Skip to main content

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This project has been archived.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 evaluation
  • anyeval 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

  1. Clone the repository:
git clone https://github.com/yourusername/anyeval.git
cd anyeval
  1. 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 .
  1. For development of the frontend (optional, requires Node.js):
cd anyeval/frontend
npm install
npm start
  1. 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:

  1. Start a web server at http://localhost:8000
  2. Automatically open your browser to the evaluation UI
  3. 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

anyeval-0.1.0.tar.gz (718.0 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

anyeval-0.1.0-py3-none-any.whl (724.0 kB view details)

Uploaded Python 3

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

Hashes for anyeval-0.1.0.tar.gz
Algorithm Hash digest
SHA256 a9ef991694d25d663a6aedc9d05d88370fd8b2c3a8b3857e437cacb1f7fd0d2d
MD5 409aedad14b545d116704768828f8d50
BLAKE2b-256 37b6e7501e72ab395706a0dfb2389c8a4041bf851995e836107ff42bc41eaf99

See more details on using hashes here.

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

Hashes for anyeval-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 3af5885d141694e0277901fbc67da331f8f2f490f7af3669cb2a261c93e92fb5
MD5 4701f19df3679a6b30adf6e848a4328f
BLAKE2b-256 840aec1df507260a02f5ffacf826c78a6d60620af69356257c1d99d77fe3287f

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page