50573ec7be
fix(ocr): address code review - add subprocess security comment and type hints in tests
...
Co-authored-by: christianlouis <361235+christianlouis@users.noreply.github.com >
2026-02-24 13:22:39 +00:00
fec032643b
feat(ocr): embed searchable text layer for providers without native PDF output
...
Co-authored-by: christianlouis <361235+christianlouis@users.noreply.github.com >
2026-02-24 13:19:52 +00:00
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
dcdef44303
feat: add Portkey provider support and null-content guard to AI abstraction layer
...
Co-authored-by: christianlouis <361235+christianlouis@users.noreply.github.com >
2026-02-23 19:42:03 +00:00
d4c7fb26ac
feat: add AI provider abstraction layer with OpenAI, Azure, Anthropic, Gemini, Ollama, OpenRouter, LiteLLM support
...
Co-authored-by: christianlouis <361235+christianlouis@users.noreply.github.com >
2026-02-23 19:26:45 +00:00
43bc58770d
refactor: consolidate linting tools into Ruff
...
Co-authored-by: christianlouis <361235+christianlouis@users.noreply.github.com >
2026-02-13 09:10:52 +00:00
ff9a3ff49f
style: fix code formatting with black, isort, and flake8
...
Co-authored-by: christianlouis <361235+christianlouis@users.noreply.github.com >
2026-02-12 03:21:41 +00:00
21ca941b26
fix(test): add log_task_progress mocks to OCR processing tests
...
Co-authored-by: christianlouis <361235+christianlouis@users.noreply.github.com >
2026-02-11 10:11:49 +00:00
b0bcccbbf1
Fix mathematical explanation in test comments
...
Co-authored-by: christianlouis <361235+christianlouis@users.noreply.github.com >
2026-02-07 19:37:57 +00:00
81a04794f9
Add comprehensive tests for OCR processing with mocked services
...
Co-authored-by: christianlouis <361235+christianlouis@users.noreply.github.com >
2026-02-07 19:36:26 +00:00
copilot-swe-agent[bot]