langchain

Commit Graph

Author	SHA1	Message	Date
Nicolas	3c7204d604	docs: Quick fix to Mendable Search (#2876 ) Fixed a small issue on the icon UI when using in Safari.	1 year ago
Harrison Chase	1e9378d0a8	Harrison/weaviate fixes (#2872 ) Co-authored-by: cs0lar <cristiano.solarino@gmail.com> Co-authored-by: cs0lar <cristiano.solarino@brightminded.com>	1 year ago
Harrison Chase	07d7096de6	Harrison/playwright (#2871 ) Co-authored-by: Manuel Saelices <msaelices@gmail.com>	1 year ago
Jon Luo	5565f56273	Use SQL dialect-specific prompts for SQLDatabaseChain (#2748 ) Mentioned the idea here initially: https://github.com/hwchase17/langchain/pull/2106#issuecomment-1487509106 Since there have been dialect-specific issues, we should use dialect-specific prompts. This way, each prompt can be separately modified to best suit each dialect as needed. This adds a prompt for each dialect supported in sqlalchemy (mssql, mysql, mariadb, postgres, oracle, sqlite). For this initial implementation, the only differencse between the prompts is the instruction for the clause to use to limit the number of rows queried for, and the instruction for wrapping column names using each dialect's identifier quote character.	1 year ago
drod	9907cb0485	Refactor similarity_search function in elastic_vector_search.py (#2761 ) Optimization :Limit search results when k < 10 Fix issue when k > 10: Elasticsearch will return only 10 docs [default-search-result](https://www.elastic.co/guide/en/elasticsearch/reference/current/paginate-search-results.html) By default, searches return the top 10 matching hits Add size parameter to the search request to limit the number of returned results from Elasticsearch. Remove slicing of the hits list, since the response will already contain the desired number of results.	1 year ago
rafael	1cc7ea333c	chat_models.openai: Set tenacity timeout to openai's recommendation (#2768 ) [OpenAI's cookbook](https://github.com/openai/openai-cookbook/blob/main/examples/How_to_handle_rate_limits.ipynb) suggest a tenacity backoff between 1 and 60 seconds. Currently langchain's backoff is between 4 and 10 seconds, which causes frequent timeout errors on my end. This PR changes the timeout to the suggested values.	1 year ago
Harrison Chase	705596b46a	Harrison/fix create sql agent (#2870 ) Co-authored-by: Timothé Pearce <timothe.pearce@gmail.com>	1 year ago
Harrison Chase	8a98e5b50b	Harrison/index name (#2869 ) Co-authored-by: Mesum Raza Hemani <mes.javacca@gmail.com>	1 year ago
Andrey Vasnetsov	dcb17503f2	Update qdrant.py (#2750 ) At the moment of upload we should already know the format of data, therefore we can skip the costly pydantic validation.	1 year ago
ecneladis	74abeb8c53	Update output in Git notebook (#2868 ) Supplemental to https://github.com/hwchase17/langchain/pull/2851. Updates one notebook cell that I forgot to commit before.	1 year ago
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.	1 year 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	1 year ago
ecneladis	016738e676	Add GitLoader (#2851 )	1 year ago
lizelive	8cfec2c5fe	torch 2 support (#2865 ) Lang-chain seems to work with torch 2	1 year 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() ```	1 year ago
Harrison Chase	ed2ef5cbe4	Harrison/rwkv utf8 (#2867 ) Co-authored-by: Akihiro <ueyama0105@gmail.com>	1 year 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.	1 year ago
Benjamin Tan Wei Hao	c26a259ba6	Fix tiny typo (#2863 )	1 year 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.	1 year ago
leo-gan	ecc1a0c051	added code-analysis-deeplake.ipynb (#2844 ) This notebook is heavily copied from the `twitter-the-algorithm-analysis-deeplake.ipynb`	1 year 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	1 year ago
Tim Asp	be4fb24b32	OpenAI LLM: update `modelname_to_contextsize` with new models (#2843 ) Token counts pulled from https://openai.com/pricing	1 year ago
vowelparrot	82d1d5f24e	Fix grammar in Vector Memory Docs (#2847 )	1 year 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	1 year ago
Harrison Chase	1609950597	Harrison/retriever memory (#2804 ) Co-authored-by: vowelparrot <130414180+vowelparrot@users.noreply.github.com>	1 year 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.	1 year ago
vowelparrot	2db9b7a45d	Revert "Add Slack Directory Loader (#2835 )" (#2839 ) This reverts commit `a6f767ae7a`. To fix the linting error.	1 year ago
KullTC	802363eb6a	Remove print statement from test (#2809 ) Remove unnecessary print statement.	1 year 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.	1 year 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>	1 year 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>	1 year ago
Harrison Chase	414dc803b6	bump version to 139 (#2834 )	1 year 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">	1 year ago
Harrison Chase	9a96691803	cr	1 year ago
了空	324e9c83d5	Add BiliBiliLoader to langchain.document_loaders.__init__.py (#2826 )	1 year ago
Nuhman Pk	ed03e965de	Update README.md (#2805 ) Added total download in a month (https://pepy.tech/project/langchain)	1 year 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.	1 year 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>	1 year ago
Harrison Chase	b2bc5ef56a	agent refactor (#2801 )	1 year 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>	1 year 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]) ```	1 year 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.	1 year 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?	1 year ago
Kah Keng Tay	1c7fb31bba	Weaviate attributes and error handling (#2800 )	1 year ago
dev2049	0e763677e4	Fix typo in qa eval chain prompt (#2797 )	1 year ago
Harrison Chase	e49f1e628c	Harrison/gpt cache (#2744 ) Co-authored-by: SimFG <bang.fu@zilliz.com>	1 year ago
Harrison Chase	425c437cd3	cr	1 year ago
Harrison Chase	a2d729e537	cr	1 year ago
Harrison Chase	7adbc4fbb4	agent memory (#2792 )	1 year ago
Nuno Campos	1bea9ea4be	Fix async task being destroyed before cancelled (#2787 )	1 year ago

1 2 3 4 5 ...

1295 Commits (3c7204d604fe3700f37d406e1f112da710a35864) All Branches Search

1295 Commits (3c7204d604fe3700f37d406e1f112da710a35864)

All Branches