langchain

Commit Graph

Author	SHA1	Message	Date
Nicolas	0226b375d9	docs: Mendable Search integration (#2803 ) Mendable Seach Integration is Finally here! Hey yall, After various requests for Mendable in Python docs, we decided to get our hands dirty and try to implement it. Here is a version where we implement our floating button that sits on the bottom right of the screen that once triggered (via press or CMD K) will work the same as the js langchain docs. Super excited about this and hopefully the community will be too. @hwchase17 will send you the admin details via dm etc. The anon_key is fine to be public. Let me know if you need any further customization. I added the langchain logo to it.	2 years ago
sergerdn	04c458a270	feat: improve pinecone tests (#2806 ) Improve the integration tests for Pinecone by adding an `.env.example` file for local testing. Additionally, add some dev dependencies specifically for integration tests. This change also helps me understand how Pinecone deals with certain things, see related issues https://github.com/hwchase17/langchain/issues/2484 https://github.com/hwchase17/langchain/issues/2816	2 years ago
ecneladis	016738e676	Add GitLoader (#2851 )	2 years ago
lizelive	8cfec2c5fe	torch 2 support (#2865 ) Lang-chain seems to work with torch 2	2 years ago
vowelparrot	bf0887c486	Add Slack Directory Loader (#2841 ) Fixes linting issue from #2835 Adds a loader for Slack Exports which can be a very valuable source of knowledge to use for internal QA bots and other use cases. ```py # Export data from your Slack Workspace first. from langchain.document_loaders import SLackDirectoryLoader SLACK_WORKSPACE_URL = "https://awesome.slack.com" loader = ("Slack_Exports", SLACK_WORKSPACE_URL) docs = loader.load() ```	2 years ago
Harrison Chase	ed2ef5cbe4	Harrison/rwkv utf8 (#2867 ) Co-authored-by: Akihiro <ueyama0105@gmail.com>	2 years ago
Adam McCabe	6be5d7c612	Update reduce_openapi_spec for PATCH and DELETE (#2861 ) My recent pull request (#2729) neglected to update the `reduce_openapi_spec` in spec.py to also accommodate PATCH and DELETE added to planner.py and prompt_planner.py.	2 years ago
Benjamin Tan Wei Hao	c26a259ba6	Fix tiny typo (#2863 )	2 years ago
Jon Luo	f3180f05f9	Update sql chain notebook to clarify use of SQLAlchemy for connections (#2850 ) Have seen questions about whether or not the `SQLDatabaseChain` supports more than just sqlite, which was unclear in the docs, so tried to clarify that and how to connect to other dialects.	2 years ago
leo-gan	ecc1a0c051	added code-analysis-deeplake.ipynb (#2844 ) This notebook is heavily copied from the `twitter-the-algorithm-analysis-deeplake.ipynb`	2 years ago
Tim Asp	70ffe470aa	Add easy print method to openai callback (#2848 ) Found myself constantly copying the snippet outputting all the callback tracking details. so adding a simple way to output the full context	2 years ago
Tim Asp	be4fb24b32	OpenAI LLM: update `modelname_to_contextsize` with new models (#2843 ) Token counts pulled from https://openai.com/pricing	2 years ago
vowelparrot	82d1d5f24e	Fix grammar in Vector Memory Docs (#2847 )	2 years ago
Tim Asp	53dc157145	[Docs] minor fixes to loaders links and rst warnings (#2846 ) The doc loaders index was picking up a bunch of subheadings because I mistakenly made the MD titles H1s. Fixed that. also the easy minor warnings from docs_build	2 years ago
Harrison Chase	1609950597	Harrison/retriever memory (#2804 ) Co-authored-by: vowelparrot <130414180+vowelparrot@users.noreply.github.com>	2 years ago
Rounak Datta	7688bf9182	WhatsApp document loader - update regex (#2776 ) I was testing out the WhatsApp Document loader, and noticed that sometimes the date is of the following format (notice the additional underscore): ``` 3/24/23, 1:54_PM - +91 99999 99999 joined using this group's invite link 3/24/23, 6:29_PM - +91 99999 99999: When are we starting then? ``` Wierdly, the underscore is visible in Vim, but not on editors like VSCode. I presume it is some unusual character/line terminator. Nevertheless, I think handling this edge case will make the document loader more robust.	2 years ago
vowelparrot	2db9b7a45d	Revert "Add Slack Directory Loader (#2835 )" (#2839 ) This reverts commit `a6f767ae7a`. To fix the linting error.	2 years ago
KullTC	802363eb6a	Remove print statement from test (#2809 ) Remove unnecessary print statement.	2 years ago
Azam Iftikhar	2a89dc8c1c	Fixing factually incorrect example (#2810 ) ### https://github.com/hwchase17/langchain/issues/2802 It appears that Google's Flan model may not perform as well as other models, I used a simple example to get factually correct answer.	2 years ago
vowelparrot	a6f767ae7a	Add Slack Directory Loader (#2835 ) Adds a loader for Slack Exports which can be a very valuable source of knowledge to use for internal QA bots and other use cases. ```py # Export data from your Slack Workspace first. from langchain.document_loaders import SLackDirectoryLoader SLACK_WORKSPACE_URL = "https://awesome.slack.com" loader = ("Slack_Exports", SLACK_WORKSPACE_URL) docs = loader.load() ``` --------- Co-authored-by: Mikhail Dubov <mikhail@chattermill.io>	2 years ago
st01cs	4f231b46ee	Add openai.api_base to support openapi proxy (#2823 ) I need access openai api through a proxy, so to add openai.api_base to support this method. Co-authored-by: bijia <bijia1@xiaomi.com>	2 years ago
Harrison Chase	414dc803b6	bump version to 139 (#2834 )	2 years ago
Preetesh Jain	61858c5a08	Fix headings in docs (ClearML and Comet) (#2808 ) This PR fixes the document structure in the [Ecosystem](https://python.langchain.com/en/latest/ecosystem.html) page. Also adds a fix for the heading on the [Comet](https://python.langchain.com/en/latest/ecosystem/comet_tracking.html) page for more consistency with other ecosystem tools. ## Screenshot <img width="878" alt="image" src="https://user-images.githubusercontent.com/6207830/231674921-9bf25376-cf14-4dba-be3c-08e0abda6154.png"> <img width="869" alt="image" src="https://user-images.githubusercontent.com/6207830/231675105-d8e42df4-2d01-435b-9e09-3371522fd2ce.png">	2 years ago
Harrison Chase	9a96691803	cr	2 years ago
了空	324e9c83d5	Add BiliBiliLoader to langchain.document_loaders.__init__.py (#2826 )	2 years ago
Nuhman Pk	ed03e965de	Update README.md (#2805 ) Added total download in a month (https://pepy.tech/project/langchain)	2 years ago
KullTC	64596b23b9	Return output of PythonAstREPLTool when falling back to exec() (#2780 ) When the code ran by the PythonAstREPLTool contains multiple statements it will fallback to exec() instead of using eval(). With this change, it will also return the output of the code in the same way the PythonREPLTool will.	2 years ago
Harrison Chase	1bb0706955	Harrison/comet ml (#2799 ) Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com> Co-authored-by: Boris Feld <lothiraldan@gmail.com>	2 years ago
Harrison Chase	b2bc5ef56a	agent refactor (#2801 )	2 years ago
Zach Jones	abfca72c0b	Add max_execution_time to openapi, pandas, and sql creators (#2779 ) In #2399 we added the ability to set `max_execution_time` when creating an AgentExecutor. This PR adds the `max_execution_time` argument to the built-in pandas, sql, and openapi agents. Co-authored-by: Zachary Jones <zjones@zetaglobal.com>	2 years ago
Matt Robinson	f0be3b0689	feat: add support for non-html in `UnstructuredURLLoader` (#2793 ) ### Summary Adds support for processing non HTML document types in the URL loader. For example, the URL loader can now process a PDF or markdown files hosted at a URL. ### Testing ```python from langchain.document_loaders import UnstructuredURLLoader urls = ["https://www.understandingwar.org/sites/default/files/Russian%20Offensive%20Campaign%20Assessment%2C%20April%2011%2C%202023.pdf"] loader = UnstructuredURLLoader(urls=urls, strategy="fast") docs = loader.load() print(docs[0].page_content[:1000]) ```	2 years ago
Tim Connors	e081c62aac	Fixed k=0 bug on ConversationBufferWindowMemory (#2796 ) Updated the "load_memory_variables" function of the ConversationBufferWindowMemory to support a window size of 0 (k=0). Previous behavior would return the full memory instead of an empty array.	2 years ago
dev2049	a094b7f807	Improve eval chain prompt (#2798 ) Eval chain is currently very sensitive to differences in phrasing, punctuation, and tangential information. This prompt has worked better for me on my examples. More general q: Do we have any framework for evaluating default prompt changes? Could maybe start doing some regression testing?	2 years ago
Kah Keng Tay	1c7fb31bba	Weaviate attributes and error handling (#2800 )	2 years ago
dev2049	0e763677e4	Fix typo in qa eval chain prompt (#2797 )	2 years ago
Harrison Chase	e49f1e628c	Harrison/gpt cache (#2744 ) Co-authored-by: SimFG <bang.fu@zilliz.com>	2 years ago
Harrison Chase	425c437cd3	cr	2 years ago
Harrison Chase	a2d729e537	cr	2 years ago
Harrison Chase	7adbc4fbb4	agent memory (#2792 )	2 years ago
Nuno Campos	1bea9ea4be	Fix async task being destroyed before cancelled (#2787 )	2 years ago
Harrison Chase	819d72614a	version 138 (#2782 )	2 years ago
wangml999	fa0c9390c2	Update custom_agent.ipynb (#2767 ) Fixed an issue the agent is not taking the user's question as input.	2 years ago
Joshua Snyder	59d054308c	Add type inference for output parsers (#2769 ) Currently, the output type of a number of OutputParser's `parse` methods is `Any` when it can in fact be inferred. This PR makes BaseOutputParser use a generic type and fixes the output types of the following parsers: - `PydanticOutputParser` - `OutputFixingParser` - `RetryOutputParser` - `RetryWithErrorOutputParser` The output of the `StructuredOutputParser` is corrected from `BaseModel` to `Any` since there are no type guarantees provided by the parser. Fixes issue #2715	2 years ago
Nuhman Pk	789cc314c5	Typo (#2747 )	2 years ago
Harrison Chase	b92a89e29f	cr	2 years ago
vowelparrot	94a92abf24	Add Retrieval Example for AI Plugins (#2737 ) This PR proposes - An NLAToolkit method to instantiate from an AI Plugin URL - A notebook that shows how to use that alongside an example of using a Retriever object to lookup specs and route queries to them on the fly --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	2 years ago
Nuhman Pk	b5bbe601fb	Update chatgpt_plugins.ipynb (#2745 ) Changed deprecated requests to requests_all in plugins example	2 years ago
Harrison Chase	b38a6ea7df	Harrison/apply llm flag (#2743 ) Co-authored-by: Nick Gibb <gibbnick@gmail.com> Co-authored-by: Nick Gibb <nick.gibb@bluedot.global>	2 years ago
vr140	dd59193757	Remove unnecessary method from Qdrant vectorstore and clean up docstrings (#2700 ) Problem: The `from_documents` method in Qdrant vectorstore is unnecessary because it does not change any default behavior from the abstract base class method of `from_documents` (contrast this with the method in Chroma which makes a change from default and turns `embeddings` into an Optional parameter). Also, the docstrings need some cleanup. Solution: Remove unnecessary method and improve docstrings. --------- Co-authored-by: Vijay Rajaram <vrajaram3@gatech.edu>	2 years ago
Matthew Plachter	933dfac583	Add Zapier NLA OAuth access_token to be used (#2726 ) This change allows the user to initialize the ZapierNLAWrapper with a valid Zapier NLA OAuth Access_Token, which would be used to make requests back to the Zapier NLA API. When a `zapier_nla_oauth_access_token` is passed to the ZapierNLAWrapper it is no longer required for the `ZAPIER_NLA_API_KEY ` environment variable to be set, still having it set will not affect the behavior as the `zapier_nla_oauth_access_token` will be used over the `ZAPIER_NLA_API_KEY`	2 years ago

1 2 3 4 5 ...

1285 Commits (0226b375d967f30b0ba27d061d465460d016e76c) All Branches Search

1285 Commits (0226b375d967f30b0ba27d061d465460d016e76c)

All Branches