11138 Commits (3555882a0de152fd621c44d9f3fafba6386a0f1c)

 

All Branches   

Search

Author	SHA1	Message	Date
崔浩	3555882a0d	community[patch]: optimize xinference llm import (#25809) ... Thank you for contributing to LangChain! - [ ] **PR title**: "community: optimize xinference llm import" - [ ] **PR message**: - **Description:** from xinferece_client import RESTfulClient when there is no importing xinference. - **Dependencies:** xinferece_client - **Why do so:** the total xinference(pip install xinference[all]) is too heavy for installing, let alone it is useless for langchain user except RESTfulClient. The modification has maintained consistency with the xinference embeddings [embeddings/xinference](../blob/master/libs/community/langchain_community/embeddings/xinference.py#L89).	3 weeks ago
Michael Rubél	9decd0b243	langchain[patch]: fix moderation chain init (#25778) ... [This commit](d3ca2cc8c3) has broken the moderation chain so we've faced a crash when migrating the LangChain from v0.1 to v0.2. The issue appears that the class attribute the code refers to doesn't hold the value processed in the `validate_environment` method. We had `extras={}` in this attribute, and it was casted to `True` when it should've been `False`. Adding a simple assignment seems to resolve the issue, though I'm not sure it's the right way. --- --------- Co-authored-by: Michael Rubél <mrubel@oroinc.com> Co-authored-by: Bagatur <baskaryan@gmail.com>	3 weeks ago
Madhu Shantan	63a1569d5f	docs: fixed syntax error in ChatAnthropic Example - rag app tutorial notebook (#25824) ... Thank you for contributing to LangChain! - [ ] **PR title**: docs: fixed syntax error in ChatAnthropic Example - rag app tutorial notebook - generation - [ ] **PR message**: - **Description:** Fixed a syntax error in the ChatAnthropic initialization example in the RAG tutorial notebook. The original code had an extra set of quotation marks around the model parameter, which would cause a Python syntax error. The corrected version removes these unnecessary quotes. - **Dependencies:** No new dependencies required for this documentation fix. I've verified that the corrected code is syntactically valid and matches the expected format for initializing a ChatAnthropic instance in LangChain. - **Twitter handle:** madhu_shantan - [ ] **Add tests and docs**: the error in Jupyter notebook: <img width="1189" alt="Screenshot 2024-08-29 at 12 43 47 AM" src="https://github.com/user-attachments/assets/07148a93-300f-40e2-ad4a-ac219cbb56a4"> the corrected cell: <img width="983" alt="Screenshot 2024-08-29 at 12 44 18 AM" src="https://github.com/user-attachments/assets/75b1455a-3671-454e-ac16-8ca77c049dbd"> - [ ] **Lint and test**: As this is a documentation-only change, I have not run the full test suite. However, I have verified that the corrected code example is syntactically valid and matches the expected usage of the ChatAnthropic class. the error in the docs is here - <img width="1020" alt="Screenshot 2024-08-29 at 12 48 36 AM" src="https://github.com/user-attachments/assets/812ccb20-b411-4a5b-afc1-41742efb32a7">	3 weeks ago
Erick Friis	e5ae988505	prompty: bump core version (#25831)	3 weeks ago
Erick Friis	c8b8335b82	core: prompt variable error msg (#25787)	3 weeks ago
ccurme	ff168aaec0	prompty: release 0.0.3 (#25830)	3 weeks ago
Matthieu	783397eacb	community: avoid double templating in `langchain_prompty` (#25777) ... ## Description In `langchain_prompty`, messages are templated by Prompty. However, a call to `ChatPromptTemplate` was initiating a second templating. We now convert parsed messages to `Message` objects before calling `ChatPromptTemplate`, signifying clearly that they are already templated. We also revert #25739 , which applied to this second templating, which we now avoid, and did not fix the original issue. ## Issue Closes #25703	3 weeks ago
ccurme	afe8ccaaa6	community[patch]: Add ID field back to Azure AI Search results (#25828) ... Commandeering https://github.com/langchain-ai/langchain/pull/23243 as maintainers don't have ability to modify that PR. Fixes https://github.com/langchain-ai/langchain/issues/22827 --------- Co-authored-by: Ming Quah <fleetadmiralbutter@icloud.com>	3 weeks ago
rbrugaro	9fa172bc26	add links in example nb with tei/tgi references (#25821) ... I have validated langchain interface with tei/tgi works as expected when TEI and TGI running on Intel Gaudi2. Adding some references to notebooks to help users find relevant info. --------- Co-authored-by: Rita Brugarolas <rbrugaro@idc708053.jf.intel.com> Co-authored-by: Chester Curme <chester.curme@gmail.com>	3 weeks ago
Erick Friis	8fb594fd2a	ai21: migrate to external repo (#25827)	3 weeks ago
Erick Friis	095b712a26	ollama: bump core version (#25826)	3 weeks ago
Erick Friis	5db6c6d96d	community: release 0.2.14 (#25822)	3 weeks ago
Erick Friis	d6c4803ab0	core: release 0.2.36 (#25819)	3 weeks ago
Erick Friis	5186325bc7	partners/ollama: release 0.1.2 (#25817) ... release for #25697	3 weeks ago
Rohit Gupta	aff50a1e6f	milvus: add array data type for collection create (#23219) ... Add array data type for milvus vector store collection create Thank you for contributing to LangChain! - [x] **PR title**: "package: description" - Where "package" is whichever of langchain, community, core, experimental, etc. is being modified. Use "docs: ..." for purely docs changes, "templates: ..." for template changes, "infra: ..." for CI changes. - Example: "community: add foobar LLM" - [x] **PR message**: ***Delete this entire checklist*** and replace with - **Description:** a description of the change - **Issue:** the issue # it fixes, if applicable - **Dependencies:** any dependencies required for this change - **Twitter handle:** if your PR gets announced, and you'd like a mention, we'll gladly shout you out! - [x] **Add tests and docs**: 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. - [x] **Lint and test**: Run `make format`, `make lint` and `make test` from the root of the package(s) you've modified. See contribution guidelines for more: https://python.langchain.com/docs/contributing/ Additional guidelines: - Make sure optional dependencies are imported within a function. - Please do not add dependencies to pyproject.toml files (even optional ones) unless they are required for unit tests. - Most PRs should not touch more than one package. - Changes should be backwards compatible. - If you are adding something to community, do not re-import it in langchain. If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17. --------- Signed-off-by: ChengZi <chen.zhang@zilliz.com> Co-authored-by: Rohit Gupta <rohit.gupta2@walmart.com> Co-authored-by: ChengZi <chen.zhang@zilliz.com> Co-authored-by: Erick Friis <erick@langchain.dev>	3 weeks ago
Cillian Berragan	754f3c41f9	community: add score to PineconeHybridSearchRetriever (#25781) ... **Description:** Adds the 'score' returned by Pinecone to the `PineconeHybridSearchRetriever` list of returned Documents. There is currently no way to return the score when using Pinecone hybrid search, so in this PR I include it by default. --------- Co-authored-by: Chester Curme <chester.curme@gmail.com>	3 weeks ago
ZhangShenao	3f1d652f15	Improvement[Community] Improve api doc for `PineconeHybridSearchRetriever` (#25803) ... - Complete missing args in api doc	3 weeks ago
Moritz Schlager	555f97becb	community[patch]: fix model initialization bug for deepinfra (#25727) ... ### Description adds an init method to ChatDeepInfra to set the model_name attribute accordings to the argument ### Issue currently, the model_name specified by the user during initialization of the ChatDeepInfra class is never set. Therefore, it always chooses the default model (meta-llama/Llama-2-70b-chat-hf, however probably since this is deprecated it always uses meta-llama/Llama-3-70b-Instruct). We stumbled across this issue and fixed it as proposed in this pull request. Feel free to change the fix according to your coding guidelines and style, this is just a proposal and we want to draw attention to this problem. ### Dependencies no additional dependencies required Feel free to contact me or @timo282 and @finitearth if you have any questions. --------- Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	3 weeks ago
Bagatur	a052173b55	together[patch]: Release 0.1.6 (#25805)	3 weeks ago
Bagatur	b0ac6fe8d3	community[patch]: Release 0.2.13 (#25806)	3 weeks ago
Bagatur	85aef7641c	openai[patch]: Release 0.1.23 (#25804)	3 weeks ago
Bagatur	0d3fd0aeb9	langchain[patch]: Release 0.2.15 (#25802)	3 weeks ago
zysoong	25a6790e1a	community[patch]: Minor Improvement of extract hyperlinks tool output (#25728) ... **Description:** Make the hyperlink only appear once in the extract_hyperlinks tool output. (for some websites output contains meaningless '#' hyperlinks multiple times which will extend the tokens of context window without any advantage) **Issue:** None **Dependencies:** None	3 weeks ago
Christophe Bornet	ff0df5ea15	core[patch]: Add B(bugbear) ruff rules (#25520) ... Co-authored-by: Bagatur <baskaryan@gmail.com>	3 weeks ago
Isaac Francisco	d5ddaac1fc	docs minor fix (#25794)	3 weeks ago
ccurme	3c784e10a8	docs: improve docs for InMemoryVectorStore (#25786) ... Closes https://github.com/langchain-ai/langchain/issues/25775	3 weeks ago
Erick Friis	1023fbc98a	databricks: mv to partner repo (#25788)	3 weeks ago
ccurme	2e5c379632	openai[patch]: fix get_num_tokens for function calls (#25785) ... Closes https://github.com/langchain-ai/langchain/issues/25784 See additional discussion [here](0a4ee864e9 (r145147380)).	3 weeks ago
Erick Friis	2aa35d80a0	docs, infra: cerebras docs, update docs template linting with better error (#25782)	3 weeks ago
venkatram-dev	48b579f6b5	date_time_parser (#25763) ... Thank you for contributing to LangChain! - [x] **PR title**: "langchain: Chains: query_constructor: add date time parser" - [x] **PR message**: - **Description:** add date time parser to langchain Chains query_constructor - **Issue: https://github.com/langchain-ai/langchain/issues/25526 - [ ] **Add tests and docs**: 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. - [ ] **Lint and test**: Run `make format`, `make lint` and `make test` from the root of the package(s) you've modified. See contribution guidelines for more: https://python.langchain.com/docs/contributing/ Additional guidelines: - Make sure optional dependencies are imported within a function. - Please do not add dependencies to pyproject.toml files (even optional ones) unless they are required for unit tests. - Most PRs should not touch more than one package. - Changes should be backwards compatible. - If you are adding something to community, do not re-import it in langchain. If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.	3 weeks ago
Tomaz Bratanic	f359e6b0a5	Add mmr to neo4j vector (#25765)	3 weeks ago
pazshalev	995305fdd5	test: fix tool calling integration tests for AI21 Jamba models (#25771) ... Ignore specific integration tests that handles specific tool calling cases that will soon be fixed.	3 weeks ago
Luis Valencia	99f9a664a5	community: Azure Search Vector Store is missing Access Token Authentication (#24330) ... Added Azure Search Access Token Authentication instead of API KEY auth. Fixes Issue: https://github.com/langchain-ai/langchain/issues/24263 Dependencies: None Twitter: @levalencia @baskaryan Could you please review? First time creating a PR that fixes some code. --------- Co-authored-by: Erick Friis <erick@langchain.dev>	4 weeks ago
Leonid Ganeline	49b0bc7b5a	docs: `integrations` reference updates 5 (#25151) ... Added missed references. Added missed provider pages. --------- Co-authored-by: Chester Curme <chester.curme@gmail.com>	4 weeks ago
ZhangShenao	44e3e2391c	Improvement[Community] Improve methods in `IMessageChatLoader` (#25746) ... - Add @staticmethod to static methods in `IMessageChatLoader`. - Format args name.	4 weeks ago
Erick Friis	815f59dba5	partners/ai21: release 0.1.8 (#25759)	4 weeks ago
amirai21	17dffd9741	AI21: tools calling support in Langchain (#25635) ... This pull request introduces support for the AI21 tools calling feature, available by the Jamba-1.5 models. When Jamba-1.5 detects the necessity to invoke a provided tool, as indicated by the 'tools' parameter passed to the model: ``` class ToolDefinition(TypedDict, total=False): type: Required[Literal["function"]] function: Required[FunctionToolDefinition] class FunctionToolDefinition(TypedDict, total=False): name: Required[str] description: str parameters: ToolParameters class ToolParameters(TypedDict, total=False): type: Literal["object"] properties: Required[Dict[str, Any]] required: List[str] ``` It will respond with a list of tool calls structured as follows: ``` class ToolCall(AI21BaseModel): id: str function: ToolFunction type: Literal["function"] = "function" class ToolFunction(AI21BaseModel): name: str arguments: str ``` This pull request incorporates the necessary modifications to integrate this functionality into the ai21-langchain library. --------- Co-authored-by: asafg <asafg@ai21.com> Co-authored-by: pazshalev <111360591+pazshalev@users.noreply.github.com> Co-authored-by: Paz Shalev <pazs@ai21.com> Co-authored-by: Erick Friis <erick@langchain.dev>	4 weeks ago
maang-h	a566a15930	Fix MoonshotChat instantiate with alias (#25755) ... - **Description:** - Fix `MoonshotChat` instantiate with alias - Add `MoonshotChat` to `__init__.py` --------- Co-authored-by: Chester Curme <chester.curme@gmail.com>	4 weeks ago
venkatram-dev	ec99f0d193	milvus: add_db_milvus_connection (#25627) ... Thank you for contributing to LangChain! - [x] **PR title**: "package: description" - Where "package" is whichever of langchain, community, core, experimental, etc. is being modified. Use "docs: ..." for purely docs changes, "templates: ..." for template changes, "infra: ..." for CI changes. - Example: "community: add foobar LLM" - "libs: langchain_milvus: add db name to milvus connection check" - [x] **PR message**: ***Delete this entire checklist*** and replace with - **Description:** add db name to milvus connection check - **Issue:** https://github.com/langchain-ai/langchain/issues/25277 - [x] **Add tests and docs**: 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. - [x] **Lint and test**: Run `make format`, `make lint` and `make test` from the root of the package(s) you've modified. See contribution guidelines for more: https://python.langchain.com/docs/contributing/ Additional guidelines: - Make sure optional dependencies are imported within a function. - Please do not add dependencies to pyproject.toml files (even optional ones) unless they are required for unit tests. - Most PRs should not touch more than one package. - Changes should be backwards compatible. - If you are adding something to community, do not re-import it in langchain. If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17. --------- Co-authored-by: Erick Friis <erick@langchain.dev>	4 weeks ago
Ashvin	af3b3a4474	Update endpoint for AzureMLEndpointApiType class. (#25725) ... This addresses the issue mentioned in #25702 I have updated the endpoint used in validating the endpoint API type in the AzureMLBaseEndpoint class from `/v1/completions` to `/completions` and `/v1/chat/completions` to `/chat/completions`. Co-authored-by: = <=>	4 weeks ago
Mohammad Mohtashim	dcf2278a05	[Community]: Added Template Format Parameter in `create_chat_prompt` for Langchain Prompty (#25739) ... - **Description:** Added a `template_format` parameter to `create_chat_prompt` to allow `.prompty` files to handle variables in different template formats. - **Issue:** #25703 --------- Co-authored-by: Chester Curme <chester.curme@gmail.com>	4 weeks ago
Dristy Srivastava	7205057c3e	[Community][minor]: Added langchain_version while calling discover API (#24428) ... - **Description:** Added langchain version while calling discover API during both ingestion and retrieval - **Issue:** NA - **Dependencies:** NA - **Tests:** NA - **Docs** NA --------- Co-authored-by: dristy.cd <dristy@clouddefense.io>	4 weeks ago
Dristy Srivastava	fbb4761199	[Community][minor]: Updating source path, and file path for SharePoint loader in PebbloSafeLoader (#25592) ... - **Description:** Updating source path and file path in Pebblo safe loader for SharePoint apps during loading - **Issue:** NA - **Dependencies:** NA - **Tests:** NA - **Docs** NA --------- Co-authored-by: dristy.cd <dristy@clouddefense.io>	4 weeks ago
Rajendra Kadam	745d1c2b8d	community[minor]: [Pebblo] Fix URL construction in newer Python versions (#25747) ... - **PR message**: **Fix URL construction in newer Python versions** - **Description:** - Update the URL construction logic to use the .value attribute for Routes enum members. - This adjustment resolves an issue where the code worked correctly in Python 3.9 but failed in Python 3.11. - Clean up unused routes. - **Issue:** NA - **Dependencies:** NA	4 weeks ago
Rajendra Kadam	58a98c7d8a	community: [PebbloRetrievalQA] Implemented Async support for prompt APIs (#25748) ... - **Description:** PebbloRetrievalQA: Implemented Async support for prompt APIs (classification and governance) - **Issue:** NA - **Dependencies:** NA	4 weeks ago
Tomaz Bratanic	6703d795c5	Handle Ollama tool raw schema in llmgraphtransformer (#25752)	4 weeks ago
Bagatur	30f1bf24ac	core[patch]: Release 0.2.35 (#25729)	4 weeks ago
Christophe Bornet	038c287b3a	all: Improve make lint command (#25344) ... * Removed `ruff check --select I` as `I` is already selected and checked in the main `ruff check` command * Added checks for non-empty `PYTHON_FILES` * Run `ruff check` only on `PYTHON_FILES` Co-authored-by: Erick Friis <erick@langchain.dev>	4 weeks ago
Mohammad Mohtashim	9a29398fe6	huggingface: fix `model` param population (#24743) ... - **Description:** Fix the validation error for `endpoint_url` for HuggingFaceEndpoint. I have given a descriptive detail of the isse in the issue that I have created. - **Issue:** #24742 --------- Co-authored-by: Erick Friis <erick@langchain.dev>	4 weeks ago
Yuki Watanabe	c7a8af2e75	databricks: add vector search and embeddings (#25648) ... ### Summary Add `DatabricksVectorSearch` and `DatabricksEmbeddings` classes to the `langchain-databricks` partner packages. Core functionality is unchanged, but the vector search class is largely refactored for readability and maintainability. This PR does not add integration tests yet. This will be added once the Databricks test workspace is ready. Tagging @efriis as POC ### Tracker [✅] Create a package and imgrate ChatDatabricks [✍️] Migrate DatabricksVectorSearch, DatabricksEmbeddings, and their docs ~[ ] Migrate UCFunctionToolkit and its doc~ [ ] Add provider document and update README.md [ ] Add integration tests and set up secrets (after moved to an external package) [ ] Add deprecation note to the community implementations. --------- Signed-off-by: B-Step62 <yuki.watanabe@databricks.com> Co-authored-by: Erick Friis <erick@langchain.dev>	4 weeks ago