Spaces:
Running
Running
Commit History
-
feat(uploads): D-light blueprint pipeline (Phase-2, no OCR)
Two-phase strategy for project documentation: Phase 1 — native-PDF text extraction over ALL pages via pypdfium2, persisted to new blueprint_uploads / blueprint_pages tables (Supabase). Stamp (АР-/КЖ-/...) and title heuristics applied per page. Phase 2 — VLM only on user-selected pages (POST /extract-sheets). The text-only LLM pass over all pages (POST /extract-text) produces object_name, address, section, sheets_index, spec_summary, missing_info_prompts. Endpoints: POST /uploads/blueprint accept PDF/JPG/HEIC GET /uploads/blueprint/{upload_id} status + page list GET /uploads/blueprint/{upload_id}/pages/{n}/preview PNG base64 POST /uploads/blueprint/{upload_id}/extract-text text-LLM summary POST /uploads/blueprint/{upload_id}/extract-sheets VLM on chosen pages Caps: 50 MB body, 64 pages, 200 KB text total budget. Preview cache un…e10629e
-
deploy: backend 2026-06-22T18:15:19Z
cb75105 -
deploy: backend 2026-06-22T12:22:55Z
6a0cb28 -
deploy: backend 2026-06-22T05:07:40Z
0c46399