Hi everyone, I having some issues

class OurLLM(CustomLLM):
    context_window: int = 1200
    num_output: int = 256
    model_name: str = "custom"
    dummy_response: str = "My response"

    @property
    def metadata(self) -> LLMMetadata:
        """Get LLM metadata."""
        return LLMMetadata(
            context_window=self.context_window,
            num_output=self.num_output,
            model_name=self.model_name,
        )
    
    def llama2_13b_gcp(self, role_user):
        """

        """
        url = "http://00.000.000.000:8080/api/chat"

        headers = {
            "accept": "application/json",
            "Content-Type": "application/json"
        }
        data = {
            "messages": [
                {"role": "system", "content": "Answer the question"},
                {"role": "user", "content": role_user}
            ]
        }

        response = requests.post(url, headers=headers, json=data)

        resp = response.json()['choices'][0]['message']['content']

        return resp
    
    @llm_completion_callback()
    def complete(self, prompt: str, **kwargs: Any) -> CompletionResponse:
        self.dummy_response = self.llama2_13b_gcp(prompt) 
        return CompletionResponse(text=self.dummy_response)

    @llm_completion_callback()
    def stream_complete(self, prompt: str, **kwargs: Any) -> CompletionResponseGen:
        full_response = self.llama2_13b_gcp(prompt)  
        yield CompletionResponse(text=full_response)