diff --git a/frigate/genai/azure-openai.py b/frigate/genai/azure-openai.py index 04a2b8d556..c671bca7db 100644 --- a/frigate/genai/azure-openai.py +++ b/frigate/genai/azure-openai.py @@ -115,6 +115,7 @@ class OpenAIClient(GenAIClient): "model": self.genai_config.model, "messages": messages, "timeout": self.timeout, + **self.genai_config.runtime_options, } if tools: @@ -212,6 +213,7 @@ class OpenAIClient(GenAIClient): "timeout": self.timeout, "stream": True, "stream_options": {"include_usage": True}, + **self.genai_config.runtime_options, } if tools: diff --git a/frigate/genai/llama_cpp.py b/frigate/genai/llama_cpp.py index 86db201288..6e2fc910c4 100644 --- a/frigate/genai/llama_cpp.py +++ b/frigate/genai/llama_cpp.py @@ -527,6 +527,7 @@ class LlamaCppClient(GenAIClient): k: v for k, v in self.provider_options.items() if k != "context_size" } payload.update(provider_opts) + payload.update(self.genai_config.runtime_options) return payload def _message_from_choice(self, choice: dict[str, Any]) -> dict[str, Any]: diff --git a/frigate/genai/ollama.py b/frigate/genai/ollama.py index fe286f64de..f9d1c62cbf 100644 --- a/frigate/genai/ollama.py +++ b/frigate/genai/ollama.py @@ -309,6 +309,7 @@ class OllamaClient(GenAIClient): "model": self.genai_config.model, "messages": request_messages, **self.provider_options, + **self.genai_config.runtime_options, } if stream: request_params["stream"] = True