Archives/langchain
2
0
Fork 1
mirror of https://github.com/hwchase17/langchain synced 2024-11-08 07:10:35 +00:00
Code Issues Packages Projects Releases Wiki Activity
6,844 Commits 835 Branches 680 Tags 674 MiB
46b7a8d913
Commit Graph

6844 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Harrison Chase
447683de6f
bump version to 0.0.55 (#521) 2023-01-03 08:37:16 -08:00
Harrison Chase
0db05b6725
Harrison/add human prefix (#520) 
Co-authored-by: Andrew Huang <jhuang16888@gmail.com>
 2023-01-03 08:03:50 -08:00
Harrison Chase
03f185bcd5
more robust handling for max iterations (#514) 
add a `generate` method which makes one final forward pass through the
llm
 2023-01-03 07:46:08 -08:00
Harrison Chase
40326c698c
unify argument name (#513) 
unify names in map reduce and refine chains to just be
return_intermediate_steps

also unify the return key
 2023-01-03 07:45:08 -08:00
lewtun
12108104c9
Add links to Hugging Face Hub docs (#518) 
This PR adds some tweaks to the Hugging Face docs, mostly with links to
the Hub + relevant docs.
 2023-01-03 07:43:57 -08:00
Harrison Chase
3efec55f93
update lobby link (#517) 2023-01-02 20:25:49 -08:00
Harrison Chase
8f6c08863a
bump version to 0.0.54 (#512) 2023-01-02 10:22:05 -08:00
Hunter Gerlach
7253fada0d
Fix/broken getting started link (#511) 
I noticed (after publication) that the getting_started link on the main
page was borked. This should fix it.

Co-authored-by: Hunter Gerlach <hunter@huntergerlach.com>
 2023-01-02 10:15:17 -08:00
Harrison Chase
985496f4be
Docs refactor (#480) 
Big docs refactor! Motivation is to make it easier for people to find
resources they are looking for. To accomplish this, there are now three
main sections:

- Getting Started: steps for getting started, walking through most core
functionality
- Modules: these are different modules of functionality that langchain
provides. Each part here has a "getting started", "how to", "key
concepts" and "reference" section (except in a few select cases where it
didnt easily fit).
- Use Cases: this is to separate use cases (like summarization, question
answering, evaluation, etc) from the modules, and provide a different
entry point to the code base.

There is also a full reference section, as well as extra resources
(glossary, gallery, etc)

Co-authored-by: Shreya Rajpal <ShreyaR@users.noreply.github.com>
 2023-01-02 08:24:09 -08:00
Keiji Kanazawa
c5f0af9398
Minor docstring update (#507) 
Update `model=` to `model_name=`.

No need to credit me for this 😄
 2023-01-01 19:17:23 -08:00
Harrison Chase
d95b39d37f
version 0.0.53 (#497) 2022-12-30 11:05:18 -05:00
Harrison Chase
0072686aab
Harrison/new search engine (#477) 
Co-authored-by: Nicolas <nicolascamara29@gmail.com>
 2022-12-30 08:06:57 -05:00
Harrison Chase
3e41ab7bff
check keys before using (#475) 2022-12-29 22:16:35 -05:00
Shuchang Zhou
12aa43469f
Update prompt_management.ipynb (#484) 2022-12-29 21:34:32 -05:00
Harrison Chase
0f1df0dc2c
bump to version 0.0.52 (#470) 2022-12-29 09:23:19 -05:00
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`.
 2022-12-29 08:22:31 -05:00
Harrison Chase
d0f194de73
add logic for agent stopping (#420) 2022-12-29 08:21:11 -05:00
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
 2022-12-29 08:20:55 -05:00
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>
 2022-12-28 17:37:53 -05:00
Nuno Campos
451665cfdf
Add watch mode for test runner (#453) 2022-12-28 17:13:08 -05:00
Harrison Chase
2b84e5cda3
Harrison/fix memory and serp (#457) 
Co-authored-by: Bruno Bornsztein <bruno.bornsztein@gmail.com>
 2022-12-28 11:07:57 -05:00
Harrison Chase
d98607408b
Harrison/v0050 (#452) 2022-12-28 09:22:43 -05:00
Harrison Chase
55007e71be
add output key for memory (#443) 
this allows chains that return multiple values to use memory
 2022-12-28 09:04:15 -05:00
Harrison Chase
5208bb8c36
make tools editable (#445) 
use dataclass instead of namedtuple, which makes it editable

add example in notebook
 2022-12-28 09:03:16 -05:00
Harrison Chase
5cc6bf1a9c
fix regex parser (#446) 2022-12-28 09:02:40 -05:00
Harrison Chase
90e8ccc898
Harrison/update links (#450) 
Co-authored-by: Sam Ching <samuelcwl@gmail.com>
Co-authored-by: Ikko Ashimine <eltociear@gmail.com>
 2022-12-28 09:02:07 -05:00
Ikko Ashimine
f3c3288761
chore: fix typo in prompt.py (#447) 
seperator -> separator
 2022-12-28 00:19:43 -05:00
Harrison Chase
9ec01dfc16
regex output parser (#435) 2022-12-27 20:28:08 -05:00
Harrison Chase
c994ce6b7f
Harrison/serp api imp (#444) 
improve serp api

Co-authored-by: Bruno Bornsztein <bruno.bornsztein@gmail.com>
 2022-12-27 20:27:18 -05:00
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