List models supported by provider

frigate/genai/__init__.py

@@ -329,6 +329,13 @@ Guidelines:
         """
         return True
 
+    def list_models(self) -> list[str]:
+        """Return the list of model names available from this provider.
+
+        Providers should override this to query their backend.
+        """
+        return []
+
     def get_context_size(self) -> int:
         """Get the context window size for this provider in tokens."""
         return 4096

frigate/genai/azure-openai.py

@@ -82,6 +82,14 @@ class OpenAIClient(GenAIClient):
             return str(result.choices[0].message.content.strip())
         return None
 
+    def list_models(self) -> list[str]:
+        """Return available model IDs from Azure OpenAI."""
+        try:
+            return sorted(m.id for m in self.provider.models.list().data)
+        except Exception as e:
+            logger.warning("Failed to list Azure OpenAI models: %s", e)
+            return []
+
     def get_context_size(self) -> int:
         """Get the context window size for Azure OpenAI."""
         return 128000

frigate/genai/gemini.py

@@ -87,6 +87,14 @@ class GeminiClient(GenAIClient):
             return None
         return description
 
+    def list_models(self) -> list[str]:
+        """Return available model names from Gemini."""
+        try:
+            return sorted(m.name for m in self.provider.models.list())
+        except Exception as e:
+            logger.warning("Failed to list Gemini models: %s", e)
+            return []
+
     def get_context_size(self) -> int:
         """Get the context window size for Gemini."""
         # Gemini Pro Vision has a 1M token context window

frigate/genai/llama_cpp.py

@@ -236,6 +236,23 @@ class LlamaCppClient(GenAIClient):
         """Whether the loaded model supports tool/function calling."""
         return self._supports_tools
 
+    def list_models(self) -> list[str]:
+        """Return available model IDs from the llama.cpp server."""
+        if self.provider is None:
+            return []
+        try:
+            response = requests.get(f"{self.provider}/v1/models", timeout=10)
+            response.raise_for_status()
+            models = []
+            for m in response.json().get("data", []):
+                models.append(m.get("id", "unknown"))
+                for alias in m.get("aliases", []):
+                    models.append(alias)
+            return sorted(models)
+        except Exception as e:
+            logger.warning("Failed to list llama.cpp models: %s", e)
+            return []
+
     def get_context_size(self) -> int:
         """Get the context window size for llama.cpp.
 

frigate/genai/manager.py

@@ -24,6 +24,7 @@ class GenAIClientManager:
         self._chat_client: Optional[GenAIClient] = None
         self._description_client: Optional[GenAIClient] = None
         self._embeddings_client: Optional[GenAIClient] = None
+        self._clients: dict[str, "GenAIClient"] = {}
         self.update_config(config)
 
     def update_config(self, config: FrigateConfig) -> None:
@@ -38,6 +39,7 @@ class GenAIClientManager:
         self._chat_client = None
         self._description_client = None
         self._embeddings_client = None
+        self._clients = {}
 
         if not config.genai:
             return
@@ -64,6 +66,8 @@ class GenAIClientManager:
                 )
                 continue
 
+            self._clients[_name] = client
+
             for role in genai_cfg.roles:
                 if role == GenAIRoleEnum.chat:
                     self._chat_client = client
@@ -86,3 +90,7 @@ class GenAIClientManager:
     def embeddings_client(self) -> "Optional[GenAIClient]":
         """Client configured for the embeddings role."""
         return self._embeddings_client
+
+    def list_models(self) -> dict[str, list[str]]:
+        """Return available models keyed by config entry name."""
+        return {name: client.list_models() for name, client in self._clients.items()}

frigate/genai/ollama.py

@@ -132,6 +132,15 @@ class OllamaClient(GenAIClient):
             logger.warning("Ollama returned an error: %s", str(e))
             return None
 
+    def list_models(self) -> list[str]:
+        """Return available model names from the Ollama server."""
+        try:
+            response = self.provider.list()
+            return sorted(m.get("name", m.get("model", "")) for m in response.get("models", []))
+        except Exception as e:
+            logger.warning("Failed to list Ollama models: %s", e)
+            return []
+
     def get_context_size(self) -> int:
         """Get the context window size for Ollama."""
         return int(

frigate/genai/openai.py

@@ -86,6 +86,14 @@ class OpenAIClient(GenAIClient):
             logger.warning("OpenAI returned an error: %s", str(e))
             return None
 
+    def list_models(self) -> list[str]:
+        """Return available model IDs from the OpenAI-compatible API."""
+        try:
+            return sorted(m.id for m in self.provider.models.list().data)
+        except Exception as e:
+            logger.warning("Failed to list OpenAI models: %s", e)
+            return []
+
     def get_context_size(self) -> int:
         """Get the context window size for OpenAI."""
         if self.context_size is not None: