gitea-admin/gh-christianlouis-docuelevate
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
1,054 Commits 28 Branches 0 Tags
4dd4e1ffa3eb82bffcfaeb0837f48741742802df
Commit Graph

3 Commits

Author SHA1 Message Date
copilot-swe-agent[bot] c7423834d5 fix(ocr): rewrite MistralOCRProvider to use native Mistral OCR API 
- PDFs are now uploaded to Mistral Files API (POST /v1/files) and
  processed via a signed document_url, resolving the 422 error caused
  by passing data:application/pdf;base64,... to an image endpoint
- Images (JPEG/PNG/GIF/WEBP/BMP/TIFF) use base64 image_url directly
- Unsupported MIME types raise a clear ValueError
- Magic-byte fallback detects PDFs with no file extension
- Switches from openai chat completions to requests HTTP calls
- Adds helper method _upload_pdf_and_get_document()
- Adds TestMistralOCRProvider with 9 unit tests covering all paths

Co-authored-by: christianlouis <361235+christianlouis@users.noreply.github.com>
 2026-02-24 12:13:38 +00:00
github-actions[bot] 5ee3d8cd84 style: apply ruff auto-fix 
- Auto-formatted code with ruff format
- Applied ruff linting fixes with --fix

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
 2026-02-23 21:24:11 +00:00
copilot-swe-agent[bot] 1f843fe460 feat(ocr): add self-hosted OCR engine support (Tesseract, EasyOCR) with multi-provider cross-checking 
Co-authored-by: christianlouis <361235+christianlouis@users.noreply.github.com>
 2026-02-23 20:59:43 +00:00