services/openai_service.py

import logging
import os
from openai import OpenAI
from openai import OpenAIError, RateLimitError
from config import OPENAI_API_KEY

# Initialize the OpenAI client with the API key from the environment variable
#api_key = os.getenv('OPENAI_API_KEY')

client = OpenAI(api_key=OPENAI_API_KEY)

def generate_rag_response(json_output, user_query):
    logging.info("Generating RAG response")

    # Extract text from the JSON output
    context_texts = [hit['chunk_text'] for hit in json_output]

    # Create the context for the prompt
    context = "\n".join(context_texts)
    prompt = f"Based on the given context, answer the user query: {user_query}\nContext:\n{context}"

    main_prompt = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]

    try:
        # Create a chat completion request
        chat_completion = client.chat.completions.create(
            messages=main_prompt,
            model="gpt-4o-mini",  # Use the gpt-4o-mini model
            timeout=10
        )

        # Log the response from the model
        logging.info("RAG response generation completed")
        logging.info(f"RAG response: {chat_completion.choices[0].message.content}")
        return chat_completion.choices[0].message.content, None

    except RateLimitError as e:
        logging.error(f"Rate limit exceeded: {e}")
        return None, "Rate limit exceeded. Please try again later."
    except OpenAIError as e:
        logging.error(f"OpenAI API error: {e}")
        return None, f"An error occurred: {str(e)}"
    except Exception as e:
        logging.error(f"Unexpected error: {e}")
        return None, str(e)