Universal Evaluation for Gen AI
This project has been archived.
The maintainers of this project have marked this project as archived. No new releases are expected.
Project description
anyeval
Universal Evaluation for Gen AI
Design
Data Schema (Parquet)
| id | dataset | meta | media | label | created_at | updated_at |
|---|
CLI Commands
anyeval run [parquet_file]open parquet file and get the UI for evaluationanyeval merge [parquet_files|dir] [output_parquet_file]merge parquet files into one
Installation
For Users
Install directly from PyPI:
pip install anyeval
This will install the complete package with the pre-built web UI.
Development Installation
- Clone the repository:
git clone https://github.com/yourusername/anyeval.git
cd anyeval
- Set up the Python environment:
# Using uv for package management (recommended)
uv venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
uv pip install -e .
- For development of the frontend (optional, requires Node.js):
cd anyeval/frontend
npm install
npm start
- To build the frontend for distribution:
python build_frontend.py
Usage
Running the Evaluation UI
To start the evaluation UI with a parquet file:
anyeval run path/to/your/data.parquet
This will:
- Start a web server at http://localhost:8000
- Automatically open your browser to the evaluation UI
- Allow you to browse and evaluate your data
Merging Parquet Files
To merge multiple parquet files into a single output file:
anyeval merge path/to/file1.parquet path/to/file2.parquet output.parquet
Or to merge all parquet files in a directory:
anyeval merge path/to/directory output.parquet
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
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 anyeval-0.1.0.tar.gz.
File metadata
- Download URL: anyeval-0.1.0.tar.gz
- Upload date:
- Size: 718.0 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.7.5
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
a9ef991694d25d663a6aedc9d05d88370fd8b2c3a8b3857e437cacb1f7fd0d2d
|
|
| MD5 |
409aedad14b545d116704768828f8d50
|
|
| BLAKE2b-256 |
37b6e7501e72ab395706a0dfb2389c8a4041bf851995e836107ff42bc41eaf99
|
File details
Details for the file anyeval-0.1.0-py3-none-any.whl.
File metadata
- Download URL: anyeval-0.1.0-py3-none-any.whl
- Upload date:
- Size: 724.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.7.5
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
3af5885d141694e0277901fbc67da331f8f2f490f7af3669cb2a261c93e92fb5
|
|
| MD5 |
4701f19df3679a6b30adf6e848a4328f
|
|
| BLAKE2b-256 |
840aec1df507260a02f5ffacf826c78a6d60620af69356257c1d99d77fe3287f
|