Commit Graph

479 Commits (4d32441b869c0ddab99cd7082ae074922e3c6fe0)
 

Author SHA1 Message Date
Parth Chadha e88e66f982
Pass verbose argument to LLMChains when using *DocumentsChain (#458)
When using chains such as Summarization chain (`load_summarize_chain`),
the verbose flag wasn't propagated to the `LLMChain`.
1 year ago
Harrison Chase d0f194de73
add logic for agent stopping (#420) 1 year ago
Harrison Chase c65efd2986
fix llm math prompt (#466)
basically, it didnt realize that the question was over after the input
and would some times hallucinate more input
1 year ago
Harrison Chase 95157d0aad
Add schema property to sql database utility class (#448) (#462)
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>

Signed-off-by: Diwank Singh Tomer <diwank.singh@gmail.com>
Co-authored-by: Nuno Campos <nuno@boringbits.io>
Co-authored-by: Diwank Singh Tomer <diwank.singh@gmail.com>
1 year ago
Nuno Campos 451665cfdf
Add watch mode for test runner (#453) 1 year ago
Harrison Chase 2b84e5cda3
Harrison/fix memory and serp (#457)
Co-authored-by: Bruno Bornsztein <bruno.bornsztein@gmail.com>
1 year ago
Harrison Chase d98607408b
Harrison/v0050 (#452) 1 year ago
Harrison Chase 55007e71be
add output key for memory (#443)
this allows chains that return multiple values to use memory
1 year ago
Harrison Chase 5208bb8c36
make tools editable (#445)
use dataclass instead of namedtuple, which makes it editable

add example in notebook
1 year ago
Harrison Chase 5cc6bf1a9c
fix regex parser (#446) 1 year ago
Harrison Chase 90e8ccc898
Harrison/update links (#450)
Co-authored-by: Sam Ching <samuelcwl@gmail.com>
Co-authored-by: Ikko Ashimine <eltociear@gmail.com>
1 year ago
Ikko Ashimine f3c3288761
chore: fix typo in prompt.py (#447)
seperator -> separator
1 year ago
Harrison Chase 9ec01dfc16
regex output parser (#435) 1 year ago
Harrison Chase c994ce6b7f
Harrison/serp api imp (#444)
improve serp api

Co-authored-by: Bruno Bornsztein <bruno.bornsztein@gmail.com>
1 year ago
Harrison Chase ffe35c396c
unify return types across map-reduce and refine (#442) 1 year ago
Harrison Chase 0c5d3fd894
version 0.0.49 (#436) 1 year ago
Harrison Chase f8b605293f
Harrison/improve memory (#432)
add AI prefix

add new type of memory

Co-authored-by: Jason <chisanch@usc.edu>
1 year ago
Harrison Chase 150b67de10
Harrison/weaviate improvements (#433)
Co-authored-by: Connor Shorten <connorshorten300@gmail.com>
1 year ago
Harrison Chase b7566b5ec3
Harrison/return intermediate steps (#428) 1 year ago
Harrison Chase 7fc4b4b3e1
Harrison/ver 0048 (#429) 1 year ago
Harrison Chase b50a56830d
Harrison/evaluation notebook (#426) 1 year ago
Harrison Chase 97f4000d3a
fix react docstore (#427) 1 year ago
Ikko Ashimine 9ae1d75318
Update integrations.md (#424)
HuggingFace -> Hugging Face
1 year ago
Harrison Chase f9562d7f1c
version 0047 (#423) 1 year ago
Harrison Chase ee3b8e89b3
better parsing of agent output (#418) 1 year ago
Harrison Chase 0d7aa1ee99
Harrison/docs to index (#419)
Add method for going directly from documents to VectorStores

Update notebook to showcase this functionality
1 year ago
Harrison Chase 48ae981d69
Harrison/multi input tools (#421)
add documentation on how to use tools that require multiple inputs
1 year ago
Andrew Wang 4416dc9d5d
Update prompt_serialization.ipynb (#417)
Fix typo.
Originally "support methods are..."
Now "support methods *that* are.."
1 year ago
Harrison Chase 22dd743eba
Harrison/version 0046 (#416) 1 year ago
Harrison Chase 01d06c1f9f
check memory variables (#411)
can have multiple input keys, if some come from memory
1 year ago
Harrison Chase 20959d8c36
check memory variables (#411)
can have multiple input keys, if some come from memory
1 year ago
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
1 year ago
Harrison Chase 2ad285aab2
bump version to 0045 (#408) 1 year ago
Shreya Rajpal f40b3ce347
Updated VectorDBQA docs to updated argument name (#405) 1 year ago
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
1 year ago
Harrison Chase 77e1743341
update example (#402) 1 year ago
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)
1 year ago
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.
1 year ago
Harrison Chase ff03242fa0
Harrison/ver 044 (#400) 1 year ago
mrbean 136f759492
Mrbean/support timeout (#398)
Add support for passing in a request timeout to the API
1 year ago
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>
1 year ago
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>
1 year ago
Harrison Chase bb76440bfa
bump version to 0.0.43 (#394) 1 year ago
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>
1 year ago
Harrison Chase ad4414b59f
update docs (#389) 1 year ago
Harrison Chase c8b4b54479
bump version to 0.0.42 (#388) 1 year ago
Harrison Chase 47ba34c83a
split up and improve agent docs (#387) 1 year ago
Abi Raja 467aa0cee0
Fix typo in docs (#386) 1 year ago
Harrison Chase 6be5747466
RFC: add cache override to LLM class (#379) 1 year ago
Harrison Chase 46c428234f
MMR example selector (#377)
implement max marginal relevance example selector
1 year ago