update the cv modal inference proxy server with optimization

workspace/sprint_1_2/CODEBASE/backend/implementation/adapters/triton_adapter.py

@@ -3,16 +3,34 @@ import json
 from typing import Any
 import numpy as np
 import requests
+from requests.adapters import HTTPAdapter
+from urllib3.util.retry import Retry
 
 
 class TritonAdapter:
     def __init__(self, endpoint_url: str, timeout: float = 60.0):
         self.endpoint_url = endpoint_url.rstrip("/")
         self.timeout = timeout
+        self._session = self._build_session()
 
+    @staticmethod
+    def _build_session() -> requests.Session:
+        session = requests.Session()
+        retry = Retry(
+            total=0,
+            connect=0,
+            read=0,
+            redirect=0,
+            status=0,
+            raise_on_status=False,
+        )
+        adapter = HTTPAdapter(max_retries=retry, pool_connections=20, pool_maxsize=50)
+        session.mount("http://", adapter)
+        session.mount("https://", adapter)
+        return session
 
     async def close(self):
-        pass
+        await asyncio.to_thread(self._session.close)
 
 
     async def infer(
@@ -61,7 +79,7 @@ class TritonAdapter:
         }
 
         url = f"{self.endpoint_url}/v2/models/{model_name}/infer"
-        response = requests.post(url, data=body, headers=headers, timeout=self.timeout)
+        response = self._session.post(url, data=body, headers=headers, timeout=self.timeout)
         response.raise_for_status()
         return self._parse_binary_response(response.headers, response.content)
 
@@ -91,7 +109,7 @@ class TritonAdapter:
 
     def _model_ready_sync(self, model_name: str) -> bool:
         url = f"{self.endpoint_url}/v2/models/{model_name}"
-        response = requests.get(url, timeout=self.timeout)
+        response = self._session.get(url, timeout=self.timeout)
         if response.status_code == 404:
             return False
         response.raise_for_status()
@@ -113,7 +131,7 @@ class TritonAdapter:
         url = f"{self.endpoint_url}/v2/repository/index"
         
         # 2. Change requests.get to requests.post with an empty json payload {}
-        response = requests.post(url, json={}, timeout=self.timeout)
+        response = self._session.post(url, json={}, timeout=self.timeout)
         response.raise_for_status()
         
         data = response.json()

workspace/sprint_1_2/CODEBASE/backend/implementation/tasks/cv_tasks.py

@@ -0,0 +1,50 @@
+import asyncio
+import base64
+import io
+import logging
+from typing import Any
+
+from PIL import Image
+
+from backend.implementation.postprocessing.calibration import calibration_config_from_params
+from backend.services.cv_inference_service import CvInferenceOptions, run_single
+from backend.services.celery_app import celery_app
+
+logger = logging.getLogger(__name__)
+
+
+def _decode_base64_to_pil(b64_str: str) -> Image.Image:
+    raw = base64.b64decode(b64_str)
+    return Image.open(io.BytesIO(raw)).convert("RGB")
+
+
+@celery_app.task(bind=True, name="cv_inference.run_chunk", max_retries=2, default_retry_delay=10)
+def run_cv_chunk(self, chunk_payload: dict) -> list[dict]:
+    images_b64 = chunk_payload.get("images_b64", [])
+    frame_ids = chunk_payload.get("frame_ids", [])
+    calibration_params = chunk_payload.get("calibration", {})
+    model_versions = chunk_payload.get("model_versions")
+
+    if not images_b64:
+        return []
+
+    images = [_decode_base64_to_pil(b64) for b64 in images_b64]
+    calibration = calibration_config_from_params(calibration_params)
+    options = CvInferenceOptions(
+        calibration=calibration,
+        model_versions=model_versions,
+        use_cache=False,
+    )
+
+    async def _run():
+        return await asyncio.gather(*[
+            run_single(img, frame_id=fid, options=options)
+            for img, fid in zip(images, frame_ids)
+        ])
+
+    try:
+        results = asyncio.run(_run())
+        return results
+    except Exception as exc:
+        logger.exception("Celery chunk task failed: %s", exc)
+        raise self.retry(exc=exc, countdown=10, max_retries=2)