Harrison Chase
b19a73be26
pal chain touch ups ( #225 )
...
expose PAL in main entrypoint
2022-11-29 18:13:21 -08:00
Andrew Gleave
ea67c049f0
Support SQL statements that return no results ( #222 )
...
Adds support for statements such as insert, update etc which do not
return any rows.
`engine.execute` is deprecated and so execution has been updated to use
`connection.exec_driver_sql` as-per:
https://docs.sqlalchemy.org/en/14/core/connections.html#sqlalchemy.engine.Engine.execute
2022-11-29 08:28:45 -08:00
Akash Samant
d368c43648
Bug Fix ( #221 )
...
Quick bug fix for semantic similarity vector injection
2022-11-29 07:03:40 -08:00
Harrison Chase
1db7b18341
bump version to 0.0.24 ( #220 )
2022-11-28 22:20:30 -08:00
Harrison Chase
1b9b8efbc9
pal chain ( #207 )
...
from https://arxiv.org/pdf/2211.10435.pdf
2022-11-28 21:38:34 -08:00
Shyamal H Anadkat
de4b255c1f
Switch default openai model to text-davinci-003 ( #215 )
2022-11-28 18:03:34 -08:00
Harrison Chase
0568998166
Harrison/fix react stateful ( #219 )
...
fix issue with react being stateful
2022-11-28 18:03:04 -08:00
Harrison Chase
03c7140228
fix self ask template ( #216 )
2022-11-28 17:27:26 -08:00
Harrison Chase
cf3569fb1b
remove check ( #217 )
...
doesnt do much
2022-11-28 17:27:11 -08:00
Hansen Qian
a39c998342
Add chain name to verbose logging ( #214 )
...
Adds some context over what chain is running, thereby making it more
obvious how different chains are entered and existed
<img width="867" alt="Screen Shot 2022-11-28 at 11 55 34 AM"
src="https://user-images.githubusercontent.com/2548973/204336849-25d87b44-6f5d-487b-b583-5455f306a470.png ">
(note that the `...` is because the output is too long and VSCode
truncated it)
2022-11-28 11:11:30 -08:00
Harrison Chase
261029cef3
bump version to 0.0.23 ( #211 )
2022-11-27 19:51:11 -08:00
Harrison Chase
b94244eb12
nits ( #210 )
...
use json.dump
move test to integration tests (since it requires huggingface_hub)
2022-11-27 13:03:09 -08:00
Akash Samant
ae72cf84b8
Save Prompts ( #194 )
2022-11-27 09:10:35 -08:00
Bagatur
b90e25f786
Add HuggingFace Hub Embeddings ( #125 )
...
Add support for calling HuggingFace embedding models
using the HuggingFaceHub Inference API. New class mirrors
the existing HuggingFaceHub LLM implementation. Currently
only supports 'sentence-transformers' models.
Closes #86
2022-11-27 00:24:59 -08:00
Dillon Chen
d0415952f7
Update README.md memory now added as a feature ( #208 )
2022-11-26 20:21:42 -08:00
Harrison Chase
287f1857ee
fix self ask w search ( #206 )
2022-11-26 15:15:43 -08:00
Mark Kretschmann
eae358810b
Fix Unicode error on Windows (Issue #200 ) ( #203 )
...
Fix Unicode error on Windows during setup, while trying to read contents
of README.md.
(Issue #200 )
2022-11-26 08:34:16 -08:00
Harrison Chase
3eddbd11e4
bump version to 22 ( #202 )
2022-11-26 06:46:47 -08:00
Harrison Chase
d4e6b7a692
Harrison/update docs mem ( #201 )
2022-11-26 06:38:49 -08:00
Harrison Chase
05c5d0b8ee
add custom prompt notebooks ( #198 )
2022-11-26 06:07:02 -08:00
Harrison Chase
fcb9b2ffe5
Harrison/agent memory ( #197 )
...
add doc for agent with memory
2022-11-26 06:06:44 -08:00
Harrison Chase
6eab5254e5
add docs for custom agents ( #196 )
2022-11-26 06:03:08 -08:00
Harrison Chase
08deed9002
Harrison/memory docs ( #195 )
...
update memory docs and change variables
2022-11-26 05:58:54 -08:00
Harrison Chase
f18a08f58d
add memory to llm chain notebook ( #193 )
2022-11-25 18:28:55 -08:00
Harrison Chase
199794086d
bump verion to 0.0.21 ( #190 )
2022-11-25 10:04:21 -08:00
Harrison Chase
c3ad99a34f
Harrison/more memory docs ( #192 )
2022-11-25 13:00:12 -05:00
Harrison Chase
b0feb3608b
documentation ( #191 )
2022-11-25 12:41:27 -05:00
Harrison Chase
b913df3774
make attrs public ( #187 )
...
since they are used outside of the class, should be public
2022-11-24 20:11:29 -08:00
Harrison Chase
ae9c6257fe
Harrison/arbitrary params ( #186 )
2022-11-24 20:01:20 -08:00
Samantha Whitmore
a408ed3ea3
Samantha/add conversation chain ( #166 )
...
Add MemoryChain and ConversationChain as chains that take a docstore in
addition to the prompt, and use the docstore to stuff context into the
prompt. This can be used to have an ongoing conversation with a chatbot.
Probably needs a bit of refactoring for code quality
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2022-11-23 16:35:38 -08:00
Harrison Chase
4334ffa6f9
Harrison/clean up language ( #179 )
...
dynamic prompts are no longer a thing
2022-11-23 16:58:41 -05:00
Harrison Chase
736b6ee65c
fix search return type ( #177 )
2022-11-23 13:13:00 -08:00
Samantha Whitmore
09f301cd38
Add add_example method to all ExampleSelector classes, with tests ( #178 )
...
Also updated docs, and noticed an issue with the add_texts method on
VectorStores that I had missed before -- the metadatas arg should be
required to match the classmethod which initializes the VectorStores
(the add_example methods break otherwise in the ExampleSelectors)
2022-11-23 13:12:47 -08:00
Harrison Chase
780ef84cf0
use action verb in documentation ( #175 )
2022-11-22 21:04:26 -08:00
Harrison Chase
1b81f3b125
bump version 0.0.20 ( #174 )
2022-11-22 18:10:42 -08:00
Harrison Chase
5d887970f6
change to agent ( #173 )
2022-11-22 18:02:20 -08:00
Harrison Chase
d70b5a2cbe
Harrison/version 0019 ( #172 )
2022-11-22 06:51:51 -08:00
Harrison Chase
d3a7429f61
(WIP) agents ( #171 )
2022-11-22 06:16:26 -08:00
Harrison Chase
22bd12a097
make prompt a variable in vector db qa ( #170 )
2022-11-21 19:30:40 -08:00
Harrison Chase
4a4dfbfbed
Harrison/sequential chains ( #168 )
...
add support for basic sequential chains
2022-11-21 13:08:53 -08:00
Harrison Chase
15c19fcc60
bump version to 0.0.18 ( #167 )
2022-11-21 09:34:44 -08:00
Samantha Whitmore
315b0c09c6
wip: add method for both docstore and embeddings ( #119 )
...
this will break atm but wanted to get thoughts on implementation.
1. should add() be on docstore interface?
2. should InMemoryDocstore change to take a list of documents as init?
(makes this slightly easier to implement in FAISS -- if we think it is
less clean then could expose a method to get the number of documents
currently in the dict, and perform the logic of creating the necessary
dictionary in the FAISS.add_texts method.
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2022-11-20 16:23:58 -08:00
Jim Salmons
e9baf9c134
Update llm.md ( #164 )
...
Without the print on the `llm` call, the new user sees no visible effect
when just getting started. The assumption here is the new user is
running this in a new sandbox script file or repl via copy-paste.
2022-11-20 15:22:53 -08:00
Harrison Chase
e49fc51492
Harrison/update docs ( #162 )
...
minor update to docs re imports
2022-11-20 07:18:43 -08:00
Harrison Chase
243211a5ae
bump version to 0017 ( #161 )
2022-11-20 07:04:09 -08:00
Harrison Chase
a19ad935b3
Harrison/verbose prompt ( #159 )
...
Add printing of prompt to LLMChain
2022-11-19 20:39:35 -08:00
Harrison Chase
c02eb199b6
add few shot example ( #148 )
2022-11-19 20:32:45 -08:00
Harrison Chase
8869b0ab0e
bump version to 0.0.16 ( #157 )
2022-11-18 06:09:03 -08:00
Harrison Chase
b15c84e19d
Harrison/chain lab ( #156 )
2022-11-18 05:50:02 -08:00
Harrison Chase
0ac08bbca6
bump version to 0.0.15 ( #154 )
2022-11-16 23:22:05 -08:00
