[AZ-180] Enhance setup and improve inference logging

- Added a new Cython extension for the engine factory to the setup configuration.
- Updated the inference module to include additional logging for video batch processing and annotation callbacks.
- Refactored test cases to standardize the detection endpoint responses and include channel IDs in headers for better event handling.

src/engines/engine_factory.pyx

@@ -0,0 +1,116 @@
+import os
+import tempfile
+from loader_http_client cimport LoaderHttpClient, LoadResult
+
+
+class EngineFactory:
+    has_build_step = False
+
+    def create(self, model_bytes: bytes):
+        raise NotImplementedError
+
+    def load_engine(self, LoaderHttpClient loader_client, str models_dir):
+        cdef str filename
+        cdef LoadResult res
+        filename = self._get_ai_engine_filename()
+        if filename is None:
+            return None
+        try:
+            res = loader_client.load_big_small_resource(filename, models_dir)
+            if res.err is None:
+                return self.create(res.data)
+        except Exception:
+            pass
+        return None
+
+    def _get_ai_engine_filename(self):
+        return None
+
+    def get_source_filename(self):
+        return None
+
+    def build_from_source(self, onnx_bytes, loader_client, models_dir):
+        raise NotImplementedError(f"{type(self).__name__} does not support building from source")
+
+
+class OnnxEngineFactory(EngineFactory):
+    def create(self, model_bytes: bytes):
+        from engines.onnx_engine import OnnxEngine
+        return OnnxEngine(model_bytes)
+
+    def get_source_filename(self):
+        import constants_inf
+        return constants_inf.AI_ONNX_MODEL_FILE
+
+
+class CoreMLEngineFactory(EngineFactory):
+    def create(self, model_bytes: bytes):
+        from engines.coreml_engine import CoreMLEngine
+        return CoreMLEngine(model_bytes)
+
+    def _get_ai_engine_filename(self):
+        return "azaion_coreml.zip"
+
+
+class TensorRTEngineFactory(EngineFactory):
+    has_build_step = True
+
+    def create(self, model_bytes: bytes):
+        from engines.tensorrt_engine import TensorRTEngine
+        return TensorRTEngine(model_bytes)
+
+    def _get_ai_engine_filename(self):
+        from engines.tensorrt_engine import TensorRTEngine
+        return TensorRTEngine.get_engine_filename()
+
+    def get_source_filename(self):
+        import constants_inf
+        return constants_inf.AI_ONNX_MODEL_FILE
+
+    def build_from_source(self, onnx_bytes, loader_client, models_dir):
+        from engines.tensorrt_engine import TensorRTEngine
+        engine_bytes = TensorRTEngine.convert_from_source(onnx_bytes, None)
+        return engine_bytes, TensorRTEngine.get_engine_filename()
+
+
+class JetsonTensorRTEngineFactory(TensorRTEngineFactory):
+    def create(self, model_bytes: bytes):
+        from engines.jetson_tensorrt_engine import JetsonTensorRTEngine
+        return JetsonTensorRTEngine(model_bytes)
+
+    def _get_ai_engine_filename(self):
+        from engines.tensorrt_engine import TensorRTEngine
+        return TensorRTEngine.get_engine_filename("int8")
+
+    def build_from_source(self, onnx_bytes, LoaderHttpClient loader_client, str models_dir):
+        cdef str calib_cache_path
+        from engines.tensorrt_engine import TensorRTEngine
+        calib_cache_path = self._download_calib_cache(loader_client, models_dir)
+        try:
+            engine_bytes = TensorRTEngine.convert_from_source(onnx_bytes, calib_cache_path)
+            return engine_bytes, TensorRTEngine.get_engine_filename("int8")
+        finally:
+            if calib_cache_path is not None:
+                try:
+                    os.unlink(calib_cache_path)
+                except Exception:
+                    pass
+
+    def _download_calib_cache(self, LoaderHttpClient loader_client, str models_dir):
+        cdef LoadResult res
+        import constants_inf
+        try:
+            res = loader_client.load_big_small_resource(
+                constants_inf.INT8_CALIB_CACHE_FILE, models_dir
+            )
+            if res.err is not None:
+                constants_inf.log(f"INT8 calibration cache not available: {res.err}")
+                return None
+            fd, path = tempfile.mkstemp(suffix=".cache")
+            with os.fdopen(fd, "wb") as f:
+                f.write(res.data)
+            constants_inf.log("INT8 calibration cache downloaded")
+            return path
+        except Exception as e:
+            constants_inf.log(f"INT8 calibration cache download failed: {str(e)}")
+            return None