Skip to content

wtcooper/app-evals

v0.1.0MIT

Evaluate an LLM application's endpoint: a fixed adversarial benchmark and adaptive multi-turn red teaming.

scripts

  • app-benchmark
  • install_dependencies.sh
  • lib/extract_transcript.js
  • lib/status_policy.js
  • lib/summarize.py
  • lib/transform_response.js
  • new_experiment.sh
  • tests/mock_server.py
  • tests/test_app_benchmark.py
  • app-redteam
  • 8 more
    • install_dependencies.sh
    • lib/extract_transcript.js
    • lib/redteam_summary.py
    • lib/status_policy.js
    • lib/transform_response.js
    • new_experiment.sh
    • tests/mock_server.py
    • tests/test_app_redteam.py
plugin.json
name
app-evals
version
0.1.0
description
Evaluate an LLM application's endpoint: a fixed adversarial benchmark and adaptive multi-turn red teaming.
author
ai-security-evals contributors
license
MIT

What else this package ships

These files come with the package and this site does not publish them. They are listed so you know what is there before you install it.

  • 6JavaScript files
  • 6Python files
  • 4shell scripts
  • 9JSON files
  • 4YAML files
  • 2other files
View on GitHub