fix(diarization-ui): validate non-empty content before LLM call, add OLLAMA_THINK flag

Empty documents caused the model to spin in its thinking loop and waste
all tokens. Now raises a clear job error before the Ollama call.
Also adds OLLAMA_THINK env var (default false) to control whether
the model uses extended thinking - disabling it avoids runaway thinking
loops on ambiguous inputs.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
2026-05-06 16:10:01 +02:00
parent aae53d91b1
commit f5756f38af
2 changed files with 5 additions and 1 deletions

View File

@@ -2,3 +2,4 @@ API_BASE=http://gx10.aquantico.lan:8093
OLLAMA_BASE_URL=http://gx10.aquantico.lan:11434
OLLAMA_MODEL=qwen3.5:9b
OLLAMA_NUM_PREDICT=4096
OLLAMA_THINK=false