update the cv modal inference proxy server with optimization

workspace/sprint_1_2/CODEBASE/backend/routers/cv_inference.py

@@ -18,6 +18,10 @@ from backend.implementation.triton_batch import TRITON_MAX_BATCH_SIZE
 from backend.services import cv_result_cache
 from backend.services import triton_runtime_service as triton_runtime
 from backend.services.cv_inference_service import CvBatchResult, CvInferenceOptions, run_batch, run_single
+from backend.services import cv_celery_service
+from backend.logging.logging_config import setup_logging
+
+setup_logging()
 
 logger = logging.getLogger(__name__)
 
@@ -135,14 +139,15 @@ async def cv_inference_health():
         )
 
 
-@router.post("/analyze")
+@router.post("/analyze") # deprecated
 async def analyze_upload(
     image: UploadFile = File(...),
     calibration: str | None = Form(default=None),
 ):
     """Spec-compliant CV pipeline: CLAHE → angle → inflammation → conditional segmentation."""
     image_pil = await _load_upload_image(image)
-    options = _build_options(_parse_calibration_form(calibration), use_cache=False)
+    
+    options = _build_options(_parse_calibration_form(calibration), use_cache=True)
 
     try:
         result = await run_single(image_pil, frame_id=None, options=options)
@@ -168,11 +173,13 @@ async def analyze_batch_upload(
     calibration: str | None = Form(default=None),
 ):
     """Spec-compliant CV batch — one full pipeline per frame (angle-first, gated segmentation)."""
+    logger.info("Starting analyze batch upload")
     if not images:
         raise HTTPException(status_code=400, detail="At least one image is required")
 
     try:
         id_list = json.loads(frame_ids)
+        # logger.info("Start to check the id_list")
     except json.JSONDecodeError as exc:
         raise HTTPException(status_code=400, detail="frame_ids must be a JSON array of strings") from exc
 
@@ -213,6 +220,68 @@ async def analyze_batch_upload(
         raise HTTPException(status_code=500, detail=str(exc)) from exc
 
 
+@router.post("/analyze/batch/celery")
+async def analyze_batch_celery(
+    images: list[UploadFile] = File(...),
+    frame_ids: str = Form(...),
+    calibration: str | None = Form(default=None),
+):
+    """Experiment: async chunk fan-out via Celery + Redis."""
+    if not images:
+        raise HTTPException(status_code=400, detail="At least one image is required")
+
+    try:
+        id_list = json.loads(frame_ids)
+    except json.JSONDecodeError as exc:
+        raise HTTPException(status_code=400, detail="frame_ids must be a JSON array of strings") from exc
+
+    if not isinstance(id_list, list) or not all(isinstance(x, str) for x in id_list):
+        raise HTTPException(status_code=400, detail="frame_ids must be a JSON array of strings")
+    if len(id_list) != len(images):
+        raise HTTPException(status_code=400, detail="frame_ids length must match images count")
+
+    image_pils: list[Image.Image] = []
+    for upload in images:
+        image_pils.append(await _load_upload_image(upload))
+
+    options = _build_options(_parse_calibration_form(calibration))
+
+    try:
+        job_id = cv_celery_service.submit_celery_batch(image_pils, id_list, options)
+        return JSONResponse({
+            "success": True,
+            "job_id": job_id,
+            "image_count": len(image_pils),
+            "mode": "celery-chunk-fanout",
+            "chunk_size": cv_celery_service.CELERY_CHUNK_SIZE,
+        })
+    except Exception as exc:
+        logger.exception("Celery batch submit failed")
+        raise HTTPException(status_code=500, detail=str(exc)) from exc
+
+
+@router.get("/analyze/batch/celery/{job_id}")
+async def analyze_batch_celery_result(job_id: str):
+    """Poll result for a Celery chunk-fan-out batch job."""
+    try:
+        result = await cv_celery_service.get_celery_batch_result(job_id)
+        status = result.get("status")
+        if status == "pending":
+            return JSONResponse(
+                status_code=202,
+                content=result,
+            )
+        if status == "unknown":
+            return JSONResponse(
+                status_code=404,
+                content=result,
+            )
+        return JSONResponse(result)
+    except Exception as exc:
+        logger.exception("Celery batch result fetch failed")
+        raise HTTPException(status_code=500, detail=str(exc)) from exc
+
+
 @router.post("/segment")
 @router.post("/segment/batch")
 @router.post("/angle")

workspace/sprint_1_2/CODEBASE/backend/routers/run_cv_inference.sh

@@ -0,0 +1,27 @@
+#!/usr/bin/env bash
+#
+# Launch the standalone CV inference FastAPI server (Modal Triton).
+#
+# Usage:
+#   ./backend/run_cv_inference.sh
+#
+# Works from any directory: it resolves the CODEBASE root relative to this
+# script, sets PYTHONPATH so `import backend...` resolves, then runs the
+# server as a module.
+#
+# Override defaults via env vars, e.g.:
+#   CV_INFERENCE_PORT=8080 ./backend/run_cv_inference.sh
+#
+set -euo pipefail
+
+# CODEBASE root = grandparent dir of this script's directory (script lives in backend/routers/).
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+CODEBASE_ROOT="$(cd "${SCRIPT_DIR}/../.." && pwd)"
+
+cd "${CODEBASE_ROOT}"
+
+export PYTHONPATH="${CODEBASE_ROOT}:${PYTHONPATH:-}"
+
+# exec python -m backend.cv_inference_server
+
+exec uvicorn backend.cv_inference_server:app --host 0.0.0.0 --port ${CV_INFERENCE_PORT:-8001}