Use thread lock for openvino to avoid concurrent requests with JinaV2

frigate/detectors/detection_runners.py

@@ -3,6 +3,7 @@
 import logging
 import os
 import platform
+import threading
 from abc import ABC, abstractmethod
 from typing import Any
 
@@ -290,6 +291,10 @@ class OpenVINOModelRunner(BaseModelRunner):
         self.infer_request = self.compiled_model.create_infer_request()
         self.input_tensor: ov.Tensor | None = None
 
+        # Thread lock to prevent concurrent inference (needed for JinaV2 which shares
+        # one runner between text and vision embeddings called from different threads)
+        self._inference_lock = threading.Lock()
+
         if not self.complex_model:
             try:
                 input_shape = self.compiled_model.inputs[0].get_shape()
@@ -333,6 +338,9 @@ class OpenVINOModelRunner(BaseModelRunner):
         Returns:
             List of output tensors
         """
+        # Lock prevents concurrent access to infer_request
+        # Needed for JinaV2: genai thread (text) + embeddings thread (vision)
+        with self._inference_lock:
             # Handle single input case for backward compatibility
             if (
                 len(inputs) == 1