From 88bad3423bf5acbdc118de1f3323427c2b6c2d8e Mon Sep 17 00:00:00 2001 From: Nicolas Mowen Date: Thu, 26 Feb 2026 15:28:58 -0700 Subject: [PATCH] Set model --- frigate/genai/llama_cpp.py | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) diff --git a/frigate/genai/llama_cpp.py b/frigate/genai/llama_cpp.py index 401412b07..03f99792e 100644 --- a/frigate/genai/llama_cpp.py +++ b/frigate/genai/llama_cpp.py @@ -138,7 +138,10 @@ class LlamaCppClient(GenAIClient): elif tool_choice == "required": openai_tool_choice = "required" - payload: dict[str, Any] = {"messages": messages, "model": self.genai_config.model} + payload: dict[str, Any] = { + "messages": messages, + "model": self.genai_config.model, + } if stream: payload["stream"] = True if tools: @@ -223,15 +226,17 @@ class LlamaCppClient(GenAIClient): to_encode = jpeg_bytes if jpeg_bytes is not None else img encoded = base64.b64encode(to_encode).decode("utf-8") # prompt_string must contain <__media__> placeholder for image tokenization - content.append({ - "prompt_string": "<__media__>\n", - "multimodal_data": [encoded], - }) + content.append( + { + "prompt_string": "<__media__>\n", + "multimodal_data": [encoded], + } + ) try: response = requests.post( f"{self.provider}/embeddings", - json={"content": content}, + json={"model": self.genai_config.model, "content": content}, timeout=self.timeout, ) response.raise_for_status()