6164 Commits (700428593a86531ae0c891096c0d02aabcbc72af)

 

All Branches   

Search

Author	SHA1	Message	Date
Tomaz Bratanic	3eb391561b	langchain[minor]: Reduce the number of tokens required to describe a Cypher/Neo4j schema (#13851) ... Instead of using JSON-like syntax to describe node and relationship properties we changed to a shorter and more concise schema description Old: ``` Node properties are the following: [{'properties': [{'property': 'name', 'type': 'STRING'}], 'labels': 'Movie'}, {'properties': [{'property': 'name', 'type': 'STRING'}], 'labels': 'Actor'}] Relationship properties are the following: [] The relationships are the following: ['(:Actor)-[:ACTED_IN]->(:Movie)'] ``` New: ``` Node properties are the following: Movie {name: STRING},Actor {name: STRING} Relationship properties are the following: The relationships are the following: (:Actor)-[:ACTED_IN]->(:Movie) ```	9 months ago
Sauhaard	7ec4dbeb80	langchain[minor]: Add StackExchange API integration (#14002) ... Implements [#12115](https://github.com/langchain-ai/langchain/issues/12115) Who can review? @baskaryan , @eyurtsev , @hwchase17 Integrated Stack Exchange API into Langchain, enabling access to diverse communities within the platform. This addition enhances Langchain's capabilities by allowing users to query Stack Exchange for specialized information and engage in discussions. The integration provides seamless interaction with Stack Exchange content, offering content from varied knowledge repositories. A notebook example and test cases were included to demonstrate the functionality and reliability of this integration. - Add StackExchange as a tool. - Add unit test for the StackExchange wrapper and tool. - Add documentation for the StackExchange wrapper and tool. If you have time, could you please review the code and provide any feedback as necessary! My team is welcome to any suggestions. --------- Co-authored-by: Yuval Kamani <yuvalkamani@gmail.com> Co-authored-by: Aryan Thakur <aryanthakur@Aryans-MacBook-Pro.local> Co-authored-by: Manas1818 <79381912+manas1818@users.noreply.github.com> Co-authored-by: aryan-thakur <61063777+aryan-thakur@users.noreply.github.com> Co-authored-by: Bagatur <baskaryan@gmail.com>	9 months ago
Bagatur	d4405bc94e	langchain[patch]: Release 0.0.343 (#14037)	9 months ago
Erick Friis	3c29b0ded5	templates[patch]: template pyproject updates (#14035)	9 months ago
Yves Zumbühl	9c0ad0cebb	langchain[patch]: Improve HyDe with custom prompts and ability to supply the run_manager (#14016) ... - **Description:** The class allows to only select between a few predefined prompts from the paper. That is not ideal, since other use cases might need a custom prompt. The changes made allow for this. To be able to monitor those, I also added functionality to supply a custom run_manager. - **Issue:** no issue, but a new feature, - **Dependencies:** none, - **Tag maintainer:** @hwchase17, - **Twitter handle:** @yvesloy --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	9 months ago
Anton Romanov	4964278ce4	docs[patch]: Update typo in map.ipynb (#14030) ... fix the typo in docs, using "with" instead of "when"	9 months ago
Chad Norvell	1c4bfb8c5f	langchain[patch]: Mathpix PDF loader supports arbitrary extra params (#13950) ... - **Description:** Support providing whatever extra parameters you want to the Mathpix PDF loader API request. - **Issue:** #12773 - **Dependencies:** None --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	9 months ago
Unai Garay Maestre	9e2ae866c4	langchain[patch]: Adds progress bar to GooglePalmEmbeddings (#13812) ... - **Description:** Adds a tqdm progress bar to GooglePalmEmbeddings when embedding a list. - **Issue:** #13637 - **Dependencies:** TQDM as a main dependency (instead of extra) Signed-off-by: ugm2 <unaigaraymaestre@gmail.com> --------- Signed-off-by: ugm2 <unaigaraymaestre@gmail.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	9 months ago
Richie	1cd9d5f332	docs[patch]: fix typo langchain version for mongodb integration (#14006) ... - **Description:** update minimal supported langchain version for [mongodb atlast integration webpage](https://python.langchain.com/docs/integrations/vectorstores/mongodb_atlas) - **Issue:** none - **Dependencies:** none ----- Just fixing a typo. In [mongodb atlas vectorstore integration page](https://python.langchain.com/docs/integrations/vectorstores/mongodb_atlas), `langchain` support for `$vectorSearch MQL stage` should be `0.0.305` rather than `0.0.35`	9 months ago
David Norman	a578076aea	Mask api key for Together LLM (#13981) ... - **Description:** Add unit tests and mask api key for Together LLM - **Issue:** the issue https://github.com/langchain-ai/langchain/issues/12165 , - **Dependencies:** N/A - **Tag maintainer:** ?, - **Twitter handle:** N/A --------- Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>	9 months ago
Pavel Zwerschke	5f5c701f2c	docs: Install langsmith from conda-forge (#13335) ... <!-- Thank you for contributing to LangChain! Replace this entire comment with: - **Description:** a description of the change, - **Issue:** the issue # it fixes (if applicable), - **Dependencies:** any dependencies required for this change, - **Tag maintainer:** for a quicker response, tag the relevant maintainer (see below), - **Twitter handle:** we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/extras` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. --> langsmith is available on conda-forge as well and also a dependency of the package so it gets installed either way by conda 306ed13308/recipe/meta.yaml (L43)	9 months ago
Piotr Ząbek	d0b818b634	DOCS: added missing imports (#13736) (#13737) ... - **Description:** Fixed missing imports in docs - **Issue:** [#13736](https://github.com/langchain-ai/langchain/issues/13736) - **Dependencies:** N/A	9 months ago
Johnny	6463d2d0bd	small fix matching engine AttributeError - object has no attribute (#13763) ... This PR is fixing an attributeError: object endpoint has no attribute "_public_match_client" when using gcp matching engine with private VPC network. @baskaryan, @eyurtsev, @hwchase17. --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	9 months ago
Amyh102	750485eaa8	Add object parsing functionality (#13864) ... * **Description:** Parses huggingface dataset Sequence objects into strings for Document loading. * **Issue:** Fixes #10674 * **Tag maintainter:** @baskaryan @eyurtsev --------- Co-authored-by: Amy Han <amyhan@Amys-Air.lan> Co-authored-by: Amy Han <amyhan@Amys-MacBook-Air.local>	9 months ago
ggeutzzang	981f78f920	Fix: (issue #13825) Getting an error with DallEAPIWrapper (#13874) ... - **Description:** As of OpenAI's Python package 1.0, the existing DallEAPIWrapper does not work correctly, so the example in the LangChain Documentation link below does not work either. https://python.langchain.com/docs/integrations/tools/dalle_image_generator Also, since OpenAI only supports DALL-E version 2 or version 3, I modified the DallEAPIWrapper to support it. - **Issue:** #13825 - **Twitter handle:** ggeutzzang	9 months ago
Kunal	74045bf5c0	max length attribute for spacy splitter for large docs (#13875) ... For large size documents spacy splitter doesn't work it throws an error as shown in below screenshot. Reason its default max_length is 1000000 and there is no option to increase it. So i added it in this PR.  --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	9 months ago
Yusuf Khan	0bc7c1b5b4	Add Outline provider doc (#13938) ... - **Description:** Added a provider doc to `docs/integrations/providers` for the new Outline integration in #13889 - **Tag maintainer:** @baskaryan	9 months ago
colton	643d28847d	[docs] fix reduce prompt in summarization example (#13726) ... <!-- Thank you for contributing to LangChain! Replace this entire comment with: - **Description:** a description of the change, - **Issue:** the issue # it fixes (if applicable), - **Dependencies:** any dependencies required for this change, - **Tag maintainer:** for a quicker response, tag the relevant maintainer (see below), - **Twitter handle:** we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/extras` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. --> Small fix to _summarization_ example, `reduce_template` should use `{docs}` variable. Bug likely introduced as following code suggests using `hub.pull("rlm/map-prompt")` instead of defined prompt.	9 months ago
Wang Wei	fe9341a29c	feat: Add ERNIE-Bot-8K model support for ErnieBotChat. (#13716) ... - **Description:** According to the document https://cloud.baidu.com/doc/WENXINWORKSHOP/s/6lp69is2a, add ERNIE-Bot-8K model support for ErnieBotChat. - **Dependencies:** Before using the ERNIE-Bot-8K, you should have the model's access authority.	9 months ago
Leonid Ganeline	5c28bb63dd	docs `microsoft` page updates (#14000) ... The Excel, PowerPoint and SharePoint document loaders were missed in the `Microsoft` platform page. - added these references	9 months ago
Leonid Ganeline	15b32cfcd4	docs `OpenAI` platform page update (#14001) ... Missed the OpenAI adapter reference in the OpenAI platform page - Added this reference	9 months ago
Burak Ömür	0e462b72ef	Update openai/create_llm_result function to consider kwargs (#13815) ... Replace this entire comment with: - **Description:** updates `create_llm_result` function within `openai.py` to consider latest `params`, - **Issue:** #8928 - **Dependencies:** -, - **Tag maintainer:** - - **Twitter handle:** [burkomr](https://twitter.com/burkomr) <!-- If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. --> --------- Co-authored-by: Burak Ömür <burakomur@retorio.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	9 months ago
chyroc	f97ab84c6b	Merge pull request #13907 ... * feat: mask api_key for jina	9 months ago
nhywieza	9b86fb3fcb	secretStr for baichuan chat model api key (#13946) ... Merge pull request #13946 * secretStr for baichuan chat model api key	9 months ago
卢靖轩	aff1dba252	Merge pull request #13945 ... * feat: mask api key for nlpcloud	9 months ago
Leonid Kuligin	85bb3a418c	Switched VertexAI models from preview (#13657) ... Replace this entire comment with: - **Description:** VertexAI models are now GA, moved away from using preview ones from the SDK - **Issue:** #13606 --------- Co-authored-by: Nuno Campos <nuno@boringbits.io>	9 months ago
WaseemH	a47f1da884	docs[patch]: RAG Cookbook example fix (#13914) ... ### Description: Hey 👋🏽 this is a small docs example fix. Hoping it helps future developers who are working with Langchain. ### Problem: Take a look at the original example code. You were not able to get the `dialogue_turn[0]` while it was a tuple. Original code: ```python def _format_chat_history(chat_history: List[Tuple]) -> str: buffer = "" for dialogue_turn in chat_history: human = "Human: " + dialogue_turn[0] ai = "Assistant: " + dialogue_turn[1] buffer += "\n" + "\n".join([human, ai]) return buffer ``` In the original code you were getting this error: ```bash human = "Human: " + dialogue_turn[0].content ~~~~~~~~~~~~~^^^ TypeError: 'HumanMessage' object is not subscriptable ``` ### Solution: The fix is to just for loop over the chat history and look to see if its a human or ai message and add it to the buffer.	9 months ago
Erick Friis	5eca1bd93f	Library Licenses (#13300) ... Same change as #8403 but in other libs also updates (c) LangChain Inc. instead of @hwchase17	9 months ago
Bagatur	14799b139a	infra[patch]: add base deps and fix docs lint (#13998)	9 months ago
Théo LEBRUN	926d4cfda7	Set default region from boto3 session for Bedrock (#13694) ... - **Description:** Set default region from boto3 session for Bedrock - **Issue:** #13683	9 months ago
Snow	1a33e5b500	Repair Wikipedia document loader `load_max_docs` and improve test coverage. (#13769) ... **Description:** Repair Wikipedia document loader `load_max_docs` and improve test coverage. **Issue:** The Wikipedia document loader was not respecting the `load_max_docs` paramater (not reported) and would always return a maximum of 10 documents. This is because the API wrapper (in `utilities/wikipedia.py`) wasn't passing `top_k_results` to the underlying [Wikipedia library](https://wikipedia.readthedocs.io/en/latest/code.html#module-wikipedia). By default this library returns 10 results. The default number of results for the document loader has been reduced from 100 to 25. This is because loading 100 results takes a very long time and is an inconvenient default. It should possibly be 10. In addition, the documentation for the loader reported that there was a hard limit (300) on the number of documents returned. In actuality 300 is the maximum Wikipedia query character length set by the API wrapper. Tests have been added for the document loader (previously missing) and to test the correct numbers of documents are being returned by each class, both by default, and when overridden. Also repaired is the `assert_docs` test which has been updated to correctly test for the default metadata (which includes `source` in recent releases). **Dependencies:** nil **Tag maintainer:** @leo-gan **Twitter handle:** @queenvictoria	9 months ago
Bob Lin	04c4878306	Remove `python_repl` from _BASE_TOOLS (#13962) ... ### **Description:** Previously `python_repl` was a built-in tool, but now it has been moved to `langchain_experimental`. When I use `load_tools` I get an error: ```python In [1]: from langchain.agents import load_tools In [2]: load_tools(["python_repl"]) --------------------------------------------------------------------------- ImportError Traceback (most recent call last) Cell In[2], line 1 ----> 1 load_tools(["python_repl"]) File ~/workspace/langchain/libs/langchain/langchain/agents/load_tools.py:530, in load_tools(tool_names, llm, callbacks, **kwargs) 528 tool_names.extend(requests_method_tools) 529 elif name in _BASE_TOOLS: --> 530 tools.append(_BASE_TOOLS[name]()) 531 elif name in _LLM_TOOLS: 532 if llm is None: File ~/workspace/langchain/libs/langchain/langchain/agents/load_tools.py:84, in _get_python_repl() 83 def _get_python_repl() -> BaseTool: ---> 84 raise ImportError( 85 "This tool has been moved to langchain experiment. " 86 "This tool has access to a python REPL. " 87 "For best practices make sure to sandbox this tool. " 88 "Read https://github.com/langchain-ai/langchain/blob/master/SECURITY.md " 89 "To keep using this code as is, install langchain experimental and " 90 "update relevant imports replacing 'langchain' with 'langchain_experimental'" 91 ) ImportError: This tool has been moved to langchain experiment. This tool has access to a python REPL. For best practices make sure to sandbox this tool. Read https://github.com/langchain-ai/langchain/blob/master/SECURITY.md To keep using this code as is, install langchain experimental and update relevant imports replacing 'langchain' with 'langchain_experimental' ``` In this case, it will be very confusing. I think it is no longer a built-in tool now, so it can be removed from `_BASE_TOOLS` ### **Issue:** https://github.com/langchain-ai/langchain/issues/13858, https://github.com/langchain-ai/langchain/issues/13859, https://github.com/langchain-ai/langchain/issues/13856 ### **Twitter handle:** [lin_bob57617](https://twitter.com/lin_bob57617)	9 months ago
Leonid Ganeline	52eee458bb	renamed `google_vertex_ai_vector_search` notebook (#13484) ... The `integrations/vectorstores/matchingengine.ipynb` example has the "Google Vertex AI Vector Search" title. This place this Title in the wrong order in the ToC (it is sorted by the file name). - Renamed `integrations/vectorstores/matchingengine.ipynb` into `integrations/vectorstores/google_vertex_ai_vector_search.ipynb`. - Updated a correspondent comment in docstring - Rerouted old URL to a new URL --------- Co-authored-by: Erick Friis <erick@langchain.dev>	9 months ago
Leonid Ganeline	f5326cfb4e	docs[patch]: link to LangSmith docs (#13740) ... It happens that there is no link to the LangSmith Docs from the LangChain Docs. Added this link	9 months ago
Leonid Ganeline	bf5787f58b	experimental[patch]: fixed namespace bug (#13585) ... It was : `from langchain.schema.prompts import BasePromptTemplate` but because of the breaking change in the ns, it is now `from langchain.schema.prompt_template import BasePromptTemplate` This bug prevents building the API Reference for the langchain_experimental	9 months ago
Leonid Ganeline	1ab8a14742	docs[patch]: top menu (#13748) ... Addressed this issue with the top menu: It allocates too much space. If the screen is small, then the top menu items are split into two lines and look unreadable. Another issue is with several top menu items: "Chat our docs" and "Also by LangChain". They are compound of several words which also hurts readability. The top menu items should be 1-word size. Updates: - "Chat our docs" -> "Chat" (the meaning is clean after clicking/opening the item) - "Also by LangChain" -> "🦜️🔗" - "🦜️🔗" moved before "Chat" item. This new item is partially copied from the first left item, the "🦜️🔗 LangChain". This design (with two 🦜️🔗 elements, visually splits the top menu into two parts. The first item in each part holds the 🦜️🔗 symbols and, when we click the second 🦜️🔗 item, it opens the drop-down menu. So, we've got two visually similar parts, which visually split the top menu on the right side: the LangChain Docs (and Doc-related items) and the lift side: other LangChain.ai (company) products/docs.	9 months ago
Bob Lin	41b3968d39	docs[patch]: Update CONTRIBUTING.md doc (#13965) ... - **Description:** The new demo notebook should be placed in [docs/docs/modules](https://github.com/langchain-ai/langchain/tree/master/docs/docs/modules) - **Twitter handle:** lin_bob57617 --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	9 months ago
Taqi Jaffri	144710ad9a	langchain[minor]: Updated DocugamiLoader, includes breaking changes (#13265) ... There are the following main changes in this PR: 1. Rewrite of the DocugamiLoader to not do any XML parsing of the DGML format internally, and instead use the `dgml-utils` library we are separately working on. This is a very lightweight dependency. 2. Added MMR search type as an option to multi-vector retriever, similar to other retrievers. MMR is especially useful when using Docugami for RAG since we deal with large sets of documents within which a few might be duplicates and straight similarity based search doesn't give great results in many cases. We are @docugami on twitter, and I am @tjaffri --------- Co-authored-by: Taqi Jaffri <tjaffri@docugami.com>	9 months ago
Bagatur	a20e8f8bb0	experimental[patch]: release 0.0.43 (#13570)	9 months ago
juan-calvo-datatonic	6137894008	templates[minor]: Add rag google sensitive data protection template (#13921) ... This is a template demonstrating how to utilize Google Sensitive Data Protection in conjunction with ChatVertexAI(). Tagging you @efriis as you reviewed my last template. :) Thanks! Proof of successful execution:  --------- Co-authored-by: Erick Friis <erick@langchain.dev>	9 months ago
Erick Friis	8b9dc5e6d3	langchain[patch]: contributing test guide update (#13993)	9 months ago
Bagatur	95a472a85f	docs[patch]: install local core (#13990)	9 months ago
Bagatur	d8fe987ef5	langchain[patch]: release 0.0.342 (#13992)	9 months ago
Bagatur	61ec71064a	docs[patch]: update stack diagram (#13902)	9 months ago
david qiu	9fb6805be4	langchain[minor]: Add retriever for Knowledge Bases for Amazon Bedrock (#13980) ... - **Description:** Adds a retriever implementation for [Knowledge Bases for Amazon Bedrock](https://aws.amazon.com/bedrock/knowledge-bases/), a new service announced at AWS re:Invent, shortly before this PR was opened. This depends on the `bedrock-agent-runtime` service, which will be included in a future version of `boto3` and of `botocore`. We will open a follow-up PR documenting the minimum required versions of `boto3` and `botocore` after that information is available. - **Issue:** N/A - **Dependencies:** `boto3>=1.33.2, botocore>=1.33.2` - **Tag maintainer:** @baskaryan - **Twitter handles:** `@pjain7` `@dead_letter_q` This PR includes a documentation notebook under `docs/docs/integrations/retrievers`, which I (@dlqqq) have verified independently. EDIT: `bedrock-agent-runtime` service is now included in `boto3>=1.33.2`: 5cf793f493 --------- Co-authored-by: Piyush Jain <piyushjain@duck.com> Co-authored-by: Erick Friis <erick@langchain.dev> Co-authored-by: Bagatur <baskaryan@gmail.com>	9 months ago
Bagatur	1aed2d1f08	core[patch]: release 0.0.7 (#13989)	9 months ago
David Duong	eb67f07e32	Track RunnableAssign as a separate run trace (#13972) ... Addressing incorrect order being sent to callbacks / tracers, due to the nature of threading --------- Co-authored-by: Nuno Campos <nuno@boringbits.io>	9 months ago
Nuno Campos	0f255bb6c4	In Runnable.stream_log build up final_output from adding output chunks (#12781) ... Add arg to omit streamed_output list, in cases where final_output is enough this saves bandwidth <!-- Thank you for contributing to LangChain! Replace this entire comment with: - **Description:** a description of the change, - **Issue:** the issue # it fixes (if applicable), - **Dependencies:** any dependencies required for this change, - **Tag maintainer:** for a quicker response, tag the relevant maintainer (see below), - **Twitter handle:** we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md If you're adding a new integration, please include: 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/extras` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. -->	9 months ago
Nuno Campos	970fe23feb	Fixes for opengpts release (#13960)	9 months ago
David Duong	947daaf833	Exclude Bedrock client and credentials_profile_name fields from serialisation (#13603)	9 months ago