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

fix: add voice+face embedding to pipeline diagram

Browse Source
This commit is contained in:
Accusys
2026-05-18 13:05:37 +08:00
parent 22e164f1a3
commit 1515a0a682
1 changed files with 13 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
docs_v1.0/API_WORKSPACE/modules/10_pipeline.md
View File

@@ -8,23 +8,27 @@
```mermaid
flowchart TB
subgraph Processors[10 Processors — execution order]
subgraph Processors[10 Processors]
direction TB
Cut -.-> ASR
ASR -.-> ASRX
YOLO -.-> VisualChunk
ASRX & Cut & YOLO & Face -.-> Story
Story -.-> FiveW1H
Cut --> ASR
ASR --> ASRX
ASRX --> Story
YOLO --> VisualChunk
VisualChunk --> Story
Face --> Story
Story --> FiveW1H
OCR
Pose
end
subgraph Ingestion[入庫 — triggered after processors complete]
subgraph Ingestion[入庫]
direction TB
ASR & ASRX --> R1[Rule1 Sentence]
R1 --> Vec[Auto-Vectorize] & P1[Pack1]
R1 --> Vec[Vectorize] & P1[Pack1]
Cut & ASR --> R3[Rule3 Scene]
Face --> Trace
ASRX --> VoiceEmb[Voice Embedding]
Face --> FaceEmb[Face Embedding]
FaceEmb --> Trace[Face Trace]
Trace --> Qdrant & TChunks[Trace Chunks] & TKG
Face & YOLO --> SceneM[Scene Meta]
Face & ASRX --> IDAgent[ID Agent]