kennethreitz/langchain
1
0
Fork 0
mirror of https://github.com/kennethreitz/langchain.git synced 2026-06-05 23:00:18 +00:00
Code Issues Packages Projects Releases Wiki Activity
265 Commits 1 Branch 0 Tags
ffe35c396c48e4a20acc827cc92ce72dfc87cbd7
Commit Graph

265 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Harrison Chase ffe35c396c unify return types across map-reduce and refine (#442) 2022-12-27 19:53:45 -05:00
Harrison Chase 0c5d3fd894 version 0.0.49 (#436) 2022-12-27 09:17:01 -05:00
Harrison Chase f8b605293f Harrison/improve memory (#432) 
add AI prefix

add new type of memory

Co-authored-by: Jason <chisanch@usc.edu>
 2022-12-27 08:23:51 -05:00
Harrison Chase 150b67de10 Harrison/weaviate improvements (#433) 
Co-authored-by: Connor Shorten <connorshorten300@gmail.com>
 2022-12-27 08:23:13 -05:00
Harrison Chase b7566b5ec3 Harrison/return intermediate steps (#428) 2022-12-27 08:22:48 -05:00
Harrison Chase 7fc4b4b3e1 Harrison/ver 0048 (#429) 2022-12-26 11:36:49 -05:00
Harrison Chase b50a56830d Harrison/evaluation notebook (#426) 2022-12-26 09:16:37 -05:00
Harrison Chase 97f4000d3a fix react docstore (#427) 2022-12-26 08:46:38 -05:00
Ikko Ashimine 9ae1d75318 Update integrations.md (#424) 
HuggingFace -> Hugging Face
 2022-12-25 23:03:05 -05:00
Harrison Chase f9562d7f1c version 0047 (#423) 2022-12-25 11:17:41 -05:00
Harrison Chase ee3b8e89b3 better parsing of agent output (#418) 2022-12-25 09:53:36 -05:00
Harrison Chase 0d7aa1ee99 Harrison/docs to index (#419) 
Add method for going directly from documents to VectorStores

Update notebook to showcase this functionality
 2022-12-25 09:53:07 -05:00
Harrison Chase 48ae981d69 Harrison/multi input tools (#421) 
add documentation on how to use tools that require multiple inputs
 2022-12-25 09:52:48 -05:00
Andrew Wang 4416dc9d5d Update prompt_serialization.ipynb (#417) 
Fix typo.
Originally "support methods are..."
Now "support methods *that* are.."
 2022-12-24 17:53:11 -05:00
Harrison Chase 22dd743eba Harrison/version 0046 (#416) 2022-12-24 10:46:23 -05:00
Harrison Chase 01d06c1f9f check memory variables (#411) 
can have multiple input keys, if some come from memory
 2022-12-24 08:36:06 -05:00
Harrison Chase 20959d8c36 check memory variables (#411) 
can have multiple input keys, if some come from memory
 2022-12-24 08:35:46 -05:00
altryne f990395211 Readme typos (#409) 
I was honored by the twitter mention, so used PyCharm to try and... help
docs even a little bit.
Mostly typo-s and correct spellings. 

PyCharm really complains about "really good" being used all the time and
recommended alternative wordings haha
 2022-12-23 13:13:07 -05:00
Harrison Chase 2ad285aab2 bump version to 0045 (#408) 2022-12-23 11:19:30 -05:00
Shreya Rajpal f40b3ce347 Updated VectorDBQA docs to updated argument name (#405) 2022-12-23 10:52:20 -05:00
Dheeraj Agrawal ea3da9a469 Fix documentation error langchain explanation of combine_docs.md (#404) 
This PR is regarding the issue here -
https://github.com/hwchase17/langchain/issues/403
 2022-12-23 08:54:26 -05:00
Harrison Chase 77e1743341 update example (#402) 2022-12-22 17:09:47 -05:00
Keiji Kanazawa 5528265142 Add macOS .DS_Store to .gitignore (#401) 
These are macOS specific files left around in directories (to save
user's display settings)
 2022-12-22 13:05:57 -05:00
Samantha Whitmore 6bc8ae63ef Add Redis cache implementation (#397) 
I'm using a hash function for the key just to make sure its length
doesn't get out of hand, otherwise the implementation is quite similar.
 2022-12-22 12:31:27 -05:00
Harrison Chase ff03242fa0 Harrison/ver 044 (#400) 2022-12-22 11:20:18 -05:00
mrbean 136f759492 Mrbean/support timeout (#398) 
Add support for passing in a request timeout to the API
 2022-12-21 23:39:07 -05:00
Harrison Chase 6b60c509ac (WIP) add HyDE (#393) 
Co-authored-by: cameronccohen <cameron.c.cohen@gmail.com>
Co-authored-by: Cameron Cohen <cameron.cohen@quantco.com>
 2022-12-21 20:46:41 -05:00
Keiji Kanazawa 543db9c2df Add Azure OpenAI LLM (#395) 
Hi!  This PR adds support for the Azure OpenAI service to LangChain.

I've tried to follow the contributing guidelines.

Co-authored-by: Keiji Kanazawa <{ID}+{username}@users.noreply.github.com>
 2022-12-21 20:45:37 -05:00
Harrison Chase bb76440bfa bump version to 0.0.43 (#394) 2022-12-20 22:28:29 -05:00
Harrison Chase c104d507bf Harrison/improve data augmented generation docs (#390) 
Co-authored-by: cameronccohen <cameron.c.cohen@gmail.com>
Co-authored-by: Cameron Cohen <cameron.cohen@quantco.com>
 2022-12-20 22:24:08 -05:00
Harrison Chase ad4414b59f update docs (#389) 2022-12-20 09:32:10 -05:00
Harrison Chase c8b4b54479 bump version to 0.0.42 (#388) 2022-12-19 20:59:34 -05:00
Harrison Chase 47ba34c83a split up and improve agent docs (#387) 2022-12-19 20:32:45 -05:00
Abi Raja 467aa0cee0 Fix typo in docs (#386) 2022-12-19 17:39:44 -05:00
Harrison Chase 6be5747466 RFC: add cache override to LLM class (#379) 2022-12-19 17:36:14 -05:00
Harrison Chase 46c428234f MMR example selector (#377) 
implement max marginal relevance example selector
 2022-12-19 17:09:27 -05:00
Harrison Chase ffed5e0056 Harrison/jinja formatter (#385) 
Co-authored-by: Benjamin <BenderV@users.noreply.github.com>
 2022-12-19 16:40:39 -05:00
mrbean fc66a32c6f fix docstring (#383) 
![Screenshot 2022-12-19 at 11 06 48
AM](https://user-images.githubusercontent.com/43734688/208468970-5cb9bafb-f535-486e-b41f-312a2f9ffffb.png)
 2022-12-19 11:10:17 -05:00
Harrison Chase a01d3e6955 fix agent memory docs (#382) 2022-12-19 09:15:32 -05:00
Harrison Chase 766b84a9d9 upgrade version to 0041 (#378) 2022-12-18 22:33:03 -05:00
Harrison Chase cf98f219f9 Harrison/tools exp (#372) 2022-12-18 21:51:23 -05:00
Harrison Chase e7b625fe03 fix text splitter (#375) 2022-12-18 20:21:43 -05:00
Harrison Chase 3474f39e21 Harrison/improve cache (#368) 
make it so everything goes through generate, which removes the need for
two types of caches
 2022-12-18 16:22:42 -05:00
Ankush Gola 8d0869c6d3 change run to use args and kwargs (#367) 
Before, `run` was not able to be called with multiple arguments. This
expands the functionality.
 2022-12-18 15:54:56 -05:00
Harrison Chase a7084ad6e4 Harrison/version 0040 (#366) 2022-12-17 07:53:22 -08:00
mrbean 50257fce59 Support Streaming Tokens from OpenAI (#364) 
https://github.com/hwchase17/langchain/issues/363

@hwchase17 how much does this make you want to cry?
 2022-12-17 07:02:58 -08:00
mrbean fe6695b9e7 Add HuggingFacePipeline LLM (#353) 
https://github.com/hwchase17/langchain/issues/354

Add support for running your own HF pipeline locally. This would allow
you to get a lot more dynamic with what HF features and models you
support since you wouldn't be beholden to what is hosted in HF hub. You
could also do stuff with HF Optimum to quantize your models and stuff to
get pretty fast inference even running on a laptop.
 2022-12-17 07:00:04 -08:00
Harrison Chase 2eef76ed3f fix documentation (#365) 2022-12-16 16:48:54 -08:00
Benjamin 85c1bd2cd0 add sqlalchemy generic cache (#361) 
Created a generic SQLAlchemyCache class to plug any database supported
by SQAlchemy. (I am using Postgres).
I also based the class SQLiteCache class on this class SQLAlchemyCache.

As a side note, I'm questioning the need for two distinct class
LLMCache, FullLLMCache. Shouldn't we merge both ?
 2022-12-16 16:47:23 -08:00
Harrison Chase 809a9f485f Harrison/new version (#362) 2022-12-16 07:42:31 -08:00