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 # Create formatter formatter = logging.Formatter("%(asctime)s - %(levelname)s - %(message)s") # Add file handler file_handler = logging.FileHandler(log_file, encoding='utf-8') file_handler.setFormatter(formatter) logger.addHandler(file_handler) # Add stdout handler stdout_handler = logging.StreamHandler() stdout_handler.setFormatter(formatter) # logger.addHandler(stdout_handler) # Simple cache configuration - use temp directory for HF Spaces import tempfile cache_file = os.path.join(tempfile.gettempdir(), "llm_cache.json") # By default, we Google Gemini 2.5 pro, as it shows great performance for code understanding 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", encoding="utf-8") 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 cached: {cache[prompt]}") return cache[prompt] # # Call the LLM if not in cache or cache disabled # client = genai.Client( # vertexai=True, # # TODO: change to your own project id and location # project=os.getenv("GEMINI_PROJECT_ID", "your-project-id"), # location=os.getenv("GEMINI_LOCATION", "us-central1") # ) # You can comment the previous line and use the AI Studio key instead: client = genai.Client( api_key=os.getenv("GEMINI_API_KEY", ""), ) # pro was too slow and janky model = os.getenv("GEMINI_MODEL", "gemini-2.5-flash") # model = os.getenv("GEMINI_MODEL", "gemini-2.5-flash-preview-04-17") 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", encoding="utf-8") as f: cache = json.load(f) except: pass # Add to cache and save cache[prompt] = response_text try: with open(cache_file, "w", encoding="utf-8") 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}")