host.today/ht-docker-ai
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(tests): improve Qwen3-VL invoice extraction test by switching to non-stream API, adding model availability/pull checks, simplifying response parsing, and tightening model options

Browse Source
This commit is contained in:
Jürgen Kunz
2026-01-18 04:17:30 +00:00
parent 9f9ec0a671
commit 7c8f10497e
2 changed files with 96 additions and 127 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
changelog.md
View File

@@ -1,5 +1,15 @@
# Changelog
## 2026-01-18 - 1.10.1 - fix(tests)
improve Qwen3-VL invoice extraction test by switching to non-stream API, adding model availability/pull checks, simplifying response parsing, and tightening model options
- Replaced streaming reader logic with direct JSON parsing of the /api/chat response
- Added ensureQwen3Vl() to check and pull the Qwen3-VL:8b model from Ollama
- Switched to ensureMiniCpm() to verify Ollama service is running before model checks
- Use /no_think prompt for direct JSON output and set temperature to 0.0 and num_predict to 512
- Removed retry loop and streaming parsing; improved error messages to include response body
- Updated logging and test setup messages for clarity
## 2026-01-18 - 1.10.0 - feat(vision)
add Qwen3-VL vision model support with Dockerfile and tests; improve invoice OCR conversion and prompts; simplify extraction flow by removing consensus voting