Commit Graph

6257 Commits

Author SHA1 Message Date
Harrison Chase
8c167627ed
bump version (#340) 2022-12-14 10:38:31 -08:00
Harrison Chase
e26b6f9c89
fix batching (#339) 2022-12-14 08:25:37 -08:00
Harrison Chase
3c6796b72e
bump version to 0036 (#333) 2022-12-13 08:17:41 -08:00
Harrison Chase
996b5a3dfb
Harrison/llm final stuff (#332) 2022-12-13 07:50:46 -08:00
Harrison Chase
9bb7195085
Harrison/llm saving (#331)
Co-authored-by: Akash Samant <70665700+asamant21@users.noreply.github.com>
2022-12-13 06:46:01 -08:00
Harrison Chase
595cc1ae1a
RFC: more complete return (#313)
Co-authored-by: Andrew Williamson <awilliamson10@indstate.edu>
Co-authored-by: awilliamson10 <aw.williamson10@gmail.com>
2022-12-13 05:50:03 -08:00
Hunter Gerlach
482611f426
unit test / code coverage improvements (#322)
This PR has two contributions:

1. Add test for when stop token is found in middle of text

2. Add code coverage tooling and instructions
- Add pytest-cov via poetry
- Add necessary config files
- Add new make instruction for `coverage`
- Update README with coverage guidance
- Update minor README formatting/spelling

Co-authored-by: Hunter Gerlach <hunter@huntergerlach.com>
2022-12-13 05:48:53 -08:00
Harrison Chase
8861770bd0
expose get_num_tokens method (#327) 2022-12-13 05:22:42 -08:00
Ankush Gola
8fdcdf4c2f
add .idea files to gitignore, add zsh note to installation docs (#329) 2022-12-13 05:20:22 -08:00
thepok
137356dbec
-1 max token description for openai (#330) 2022-12-13 05:15:51 -08:00
Christian Clauss
2fbb152386
Add Python 3.11 to the testing (#324) 2022-12-12 07:19:52 -08:00
Christian Clauss
d946be2f3d
Add Python 3.11 to the testing (#323) 2022-12-12 06:09:08 -08:00
Harrison Chase
292f1cfa96
Harrison/add contributing docs (#315) 2022-12-12 06:07:40 -08:00
Harrison Chase
948e999eff
bump version to 0035 (#312) 2022-12-11 11:07:30 -08:00
Harrison Chase
a7c8e37e77
Harrison/token counts (#311)
Co-authored-by: thepok <richterthepok@yahoo.de>
2022-12-11 07:43:40 -08:00
Shobith Alva
19a9fa16a9
Add clear() method for Memory (#305)
a simple helper to clear the buffer in `Conversation*Memory` classes
2022-12-11 07:09:06 -08:00
Harrison Chase
e02d6b2288
beta: logger (#307) 2022-12-10 23:17:19 -08:00
Harrison Chase
36b4c58acf
expose more stuff (#306) 2022-12-10 23:16:32 -08:00
Harrison Chase
7827f0a844
fix typing (int -> float) (#308) 2022-12-10 20:31:55 -08:00
Hunter Gerlach
9ee6115deb
Minor grammar fixes for memory docs to improve readability (#303)
Nothing of substance was changed. I simply corrected a few minor errors
that could slow down the reader.

Co-authored-by: Hunter Gerlach <hunter@huntergerlach.com>
2022-12-10 16:18:01 -08:00
Harrison Chase
9d08384d5f
Harrison/bump version (#300) 2022-12-10 09:37:42 -08:00
Harrison Chase
853894dd47
add moderation chain (#299) 2022-12-10 09:19:16 -08:00
andersenchen
5267ebce2d
Add LLMCheckerChain (#281)
Implementation of https://github.com/jagilley/fact-checker. Works pretty
well.

<img width="993" alt="Screenshot 2022-12-07 at 4 41 47 PM"
src="https://user-images.githubusercontent.com/101075607/206302751-356a19ff-d000-4798-9aee-9c38b7f532b9.png">

Verifying this manually:
1. "Only two kinds of egg-laying mammals are left on the planet
today—the duck-billed platypus and the echidna, or spiny anteater."
https://www.scientificamerican.com/article/extreme-monotremes/
2. "An [Echidna] egg weighs 1.5 to 2 grams (0.05 to 0.07
oz)[[19]](https://en.wikipedia.org/wiki/Echidna#cite_note-19) and is
about 1.4 centimetres (0.55 in) long."
https://en.wikipedia.org/wiki/Echidna#:~:text=sleep%20is%20suppressed.-,Reproduction,a%20reptile%2Dlike%20egg%20tooth.
3. "A [platypus] lays one to three (usually two) small, leathery eggs
(similar to those of reptiles), about 11 mm (7⁄16 in) in diameter and
slightly rounder than bird eggs."
https://en.wikipedia.org/wiki/Platypus#:~:text=It%20lays%20one%20to%20three,slightly%20rounder%20than%20bird%20eggs.
4. Therefore, an Echidna is the mammal that lays the biggest eggs.


cc @hwchase17
2022-12-09 12:49:05 -08:00
Harrison Chase
43c9bd869f
add memprompt docs (#294) 2022-12-09 12:40:24 -08:00
Ben
0f399350f1
Fix typo in Getting Started / LLM Chains docs (#291)
I noticed this typo when reading the getting started guide, hope this
fix makes sense.
2022-12-09 06:48:02 -08:00
Harrison Chase
85c66dc6a4
bump version to 0033 (#290) 2022-12-09 06:47:49 -08:00
Samantha Whitmore
b10be842f6
ChatGPT Clone: adding ConversationBufferWindowMemory to replicate vir… (#288)
…tual env example
2022-12-08 23:01:08 -08:00
Harrison Chase
e2e501aa06
Harrison/version 0032 (#283) 2022-12-08 07:59:58 -08:00
Harrison Chase
e9b1c8cdfa
Harrison/base combine doc chain (#264) 2022-12-07 22:56:26 -08:00
Harrison Chase
c27a6fa8a4
update docs (#278) 2022-12-07 08:40:08 -08:00
Harrison Chase
1690292b09
bump version to 0031 (#276) 2022-12-07 07:29:08 -08:00
Harrison Chase
834b391792
update notebooks (#275) 2022-12-06 22:55:27 -08:00
Harrison Chase
3c1c7ba672
update branch name in gha (#274) 2022-12-06 22:28:50 -08:00
Akash Samant
48b093823e
Add a Transformation Chain (#257)
Arbitrary transformation chains that can be used to add dictionary
extractions from llms/other chains
2022-12-06 21:58:16 -08:00
coyotespike
b7bef36ee1
BashChain (#260)
Love the project, a ton of fun!

I think the PR is pretty self-explanatory, happy to make any changes! I
am working on using it in an `LLMBashChain` and may update as that
progresses.

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2022-12-06 21:57:50 -08:00
Harrison Chase
28be37f470
LLMRequestsChain (#267) 2022-12-06 21:55:02 -08:00
John McDonnell
68666d6a22
Gracefully degrade when model asks for nonexistent tool (#268)
Not yet tested, but very simple change, assumption is that we're cool
with just producing a generic output when tool is not found
2022-12-06 21:52:48 -08:00
Harrison Chase
2180a91196
bump 0.0.30 (#269) 2022-12-06 05:57:00 -08:00
Harrison Chase
2163d064f3
add return of ids (#254)
not actually sure the desired return in add_example to example selector
is actually general/good - whats the use case?
2022-12-05 12:50:48 -08:00
Harrison Chase
8cba5b791a
hotfix for api logging (#262) 2022-12-04 21:12:05 -08:00
Harrison Chase
5cd6956d58
Harrison/version 0028 (#259) 2022-12-04 17:44:40 -08:00
Harrison Chase
f5c665a544
combine python files (#256) 2022-12-04 15:57:36 -08:00
Steven Hoelscher
98fb19b535
chore: use poetry as dependency manager (#242)
* Adopts [Poetry](https://python-poetry.org/) as a dependency manager
* Introduces dependency version requirements
* Deprecates Python 3.7 support

**TODO**
- [x] Update developer guide
- [x] Add back `playwright`, `manifest-ml`, and `jupyter` to dependency
group

**Not Doing => Fast Follow**
- Investigate single source for version, perhaps relying on GitHub tags
and [tackling this
issue](https://github.com/hwchase17/langchain/issues/26)
2022-12-03 16:42:59 -08:00
Harrison Chase
988cb51a7c
fix out of date docs (#255) 2022-12-03 14:48:42 -08:00
Harrison Chase
9481a23314
stop using chained input except in agent (#249) 2022-12-03 14:15:56 -08:00
Harrison Chase
b5d8434a50
Harrison/improve chain docs (#251) 2022-12-03 13:28:50 -08:00
Harrison Chase
ac2c2f6f28
Harrison/delete bad code (#253) 2022-12-03 13:28:29 -08:00
Harrison Chase
db58032973
introduce output parser (#250) 2022-12-03 13:28:07 -08:00
Scott Leibrand
b4762dfff0
Refine Olivia Wilde's boyfriend example prompt to work better (#248)
With the original prompt, the chain keeps trying to jump straight to
doing math directly, without first looking up ages. With this two-part
question, it behaves more as intended:


> Entering new ZeroShotAgent chain...
How old is Olivia Wilde's boyfriend? What is that number raised to the
0.23 power?
Thought: I need to find out how old Olivia Wilde's boyfriend is, and
then use a calculator to calculate the power.
Action: Search
Action Input: Olivia Wilde's boyfriend age
Observation: While Wilde, 37, and Styles, 27, have both kept a low
profile when it comes to talking about their relationship, Wilde did
address their ...
Thought: Olivia Wilde's boyfriend is 27 years old.
Action: Calculator
Action Input: 27^0.23

> Entering new LLMMathChain chain...
27^0.23

```python
import math
print(math.pow(27, 0.23))
```

Answer: 2.1340945944237553

> Finished LLMMathChain chain.

Observation: Answer: 2.1340945944237553

Thought: I now know the final answer.
Final Answer: 2.1340945944237553
> Finished ZeroShotAgent chain.
2022-12-03 08:11:38 -08:00
Harrison Chase
a9ce04201f
Harrison/improve usability of api chain (#247)
improve usability of api chain
2022-12-02 15:44:10 -08:00