from google import genai import os import logging import json from datetime import datetime # Configure logging log_directory = os.getenv("LOG_DIR", "logs") os.makedirs(log_directory, exist_ok=True) log_file = os.path.join(log_directory, f"llm_calls_{datetime.now().strftime('%Y%m%d')}.log") # Set up logger logger = logging.getLogger("llm_logger") logger.setLevel(logging.INFO) logger.propagate = False # Prevent propagation to root logger file_handler = logging.FileHandler(log_file) file_handler.setFormatter(logging.Formatter('%(asctime)s - %(levelname)s - %(message)s')) logger.addHandler(file_handler) # Simple cache configuration cache_file = "llm_cache.json" def call_llm(prompt: str, use_cache: bool = True) -> str: # Log the prompt logger.info(f"PROMPT: {prompt}") # Check cache if enabled if use_cache: # Load cache from disk cache = {} if os.path.exists(cache_file): try: with open(cache_file, 'r') as f: cache = json.load(f) except: logger.warning(f"Failed to load cache, starting with empty cache") # Return from cache if exists if prompt in cache: logger.info(f"RESPONSE: {cache[prompt]}") return cache[prompt] # Call the LLM if not in cache or cache disabled client = genai.Client( vertexai=True, project=os.getenv("GEMINI_PROJECT_ID", "your-project-id"), location=os.getenv("GEMINI_LOCATION", "us-central1") ) model = os.getenv("GEMINI_MODEL", "gemini-2.5-pro-exp-03-25") response = client.models.generate_content( model=model, contents=[prompt] ) response_text = response.text # Log the response logger.info(f"RESPONSE: {response_text}") # Update cache if enabled if use_cache: # Load cache again to avoid overwrites cache = {} if os.path.exists(cache_file): try: with open(cache_file, 'r') as f: cache = json.load(f) except: pass # Add to cache and save cache[prompt] = response_text try: with open(cache_file, 'w') as f: json.dump(cache, f) except Exception as e: logger.error(f"Failed to save cache: {e}") return response_text if __name__ == "__main__": test_prompt = "Hello, how are you?" # First call - should hit the API print("Making call...") response1 = call_llm(test_prompt, use_cache=False) print(f"Response: {response1}")