Benjamin Admin e171a736e7 fix(ocr-pipeline): increase LLM timeout to 300s and disable qwen3 thinking ...

- Add /no_think tag to prompt (qwen3 thinking mode causes massive slowdown)
- Increase httpx timeout from 120s to 300s for large vocab tables
- Improve error logging with traceback and exception type

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-03-02 11:31:03 +01:00

..

backend

fix(ocr-pipeline): increase LLM timeout to 300s and disable qwen3 thinking

2026-03-02 11:31:03 +01:00

docs

Initial commit: breakpilot-lehrer - Lehrer KI Platform

2026-02-11 23:47:26 +01:00

frontend

Initial commit: breakpilot-lehrer - Lehrer KI Platform

2026-02-11 23:47:26 +01:00

scripts

Initial commit: breakpilot-lehrer - Lehrer KI Platform

2026-02-11 23:47:26 +01:00

Dockerfile

perf(klausur-service): split Dockerfile into base + app layer

2026-02-26 17:43:24 +01:00

Dockerfile.base

fix(ocr-pipeline): add libgl1 for RapidOCR OpenCV dependency

2026-02-28 17:30:12 +01:00