5 Commits

Author SHA1 Message Date
oval 3601d48f5a Fix SDK compatibility: poll response field names and file metadata format 2026-06-08 12:11:48 +02:00
oval 5883565b87 Implement Datalab-compatible API with async endpoints and deepseek OCR backend
- New endpoints: /api/v1/convert, /api/v1/extract, /api/v1/segment,
  /api/v1/ocr, /api/v1/table_rec, /api/v1/marker (deprecated),
  /api/v1/create-document, /api/v1/files/*, /api/v1/thumbnails
- Async submit-and-poll pattern matching Datalab API spec
- X-API-Key authentication via API_KEY env var
- Filesystem-based request store for multi-worker support
- OCR_BACKEND=deepseek mode: uses deepseek-ocr via ollama for OCR
  (prompt: <|grounding|>Free OCR.)
- build_options() now propagates output_format to parsed_opts
- Fixed docs page CSS curly brace conflict with .format()
- Renamed marker_endpoint_referece.md -> marker_endpoint_reference.md
- Containerfile: added poppler-utils, pandoc; 3 gunicorn workers
- gunicorn.conf: post_fork hook for background worker threads
2026-06-08 11:12:55 +02:00
oval 0c4bcdc7d2 Switch from Vega20 (gfx906) base to ROCm 7.2 for gfx1151; set local ollama :11435 2026-06-07 22:39:28 +02:00
oval 94003f7dda Remove use_llm default from build_options() to prevent Click duplicate parameter warning 2026-06-06 02:14:53 +02:00
oval 460fc0003b Initial marker-api benchmark setup: Containerfile, app.py, convert_both.py, compare_conversions.py 2026-06-05 13:26:25 +02:00