2cfcfdd1af
feat: Phase 2.6 edges migration to Qdrant (TKG-only architecture)
...
Phase 2.6.1: co_occurrence_edges migration
- build_co_occurrence_edges_from_qdrant()
- Qdrant embeddings → frame grouping → YOLO objects
- Result: 6679 edges (vs 6701 PostgreSQL)
Phase 2.6.2: face_face_edges migration
- build_face_face_edges_from_qdrant()
- Qdrant embeddings → frame grouping → face pairs
- mutual_gaze detection preserved
- Result: 6 edges (exact match)
Phase 2.6.3: speaker_face_edges migration
- build_speaker_face_edges_from_qdrant()
- Qdrant embeddings → trace_id frame ranges
- SPEAKS_AS edge creation
Architecture:
- All edges use Qdrant payload (no face_detections queries)
- PostgreSQL fallback for empty Qdrant
- Estimated 3.6x performance improvement
Testing:
- Playground (3003): ✓ All Phase 2.6 logs verified
- Edge counts: ✓ Close match with PostgreSQL
- Fallback: ✓ Working
Docs:
- docs_v1.0/DESIGN/TKG_PHASE2_6_EDGES_MIGRATION.md
- docs_v1.0/M4_workspace/2026-06-21_phase2_6_test.md
2026-06-21 04:47:49 +08:00
17e4e15860
feat: add Vision LLM integration (CLIP + Qwen3-VL cascade)
...
- Add Qwen3-VL dynamic management (start/stop/status CLI)
- Add CLIP + Qwen3-VL cascade detection strategy
- Add Vision CLI commands (vision start/stop/status, detect)
- Add cascade_vision processor module
- Add clip processor module
- Add qwen_vl_manager module
Changes:
- scripts/start_qwen3vl.sh, stop_qwen3vl.sh: Qwen3-VL management scripts
- src/core/vision/: Qwen3-VL manager module
- src/core/processor/cascade_vision.rs: CLIP + Qwen3-VL cascade logic
- src/core/processor/clip.rs: CLIP classification and detection
- src/api/clip_api.rs: CLIP API endpoints
- src/cli/vision.rs: Vision CLI implementation
- src/cli/args.rs: Add Vision and Detect commands
- src/main.rs: Integrate Vision CLI
- src/core/mod.rs: Add vision module
- src/core/processor/mod.rs: Add cascade_vision module
2026-06-13 16:25:52 +08:00
bd82028f34
refactor: unified LLM config - CHAT_URL/VISION_URL/SUMMARY_URL with env var overrides
2026-05-22 15:47:17 +08:00
3a33d00449
refactor: modularize server.rs into separate route modules
...
- Extract scan.rs, files.rs, types.rs, processing.rs, visual_chunk_search.rs
- Move AppState and AppConfig to types.rs
- Each module exposes pub fn xxx_routes() -> Router<AppState>
- server.rs reduced from 5005 to 118 lines (orchestrator only)
- All stubs filled with real implementations from git history
- Verify: cargo check, clippy, tests all pass
2026-05-21 16:38:49 +08:00
bebaa743ed
feat: trace-level matching, health watcher/worker status, timezone config
2026-05-21 01:08:30 +08:00
3164a65554
update: pipeline, search, clip, embedding fixes
2026-05-17 19:46:35 +08:00
2b23d1cfbd
feat: update core API, database layer, and worker modules
...
- Remove unused imports (n8n_search, universal_search, Client, Arc, etc.)
- Update API endpoints for identity, face recognition, search
- Fix postgres_db.rs search_videos parent_uuid column
- Add snapshot API and identity agent API
- Clean up backup files (.bak, .bak2)
2026-04-30 15:07:02 +08:00
5e896fb509
feat: implement Phase 6 Agent Integration (Translation API)
2026-04-26 00:07:18 +08:00
Accusys