Model and genai fixes (#14481)

* disable mem arena in options for cpu only

* add try/except around ollama initialization

* update docs

frigate/genai/ollama.py

@@ -21,12 +21,20 @@ class OllamaClient(GenAIClient):
 
     def _init_provider(self):
         """Initialize the client."""
-        client = ApiClient(host=self.genai_config.base_url, timeout=self.timeout)
-        response = client.pull(self.genai_config.model)
-        if response["status"] != "success":
-            logger.error("Failed to pull %s model from Ollama", self.genai_config.model)
+        try:
+            client = ApiClient(host=self.genai_config.base_url, timeout=self.timeout)
+            # ensure the model is available locally
+            response = client.show(self.genai_config.model)
+            if response.get("error"):
+                logger.error(
+                    "Ollama error: %s",
+                    response["error"],
+                )
+                return None
+            return client
+        except Exception as e:
+            logger.warning("Error initializing Ollama: %s", str(e))
             return None
-        return client
 
     def _send(self, prompt: str, images: list[bytes]) -> Optional[str]:
         """Submit a request to Ollama"""

frigate/util/model.py

@@ -20,7 +20,7 @@ def get_ort_providers(
             ["CPUExecutionProvider"],
             [
                 {
-                    "arena_extend_strategy": "kSameAsRequested",
+                    "enable_cpu_mem_arena": False,
                 }
             ],
         )
@@ -53,7 +53,7 @@ def get_ort_providers(
             providers.append(provider)
             options.append(
                 {
-                    "arena_extend_strategy": "kSameAsRequested",
+                    "enable_cpu_mem_arena": False,
                 }
             )
         else:
@@ -85,12 +85,8 @@ class ONNXModelRunner:
         else:
             # Use ONNXRuntime
             self.type = "ort"
-            options = ort.SessionOptions()
-            if device == "CPU":
-                options.enable_cpu_mem_arena = False
             self.ort = ort.InferenceSession(
                 model_path,
-                sess_options=options,
                 providers=providers,
                 provider_options=options,
             )