7206 Commits (52f4ad82164139d214a7d88eacc9bc563a7e41b8)

 

All Branches   

Search

Author	SHA1	Message	Date
Killinsun - Ryota Takeuchi	52f4ad8216	community: Add new fields in metadata for qdrant vector store (#16608) ... ## Description The PR is to return the ID and collection name from qdrant client to metadata field in `Document` class. ## Issue The motivation is almost same to [11592](https://github.com/langchain-ai/langchain/issues/11592) Returning ID is useful to update existing records in a vector store, but we cannot know them if we use some retrievers. In order to avoid any conflicts, breaking changes, the new fields in metadata have a prefix `_` ## Dependencies N/A ## Twitter handle @kill_in_sun <!-- Thank you for contributing to LangChain! Please title your PR "<package>: <description>", where <package> is whichever of langchain, community, core, experimental, etc. is being modified. 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, - **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` from the root of the package you've modified to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://python.langchain.com/docs/contributing/ 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. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. -->	5 months ago
hulitaitai	32cad38ec6	<langchain_community\llms\chatglm.py>: <Correcting "history"> (#16729) ... Use the real "history" provided by the original program instead of putting "None" in the history. - **Description:** I change one line in the code to make it return the "history" of the chat model. - **Issue:** At the moment it returns only the answers of the chat model. However the chat model himself provides a history more complet with the questions of the user. - **Dependencies:** no dependencies required for this change,	5 months ago
Jacob Lee	4a027e622f	docs[patch]: Lower temperature in chatbot usecase notebooks for consistency (#16750) ... CC @baskaryan	5 months ago
Jacob Lee	12d2b2ebcf	docs[minor]: LCEL rewrite of chatbot use-case (#16414) ... CC @baskaryan @hwchase17 TODO: - [x] Draft of main quickstart - [x] Index intro page - [x] Add subpage guide for Memory management - [x] Add subpage guide for Retrieval - [x] Add subpage guide for Tool usage - [x] Add LangSmith traces illustrating query transformation	5 months ago
Bassem Yacoube	85e93e05ed	community[minor]: Update OctoAI LLM, Embedding and documentation (#16710) ... This PR includes updates for OctoAI integrations: - The LLM class was updated to fix a bug that occurs with multiple sequential calls - The Embedding class was updated to support the new GTE-Large endpoint released on OctoAI lately - The documentation jupyter notebook was updated to reflect using the new LLM sdk Thank you!	5 months ago
Hank	6d6226d96d	docs: Remove accidental extra ``` in QuickStart doc. (#16740) ... Description: One too many set of triple-ticks in a sample code block in the QuickStart doc was causing "\`\`\`shell" to appear in the shell command that was being demonstrated. I just deleted the extra "```". Issue: Didn't see one Dependencies: None	5 months ago
Shay Ben Elazar	84ebfb5b9d	openai[patch]: Added annotations support to azure openai (#13704) ... - **Description:** Added Azure OpenAI Annotations (content filtering results) to ChatResult - **Issue:** 13090 - **Twitter handle:** ElazarShay Co-authored-by: Bagatur <baskaryan@gmail.com>	5 months ago
Volodymyr Machula	32c5be8b73	community[minor]: Connery Tool and Toolkit (#14506) ... ## Summary This PR implements the "Connery Action Tool" and "Connery Toolkit". Using them, you can integrate Connery actions into your LangChain agents and chains. Connery is an open-source plugin infrastructure for AI. With Connery, you can easily create a custom plugin with a set of actions and seamlessly integrate them into your LangChain agents and chains. Connery will handle the rest: runtime, authorization, secret management, access management, audit logs, and other vital features. Additionally, Connery and our community offer a wide range of ready-to-use open-source plugins for your convenience. Learn more about Connery: - GitHub: https://github.com/connery-io/connery-platform - Documentation: https://docs.connery.io - Twitter: https://twitter.com/connery_io ## TODOs - [x] API wrapper - [x] Integration tests - [x] Connery Action Tool - [x] Docs - [x] Example - [x] Integration tests - [x] Connery Toolkit - [x] Docs - [x] Example - [x] Formatting (`make format`) - [x] Linting (`make lint`) - [x] Testing (`make test`)	5 months ago
Harrison Chase	8457c31c04	community[patch]: activeloop ai tql deprecation (#14634) ... Co-authored-by: AdkSarsen <adilkhan@activeloop.ai>	5 months ago
Neli Hateva	c95facc293	langchain[minor], community[minor]: Implement Ontotext GraphDB QA Chain (#16019) ... - **Description:** Implement Ontotext GraphDB QA Chain - **Issue:** N/A - **Dependencies:** N/A - **Twitter handle:** @OntotextGraphDB	5 months ago
chyroc	a08f9a7ff9	langchain[patch]: support OpenAIAssistantRunnable async (#15302) ... fix https://github.com/langchain-ai/langchain/issues/15299 --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	5 months ago
Elliot	39eb00d304	community[patch]: Adapt more parameters related to MemorySearchPayload for the search method of ZepChatMessageHistory (#15441) ... - **Description:** To adapt more parameters related to MemorySearchPayload for the search method of ZepChatMessageHistory, - **Issue:** None, - **Dependencies:** None, - **Twitter handle:** None	5 months ago
Kirushikesh DB	47bd58dc11	docs: Added illustration of using RetryOutputParser with LLMChain (#16722) ... **Description:** Updated the retry.ipynb notebook, it contains the illustrations of RetryOutputParser in LangChain. But the notebook lacks to explain the compatibility of RetryOutputParser with existing chains. This changes adds some code to illustrate the workflow of using RetryOutputParser with the user chain. Changes: 1. Changed RetryWithErrorOutputParser with RetryOutputParser, as the markdown text says so. 2. Added code at the last of the notebook to define a chain which passes the LLM completions to the retry parser, which can be customised for user needs. **Issue:** Since RetryOutputParser/RetryWithErrorOutputParser does not implement the parse function it cannot be used with LLMChain directly like [this](https://python.langchain.com/docs/expression_language/cookbook/prompt_llm_parser#prompttemplate-llm-outputparser). This also raised various issues #15133 #12175 #11719 still open, instead of adding new features/code changes its best to explain the "how to integrate LLMChain with retry parsers" clearly with an example in the corresponding notebook. Inspired from: https://github.com/langchain-ai/langchain/issues/15133#issuecomment-1868972580 --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	5 months ago
Jael Gu	a1aa3a657c	community[patch]: Milvus supports add & delete texts by ids (#16256) ... # Description To support [langchain indexing](https://python.langchain.com/docs/modules/data_connection/indexing) as requested by users, vectorstore Milvus needs to support: - document addition by id (`add_documents` method with `ids` argument) - delete by id (`delete` method with `ids` argument) Example usage: ```python from langchain.indexes import SQLRecordManager, index from langchain.schema import Document from langchain_community.vectorstores import Milvus from langchain_openai import OpenAIEmbeddings collection_name = "test_index" embedding = OpenAIEmbeddings() vectorstore = Milvus(embedding_function=embedding, collection_name=collection_name) namespace = f"milvus/{collection_name}" record_manager = SQLRecordManager( namespace, db_url="sqlite:///record_manager_cache.sql" ) record_manager.create_schema() doc1 = Document(page_content="kitty", metadata={"source": "kitty.txt"}) doc2 = Document(page_content="doggy", metadata={"source": "doggy.txt"}) index( [doc1, doc1, doc2], record_manager, vectorstore, cleanup="incremental", # None, "incremental", or "full" source_id_key="source", ) ``` # Fix issues Fix https://github.com/milvus-io/milvus/issues/30112 --------- Signed-off-by: Jael Gu <mengjia.gu@zilliz.com> Co-authored-by: Bagatur <baskaryan@gmail.com>	5 months ago
Michard Hugo	e9d3527b79	community[patch]: Add missing async similarity_distance_threshold handling in RedisVectorStoreRetriever (#16359) ... Add missing async similarity_distance_threshold handling in RedisVectorStoreRetriever - **Description:** added method `_aget_relevant_documents` to `RedisVectorStoreRetriever` that overrides parent method to add support of `similarity_distance_threshold` in async mode (as for sync mode) - **Issue:** #16099 - **Dependencies:** N/A - **Twitter handle:** N/A	5 months ago
Jarod Stewart	7c6a2a8384	templates: Ionic Shopping Assistant (#16648) ... - **Description:** This is a template for creating shopping assistant chat bots - **Issue:** Example for creating a shopping assistant with OpenAI Tools Agent - **Dependencies:** Ionic https://github.com/ioniccommerce/ionic_langchain - **Twitter handle:** @ioniccommerce --------- Co-authored-by: Erick Friis <erick@langchain.dev>	5 months ago
Bagatur	7237dc67d4	core[patch]: Release 0.1.17 (#16737)	5 months ago
Anthony Bernabeu	2db79ab111	community[patch]: Implement TTL for DynamoDBChatMessageHistory (#15478) ... - **Description:** Implement TTL for DynamoDBChatMessageHistory, - **Issue:** see #15477, - **Dependencies:** N/A, --------- Co-authored-by: Piyush Jain <piyushjain@duck.com>	5 months ago
Massimiliano Pronesti	1bc8d9a943	experimental[patch]: missing resolution strategy in anonymization (#16653) ... - **Description:** Presidio-based anonymizers are not working because `_remove_conflicts_and_get_text_manipulation_data` was being called without a conflict resolution strategy. This PR fixes this issue. In addition, it removes some mutable default arguments (antipattern). To reproduce the issue, just run the very first cell of this [notebook](https://python.langchain.com/docs/guides/privacy/2/) from langchain's documentation. <!-- Thank you for contributing to LangChain! Please title your PR "<package>: <description>", where <package> is whichever of langchain, community, core, experimental, etc. is being modified. 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, - **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` from the root of the package you've modified to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://python.langchain.com/docs/contributing/ 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. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. -->	5 months ago
Abhinav	8e44363ec9	langchain_community: Update documentation for installing llama-cpp-python on windows (#16666) ... **Description** : This PR updates the documentation for installing llama-cpp-python on Windows. - Updates install command to support pyproject.toml - Makes CPU/GPU install instructions clearer - Adds reinstall with GPU support command **Issue**: Existing [documentation](https://python.langchain.com/docs/integrations/llms/llamacpp#compiling-and-installing) lists the following commands for installing llama-cpp-python ``` python setup.py clean python setup.py install ```` The current version of the repo does not include a `setup.py` and uses a `pyproject.toml` instead. This can be replaced with ``` python -m pip install -e . ``` As explained in https://github.com/abetlen/llama-cpp-python/issues/965#issuecomment-1837268339 **Dependencies**: None **Twitter handle**: None --------- Co-authored-by: blacksmithop <angstycoder101@gmaii.com>	5 months ago
taimo	d3d9244fee	langchain-community: fix unicode escaping issue with SlackToolkit (#16616) ... - **Description:** fix unicode escaping issue with SlackToolkit - **Issue:** #16610	5 months ago
Benito Geordie	f3fdc5c5da	community: Added integrations for ThirdAI's NeuralDB with Retriever and VectorStore frameworks (#15280) ... **Description:** Adds ThirdAI NeuralDB retriever and vectorstore integration. NeuralDB is a CPU-friendly and fine-tunable text retrieval engine.	5 months ago
Jonathan Bennion	815896ff13	langchain: pubmed tool path update in doc (#16716) ... - **Description:** The current pubmed tool documentation is referencing the path to langchain core not the path to the tool in community. The old tool redirects anyways, but for efficiency of using the more direct path, just adding this documentation so it references the new path - **Issue:** doesn't fix an issue - **Dependencies:** no dependencies - **Twitter handle:** rooftopzen	5 months ago
Lance Martin	1bfadecdd2	Update Slack agent toolkit (#16732) ... Co-authored-by: taimoOptTech <132860814+taimo3810@users.noreply.github.com>	5 months ago
Pashva Mehta	22d90800c8	community: Fixed schema discrepancy in from_texts function for weaviate vectorstore (#16693) ... * Description: Fixed schema discrepancy in **from_texts** function for weaviate vectorstore which created a redundant property "key" inside a class. * Issue: Fixed: https://github.com/langchain-ai/langchain/issues/16692 * Twitter handle: @pashvamehta1	5 months ago
Choi JaeHun	ba70630829	docs: Syntax correction according to langchain version update in 'Retry Parser' tutorial example (#16699) ... - **Description:** Syntax correction according to langchain version update in 'Retry Parser' tutorial example, - **Issue:** #16698 --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	5 months ago
ccurme	ec0ae23645	core: expand docstring for RunnableGenerator (#16672) ... - **Description:** expand docstring for RunnableGenerator - **Issue:** https://github.com/langchain-ai/langchain/issues/16631	5 months ago
Bob Lin	0866a984fe	Update `n_gpu_layers`"s description (#16685) ... The `n_gpu_layers` parameter in `llama.cpp` supports the use of `-1`, which means to offload all layers to the GPU, so the document has been updated. Ref: 35918873b4/llama_cpp/server/settings.py (L29C22-L29C117) 35918873b4/llama_cpp/llama.py (L125)	5 months ago
Daniel Erenrich	0600998f38	community: Wikidata tool support (#16691) ... - **Description:** Adds Wikidata support to langchain. Can read out documents from Wikidata. - **Issue:** N/A - **Dependencies:** Adds implicit dependencies for `wikibase-rest-api-client` (for turning items into docs) and `mediawikiapi` (for hitting the search endpoint) - **Twitter handle:** @derenrich You can see an example of this tool used in a chain [here](https://nbviewer.org/urls/d.erenrich.net/upload/Wikidata_Langchain.ipynb) or [here](https://nbviewer.org/urls/d.erenrich.net/upload/Wikidata_Lars_Kai_Hansen.ipynb) <!-- Thank you for contributing to LangChain! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` from the root of the package you've modified to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://python.langchain.com/docs/contributing/ 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. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. -->	5 months ago
Tze Min	6ef718c5f4	Core: fix Anthropic json issue in streaming (#16670) ... **Description:** fix ChatAnthropic json issue in streaming **Issue:** https://github.com/langchain-ai/langchain/issues/16423 **Dependencies:** n/a --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	5 months ago
Owen Sims	e451c8adc1	Community: Update Ionic Shopping Docs (#16700) ... - **Description:** Update to docs as originally introduced in https://github.com/langchain-ai/langchain/pull/16649 (reviewed by @baskaryan), - **Twitter handle:** [@ioniccommerce](https://twitter.com/ioniccommerce)	5 months ago
Christophe Bornet	2e3af04080	Use Postponed Evaluation of Annotations in Astra and Cassandra doc loaders (#16694) ... Minor/cosmetic change	5 months ago
Yelin Zhang	bc7607a4e9	docs: remove iprogress warnings (#16697) ... - **Description:** removes iprogress warning texts from notebooks, resulting in a little nicer to read documentation	5 months ago
Erick Friis	0255c5808b	infra: move release workflow back (#16707)	5 months ago
Erick Friis	88e3129587	robocorp: release 0.0.2 (#16706)	5 months ago
Christophe Bornet	36e432672a	community[minor]: Add async methods to AstraDBLoader (#16652)	5 months ago
William FH	38425c99d2	core[minor]: Image prompt template (#14263) ... Builds on Bagatur's (#13227). See unit test for example usage (below) ```python def test_chat_tmpl_from_messages_multipart_image() -> None: base64_image = "abcd123" other_base64_image = "abcd123" template = ChatPromptTemplate.from_messages( [ ("system", "You are an AI assistant named {name}."), ( "human", [ {"type": "text", "text": "What's in this image?"}, # OAI supports all these structures today { "type": "image_url", "image_url": "data:image/jpeg;base64,{my_image}", }, { "type": "image_url", "image_url": {"url": "data:image/jpeg;base64,{my_image}"}, }, {"type": "image_url", "image_url": "{my_other_image}"}, { "type": "image_url", "image_url": {"url": "{my_other_image}", "detail": "medium"}, }, { "type": "image_url", "image_url": {"url": "https://www.langchain.com/image.png"}, }, { "type": "image_url", "image_url": {"url": "data:image/jpeg;base64,foobar"}, }, ], ), ] ) messages = template.format_messages( name="R2D2", my_image=base64_image, my_other_image=other_base64_image ) expected = [ SystemMessage(content="You are an AI assistant named R2D2."), HumanMessage( content=[ {"type": "text", "text": "What's in this image?"}, { "type": "image_url", "image_url": {"url": f"data:image/jpeg;base64,{base64_image}"}, }, { "type": "image_url", "image_url": { "url": f"data:image/jpeg;base64,{other_base64_image}" }, }, { "type": "image_url", "image_url": {"url": f"{other_base64_image}"}, }, { "type": "image_url", "image_url": { "url": f"{other_base64_image}", "detail": "medium", }, }, { "type": "image_url", "image_url": {"url": "https://www.langchain.com/image.png"}, }, { "type": "image_url", "image_url": {"url": "data:image/jpeg;base64,foobar"}, }, ] ), ] assert messages == expected ``` --------- Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Brace Sproul <braceasproul@gmail.com>	5 months ago
ARKA1112	3c387bc12d	docs: Error when importing packages from pydantic [docs] (#16564) ... URL : https://python.langchain.com/docs/use_cases/extraction Desc: <b> While the following statement executes successfully, it throws an error which is described below when we use the imported packages</b> ```py from pydantic import BaseModel, Field, validator ``` Code: ```python from langchain.output_parsers import PydanticOutputParser from langchain.prompts import ( PromptTemplate, ) from langchain_openai import OpenAI from pydantic import BaseModel, Field, validator # Define your desired data structure. class Joke(BaseModel): setup: str = Field(description="question to set up a joke") punchline: str = Field(description="answer to resolve the joke") # You can add custom validation logic easily with Pydantic. @validator("setup") def question_ends_with_question_mark(cls, field): if field[-1] != "?": raise ValueError("Badly formed question!") return field ``` Error: ```md PydanticUserError: The `field` and `config` parameters are not available in Pydantic V2, please use the `info` parameter instead. For further information visit https://errors.pydantic.dev/2.5/u/validator-field-config-info ``` Solution: Instead of doing: ```py from pydantic import BaseModel, Field, validator ``` We should do: ```py from langchain_core.pydantic_v1 import BaseModel, Field, validator ``` Thanks. --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	5 months ago
Rashedul Hasan Rijul	481493dbce	community[patch]: apply embedding functions during query if defined (#16646) ... **Description:** This update ensures that the user-defined embedding function specified during vector store creation is applied during queries. Previously, even if a custom embedding function was defined at the time of store creation, Bagel DB would default to using the standard embedding function during query execution. This pull request addresses this issue by consistently using the user-defined embedding function for queries if one has been specified earlier.	5 months ago
Serena Ruan	f01fb47597	community[patch]: MLflowCallbackHandler -- Move textstat and spacy as optional dependency (#16657) ... Signed-off-by: Serena Ruan <serena.rxy@gmail.com>	5 months ago
Zhuoyun(John) Xu	508bde7f40	community[patch]: Ollama - Pass headers to post request in async method (#16660) ... # Description A previous PR (https://github.com/langchain-ai/langchain/pull/15881) added option to pass headers to ollama endpoint, but headers are not pass to the async method.	5 months ago
Leonid Ganeline	5e73603e8a	docs: `DeepInfra` provider page update (#16665) ... - added description, links - consistent formatting - added links to the example pages	5 months ago
João Carlos Ferra de Almeida	3e87b67a3c	community[patch]: Add Cookie Support to Fetch Method (#16673) ... - **Description:** This change allows the `_fetch` method in the `WebBaseLoader` class to utilize cookies from an existing `requests.Session`. It ensures that when the `fetch` method is used, any cookies in the provided session are included in the request. This enhancement maintains compatibility with existing functionality while extending the utility of the `fetch` method for scenarios where cookie persistence is necessary. - **Issue:** Not applicable (new feature), - **Dependencies:** Requires `aiohttp` and `requests` libraries (no new dependencies introduced), - **Twitter handle:** N/A Co-authored-by: Joao Almeida <joao.almeida@mercedes-benz.io>	5 months ago
Daniel Erenrich	c314137f5b	docs: Fix broken link in CONTRIBUTING.md (#16681) ... - **Description:** link in CONTRIBUTING.md is broken - **Issue:** N/A - **Dependencies:** N/A - **Twitter handle:** @derenrich	5 months ago
Harrison Chase	27665e3546	[community] fix anthropic streaming (#16682)	5 months ago
Bagatur	5975bf39ec	infra: delete old CI workflows (#16680)	5 months ago
Christophe Bornet	4915c3cd86	[Fix] Fix Cassandra Document loader default page content mapper (#16273) ... We can't use `json.dumps` by default as many types returned by the cassandra driver are not serializable. It's safer to use `str` and let users define their own custom `page_content_mapper` if needed.	5 months ago
Nuno Campos	e86fd946c8	In stream_event and stream_log handle closed streams (#16661) ... if eg. the stream iterator is interrupted then adding more events to the send_stream will raise an exception that we should catch (and handle where appropriate) <!-- Thank you for contributing to LangChain! Please title your PR "<package>: <description>", where <package> is whichever of langchain, community, core, experimental, etc. is being modified. 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, - **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` from the root of the package you've modified to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://python.langchain.com/docs/contributing/ 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. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. -->	5 months ago
Jarod Stewart	0bc397957b	docs: document Ionic Tool (#16649) ... - **Description:** Documentation for the Ionic Tool. A shopping assistant tool that effortlessly adds e-commerce capabilities to your Agent.	5 months ago
Nuno Campos	52ccae3fb1	Accept message-like things in Chat models, LLMs and MessagesPlaceholder (#16418)	5 months ago