs/namespaces --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	1 year ago
Raunak Chowdhuri	b338e492fc	Remembrall Integration (#10767) ... - **Description:** Added integration instructions for Remembrall. - **Tag maintainer:** @hwchase17 - **Twitter handle:** @raunakdoesdev Fun fact, this project originated at the Modal Hackathon in NYC where it won the Best LLM App prize sponsored by Langchain. Thanks for your support 🦜	1 year ago
Bagatur	0d1550da91	Bagatur/bump 295 (#10785)	1 year ago
Aashish Saini	6a98974bd0	Update argilla.ipynb with spelling fix (#10611) ... Fixed spelling of **responses** and removed extra "the"	1 year ago
Vikram Shitole	a4e858b111	Sagemaker endpoint capability to inject boto3 client for cross account scenarios (#10728) ... - **Description: Allow to inject boto3 client for Cross account access type of scenarios in using Sagemaker Endpoint ** - **Issue:#10634 #10184** - **Dependencies: None** - **Tag maintainer:** - **Twitter handle:lethargicoder** Co-authored-by: Vikram(VS) <vssht@amazon.com>	1 year ago
William FH	c8f386db97	Merge metadata + tags in config (#10762) ... Think these should be a merge/update rather than overwrite	1 year ago
Jacob Lee	71025013f8	Update routing cookbook to include a RunnableBranch example (#10754) ... ~~Because we can't pass extra parameters into a prompt, we have to prepend a function before the runnable calls in the branch and it's a bit less elegant than I'd like.~~ All good now that #10765 has landed! @eyurtsev @hwchase17 --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	1 year ago
BarberAlec	c898a4d7ba	Update ContextCallbackHandler Docstring & metadata key (#10732) ... - **Description:** Updating URL in Context Callback Docstrings and update metadata key Context CallbackHandler uses to send model names. - **Issue:** The URL in ContextCallbackHandler is out of date. Model data being sent to Context should be under the "model" key and not "llm_model". This allows Context to do more sophisticated analysis. - **Dependencies:** None Tagging @agamble.	1 year ago
Taqi Jaffri	54763a61f8	fix broken link in docugami loader docs (#10753) ... Just fixing the link to the self query retriever in docugami loader docs Co-authored-by: Taqi Jaffri <tjaffri@docugami.com>	1 year ago
Harrison Chase	8b68d1a03b	keep reference to old embeddings base (#10759)	1 year ago