admin/momentry_core
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: face_detections INSERT in pipeline, add dependency graph doc

Browse Source
This commit is contained in:
Accusys
2026-05-17 22:16:20 +08:00
parent d6c8930f84
commit a880c80556
4 changed files with 149 additions and 24 deletions
Download Patch File Download Diff File Expand all files Collapse all files

69
docs_v1.0/API_WORKSPACE/modules/10_pipeline.md
View File

@@ -4,6 +4,52 @@
## Pipeline
### Dependency Graph
```mermaid
flowchart TB
subgraph Processors["10 Processors"]
Cut[Cut] --> ASR[ASR]
ASR --> ASRX[ASRX]
ASRX --> Story[Story]
Cut --> Story
YOLO[YOLO] --> VisualChunk[VisualChunk]
VisualChunk --> Story
Face[Face] --> Story
Story --> FiveW1H[5W1H]
OCR[OCR]
Pose[Pose]
end
subgraph Ingestion["入庫 (Post-Processing)"]
ASR --> Rule1[Rule 1 Sentence]
ASRX --> Rule1
Rule1 --> Vectorize[Auto-Vectorize]
Rule1 --> Phase1[Phase 1 Pack]
Cut --> Rule3[Rule 3 Scene]
ASR --> Rule3
Face --> Trace[Face Trace]
Trace --> Qdrant[Qdrant Sync]
Trace --> TraceChunks[Trace Chunks]
Trace --> TKG[TKG Builder]
Face --> TMDbMatch[TMDb Match]
Face --> SceneMeta[Scene Metadata]
YOLO --> SceneMeta
Face --> IdentityAgent[Identity Agent]
ASRX --> IdentityAgent
Cut --> Agent5W1H[5W1H Agent]
ASR --> Agent5W1H
Agent5W1H --> Phase2[Phase 2 Pack]
end
style Processors fill:#1a1a2e,stroke:#e94560
style Ingestion fill:#16213e,stroke:#0f3460
```
### 10 Processor Stages
| # | Processor | Depends On | Description |
@@ -16,7 +62,7 @@
| 6 | `Face` | — | Face detection + recognition (InsightFace + CoreML) |
| 7 | `Pose` | — | Pose estimation |
| 8 | `VisualChunk` | YOLO | Visual object chunking |
| 9 | `Story` | ASRX + Cut | Narrative scene summarization (LLM, with embedding) |
| 9 | `Story` | ASRX + Cut + YOLO + Face | Narrative scene summarization (LLM, with embedding) |
| 10 | `5W1H` | Story | Who/What/When/Where/Why extraction (LLM, with embedding) |
### Post-Processing (入庫)
@@ -27,16 +73,17 @@ After all 10 processors complete, the pipeline runs the following storage & enri
|---|------|----------|----------|
| 1 | **Rule 1 Sentence Chunking** | ASR + ASRX | `chunk` table, `chunk_type = 'sentence'` |
| 2 | **Auto-Vectorize** | Rule 1 | `chunk.embedding` IS NOT NULL (pgvector) |
| 3 | **Rule 3 Scene Chunking** | Cut + ASR | `chunk` table, `chunk_type = 'cut'` |
| 4 | **Face Trace + DB Store** | Face | `face_detections.trace_id` IS NOT NULL |
| 5 | **Qdrant Face Sync** | Face Trace | Qdrant collection (face embeddings) |
| 6 | **Trace Chunks** | Face Trace | `chunk` table, `chunk_type = 'trace'` |
| 7 | **TKG Builder** | Face Trace | `tkg_nodes` + `tkg_edges` tables |
| 8 | **TMDb Face Matching** | Face + TMDb enabled | `face_detections.identity_id` IS NOT NULL |
| 9 | **Heuristic Scene Metadata** | Face + YOLO | `{file_uuid}.scene_meta.json` on disk |
| 10 | **Identity Agent** | Face + ASRX | `identities` with `source = 'identity_agent'` |
| 11 | **5W1H Agent** | Cut + ASR | `chunk.summary_text` IS NOT NULL (chunk_type = 'cut') |
| 12 | **Release Pack** | 5W1H Agent | `release_pack.py --phase 2` output |
| 3 | **Phase 1 Pack** | Rule 1 | `release_pack.py --phase 1` |
| 4 | **Rule 3 Scene Chunking** | Cut + ASR | `chunk` table, `chunk_type = 'cut'` |
| 5 | **Face Trace** | Face | `face_detections.trace_id` IS NOT NULL |
| 6 | **Qdrant Face Sync** | Face Trace | Qdrant face_embedding collection |
| 7 | **Trace Chunks** | Face Trace | `chunk` table, `chunk_type = 'trace'` |
| 8 | **TKG Builder** | Face Trace | `tkg_nodes` + `tkg_edges` tables |
| 9 | **TMDb Face Matching** | Face + TMDb enabled | `face_detections.identity_id` IS NOT NULL |
| 10 | **Heuristic Scene Metadata** | Face + YOLO | `{file_uuid}.scene_meta.json` on disk |
| 11 | **Identity Agent** | Face + ASRX | `identities` with `source = 'identity_agent'` |
| 12 | **5W1H Agent** | Cut + ASR | `chunk.summary_text` IS NOT NULL (chunk_type = 'cut') |
| 13 | **Release Pack** | 5W1H Agent | `release_pack.py --phase 2` output |
### Ingestion Status