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
This commit is contained in:
Accusys
2026-06-13 16:25:52 +08:00
parent 834b0d4865
commit 17e4e15860
37 changed files with 2185 additions and 294 deletions
+7 -5
View File
@@ -1002,15 +1002,17 @@ pub async fn bind_speakers(pool: &sqlx::PgPool, file_uuid: &str) -> anyhow::Resu
// Also update speaker_detections with the identity_id
let sd_table = schema::table_name("speaker_detections");
let _ = sqlx::query(
&format!("UPDATE {} SET identity_id = $1, confidence = $2 \
WHERE file_uuid = $3 AND speaker_id = $4 AND identity_id IS NULL", sd_table)
)
let _ = sqlx::query(&format!(
"UPDATE {} SET identity_id = $1, confidence = $2 \
WHERE file_uuid = $3 AND speaker_id = $4 AND identity_id IS NULL",
sd_table
))
.bind(identity_id)
.bind(overlap_ratio)
.bind(file_uuid)
.bind(&best_speaker)
.execute(pool).await;
.execute(pool)
.await;
bindings += 1;
}