MCPcopy
hub / github.com/algorithmicsuperintelligence/optillm / get_llm_response

Function get_llm_response

scripts/eval_math500_benchmark.py:677–704  ·  view source on GitHub ↗

Get response from the LLM for a given problem. Args: problem (str): The problem text model (str): The model identifier Returns: str: Model's response

(problem: str, model: str)

Source from the content-addressed store, hash-verified

675 return result
676
677def get_llm_response(problem: str, model: str) -> str:
678 """
679 Get response from the LLM for a given problem.
680
681 Args:
682 problem (str): The problem text
683 model (str): The model identifier
684
685 Returns:
686 str: Model's response
687 """
688 try:
689 response = client.chat.completions.create(
690 model=model,
691 temperature=0.6, # Lower temperature for more consistent answers
692 messages=[
693 {"role": "user", "content": SYSTEM_PROMPT + "\n" + problem}
694 ],
695 max_tokens=8192, # for thinking models, we need to use a lot more tokens
696 # extra_body = {
697 # "decoding" : "thinkdeeper",
698 # }
699 )
700 return response.choices[0].message.content.strip()
701
702 except Exception as e:
703 logger.error(f"Error getting LLM response: {e}")
704 return ""
705
706def load_existing_results(filename: str) -> list[Dict]:
707 """Load existing results from file if it exists."""

Callers 1

mainFunction · 0.70

Calls 1

createMethod · 0.45

Tested by

no test coverage detected