- Add evals/promptfoo.ollama.yaml: same 19 cases hitting Ollama OpenAI-compat API directly (no extraction-service needed); all assertions use inline JSON.parse(output) to handle raw string response from Ollama - Add evals/compare-evals.sh: runs Gemini + Ollama evals back-to-back and prints side-by-side pass-rate comparison table - Supports OLLAMA_MODEL env var (default: llama3.1:8b) |
||
|---|---|---|
| .. | ||
| evals | ||
| python | ||
| src | ||
| .env.example | ||
| Dockerfile | ||
| package.json | ||
| supervisord.conf | ||
| tsconfig.json | ||