.env.example

API_BASE=http://gx10.aquantico.lan:8093
OLLAMA_BASE_URL=http://gx10.aquantico.lan:11434
OLLAMA_MODEL=qwen3.5:9b
OLLAMA_NUM_PREDICT=16384
OLLAMA_THINK=true
chore(diarization-ui): default API_BASE to gx10 and use fully qualified nginx image for podman 2026-03-21 13:24:11 +01:00			`API_BASE=http://gx10.aquantico.lan:8093`
feat(diarization-ui): add FastAPI UI backend with sqlite storage and Ollama analysis pipeline 2026-03-21 13:47:36 +01:00			`OLLAMA_BASE_URL=http://gx10.aquantico.lan:11434`
			`OLLAMA_MODEL=qwen3.5:9b`
fix(diarization-ui): raise default num_predict to 16384 Thinking tokens count against num_predict. At 4096 the model was running out mid-response after spending ~3000 tokens on thinking. 16384 gives enough headroom for thinking + full response. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> 2026-05-06 16:26:55 +02:00			`OLLAMA_NUM_PREDICT=16384`
fix(diarization-ui): enable thinking by default (OLLAMA_THINK=true) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> 2026-05-06 16:12:25 +02:00			`OLLAMA_THINK=true`