Open Issues Need Help
View All on GitHub Add licensed public multimodal dataset adapters 3 months ago
enhancement help wanted
cavadalabs/cavadalabs-evals cavadalabs/cavadalabs-evals Local-first, auditable evaluation framework for AI quality, safety, compliance evidence, and serving performance.
Open project →
1
Local-first, auditable evaluation framework for AI quality, safety, compliance evidence, and serving performance.
Python
#ai-evaluation#ai-safety#benchmarking#llm-evaluation#performance-testing#python
Document the offline demo JSON output contract 3 months ago
documentation good first issue
cavadalabs/cavadalabs-evals cavadalabs/cavadalabs-evals Local-first, auditable evaluation framework for AI quality, safety, compliance evidence, and serving performance.
Open project →
1
Local-first, auditable evaluation framework for AI quality, safety, compliance evidence, and serving performance.
Python
#ai-evaluation#ai-safety#benchmarking#llm-evaluation#performance-testing#python
Improve offline demo report accessibility checks 3 months ago
enhancement good first issue
cavadalabs/cavadalabs-evals cavadalabs/cavadalabs-evals Local-first, auditable evaluation framework for AI quality, safety, compliance evidence, and serving performance.
Open project →
1
Local-first, auditable evaluation framework for AI quality, safety, compliance evidence, and serving performance.
Python
#ai-evaluation#ai-safety#benchmarking#llm-evaluation#performance-testing#python
Add Windows CI smoke coverage for the offline demo 3 months ago
good first issue github_actions
cavadalabs/cavadalabs-evals cavadalabs/cavadalabs-evals Local-first, auditable evaluation framework for AI quality, safety, compliance evidence, and serving performance.
Open project →
1
Local-first, auditable evaluation framework for AI quality, safety, compliance evidence, and serving performance.
Python
#ai-evaluation#ai-safety#benchmarking#llm-evaluation#performance-testing#python
enhancement help wanted python
cavadalabs/cavadalabs-evals cavadalabs/cavadalabs-evals Local-first, auditable evaluation framework for AI quality, safety, compliance evidence, and serving performance.
Open project →
1
Local-first, auditable evaluation framework for AI quality, safety, compliance evidence, and serving performance.
Python
#ai-evaluation#ai-safety#benchmarking#llm-evaluation#performance-testing#python