| .. |
| examples | Make eval more resilient to bad input from LLM (#29703) | 1 year ago |
| assertions.rs | eval: Fine-grained assertions (#29246) | 1 year ago |
| eval.rs | Make the default repetitions be 8, and concurrency 4 (#29576) | 1 year ago |
| example.rs | Code block evals (#29619) | 1 year ago |
| explorer.html | eval: Add HTML overview for evaluation runs (#29413) | 1 year ago |
| explorer.rs | eval: Add HTML overview for evaluation runs (#29413) | 1 year ago |
| ids.rs | Add new action to run agent eval (#29158) | 1 year ago |
| instance.rs | Fix eval judging missing final response (#29638) | 1 year ago |
| judge_diff_prompt.hbs | eval: Fine-grained assertions (#29246) | 1 year ago |
| judge_thread_prompt.hbs | eval: Fine-grained assertions (#29246) | 1 year ago |
| tool_metrics.rs | eval: Fine-grained assertions (#29246) | 1 year ago |