4362 Commits (master)

Author	SHA1	Message	Date
maang-h	9aba9e3e33	community[patch]: Update the default “API URL” and “MODEL” of sparkllm (#22070) ... - **Description:** When I was running the sparkllm, I found that the default parameters currently used could no longer run correctly. - original parameters & values: - spark_api_url: "wss://spark-api.xf-yun.com/v3.1/chat" - spark_llm_domain: "generalv3" ```python # example from langchain_community.chat_models import ChatSparkLLM spark = ChatSparkLLM(spark_app_id="my_app_id", spark_api_key="my_api_key", spark_api_secret="my_api_secret") spark.invoke("hello") ```  So I updated them to 3.5 (same as sparkllm official website). After the update, they can be used normally. - new parameters & values: - spark_api_url: "wss://spark-api.xf-yun.com/v3.5/chat" - spark_llm_domain: "generalv3.5"	2 weeks ago
junkeon	4fda7bf4f2	upstage[patch] : fix error handling in Layout Analysis parser (#22054) ... This pull request addresses and fixes exception handling in the UpstageLayoutAnalysisParser and enhances the test coverage by adding error exception tests for the document loader. These improvements ensure robust error handling and increase the reliability of the system when dealing with external API calls and JSON responses. ### Changes Made 1. Fix Request Exception Handling: - Issue: The existing implementation of UpstageLayoutAnalysisParser did not properly handle exceptions thrown by the requests library, which could lead to unhandled exceptions and potential crashes. - Solution: Added comprehensive exception handling for requests.RequestException to catch any request-related errors. This includes logging the error details and raising a ValueError with a meaningful error message. 2. Add Error Exception Tests for Document Loader: - New Tests: Introduced new test cases to verify the robustness of the UpstageLayoutAnalysisLoader against various error scenarios. The tests ensure that the loader gracefully handles: - RequestException: Simulates network issues or invalid API requests to ensure appropriate error handling and user feedback. - JSONDecodeError: Simulates scenarios where the API response is not a valid JSON, ensuring the system does not crash and provides clear error messaging.	2 weeks ago
JuHyung Son	d9eff44400	partner-upstage[patch]: embeddings empty list bug (#22057) ... Fixed an error in `embed_documents` when the input was given as an empty list. And I have revised the document.	2 weeks ago
Martin Triska	2df8ac402a	community[minor]: Added propagation of document metadata from O365BaseLoader (#20663) ... **Description:** - Added propagation of document metadata from O365BaseLoader to FileSystemBlobLoader (O365BaseLoader uses FileSystemBlobLoader under the hood). - This is done by passing dictionary `metadata_dict`: key=filename and value=dictionary containing document's metadata - Modified `FileSystemBlobLoader` to accept the `metadata_dict`, use `mimetype` from it (if available) and pass metadata further into blob loader. **Issue:** - `O365BaseLoader` under the hood downloads documents to temp folder and then uses `FileSystemBlobLoader` on it. - However metadata about the document in question is lost in this process. In particular: - `mime_type`: `FileSystemBlobLoader` guesses `mime_type` from the file extension, but that does not work 100% of the time. - `web_url`: this is useful to keep around since in RAG LLM we might want to provide link to the source document. In order to work well with document parsers, we pass the `web_url` as `source` (`web_url` is ignored by parsers, `source` is preserved) **Dependencies:** None **Twitter handle:** @martintriska1 Please review @baskaryan --------- Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com> Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>	2 weeks ago
Eugene Yurtsev	e5541d1da7	community[patch]: Update doc-string in CloudBlobLoader (#22069) ... Update doc-string	2 weeks ago
Philippe PRADOS	6dd621d636	community[minor]: Add CloudBlobLoader that supports loading data from cloud buckets (#21957) ... Thank you for contributing to LangChain! - [ ] **PR title**: "Add CloudBlobLoader" - community: Add CloudBlobLoader - [ ] **PR message**: Add cloud blob loader - **Description:** Langchain provides several approaches to read different file formats: Specific loaders (`CVSLoader`) or blob-compatible loaders (`FileSystemBlobLoader`). The only implementation proposed for BlobLoader is `FileSystemBlobLoader`. Many projects retrieve files from cloud storage. We propose a new implementation of `BlobLoader` to read files from the three cloud storage systems. The interface is strictly identical to `FileSystemBlobLoader`. The only difference is the constructor, which takes a cloud "url" object such as `s3://my-bucket`, `az://my-bucket`, or `gs://my-bucket`. By streamlining the process, this novel implementation eliminates the requirement to pre-download files from cloud storage to local temporary files (which are seldom removed). The code relies on the [CloudPathLib](https://cloudpathlib.drivendata.org/stable/) library to interpret cloud URLs. This has been added as an optional dependency. ```Python loader = CloudBlobLoader("s3://mybucket/id") for blob in loader.yield_blobs(): print(blob) ``` - [X] **Dependencies:** CloudPathLib - [X] **Twitter handle:** pprados - [X] **Add tests and docs**: Add unit test, but it's easy to convert to integration test, with some files in a cloud storage (see `test_cloud_blob_loader.py`) - [X] **Lint and test**: Run `make format`, `make lint` and `make test` from the root of the package(s) you've modified. Hello from Paris @hwchase17. Can you review this PR? --------- Co-authored-by: Eugene Yurtsev <eugene@langchain.dev>	2 weeks ago
Christophe Bornet	74947ec894	community[minor]: Add Cassandra ByteStore (#22064)	2 weeks ago
Christophe Bornet	fea6b99b16	community[minor]: Add async methods to CassandraChatMessageHistory (#21975)	2 weeks ago
Sky	12d65f17ff	community[patch]: surrealdb provide functions for MMR (Maximal Marginal Relevance) (#21185) ... This PR contains 4 added functions: - max_marginal_relevance_search_by_vector - amax_marginal_relevance_search_by_vector - max_marginal_relevance_search - amax_marginal_relevance_search I'm no langchain expert, but tried do inspect other vectorstore sources like chroma, to build these functions for SurrealDB. If someone has some changes for me, please let me know. Otherwise I would be happy, if these changes are added to the repository, so that I can use the orignal repo and not my local monkey patched version. --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com> Co-authored-by: Bagatur <baskaryan@gmail.com>	2 weeks ago
Bruno Alvisio	5eabe90494	community[patch]: Adding HEADER to the list of supported locations (#21946) ... **Description:** adds headers to the list of supported locations when generating the openai function schema	2 weeks ago
Bagatur	50186da0a1	infra: rm unused # noqa violations (#22049) ... Updating #21137	2 weeks ago
acho98	45ed5f3f51	community[minor]: Add Clova Embeddings for LangChain Community (#21890) ... - [ ] **PR title**: "Add Naver ClovaX embedding to LangChain community" - HyperClovaX is a large language model developed by [Naver](https://clova-x.naver.com/welcome). It's a powerful and purpose-trained LLM. - You can visit the embedding service provided by [ClovaX](https://www.ncloud.com/product/aiService/clovaStudio) - You may get CLOVA_EMB_API_KEY, CLOVA_EMB_APIGW_API_KEY, CLOVA_EMB_APP_ID From https://www.ncloud.com/product/aiService/clovaStudio --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	2 weeks ago
arpitkumar980	444c2a3d9f	community[patch]: sharepoint loader identity enabled (#21176) ... 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:https://github.com/arpitkumar980/langchain.git - 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, hwchase17. --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com> Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	2 weeks ago
HuiyuanYan	bf3aefce93	community[patch]: Update tongyi.py to support MultimodalConversation in dashscope. (#21249) ... Add the support of multimodal conversation in dashscope,now we can use multimodal language model "qwen-vl-v1", "qwen-vl-chat-v1", "qwen-audio-turbo" to processing picture an audio. :) - [ ] **PR title**: "community: add multimodal conversation support in dashscope" - [ ] **PR message**: ***Delete this entire checklist*** and replace with - **Description:** add multimodal conversation support in dashscope - **Issue:** - **Dependencies:** dashscope≥1.18.0 - **Twitter handle:** none :) - [ ] **How to use it?**: - ```python Tongyi_chat = ChatTongyi( top_p=0.5, dashscope_api_key=api_key, model="qwen-vl-v1" ) response= Tongyi_chat.invoke( input = [ { "role": "user", "content": [ {"image": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg"}, {"text": "这是什么?"} ] } ] ) ``` --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	2 weeks ago
mochi	63284ffebf	experimental[patch], docs: refine notebook for MyScale `SelfQueryRetriever` (#22016) ... - **Description:** upgrade model to `gpt-4o`	2 weeks ago
MSubik	d948783a4c	community[patch]: standardize init args, update for javelin sdk release. (#21980) ... Related to [20085](https://github.com/langchain-ai/langchain/issues/20085) Updated the Javelin chat model to standardize the initialization argument. Also fixed an existing bug, where code was initialized with incorrect call to the JavelinClient defined in the javelin_sdk, resulting in an initialization error. See related [Javelin Documentation](https://docs.getjavelin.io/docs/javelin-python/quickstart).	2 weeks ago
Mohammad Mohtashim	16617dd239	community[patch]: AzureSearchVectorStoreRetriever Fixed to account for search_kwargs (#21572) ... - **Description:** Fixed `AzureSearchVectorStoreRetriever` to account for search_kwargs. More explanation is in the mentioned issue. - **Issue:** #21492 --------- Co-authored-by: MAC <mac@MACs-MacBook-Pro.local> Co-authored-by: Massimiliano Pronesti <massimiliano.pronesti@gmail.com> Co-authored-by: Bagatur <baskaryan@gmail.com>	2 weeks ago
Klaudia Lemiec	45351d1bc6	docs: Chroma docstrings update (#22001) ... Thank you for contributing to LangChain! - [X] **PR title**: "docs: Chroma docstrings update" - 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**: - **Description:** Added and updated Chroma docstrings - **Issue:** https://github.com/langchain-ai/langchain/issues/21983 - [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. - only docs - [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.	2 weeks ago
Jerron Lim	28456c2c33	community[patch]: add args_schema to WikipediaQueryRun (#22019) ... Description: This change adds args_schema (pydantic BaseModel) to WikipediaQueryRun for correct schema formatting on LLM function calls Issue: currently using WikipediaQueryRun with OpenAI function calling returns the following error "TypeError: WikipediaQueryRun._run() got an unexpected keyword argument '__arg1' ". This happens because the schema sent to the LLM is "input: '{"__arg1":"Hunter x Hunter"}'" while the method should be called with the "query" parameter. --------- Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com> Co-authored-by: Bagatur <baskaryan@gmail.com>	2 weeks ago
Mazen Ramadan	3c1d77dd64	community[minor]: Add Scrapfly Loader community integration (#22036) ... Added [Scrapfly](https://scrapfly.io/) Web Loader integration. Scrapfly is a web scraping API that allows extracting web page data into accessible markdown or text datasets. - __Description__: Added Scrapfly web loader for retrieving web page data as markdown or text. - Dependencies: scrapfly-sdk - Twitter: @thealchemi1st --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	2 weeks ago
ccurme	b51a1eba4d	langchain, community: move OpenAIAssistantV2Runnable to community (#22044)	2 weeks ago
CaroFG	6b98140b38	community[patch]: update for compatibility with Meilisearch v1.8 (#21979) ... 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:** Updates Meilisearch vectorstore for compatibility with v1.8. Adds [”showRankingScore”: true”](https://www.meilisearch.com/docs/reference/api/search#ranking-score) in the search parameters and replaces `_semanticScore` field with ` _rankingScore` - [ ] **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.	2 weeks ago
Oleksii Pokotylo	98c0b093bb	community[patch]: Extend AzureSearch with `maximal_marginal_relevance`, `from_embeddings` (#21065) ... **Description:** - Extend AzureSearch with `maximal_marginal_relevance` (for vector and hybrid search) - Add construction `from_embeddings` - if the user has already embedded the texts - Add `add_embeddings` - Refactor common parts (`_simple_search`, `_results_to_documents`, `_reorder_results_with_maximal_marginal_relevance`) - Add `vector_search_dimensions` as a parameter to the constructor to avoid extra calls to `embed_query` (most of the time the user applies the same model and knows the dimension) **Issue:** none **Dependencies:** none - [x] **Add tests and docs**: The docstrings have been added to the new functions, and unified for the existing ones. The example notebook is great in illustrating the main usage of AzureSearch, adding the new methods would only dilute the main content. - [x] **Lint and test** --------- Co-authored-by: Oleksii Pokotylo <oleksii.pokotylo@pwc.com> Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com> Co-authored-by: Bagatur <baskaryan@gmail.com>	2 weeks ago
SaschaStoll	709664a079	community[patch]: Performant filter columns option for Hanavector (#21971) ... **Description:** Backwards compatible extension of the initialisation interface of HanaDB to allow the user to specify specific_metadata_columns that are used for metadata storage of selected keys which yields increased filter performance. Any not-mentioned metadata remains in the general metadata column as part of a JSON string. Furthermore switched to executemany for batch inserts into HanaDB. **Issue:** N/A **Dependencies:** no new dependencies added **Twitter handle:** @sapopensource --------- Co-authored-by: Martin Kolb <martin.kolb@sap.com> Co-authored-by: Bagatur <baskaryan@gmail.com>	2 weeks ago
Bagatur	16b55b0704	langchain[patch]: remove dataclasses-json dep (#22042) ... vestigial dep afaict	2 weeks ago
Christos Boulmpasakos	c3bcfad66d	text-splitters[patch]: Extend TextSplitter:keep_separator functionality (#21130) ... **Description:** Added extra functionality to `CharacterTextSplitter`, `TextSplitter` classes. The user can select whether to append the separator to the previous chunk with `keep_separator='end' ` or else prepend to the next chunk. Previous functionality prepended by default to next chunk. **Issue:** Fixes #20908 --------- Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	2 weeks ago
Eric Zhang	e7e41eaabe	langchain: add RankLLM Reranker (#21171) ... Integrate RankLLM reranker (https://github.com/castorini/rank_llm) into LangChain An example notebook is given in `docs/docs/integrations/retrievers/rankllm-reranker.ipynb` --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	2 weeks ago
maang-h	fc93bed8c4	community: Fix CSVLoader columns is None (#20701) ... - **Bug code**: In langchain_community/document_loaders/csv_loader.py:100 - **Description**: currently, when 'CSVLoader' reads the column as None in the 'csv' file, it will report an error because the 'CSVLoader' does not verify whether the column is of str type and does not consider how to handle the corresponding 'row_data' when the column is' None 'in the csv. This pr provides a solution. - **Issue:** Fix #20699 - **thinking:** 1. Refer to the processing method for 'langchain_community/document_loaders/csv_loader.py:100' when **'v'** equals'None', and apply the same method to '**k**'. (Reference`csv.DictReader` ,**'k'** will only be None when ` len(columns) < len(number_row_data)` is established) 2. **‘k’** equals None only holds when it is the last column, and its corresponding **'v'** type is a list. Therefore, I referred to the data format in 'Document' and used ',' to concatenated the elements in the list.(But I'm not sure if you accept this form, if you have any other ideas, communicate) --------- Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	2 weeks ago
Nithin James Padayatti	403142eaba	langchain: added revision_example prompt template (#20916) ... **Description:** Added revision_example prompt template to include the revision request and revision examples in the revision chain. **Issue:** Not Applicable **Dependencies:** Not Applicable **Twitter handle:** @nithinjp09	2 weeks ago
Sihan Chen	1f81277b9b	community[minor]: allow enabling proxy in aiohttp session in AsyncHTML (#19499) ... Allow enabling proxy in aiohttp session async html	2 weeks ago
Eugene Yurtsev	36813d2f00	community[patch]: Fix remaining __inits__ in community (#22037) ... Fixes the __init__ files in community to use __all__ which is statically defined.	2 weeks ago
Eugene Yurtsev	58360a1e53	community[patch]: Add unit test to verify that init is correctly defined (#22030) ... Fix some __init__ files and add a unit test	2 weeks ago
Erick Friis	ef53ccf54b	robocorp: release 0.0.8 (#22034)	2 weeks ago
Matthew Hoffman	4f2e3bd7fd	community[patch]: fix public interface for embeddings module (#21650) ... ## Description The existing public interface for `langchain_community.emeddings` is broken. In this file, `__all__` is statically defined, but is subsequently overwritten with a dynamic expression, which type checkers like pyright do not support. pyright actually gives the following diagnostic on the line I am requesting we remove: [reportUnsupportedDunderAll](https://github.com/microsoft/pyright/blob/main/docs/configuration.md#reportUnsupportedDunderAll): ``` Operation on "__all__" is not supported, so exported symbol list may be incorrect ``` Currently, I get the following errors when attempting to use publicablly exported classes in `langchain_community.emeddings`: ```python import langchain_community.embeddings langchain_community.embeddings.HuggingFaceEmbeddings(...) # error: "HuggingFaceEmbeddings" is not exported from module "langchain_community.embeddings" (reportPrivateImportUsage) ``` This is solved easily by removing the dynamic expression.	2 weeks ago
Eugene Yurtsev	8d82160a8a	community[patch]: Clean up logic in import checking unit test (#22026) ... Clean up unit test	2 weeks ago
Tomaz Bratanic	d8a1f1114d	community[patch]: Handle exceptions where node props aren't consistent in neo4j schema (#22027)	2 weeks ago
WeichenXu	b0ef5e778a	community[patch]: Fix ChatDatabricsk in case that streaming response doesn't have role field in delta chunk (#21897) ... 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" **Description:** Fix ChatDatabricsk in case that streaming response doesn't have role field in delta chunk - [ ] **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, hwchase17. --------- Signed-off-by: Weichen Xu <weichen.xu@databricks.com>	2 weeks ago
Eugene Yurtsev	aed64daabb	community[patch]: Add unit test to catch bad __all__ definitions (#21996) ... This will catch all dynamic __all__ definitions.	2 weeks ago
Bagatur	3b0437c05b	core[patch]: Release 0.2.1 (#22003)	2 weeks ago
Kefan You	24b5c27bb1	community[patch]: raise_for_status logic missing in async _fetch of WebBaseLoader (#21948) ... ## 'raise_for_status' parameter of WebBaseLoader works in sync load but not in async load. In webBaseLoader: Sync load is calling `_scrape` and has `raise_for_status` properly handled. ``` def _scrape( self, url: str, parser: Union[str, None] = None, bs_kwargs: Optional[dict] = None, ) -> Any: from bs4 import BeautifulSoup if parser is None: if url.endswith(".xml"): parser = "xml" else: parser = self.default_parser self._check_parser(parser) html_doc = self.session.get(url, **self.requests_kwargs) if self.raise_for_status: html_doc.raise_for_status() if self.encoding is not None: html_doc.encoding = self.encoding elif self.autoset_encoding: html_doc.encoding = html_doc.apparent_encoding return BeautifulSoup(html_doc.text, parser, **(bs_kwargs or {})) ``` Async load is calling `_fetch` but missing `raise_for_status` logic. ``` async def _fetch( self, url: str, retries: int = 3, cooldown: int = 2, backoff: float = 1.5 ) -> str: async with aiohttp.ClientSession() as session: for i in range(retries): try: async with session.get( url, headers=self.session.headers, ssl=None if self.session.verify else False, cookies=self.session.cookies.get_dict(), ) as response: return await response.text() ``` Co-authored-by: kefan.you <darkfss@sina.com>	2 weeks ago
Surya Rath	eb096675a8	OpenAI Assistants v2 api support for OpenAIAssistantRunnable (#21484) ... **Title**: "langchain: OpenAI Assistants v2 api support" ***Descriptions*** - [x] "attachments" support added along with backward compatibility of "file_ids" - [x] "tool_resources" support added while creating new assistant - [ ] "tool_choice" parameter support - [ ] Streaming support - **Dependencies:** OpenAI v2 API (openai>=1.23.0) - **Twitter handle:** @skanta_rath --------- Co-authored-by: Chester Curme <chester.curme@gmail.com>	2 weeks ago
Eugene Yurtsev	7a5d042bd2	langchain[patch]: Add unit test to detect changes to community imports (#21998) ... Add unit tests for community imports	2 weeks ago
Eugene Yurtsev	90f4d8842f	langchain[patch]: Turn on all deprecations for 0.2 (#21999) ... - Turn on all 0.2 import deprecations. - Update error messag with URL to upgrade instructions.	2 weeks ago
Asaf Joseph Gardin	a042e804b4	ai21: AI21 Jamba docs (#21978) ... - Updated docs to have an example to use Jamba instead of J2 --------- Co-authored-by: Asaf Gardin <asafg@ai21.com> Co-authored-by: Erick Friis <erick@langchain.dev>	2 weeks ago
Pengcheng Liu	4cf523949a	community[patch]: Update model client to support vision model in Tong… (#21474) ... - **Description:** Tongyi uses different client for chat model and vision model. This PR chooses proper client based on model name to support both chat model and vision model. Reference [tongyi document](https://help.aliyun.com/zh/dashscope/developer-reference/tongyi-qianwen-vl-plus-api?spm=a2c4g.11186623.0.0.27404c9a7upm11) for details. ``` from langchain_core.messages import HumanMessage from langchain_community.chat_models import ChatTongyi llm = ChatTongyi(model_name='qwen-vl-max') image_message = { "image": "https://lilianweng.github.io/posts/2023-06-23-agent/agent-overview.png" } text_message = { "text": "summarize this picture", } message = HumanMessage(content=[text_message, image_message]) llm.invoke([message]) ``` - **Issue:** None - **Dependencies:** None - **Twitter handle:** None	2 weeks ago
Sevin F. Varoglu	1bc0ea5496	community[patch]: update OctoAIEmbeddings to subclass OpenAIEmbeddings (#21805)	2 weeks ago
Eugene Yurtsev	ded53297e0	core[patch]: Add unit test for RunnableGenerator for eventstream v2 (#21990) ... No unit tests with runnable generator	2 weeks ago
Nuno Campos	fb6108c8f5	core[patch]: In astream_events(version=v2) tap output of root run (#21977) ... - if tap_output_iter/aiter is called multiple times for the same run issue events only once - if chat model run is tapped don't issue duplicate on_llm_new_token events - if first chunk arrives after run has ended do not emit it as a stream event --------- Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>	2 weeks ago
Bagatur	72d4a8eeed	community[patch]: AzureSearch dont overwrite default async (#21989)	2 weeks ago
ccurme	a983465694	docs: set default anthropic model (#21988) ... `ChatAnthropic()` raises ValidationError.	2 weeks ago
ccurme	4be5537837	Revert "anthropic: set default model" (#21987) ... Reverts langchain-ai/langchain#21986	2 weeks ago
ccurme	35439cf3bd	anthropic: set default model (#21986) ... Various docs reference `ChatAnthropic()`, but this currently raises ValidationError.	2 weeks ago
ccurme	0923136851	langchain: default to Runnable in MultiQueryRetriever (#21770) ... - `llm_chain` becomes `Union[LLMChain, Runnable]` - `.from_llm` creates a runnable tested by verifying that docs/how_to/MultiQueryRetriever.ipynb runs unchanged with sync/async invoke (and that it runs if we specifically instantiate with LLMChain).	2 weeks ago
Yulong Wang	8e1aeb8ad5	community[patch]: Fix typo in arxiv tool's doc (#21970) ... Fix typo in arxiv tool's doc	2 weeks ago
Robert Caulk	54adcd9e82	community[minor]: add AskNews retriever and AskNews tool (#21581) ... We add a tool and retriever for the [AskNews](https://asknews.app) platform with example notebooks. The retriever can be invoked with: ```py from langchain_community.retrievers import AskNewsRetriever retriever = AskNewsRetriever(k=3) retriever.invoke("impact of fed policy on the tech sector") ``` To retrieve 3 documents in then news related to fed policy impacts on the tech sector. The included notebook also includes deeper details about controlling filters such as category and time, as well as including the retriever in a chain. The tool is quite interesting, as it allows the agent to decide how to obtain the news by forming a query and deciding how far back in time to look for the news: ```py from langchain_community.tools.asknews import AskNewsSearch from langchain import hub from langchain.agents import AgentExecutor, create_openai_functions_agent from langchain_openai import ChatOpenAI tool = AskNewsSearch() instructions = """You are an assistant.""" base_prompt = hub.pull("langchain-ai/openai-functions-template") prompt = base_prompt.partial(instructions=instructions) llm = ChatOpenAI(temperature=0) asknews_tool = AskNewsSearch() tools = [asknews_tool] agent = create_openai_functions_agent(llm, tools, prompt) agent_executor = AgentExecutor( agent=agent, tools=tools, verbose=True, ) agent_executor.invoke({"input": "How is the tech sector being affected by fed policy?"}) ``` --------- Co-authored-by: Emre <e@emre.pm>	2 weeks ago
Jesse S	fc79b372cb	community[minor]: add aerospike vectorstore integration (#21735) ... Please let me know if you see any possible areas of improvement. I would very much appreciate your constructive criticism if time allows. **Description:** - Added a aerospike vector store integration that utilizes [Aerospike-Vector-Search](https://aerospike.com/products/vector-database-search-llm/) add-on. - Added both unit tests and integration tests - Added a docker compose file for spinning up a test environment - Added a notebook **Dependencies:** any dependencies required for this change - aerospike-vector-search **Twitter handle:** - No twitter, you can use my GitHub handle or LinkedIn if you'd like Thanks! --------- Co-authored-by: Jesse Schumacher <jschumacher@aerospike.com> Co-authored-by: Bagatur <baskaryan@gmail.com>	2 weeks ago
Prince Canuma	3587c60396	community[patch]: Fix MLX LLM Stream (#20575) ... Closes #20561 This PR fixes MLX LLM stream `AttributeError`. Recently, `mlx-lm` changed the token decoding logic, which affected the LC+MLX integration. Additionally, I made minor fixes such as: docs example broken link and enforcing pipeline arguments (max_tokens, temp and etc) for invoke. - **Issue:** #20561 - **Twitter handle:** @Prince_Canuma	2 weeks ago
Rahul Triptahi	96bd0b0844	community[patch]: Remove redundant pebblo cloud api call (#21589) ... Description: removed redundant pebblo cloud api call. Changed classified `doc` key to `ai_apps_data`. Documentation: N/A Unit tests: N/A	2 weeks ago
Param Singh	d07885f8b7	community[patch]: standardized sparkllm init args (#21633) ... Related to #20085 @baskaryan Thank you for contributing to LangChain! community:sparkllm[patch]: standardized init args updated `spark_api_key` so that aliased to `api_key`. Added integration test for `sparkllm` to test that it continues to set the same underlying attribute. updated temperature with Pydantic Field, added to the integration test. Ran `make format`,`make test`, `make lint`, `make spell_check`	2 weeks ago
Dhruv Chawla	d4359d3de6	community[patch]: Update UpTrain Callback Handler to support the new UpTrain evaluation schema (#21656) ... UpTrain has a new dashboard now that makes it easier to view projects and evaluations. Using this requires specifying both project_name and evaluation_name when performing evaluations. I have updated the code to support it.	2 weeks ago
Alex Riina	c0e3c3a350	openai[patch], community[patch]: add pricing and max context window for GPT-4o (#21673) ... # Add pricing and max context window for GPT-4o - community: add cost per 1k tokens and max context window - partners: add max context window **Description:** adds static information about GPT-4o based on https://openai.com/api/pricing/ and https://platform.openai.com/docs/models/gpt-4o so that GPT-4o reporting is accurate. --------- Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com> Co-authored-by: Bagatur <baskaryan@gmail.com>	2 weeks ago
缨缨	bd39b2ccdf	community: enable SupabaseVectorStore to support extended table fields (#21762) ... Thank you for contributing to LangChain! - [x] **PR title**: "community: enable SupabaseVectorStore to support extended table fields" - [x] **PR message**: - Added extension fields to the function _add_vectors so that users can add other custom fields when insert a record into the database. eg:  --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	2 weeks ago
Leonid Ganeline	e98a4fd19a	ai21[patch]: configuration fix (#21790) ... added "repository" and "Source Code" parameters (these parameters are missed only in this partner package configuration).	2 weeks ago
Trayan Azarov	f54cbf8ff5	chroma[patch]: Chroma - remove reference to collection upon delete_collection (#21817) ... **Description**: - Reference to `Collection` object is set to `None` when deleting a collection `delete_collection()` - Added utility method `reset_collection()` to allow recreating the collection - Moved collection creation out of `__init__` into `__ensure_collection()` to be reused by object init and `reset_collection()` - `_collection` is now a property to avoid breaking changes **Issues**: - chroma-core/chroma#2213 **Twitter**: @t_azarov	2 weeks ago
Jens	b0b302ec6b	community[patch]: fixed aleph alpha default emedding request (#21826) ... - **Description:** In the aleph alpha client the paramater `normalize` is *not* optional. Setting this to `None` gives an error. - **Dependencies:** None Co-authored-by: Jens Lücke <jens.luecke@tngtech.com> Co-authored-by: Jens <jens.luecke@hu-berlin.de> Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	2 weeks ago
Jorge Piedrahita Ortiz	e6207ad4f3	community[patch]: Sambanova integration api update (#21848) ... - **Description:**: SambaStudio generic endpoint compatibility added Improved error description, and handling streaming examples added	2 weeks ago
Michael Reed	7a5e1bcf99	core[patch]: Fix NPE in function_calling._get_python_function_required_args (#21863) ... Example error message: line 206, in _get_python_function_required_args if is_function_type and required[0] == "self": ~~~~~~~~^^^ IndexError: list index out of range 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, hwchase17. --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	2 weeks ago
Liuww	332ffed393	community[patch]: Adopting the lighter-weight xinference_client (#21900) ... While integrating the xinference_embedding, we observed that the downloaded dependency package is quite substantial in size. With a focus on resource optimization and efficiency, if the project requirements are limited to its vector processing capabilities, we recommend migrating to the xinference_client package. This package is more streamlined, significantly reducing the storage space requirements of the project and maintaining a feature focus, making it particularly suitable for scenarios that demand lightweight integration. Such an approach not only boosts deployment efficiency but also enhances the application's maintainability, rendering it an optimal choice for our current context. --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	2 weeks ago
Tomaz Bratanic	a43515ca65	experimental[patch]: Pass enum only to openai in llm graph transformer (#21860) ... Some models like Groq return bad request if you pass in `enum` parameter in tool definition	2 weeks ago
Jiří Spilka	6499897c87	community[patch]: update apify integration to attribute API activity to langchain (#21909) ... **Description:** Add `Origin/langchain` to Apify's client's user-agent to attribute API activity to LangChain (at Apify, we aim to monitor our integrations to evaluate whether we should invest more in the LangChain integration regarding functionality and content) **Issue:** None **Dependencies:** None **Twitter handle:** None	2 weeks ago
Jared Van Bortel	25d1c1c9bb	nomic: implement local embeddings with the inference_mode parameter (#21934) ... ## Description This PR implements local and dynamic mode in the Nomic Embed integration using the inference_mode and device parameters. They work as documented [here](https://docs.nomic.ai/reference/python-api/embeddings#local-inference). <!-- If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, hwchase17. --> --------- Co-authored-by: Erick Friis <erickfriis@gmail.com>	2 weeks ago
ccurme	0e72ed39a0	infra: fix CI on text-splitters (#21935)	2 weeks ago
ccurme	4470d3b4a0	partners: bump core in packages implementing ls_params (#21868) ... These packages all import `LangSmithParams` which was released in langchain-core==0.2.0. N.B. we will need to release `openai` and then bump `langchain-openai` in `together` and `upstage`.	2 weeks ago
ccurme	9c76739425	mistral: implement ls_params (#21867)	2 weeks ago
Tomaz Bratanic	d85e46321a	community[patch]: Better error message for neo4j vector when text is null (#21861)	2 weeks ago
Stefano Lottini	f2e75f9500	cli[minor]: fix import path for two Astra DB classes in the migration json data (#21926) ... This PR fixes two mistakes in the import paths from community for the json data aiding the cli migration to 0.2. It is intended as a quick follow-up to https://github.com/langchain-ai/langchain/pull/21913 . @nicoloboschi FYI	2 weeks ago
WilliamEspegren	30bca57aae	doc list not empty (#21208) ... Make sure the doc list is not empty, and set Metadata: true in param, to enable the user to disable metadata for slightly faster crawls.	2 weeks ago
David Charles	8da35fba7f	langchain[minor]: add libs/partners to dev.Dockerfile (#21902) ... Resolves #21886 by adding "COPY libs/partners ../partners/" to libs/dev.Dockerfile Twitter: @kabakongo	2 weeks ago
TJ	8cd6ed3e1e	community[patch]: Update documentation string in databricks chat model (#21915) ... Update typos in documentation string in databricks chat model	2 weeks ago
Nicolò Boschi	dd00aac7ad	cli[minor]: add astradb in the cli migration to 0.2 (#21913) ... astradb has a new partner package but the automatic migration cli tool doesn't take care of migration astradb integrations	2 weeks ago
Coozywana	b6c8b6f944	Fix base.py typo (#21862) ... ChatOpenaAI --> ChatOpenAI 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, hwchase17.	2 weeks ago
fzowl	d3624eaba1	partners: Remove unnecessary print from voyageai embeddings (#21865) ... Thank you for contributing to LangChain! Remove unnecessary print from voyageai embeddings - [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, hwchase17.	2 weeks ago
Bagatur	8b3c5f93f5	docs: lcel how to and cheatsheet (#21851)	2 weeks ago
Nuno Campos	b1e7b40b6a	core: Tap output of sync iterators for astream_events (#21842) ... 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, hwchase17.	2 weeks ago
Eugene Yurtsev	67b6f6c82a	core[patch]: Check if event loop is closed in memory stream (#21841) ... Check if event stream is closed in memory loop. Using try/except here to avoid race condition, but this may incur a small overhead in versions prios to 3.11	2 weeks ago
Erick Friis	2d3f4e1a16	experimental: release 0.0.59 (#21835)	2 weeks ago
Erick Friis	169f525cfb	community: release 0.2.0 (#21834)	2 weeks ago
Erick Friis	e5046cbd72	langchain: release 0.2.0, fix min deps (#21833)	2 weeks ago
Erick Friis	1b555021f7	text-splitters: release 0.2.0 (#21832)	2 weeks ago
Erick Friis	0ad8de5eb7	langchain: release 0.2.0 (#21831)	2 weeks ago
Erick Friis	23310626b3	core: release 0.2.0 (#21829)	2 weeks ago
Eugene Yurtsev	e3f30b4cde	docs: clean up link to bing search (#21825) ... Documentation should be inlined, not linking to medium article.	2 weeks ago
ccurme	181dfef118	core, standard tests, partner packages: add test for model params (#21677) ... 1. Adds `.get_ls_params` to BaseChatModel which returns ```python class LangSmithParams(TypedDict, total=False): ls_provider: str ls_model_name: str ls_model_type: Literal["chat"] ls_temperature: Optional[float] ls_max_tokens: Optional[int] ls_stop: Optional[List[str]] ``` by default it will only return ```python {ls_model_type="chat", ls_stop=stop} ``` 2. Add these params to inheritable metadata in `CallbackManager.configure` 3. Implement `.get_ls_params` and populate all params for Anthropic + all subclasses of BaseChatOpenAI Sample trace: https://smith.langchain.com/public/d2962673-4c83-47c7-b51e-61d07aaffb1b/r **OpenAI**: <img width="984" alt="Screenshot 2024-05-17 at 10 03 35 AM" src="https://github.com/langchain-ai/langchain/assets/26529506/2ef41f74-a9df-4e0e-905d-da74fa82a910"> **Anthropic**: <img width="978" alt="Screenshot 2024-05-17 at 10 06 07 AM" src="https://github.com/langchain-ai/langchain/assets/26529506/39701c9f-7da5-4f1a-ab14-84e9169d63e7"> **Mistral** (and all others for which params are not yet populated): <img width="977" alt="Screenshot 2024-05-17 at 10 08 43 AM" src="https://github.com/langchain-ai/langchain/assets/26529506/37d7d894-fec2-4300-986f-49a5f0191b03">	2 weeks ago
Sen Lin	eb7f07ae36	community[patch]: fix typo in ValueError message in load_local function (#21818) ... **Description:** Corrected an error in the `allow_dangerous_deserialization` message within the `load_local` functions	2 weeks ago
Jorge Piedrahita Ortiz	700b1c7212	community: sambaverse api update (#21816) ... - **Description:** fix sambaverse integration to make it compatible with sambaverse API update / minor changes in docs	2 weeks ago
maang-h	9f8d18c028	community[patch]: Fix unintended newline in print statement in exception for BaichuanTextEmbeddings (#21820) ... - **Code:** langchain_community/embeddings/baichuan.py:82 - **Description:** When I make an error using 'baichuan embeddings', the printed error message is wrapped (there is actually no need to wrap) ```python # example from langchain_community.embeddings import BaichuanTextEmbeddings # error key BAICHUAN_API_KEY = "sk-xxxxxxxxxxxxx" embeddings = BaichuanTextEmbeddings(baichuan_api_key=BAICHUAN_API_KEY) text_1 = "今天天气不错" query_result = embeddings.embed_query(text_1) ``` 	2 weeks ago
Bakar Tavadze	3b5ac44e03	langchain-robocorp[minor]: Enable passing additional headers to the action server. (#21809) ... Actions can optionally receive secrets via request headers. This PR enables this functionality.	2 weeks ago
Asaf Joseph Gardin	f3289b898c	partners: Revert AI21 Labs docs scan feature (#21699) ... Description: Reverted commit #21614 --------- Co-authored-by: Asaf Gardin <asafg@ai21.com> Co-authored-by: Erick Friis <erick@langchain.dev>	2 weeks ago
Eugene Yurtsev	8607735b80	langchain[patch],community[patch]: Move unit tests that depend on community to community (#21685)	2 weeks ago
Marco Lamina	d0fae6cd54	community: Add token cost for GPT-4o model (#21771) ... Adding [token cost for the new GPT-4o model](https://openai.com/api/pricing/): * Input cost US$5.00 / 1M tokens * Output cost US$15.00 / 1M tokens	2 weeks ago