langchain

Commit Graph

Author	SHA1	Message	Date
Harrison Chase	e9301bf833	bump version to 0.0.62 (#607 )	1 year ago
Harrison Chase	9f9afbb6a8	add custom prompt for LLMMathChain and SQLDatabase chain (#605 )	1 year ago
Smit Shah	a87a2aacaa	[Minor Fix] Fix spacy TextSplitter init (#606 )	1 year ago
Sasmitha Manathunga	3e55f1474e	docs: fix typo (#604 )	1 year ago
babbldev	b5eb91536a	Added filter argument to pinecone queries, fixes #600 (#601 ) Added filter argument to similarity_search() and similarity_search_with_score() Co-authored-by: Sam Cartford (MBP) <cartford@hey.com>	1 year ago
Sam Ching	c4c6bf6e6e	Add subsection for colab notebooks (#599 ) Motivation is that these don't get lost in the Twitterverse!	1 year ago
Rukmal Weerawarana	0f544a8811	Fix minor error in LLM documentation (#602 )	1 year ago
Ikko Eltociear Ashimine	60dfe58325	Fix typo in vector_db_qa.ipynb (#597 ) paramter -> parameter	1 year ago
Harrison Chase	950a81399a	bump version to 61 (#596 )	1 year ago
Harrison Chase	d574bf0a27	add documentation on how to load different chain types (#595 )	1 year ago
Harrison Chase	956416c150	Harrison/update links1 (#594 ) update links to be relative Co-authored-by: Marc Green <marcgreen@users.noreply.github.com>	1 year ago
Harrison Chase	8ab09c18a1	Return source documents option in VectorDBQA (#585 ) (#592 ) Co-authored-by: lesscomfortable <pancho_ingham@hotmail.com> Co-authored-by: Francisco Ingham <fpingham@gmail.com> Co-authored-by: lesscomfortable <pancho_ingham@hotmail.com>	1 year ago
Harrison Chase	4c6c5f0391	wolfram alpha improvements (#591 ) Co-authored-by: Nicolas <nicolascamara29@gmail.com>	1 year ago
Harrison Chase	a5ee7de650	pinecone changes (#590 ) Co-authored-by: Smit Shah <who828@gmail.com> Co-authored-by: iocuydi <46613640+iocuydi@users.noreply.github.com>	1 year ago
Harrison Chase	7b6e7f6e12	bump to version 60 (#583 )	1 year ago
Harrison Chase	3f2ea5c35e	Harrison/load from hub (#580 )	1 year ago
Harrison Chase	f74ce7a104	Harrison/combine memories (#582 ) Signed-off-by: Diwank Singh Tomer <diwank.singh@gmail.com> Co-authored-by: Diwank Singh Tomer <diwank.singh@gmail.com>	1 year ago
Harrison Chase	2aa08631cb	add similarity score method to faiss (#574 ) adds `similarity_search_with_score` to faiss wrapper	1 year ago
Harrison Chase	5ba46f6d0c	Harrison/namespace pinecone (#581 ) Co-authored-by: mmorzywolek <89693033+mmorzywolek@users.noreply.github.com>	1 year ago
Harrison Chase	ffc7e04d44	Harrison/wolfram alpha (#579 ) Co-authored-by: Nicolas <nicolascamara29@gmail.com>	1 year ago
Harrison Chase	94765e7487	more gallery (#577 )	1 year ago
Harrison Chase	50a49eff15	gallery updates (#573 )	1 year ago
Harrison Chase	6966863d7d	Harrison/deployments (#572 )	1 year ago
Harrison Chase	7de5139750	add example selector docs (#564 )	1 year ago
Yong723	94c06c55e8	modify docstring (#569 ) Sorry for the detail. this is a correction to the docstring.	1 year ago
Yong723	e1f3871a78	fix typo (#570 ) I found a typo, which might be important for a conversational Agent. if My PR is wrong, I am so sorry	1 year ago
Harrison Chase	6374df5a31	bump version (#565 )	1 year ago
Harrison Chase	b06a2a6191	improve documentation on how to pass in custom prompts (#561 )	1 year ago
Harrison Chase	1511606799	Harrison/fix splitting (#563 ) fix issue where text splitting could possibly create empty docs	1 year ago
Harrison Chase	1192cc0767	smart text splitter (#530 ) smart text splitter that iteratively tries different separators until it works!	1 year ago
Harrison Chase	8dfad874a2	map rerank chain (#516 ) add a chain that applies a prompt to all inputs and then returns not only an answer but scores it add examples for question answering and question answering with sources	1 year ago
Nicolas	948eee9fe1	Docs: side menu to match the order (llms) (#557 ) Small quick fix: Suggest making the order of the menu the same as it is written on the page (Getting Started -> Key Concepts). Before the menu order was not the same as it was on the page. Not sure if this is the only place the menu is affected. Mismatch is found here: https://langchain.readthedocs.io/en/latest/modules/llms.html	1 year ago
Harrison Chase	823a44ef80	bump to 0058 (#556 )	1 year ago
Benjamin	42d5d988fa	add openai logit bias (#553 ) Add [`logit_bias`](https://beta.openai.com/docs/api-reference/completions/create#completions/create-logit_bias) params to OpenAI See [here](https://beta.openai.com/tokenizer) for the tokenizer. NB: I see that others (like Cohere) have the same parameter, but since I don't have an access to it, I don't want to make a mistake. --- Just to make sure the default "{}" works for openai: ``` from langchain.llms import OpenAI OPENAI_API_KEY="XXX" llm = OpenAI(openai_api_key=OPENAI_API_KEY) llm.generate('Write "test":') llm = OpenAI(openai_api_key=OPENAI_API_KEY, logit_bias={'9288': -100, '1332': -100, '14402': -100, '6208': -100}) llm.generate('Write "test":') ```	1 year ago
Harrison Chase	9833fcfe32	fix caching (#555 )	1 year ago
Harrison Chase	74932f2516	RFC: conversational agent (#464 ) Co-authored-by: Bruno Bornsztein <bruno.bornsztein@gmail.com>	1 year ago
Harrison Chase	330a5b42d4	fix map reduce chain (#550 )	1 year ago
Diwank Singh Tomer	ba0cbb4a41	Add finish reason to Generation for usage downstream (#526 ) Add `finish_reason` to `Generation` as well as extend `BaseOpenAI._generate` to include it in the output. This can be useful for usage in downstream tasks when we need to filter for only generations that finished because of `"stop"` for example. Maybe we should add this to `LLMChain` as well? For more details, see https://beta.openai.com/docs/guides/completion/best-practices Signed-off-by: Diwank Singh Tomer <diwank.singh@gmail.com>	1 year ago
Harrison Chase	e64ed7b975	Harrison/tools priority (#554 ) Co-authored-by: Yong723 <50616781+Yongtae723@users.noreply.github.com>	1 year ago
Harrison Chase	4974f49bb7	add return_direct flag to tool (#537 ) adds a return_direct flag to tools, which just returns the tool output as the final output	1 year ago
Harrison Chase	1f248c47f3	bump version to 0.0.57 (#548 )	1 year ago
Harrison Chase	0c2f7d8da1	changes to qa chain (#543 )	1 year ago
Hunter Gerlach	5b4c972fc5	Add linkcheck badge to signify when/if links are failing (#546 ) Detect whether or not most recent GitHub Action running linkcheck was successful.	1 year ago
Harrison Chase	9753bccc71	Feature: linkcheck-action (#534 ) (#542 ) - Add support for local build and linkchecking of docs - Add GitHub Action to automatically check links before prior to publication - Minor reformat of Contributing readme - Fix existing broken links Co-authored-by: Hunter Gerlach <hunter@huntergerlach.com> Co-authored-by: Hunter Gerlach <HunterGerlach@users.noreply.github.com> Co-authored-by: Hunter Gerlach <hunter@huntergerlach.com>	1 year ago
Harrison Chase	5aefc2b7ce	add handling on error (#541 )	1 year ago
Harrison Chase	1631981f84	Harrison/fix and test caching (#538 )	1 year ago
Harrison Chase	73f7ebd9d1	Harrison/sqlalchemy cache store (#536 ) Co-authored-by: Jason Gill <jasongill@gmail.com>	1 year ago
Sam Ching	870cccb877	Add info to Contributors.md to avoid Conda/Pyenv dependency conflicts (#540 ) As discussed in the [Discord](https://discord.com/channels/1038097195422978059/1038097349660135474/1060194710485995521), adding the following instructions to help future contributors avoid dependency conflicts if they use Conda / Pyenv on their system.	1 year ago
Yongtae723	f48ab642be	replace forbid into ignore (#539 ) this is the second PR of #519. in #519 I suggested deleting Extra.forbid. I was very confused but I replaced Extra.forbid to Extra.ignore, which is the default of pydantic. Since the [BaseLLM](`4b7b8229de/langchain/llms/base.py (L20)`) from which it is inherited is set in Extra.forbid, I wanted to avoid having the Extra.forbid settings inherited by simply deleting it.	1 year ago
Yongtae723	4b7b8229de	add logger (#529 ) As talking #519, I made 2 PRs. this is the first PR for adding a logger. I am concerned about the following two points and would appreciate your opinion. 1. Since the logger is not formatted, the statement itself is output like a print statement, and I thought it was difficult to understand that it was a warning, so I put WARNING! at the beginning of the warning statement. After the logger formatting is done properly, the word WARNING can be repeated. 2. Statement `Please confirm that {field_name} is what you intended.` can be replaced like `If {field_name} is intended parameters, enter it to model_kwargs` thank you! Yongtae	1 year ago

... 178 179 180 181 182 ...

9299 Commits (master) All Branches Search

9299 Commits (master)

All Branches