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
+76
-62
@@ -471,12 +471,19 @@ impl JobWorker {
|
||||
);
|
||||
continue;
|
||||
}
|
||||
|
||||
debug!("Output file not found, checking result_map for {}", processor_type.as_str());
|
||||
|
||||
debug!(
|
||||
"Output file not found, checking result_map for {}",
|
||||
processor_type.as_str()
|
||||
);
|
||||
|
||||
// Check if processor already in terminal state
|
||||
if let Some(result) = result_map.get(processor_type) {
|
||||
debug!("Found existing result for {}: status={:?}", processor_type.as_str(), result.status);
|
||||
debug!(
|
||||
"Found existing result for {}: status={:?}",
|
||||
processor_type.as_str(),
|
||||
result.status
|
||||
);
|
||||
match result.status {
|
||||
ProcessorJobStatus::Completed => {
|
||||
info!(
|
||||
@@ -606,7 +613,10 @@ impl JobWorker {
|
||||
}
|
||||
}
|
||||
|
||||
debug!("Checking capacity before starting {}", processor_type.as_str());
|
||||
debug!(
|
||||
"Checking capacity before starting {}",
|
||||
processor_type.as_str()
|
||||
);
|
||||
// Check capacity before starting processor
|
||||
if !self.processor_pool.can_start().await {
|
||||
info!(
|
||||
@@ -679,7 +689,11 @@ impl JobWorker {
|
||||
.upsert_processor_result(job.id, *processor_type, &job.uuid, "pending")
|
||||
.await?;
|
||||
|
||||
info!("Upserted processor_result for {}: id={}", processor_type.as_str(), processor_result_id);
|
||||
info!(
|
||||
"Upserted processor_result for {}: id={}",
|
||||
processor_type.as_str(),
|
||||
processor_result_id
|
||||
);
|
||||
|
||||
self.redis
|
||||
.update_worker_processor_status(
|
||||
@@ -737,12 +751,10 @@ impl JobWorker {
|
||||
|
||||
let fu = uuid;
|
||||
// Only check conditions relevant to the job's processors
|
||||
let has_asr_or_asrx = job_processors.is_empty()
|
||||
|| job_processors.iter().any(|p| p == "asrx" || p == "asr");
|
||||
let has_cut = job_processors.is_empty()
|
||||
|| job_processors.iter().any(|p| p == "cut");
|
||||
let has_face = job_processors.is_empty()
|
||||
|| job_processors.iter().any(|p| p == "face");
|
||||
let has_asr_or_asrx =
|
||||
job_processors.is_empty() || job_processors.iter().any(|p| p == "asrx" || p == "asr");
|
||||
let has_cut = job_processors.is_empty() || job_processors.iter().any(|p| p == "cut");
|
||||
let has_face = job_processors.is_empty() || job_processors.iter().any(|p| p == "face");
|
||||
|
||||
let rule1 = !has_asr_or_asrx
|
||||
|| check!(&format!(
|
||||
@@ -852,11 +864,9 @@ impl JobWorker {
|
||||
if has_asrx {
|
||||
// Guard: only spawn Rule 1 if sentence chunks don't exist yet
|
||||
let chunk_t = schema::table_name("chunk");
|
||||
let already_spawned: bool = sqlx::query_scalar::<_, i64>(
|
||||
&format!(
|
||||
"SELECT 1 FROM {chunk_t} WHERE file_uuid = $1 AND chunk_type = 'sentence' LIMIT 1"
|
||||
),
|
||||
)
|
||||
let already_spawned: bool = sqlx::query_scalar::<_, i64>(&format!(
|
||||
"SELECT 1 FROM {chunk_t} WHERE file_uuid = $1 AND chunk_type = 'sentence' LIMIT 1"
|
||||
))
|
||||
.bind(uuid)
|
||||
.fetch_optional(self.db.pool())
|
||||
.await?
|
||||
@@ -864,66 +874,70 @@ impl JobWorker {
|
||||
> 0;
|
||||
|
||||
if already_spawned {
|
||||
info!(
|
||||
"✅ Rule 1 already completed for {}, skipping spawn",
|
||||
uuid
|
||||
);
|
||||
info!("✅ Rule 1 already completed for {}, skipping spawn", uuid);
|
||||
} else {
|
||||
info!("📝 Prerequisites met for Rule 1 Chunking. Starting ingestion...");
|
||||
let db_clone = self.db.clone();
|
||||
let uuid_clone = uuid.to_string();
|
||||
tokio::spawn(async move {
|
||||
match db_clone.get_video_by_uuid(&uuid_clone).await {
|
||||
Ok(Some(video)) => {
|
||||
let fps = video.fps;
|
||||
match rule1_ingest::execute_rule1(&db_clone, &uuid_clone, fps).await {
|
||||
Ok(count) => {
|
||||
info!("✅ Rule 1 Ingestion completed: {} chunks inserted.", count);
|
||||
if count > 0 {
|
||||
match db_clone.get_video_by_uuid(&uuid_clone).await {
|
||||
Ok(Some(video)) => {
|
||||
let fps = video.fps;
|
||||
match rule1_ingest::execute_rule1(&db_clone, &uuid_clone, fps).await {
|
||||
Ok(count) => {
|
||||
info!(
|
||||
"📝 Starting automatic vectorize for {} chunks...",
|
||||
"✅ Rule 1 Ingestion completed: {} chunks inserted.",
|
||||
count
|
||||
);
|
||||
if let Err(e) =
|
||||
Self::vectorize_chunks(&db_clone, &uuid_clone).await
|
||||
{
|
||||
error!(
|
||||
"❌ Auto-vectorize failed for {}: {}",
|
||||
uuid_clone, e
|
||||
if count > 0 {
|
||||
info!(
|
||||
"📝 Starting automatic vectorize for {} chunks...",
|
||||
count
|
||||
);
|
||||
if let Err(e) =
|
||||
Self::vectorize_chunks(&db_clone, &uuid_clone).await
|
||||
{
|
||||
error!(
|
||||
"❌ Auto-vectorize failed for {}: {}",
|
||||
uuid_clone, e
|
||||
);
|
||||
}
|
||||
}
|
||||
info!("📦 Phase 1 release packaging...");
|
||||
let executor =
|
||||
match crate::core::processor::PythonExecutor::new() {
|
||||
Ok(ex) => ex,
|
||||
Err(e) => {
|
||||
error!(
|
||||
"Failed PythonExecutor for release pack: {}",
|
||||
e
|
||||
);
|
||||
return;
|
||||
}
|
||||
};
|
||||
match executor
|
||||
.run(
|
||||
"release_pack.py",
|
||||
&["--phase", "1", "--file-uuid", &uuid_clone],
|
||||
None,
|
||||
"RELEASE_P1",
|
||||
Some(std::time::Duration::from_secs(120)),
|
||||
)
|
||||
.await
|
||||
{
|
||||
Ok(()) => {
|
||||
info!("✅ Phase 1 release packaged for {}", uuid_clone)
|
||||
}
|
||||
Err(e) => error!("❌ Phase 1 release pack failed: {}", e),
|
||||
}
|
||||
}
|
||||
info!("📦 Phase 1 release packaging...");
|
||||
let executor = match crate::core::processor::PythonExecutor::new() {
|
||||
Ok(ex) => ex,
|
||||
Err(e) => {
|
||||
error!("Failed PythonExecutor for release pack: {}", e);
|
||||
return;
|
||||
}
|
||||
};
|
||||
match executor
|
||||
.run(
|
||||
"release_pack.py",
|
||||
&["--phase", "1", "--file-uuid", &uuid_clone],
|
||||
None,
|
||||
"RELEASE_P1",
|
||||
Some(std::time::Duration::from_secs(120)),
|
||||
)
|
||||
.await
|
||||
{
|
||||
Ok(()) => {
|
||||
info!("✅ Phase 1 release packaged for {}", uuid_clone)
|
||||
}
|
||||
Err(e) => error!("❌ Phase 1 release pack failed: {}", e),
|
||||
}
|
||||
Err(e) => error!("❌ Rule 1 Ingestion failed: {}", e),
|
||||
}
|
||||
Err(e) => error!("❌ Rule 1 Ingestion failed: {}", e),
|
||||
}
|
||||
Ok(None) => error!("Video not found for chunking: {}", uuid_clone),
|
||||
Err(e) => error!("Failed to get video info for chunking: {}", e),
|
||||
}
|
||||
Ok(None) => error!("Video not found for chunking: {}", uuid_clone),
|
||||
Err(e) => error!("Failed to get video info for chunking: {}", e),
|
||||
}
|
||||
});
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -1089,8 +1089,8 @@ impl ProcessorPool {
|
||||
segment.start_time,
|
||||
segment.end_time,
|
||||
segment.text.clone(),
|
||||
None::<String>, // chunk_id: unknown yet, filled later
|
||||
0.0, // confidence: updated after binding
|
||||
None::<String>, // chunk_id: unknown yet, filled later
|
||||
0.0, // confidence: updated after binding
|
||||
));
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user