Commit Graph

4837 Commits

Author SHA1 Message Date
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
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