[AZ-178] Implement streaming video detection endpoint

- Added `/detect/video` endpoint for true streaming video detection, allowing inference to start as upload bytes arrive.
- Introduced `run_detect_video_stream` method in the inference module to handle video processing from a file-like object.
- Updated media hashing to include a new function for computing hashes directly from files with minimal I/O.
- Enhanced documentation to reflect changes in video processing and API behavior.

Made-with: Cursor

src/inference.pyx

@@ -199,6 +199,25 @@ cdef class Inference:
             writer_done.wait()
             wt.join(timeout=3600)
 
+    cpdef run_detect_video_stream(self, object readable, AIRecognitionConfig ai_config, str media_name,
+                                  object annotation_callback, object status_callback=None):
+        cdef str original_media_name
+        self._annotation_callback = annotation_callback
+        self._status_callback = status_callback
+        self.stop_signal = <bint>False
+        self.init_ai()
+        if self.engine is None:
+            constants_inf.log(<str> "AI engine not available. Conversion may be in progress. Skipping inference.")
+            return
+        original_media_name = media_name.replace(" ", "")
+        self.detection_counts = {}
+        self.detection_counts[original_media_name] = 0
+        container = av.open(readable)
+        try:
+            self._process_video_pyav(ai_config, original_media_name, container)
+        finally:
+            container.close()
+
     cdef _process_video_pyav(self, AIRecognitionConfig ai_config, str original_media_name, object container):
         cdef int frame_count = 0
         cdef int batch_count = 0