Harrison Chase
73f7ebd9d1
Harrison/sqlalchemy cache store ( #536 )
...
Co-authored-by: Jason Gill <jasongill@gmail.com>
2023-01-04 18:38:15 -08:00
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.
2023-01-04 18:28:42 -08:00
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.
2023-01-04 18:26:50 -08:00
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
2023-01-04 10:44:24 -08:00
Rubens Mau
020e73017b
Updated embeddings.ipynb ( #531 )
...
updated embeddings.ipynb
2023-01-04 10:43:52 -08:00
Ikko Eltociear Ashimine
ca9aaac36e
Fix typo in key_concepts.md ( #535 )
...
therefor -> therefore
2023-01-04 10:43:02 -08:00
Harrison Chase
680f267179
bump version to 0056 ( #533 )
2023-01-04 09:12:56 -08:00
Harrison Chase
9e04c34e20
Add BaseCallbackHandler and CallbackManager ( #478 )
...
Co-authored-by: Ankush Gola <9536492+agola11@users.noreply.github.com>
2023-01-04 07:54:25 -08:00
Nuno Campos
6d78be0c83
Add link to gihub repo in header of new docs ( #524 )
2023-01-03 10:16:59 -08:00
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