Evaluation for AI apps and agent.
Project description
LangEval
Evaluation for AI apps and agent
▄▄▌ ▄▄▄· ▐ ▄ ▄▄ • ▄▄▄ . ▌ ▐· ▄▄▄· ▄▄▌
██• ▐█ ▀█ •█▌▐█▐█ ▀ ▪▀▄.▀·▪█·█▌▐█ ▀█ ██•
██▪ ▄█▀▀█ ▐█▐▐▌▄█ ▀█▄▐▀▀▪▄▐█▐█•▄█▀▀█ ██▪
▐█▌▐▌▐█ ▪▐▌██▐█▌▐█▄▪▐█▐█▄▄▌ ███ ▐█ ▪▐▌▐█▌▐▌
.▀▀▀ ▀ ▀ ▀▀ █▪·▀▀▀▀ ▀▀▀ . ▀ ▀ ▀ .▀▀▀
Table of Contents
Installation
pip install langeval-cli
Documents
TODOs:
- merge uncommit changes in wsl
- support openai 2.0
- both support pydantic v1 & v2
- support qianfan the latest version
- total re-write examples
- support re-run
How to use
see ./examples for more details.
Development
# Create virtual environment
hatch env create
# Activate virtual environment
hatch shell
# Run test
hatch run test
# Run lint
hatch run lint:style
# Version dump
hatch version patch/minor/major
# Build
hatch build
# Upload to pypi
hatch publish
License
LangEval is distributed under the terms of the MIT license.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
langeval_cli-0.3.2.tar.gz
(60.4 kB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file langeval_cli-0.3.2.tar.gz.
File metadata
- Download URL: langeval_cli-0.3.2.tar.gz
- Upload date:
- Size: 60.4 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: python-httpx/0.24.1
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
482e208720456c9fa1593f2dabe2425aa47c6d2de9f4471b84b482a88bbb164b
|
|
| MD5 |
d328cad1f6f9affc76eb9a591cf55d03
|
|
| BLAKE2b-256 |
e32f4c1e788fe2349ad819d55fcc6f4ccf0bf646a321db64ab9b1671be7215fd
|
File details
Details for the file langeval_cli-0.3.2-py3-none-any.whl.
File metadata
- Download URL: langeval_cli-0.3.2-py3-none-any.whl
- Upload date:
- Size: 39.3 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: python-httpx/0.24.1
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
93417b908d868eb0c7faa129b332146e5d78d70c0ae8a3e7bc05ee163c4f7b08
|
|
| MD5 |
9988a8548b5fb264eb2e04642cc98315
|
|
| BLAKE2b-256 |
a8a7f71450cee06502427973ed799ed3f4b6c1dad98a01c21ac4963e1c68f4fb
|