4384 Commits (master)

Author	SHA1	Message	Date
Michal Gregor	98b2e7b195	huggingface[patch]: Support for HuggingFacePipeline in ChatHuggingFace. (#22194) ... - **Description:** Added support for using HuggingFacePipeline in ChatHuggingFace (previously it was only usable with API endpoints, probably by oversight). - **Issue:** #19997 - **Dependencies:** none - **Twitter handle:** none --------- Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	12 hours ago
Fahreddin Özcan	0061ded002	community[patch]: Upstash Vector Store Namespace Support (#22251) ... This PR introduces namespace support for Upstash Vector Store, which would allow users to partition their data in the vector index. --------- Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	12 hours ago
Guangdong Liu	bc7e32f315	core(patch):fix partial_variables not working with SystemMessagePromptTemplate (#20711) ... - **Issue:** close #17560 - @baskaryan, @eyurtsev	13 hours ago
Dristy Srivastava	ef3df45d9d	community[minor]: Updating payload for pebblo discover API (#22309) ... **Description:** Updating response for pebblo discover API. Also updating filed name case type **Documentation:** N/A **Unit tests:** N/A	14 hours ago
Miroslav	cbd5720011	huggingface[patch]: Skip Login to HuggingFaceHub when token is not set (#22365)	14 hours ago
bhardwaj-vipul	f397a84a59	langchain[patch]: Fix MongoDBAtlasVectorSearch reference in self query retriever (#22401) ... **Description:** SelfQuery Retriever with MongoDBAtlasVectorSearch (from langchain_mongodb import MongoDBAtlasVectorSearch) and Chroma (from langchain_chroma import Chroma) is not supported. The imports in the [builtin translators](8cbce684d4/libs/langchain/langchain/retrievers/self_query/base.py (L73)) points to the [deprecated](acaf214a45/libs/community/langchain_community/vectorstores/mongodb_atlas.py (L36)) vectorstore. **Issue:** #22272 --------- Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	14 hours ago
ccurme	afe89a1411	community: add standard chat model params to Ollama (#22446)	15 hours ago
Ethan Yang	52da6a160d	community[patch]: Update OpenVINO embedding and reranker to support static input shape (#22171) ... It can help to deploy embedding models on NPU device	16 hours ago
Tom Clelford	c599732e1a	text-splitters[patch]: fix HTMLSectionSplitter parsing of xslt paths (#22176) ... ## Description This PR allows passing the HTMLSectionSplitter paths to xslt files. It does so by fixing two trivial bugs with how passed paths were being handled. It also changes the default value of the param `xslt_path` to `None` so the special case where the file was part of the langchain package could be handled. ## Issue #22175	16 hours ago
maang-h	01352bb55f	community[minor]: Implement MiniMaxChat interface (#22391) ... - **Description:** Implement MiniMaxChat interface, include: - No longer inherits the LLM class (like other chat model) - Update request parameters (v1 -> v2) - update `base url` - update message role (system, user, assistant) - add `stream` function - no longer use `group id` - Implement the `_stream`, `_agenerate`, and `_astream` interfaces [minimax v2 api document](https://platform.minimaxi.com/document/guides/chat-model/V2?id=65e0736ab2845de20908e2dd)	16 hours ago
Brandon Sharp	56e5aa4dd9	community[patch]: Airtable to allow for addtl params (#22092) ... - [X] **PR title**: "community: added optional params to Airtable table.all()" - [X] **PR message**: - **Description:** Add's **kwargs to AirtableLoader to allow for kwargs: https://pyairtable.readthedocs.io/en/latest/api.html#pyairtable.Table.all - **Issue:** N/A - **Dependencies:** N/A - **Twitter handle:** parakoopa88 - [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/ If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17. --------- Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	17 hours ago
Harichandan Roy	1f751343e2	community[patch]: update embeddings/oracleai.py (#22240) ... Thank you for contributing to LangChain! - [ ] **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" "community/embeddings: update oracleai.py" - [ ] **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! Adding oracle VECTOR_ARRAY_T support. - [ ] **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. Tests are not impacted. - [ ] **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/ Done. 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.	17 hours ago
maang-h	13140dc4ff	community[patch]: Update the default api_url and reqeust_body of sparkllm embedding (#22136) ... - **Description:** When I was running the SparkLLMTextEmbeddings, app_id, api_key and api_secret are all correct, but it cannot run normally using the current URL. ```python # example from langchain_community.embeddings import SparkLLMTextEmbeddings embedding= SparkLLMTextEmbeddings( spark_app_id="my-app-id", spark_api_key="my-api-key", spark_api_secret="my-api-secret" ) embedding= "hello" print(spark.embed_query(text1)) ```  So I updated the url and request body parameters according to [Embedding_api](https://www.xfyun.cn/doc/spark/Embedding_api.html), now it is runnable.	17 hours ago
Yuwen Hu	ba0dca46d7	community[minor]: Add IPEX-LLM BGE embedding support on both Intel CPU and GPU (#22226) ... **Description:** [IPEX-LLM](https://github.com/intel-analytics/ipex-llm) is a PyTorch library for running LLM on Intel CPU and GPU (e.g., local PC with iGPU, discrete GPU such as Arc, Flex and Max) with very low latency. This PR adds ipex-llm integrations to langchain for BGE embedding support on both Intel CPU and GPU. **Dependencies:** `ipex-llm`, `sentence-transformers` **Contribution maintainer**: @Oscilloscope98 **tests and docs**: - langchain/docs/docs/integrations/text_embedding/ipex_llm.ipynb - langchain/docs/docs/integrations/text_embedding/ipex_llm_gpu.ipynb - langchain/libs/community/tests/integration_tests/embeddings/test_ipex_llm.py --------- Co-authored-by: Shengsheng Huang <shannie.huang@gmail.com>	17 hours ago
Jacob Lee	c01467b1f4	core[patch]: RFC: Allow concatenation of messages with multi part content (#22002) ... Anthropic's streaming treats tool calls as different content parts (streamed back with a different index) from normal content in the `content`. This means that we need to update our chunk-merging logic to handle chunks with multi-part content. The alternative is coerceing Anthropic's responses into a string, but we generally like to preserve model provider responses faithfully when we can. This will also likely be useful for multimodal outputs in the future. This current PR does unfortunately make `index` a magic field within content parts, but Anthropic and OpenAI both use it at the moment to determine order anyway. To avoid cases where we have content arrays with holes and to simplify the logic, I've also restricted merging to chunks in order. TODO: tests CC @baskaryan @ccurme @efriis	20 hours ago
Dan	86509161b0	community: fix AzureSearch delete documents (#22315) ... **Description** Fix AzureSearch delete documents method by using FIELDS_ID variable instead of the hard coded "id" value **Issue:** This is linked to this issue: https://github.com/langchain-ai/langchain/issues/22314 Co-authored-by: dseban <dan.seban@neoxia.com>	21 hours ago
Harrison Chase	8fad2e209a	fix error message (#22437) ... Was confusing when language is in Enum but not implemented	21 hours ago
Bagatur	678a19a5f7	infra: bump anthropic mypy 1 (#22373)	21 hours ago
Nuno Campos	ceb73ad06f	core: In BaseRetriever make get_relevant_docs delegate to invoke (#22434) ... - This fixes all the tracing issues with people still using get_relevant_docs, and a change we need for 0.3 anyway Thank you for contributing to LangChain! - [ ] **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" - [ ] **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! - [ ] **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.	22 hours ago
Charles John	2d81a72884	community: fix missing `apify_api_token` field in ApifyWrapper (#22421) ... - **Description:** The `ApifyWrapper` class expects `apify_api_token` to be passed as a named parameter or set as an environment variable. But the corresponding field was missing in the class definition causing the argument to be ignored when passed as a named param. This patch fixes that.	22 hours ago
Joan Fontanals	a7ae16f912	add `embed_image` API to JinaEmbedding (#22416) ... - **Description:** Add `embed_image` to JinaEmbedding to embed images - **Twitter handle:** https://x.com/JinaAI_	22 hours ago
Nuno Campos	ed8e9c437a	core: In RunnableSequence pass kwargs to the first step (#22393) ... - This is a pattern that shows up occasionally in langgraph questions, people chain a graph to something else after, and want to pass the graph some kwargs (eg. stream_mode)	22 hours ago
Bagatur	a8098f5ddb	anthropic[patch]: Release 0.1.15, fix sdk tools break (#22369)	4 days ago
Erick Friis	6ffa0acf32	ai21: fix text-splitters version (#22366)	4 days ago
Bagatur	2b9f1469d8	core[patch]: Release 0.2.3 (#22329)	5 days ago
Harrison Chase	ee32369265	core[patch]: fix runnable history and add docs (#22283)	5 days ago
William FH	dcec133b85	[Core] Update Tracing Interops (#22318) ... LangSmith and LangChain context var handling evolved in parallel since originally we didn't expect people to want to interweave the decorator and langchain code. Once we get a new langsmith release, this PR will let you seemlessly hand off between @traceable context and runnable config context so you can arbitrarily nest code. It's expected that this fails right now until we get another release of the SDK	5 days ago
ccurme	f34337447f	openai: update ChatOpenAI api ref (#22324) ... Update to reflect that token usage is no longer default in streaming mode. Add detail for streaming context under Token Usage section.	5 days ago
ChengZi	2443e85533	docs: fix milvus import and update template (#22306) ... docs: fix milvus import problem update milvus-rag template with milvus-lite Signed-off-by: ChengZi <chen.zhang@zilliz.com>	5 days ago
WU LIFU	86698b02a9	doc: fix wrong documentation on FAISS load_local function (#22310) ... ### Issue: #22299 ### descriptions The documentation appears to be wrong. When the user actually sets this parameter "asynchronous" to be True, it fails because the __init__ function of FAISS class doesn't allow this parameter. In fact, most of the class/instance functions of this class have both the sync/async version, so it looks like what we need is just to remove this parameter from the doc. 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! - [ ] **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. Co-authored-by: Lifu Wu <lifu@nextbillion.ai>	5 days ago
maang-h	596c062cba	community[patch]: Standardize qianfan model init args name (#22322) ... - **Description:** - Standardize qianfan chat model intialization arguments name - qianfan_ak (qianfan api key) -> api_key - qianfan_sk (qianfan secret key) -> secret_key - Delete unuse variable - **Issue:** #20085	5 days ago
Dobiichi-Origami	10b12e1c08	community: adding tool_call_id for every ToolCall (#22323) ... - **Description:** This PR contains a bugfix which result in malfunction of multi-turn conversation in QianfanChatEndpoint and adaption for ToolCall and ToolMessage	5 days ago
ccurme	f39e1a2288	community, docs: update token usage tracking callback + how-to guides (#22145)	6 days ago
Bagatur	2bc50fb895	docs, cli[patch]: chat model template nit (#22294)	6 days ago
Bagatur	aa6c31df53	cli[patch]: Release 0.0.24 (#22293)	6 days ago
Bagatur	627a337887	docs, cli[patch]: chat model doc template (#22290) ... Update ChatModel integration doc template, integration docstring, and adds langchain-cli command to easily create just doc (for updating existing integrations): ```bash langchain-cli integration create-doc --name "foo-bar" ```	6 days ago
ccurme	6e1df72a88	openai[patch]: Release 0.1.8 (#22291)	6 days ago
ccurme	e71b0b5827	core[patch]: Release 0.2.2 (#22289)	6 days ago
Bagatur	6dd0f095c3	docs: revamp ChatOpenAI (#22253) ... Can build API ref docs by running ```bash make api_docs_clean; make api_docs_quick_preview API_PKG=openai ``` only builds openai ref, takes ~20 sec	6 days ago
Erick Friis	00c70d98c2	robocorp: release 0.0.9 (#22282)	6 days ago
Mikko Korpela	fc5909ad6f	langchain-robocorp: Fix parsing of Union types (such as Optional). (#22277)	6 days ago
ccurme	af1f723ada	openai: don't override stream_options default (#22242) ... ChatOpenAI supports a kwarg `stream_options` which can take values `{"include_usage": True}` and `{"include_usage": False}`. Setting include_usage to True adds a message chunk to the end of the stream with usage_metadata populated. In this case the final chunk no longer includes `"finish_reason"` in the `response_metadata`. This is the current default and is not yet released. Because this could be disruptive to workflows, here we remove this default. The default will now be consistent with OpenAI's API (see parameter [here](https://platform.openai.com/docs/api-reference/chat/create#chat-create-stream_options)). Examples: ```python from langchain_openai import ChatOpenAI llm = ChatOpenAI() for chunk in llm.stream("hi"): print(chunk) ``` ``` content='' id='run-8cff4721-2acd-4551-9bf7-1911dae46b92' content='Hello' id='run-8cff4721-2acd-4551-9bf7-1911dae46b92' content='!' id='run-8cff4721-2acd-4551-9bf7-1911dae46b92' content='' response_metadata={'finish_reason': 'stop'} id='run-8cff4721-2acd-4551-9bf7-1911dae46b92' ``` ```python for chunk in llm.stream("hi", stream_options={"include_usage": True}): print(chunk) ``` ``` content='' id='run-39ab349b-f954-464d-af6e-72a0927daa27' content='Hello' id='run-39ab349b-f954-464d-af6e-72a0927daa27' content='!' id='run-39ab349b-f954-464d-af6e-72a0927daa27' content='' response_metadata={'finish_reason': 'stop'} id='run-39ab349b-f954-464d-af6e-72a0927daa27' content='' id='run-39ab349b-f954-464d-af6e-72a0927daa27' usage_metadata={'input_tokens': 8, 'output_tokens': 9, 'total_tokens': 17} ``` ```python llm = ChatOpenAI().bind(stream_options={"include_usage": True}) for chunk in llm.stream("hi"): print(chunk) ``` ``` content='' id='run-59918845-04b2-41a6-8d90-f75fb4506e0d' content='Hello' id='run-59918845-04b2-41a6-8d90-f75fb4506e0d' content='!' id='run-59918845-04b2-41a6-8d90-f75fb4506e0d' content='' response_metadata={'finish_reason': 'stop'} id='run-59918845-04b2-41a6-8d90-f75fb4506e0d' content='' id='run-59918845-04b2-41a6-8d90-f75fb4506e0d' usage_metadata={'input_tokens': 8, 'output_tokens': 9, 'total_tokens': 17} ```	6 days ago
Karim Lalani	a1899439fc	[experimental][llms][ollama_functions] Update OllamaFunctions to send `tool_calls` attribute (#21625) ... Update OllamaFunctions to return `tool_calls` for AIMessages when used for tool calling.	6 days ago
Bagatur	d61bdeba25	core[patch]: allow access RunnableWithFallbacks.runnable attrs (#22139) ... RFC, candidate fix for #13095 #22134	7 days ago
SteveLiao	7496fe2b16	Update parent_document_retriever.py about **kwargs (#22219) ... Add kwargs in add_documents function **langchain**: Add **kwargs in parent_document_retriever" - **Add kwargs for `add_document` in `parent_document_retriever.py`** If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.	7 days ago
Erick Friis	93240fac68	milvus: fix core dep (#22239)	7 days ago
ChengZi	404d92ded0	milvus: New langchain_milvus package and new milvus features (#21077) ... New features: - New langchain_milvus package in partner - Milvus collection hybrid search retriever - Zilliz cloud pipeline retriever - Milvus Local guid - Rag-milvus template --------- Signed-off-by: ChengZi <chen.zhang@zilliz.com> Signed-off-by: Jael Gu <mengjia.gu@zilliz.com> Co-authored-by: Jael Gu <mengjia.gu@zilliz.com> Co-authored-by: Jackson <jacksonxie612@gmail.com> Co-authored-by: Erick Friis <erick@langchain.dev> Co-authored-by: Erick Friis <erickfriis@gmail.com>	7 days ago
Leonid Ganeline	d6995e814b	ai21[patch]: added `license` (#22153) ... The `pyproject.toml` missed the `license` parameter. I've added it as `MIT`	1 week ago
Maddy Adams	8332a36f69	infra: update langchainhub and add integration test (#22154) ... **Description:** Update langchainhub integration test dependency and add an integration test for pulling private prompt **Dependencies:** langchainhub 0.1.16	1 week ago
Will Higgins	83d10df78d	community[patch]: Update firecrawl api key name (#22183) ... Change 'FIREWALL' to 'FIRECRAWL' as I believe this may have been in error. Other docs refer to 'FIRECRAWL_API_KEY'. Thank you for contributing to LangChain! - [ ] **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" - [ ] **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! - [ ] **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. --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	1 week ago