Harrison Chase
d2f9288be6
add metadata to documents ( #153 )
...
add concept of metadata to document
2022-11-16 21:58:05 -08:00
Harrison Chase
d775ddd749
add apply functionality ( #150 )
2022-11-16 21:39:02 -08:00
thesved
47e35d7d0e
Fix notebook links ( #149 )
...
Example notebook links were broken.
2022-11-16 15:13:12 -08:00
Harrison Chase
4f1bf159f4
bump version to 0.0.14 ( #145 )
2022-11-14 22:07:54 -08:00
Harrison Chase
b504cd739f
Harrison/cleanup env check ( #144 )
2022-11-14 22:05:41 -08:00
Harrison Chase
a4b502d92f
fix env var loader ( #143 )
2022-11-14 21:42:43 -08:00
Harrison Chase
1835e8a681
prompt nit ( #141 )
...
doing some cleanup, and i think this just simplifies things...
2022-11-14 21:30:33 -08:00
Harrison Chase
bbb405a492
update colors ( #140 )
2022-11-14 20:27:36 -08:00
Predrag Gruevski
1a95252f00
Use pull_request not pull_request_target in GitHub Actions. ( #139 )
...
`pull_request` runs on the merge commit between the opened PR and the
target branch where the PR is to be merged — `master` in this case. This
is desirable because that way the new changes get linted and tested.
The existing `pull_request_target` specifier causes lint and test to run
_on the target branch itself_ (i.e. `master` in this case). That way the
new code in the PR doesn't get linted and tested at all. This can also
lead to security vulnerabilities, as described in the GitHub docs:
Screenshot from here:
https://docs.github.com/en/actions/using-workflows/events-that-trigger-workflows#pull_request_target
Link from the screenshot:
https://securitylab.github.com/research/github-actions-preventing-pwn-requests/
2022-11-14 11:34:08 -08:00
Harrison Chase
9f223e6ccc
Harrison/fix lint ( #138 )
2022-11-14 08:55:59 -08:00
Delip Rao
76cecf8165
A fix for Jupyter environment variable issue ( #135 )
...
- fixes the Jupyter environment variable issues mentioned in issue #134
- fixes format/lint issues in some unrelated files (from make
format/lint)
2022-11-14 08:34:01 -08:00
Harrison Chase
ced29b816b
remove extra run from merge conflict ( #133 )
2022-11-13 21:07:20 -08:00
Harrison Chase
11d37d556e
bump version 0.0.13 ( #132 )
2022-11-13 21:06:50 -08:00
Harrison Chase
b1b6b27c5f
Harrison/redo docs ( #130 )
...
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
2022-11-13 20:13:23 -08:00
Harrison Chase
f23b3ceb49
consolidate run functions ( #126 )
...
consolidating logic for when a chain is able to run with single input
text, single output text
open to feedback on naming, logic, usefulness
2022-11-13 18:14:35 -08:00
Harrison Chase
1fe3a4f724
extra requires ( #129 )
...
add extra requires
2022-11-13 17:34:58 -08:00
Eugene Yurtsev
2910f50a3c
Fix a few typos and wrapped f-strings ( #128 )
...
Fix a few typos and wrapped f-strings
2022-11-13 13:16:19 -08:00
Edmar Ferreira
8a5ec894e7
Prompt from file proof of concept using plain text ( #127 )
...
This is a simple proof of concept of using external files as templates.
I'm still feeling my way around the codebase.
As a user, I want to use files as prompts, so it will be easier to
manage and test prompts.
The future direction is to use a template engine, most likely Mako.
2022-11-13 13:15:30 -08:00
Harrison Chase
d87e73ddb1
huggingface tokenizer ( #75 )
2022-11-13 09:37:44 -08:00
Eugene Yurtsev
b542941234
Bumping python version for read the docs ( #122 )
...
Haven't checked whether things work with new python version, hoping
error will
be caught with CI
2022-11-12 13:43:39 -08:00
Eugene Yurtsev
6df08eec52
Readme: Fix link to embeddings example and use python markup for code examples ( #123 )
...
* Fix URL to embeddings notebook
* Specify python is used for the code block
2022-11-12 11:26:08 -08:00
Eugene Yurtsev
f5a588a165
Add py.typed marker to package ( #121 )
...
- Update
- update
2022-11-12 11:22:32 -08:00
Harrison Chase
47af2bcee4
vector db qa ( #71 )
2022-11-12 07:24:49 -08:00
Harrison Chase
4c0b684f79
new manifest notebook ( #118 )
2022-11-11 06:49:06 -08:00
Harrison Chase
7467243a42
bump version 0.0.12 ( #116 )
2022-11-11 06:41:07 -08:00
Harrison Chase
e43534d41c
add integration with manifest ( #62 )
2022-11-10 11:24:11 -08:00
Harrison Chase
5e76c12455
Harrison/fix docs ( #115 )
2022-11-10 08:59:51 -08:00
Harrison Chase
9f878e43d8
Harrison/lintai21 ( #114 )
2022-11-10 08:46:35 -08:00
tomeras91
d8734ce5ad
Add AI21 LLMs ( #99 )
...
Integrate AI21 /complete API into langchain, to allow access to Jurassic
models.
2022-11-10 08:12:28 -08:00
Harrison Chase
2179ea3103
remove unnecc variables ( #113 )
...
i dont think either of these variables are used?
2022-11-10 07:53:45 -08:00
Harrison Chase
da445e474d
version 0.0.11 ( #112 )
2022-11-09 23:10:29 -08:00
Harrison Chase
b92e9abdf1
Harrison/fix name ( #111 )
2022-11-09 23:10:16 -08:00
Samantha Whitmore
a0780cc930
OptimizedPrompt -- k-shot example choice backed by semantic search ( #91 )
2022-11-09 21:15:42 -08:00
Delip Rao
3ee6e332dd
Implements NLTK and Spacy-based TextSplitters ( #103 )
...
This PR is for Issue #88
- [x] `make format`
- [x] `make lint`
- [x] `make tests`
2022-11-09 20:45:30 -08:00
issam9
28282ad099
Issam9/cohere embeddings ( #105 )
...
Add support for cohere embeddings
2022-11-09 13:44:27 -08:00
Delip Rao
95dd2f140e
Make Integration Tests "work" again ( #106 )
...
This fixes Issue #104
The tests for HF Embeddings is skipped because of the segfault issue
mentioned there. Perhaps, a new issue should be created for that?
2022-11-09 13:26:58 -08:00
Nicholas Larus-Stone
abe4fc04fa
docs: fix some minor typos in README ( #107 )
...
Small docs fixes
2022-11-09 13:23:29 -08:00
Delip Rao
bd462e9df0
Fix pip install issue due to FAISS ( #102 )
...
- change requirements.txt to fix Issue #101
- update .gitignore to support VSCode dev environment
2022-11-09 13:23:17 -08:00
Samantha Whitmore
386a14a19f
Change NLPCloud default model ( #100 )
2022-11-09 09:30:09 -08:00
Harrison Chase
5b7aed34a3
bump version to 0.0.10 ( #98 )
2022-11-09 00:20:46 -08:00
Harrison Chase
db37bd089f
model laboratory ( #95 )
2022-11-08 22:17:10 -08:00
Samantha Whitmore
2ddab88c06
Update VectorStore interface to contain from_texts, enforce common in… ( #97 )
...
…terface
2022-11-08 21:55:22 -08:00
Samantha Whitmore
61f12229df
Create VectorStore interface ( #92 )
2022-11-08 18:19:39 -08:00
Harrison Chase
b9f61390e9
add text2text generation ( #93 )
...
fixes issue #90
2022-11-08 18:08:46 -08:00
Samantha Whitmore
e48e562ea5
ElasticVectorSearch: Add in vector search backed by Elastic ( #67 )
...
woo!
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2022-11-08 07:01:42 -08:00
Samantha Whitmore
efbc03bda8
NLPCloud client integration ( #81 )
...
lots of kwargs! generation docs here:
https://docs.nlpcloud.com/#generation
This somewhat breaks the paradigm introduced in LLM base class as the
stop sequence isn't a list, and should rightfully be introduced at the
time of initialization of the class, along with the other kwargs that
depend on its presence (e.g. remove_end_sequence, etc.) curious if you'd
want to refactor LLM base class to take out stop as a specific named
kwarg?
2022-11-08 06:24:23 -08:00
Harrison Chase
6d8a657676
bump to version 0.0.9 ( #82 )
2022-11-07 20:42:25 -08:00
Harrison Chase
6cff2837bb
Harrison/fix lint ( #80 )
2022-11-07 15:22:37 -08:00
Cameron Whitehead
54e325be2f
Improve credential handing to allow passing in constructors ( #79 )
...
Addresses the issue in #76 by either using the relevant environment
variable if set or using a string passed in the constructor.
Prefers the constructor string over the environment variable, which
seemed like the natural choice to me.
2022-11-07 13:34:45 -08:00
Harrison Chase
9679bdc34c
run workflows on forks ( #78 )
...
per
https://stackoverflow.com/questions/58221321/is-github-actions-available-on-forked-repositories
2022-11-07 05:53:17 -08:00
