src/api/openai_api.py

"""
OpenAI API integration for Norwegian RAG chatbot.
Provides functions to interact with OpenAI API for both GPT-4o and embedding models.
"""

import os
import json
import time
import requests
from typing import Dict, List, Optional, Union, Any
import openai

class OpenAIAPI:
    """
    Client for interacting with OpenAI API.
    Supports both text generation (GPT-4o) and embedding generation.
    """
    
    def __init__(
        self, 
        api_key: Optional[str] = None,
        model: str = "gpt-4o",
        embedding_model: str = "text-embedding-3-small"
    ):
        """
        Initialize the OpenAI API client.
        
        Args:
            api_key: OpenAI API key (optional, can use OPENAI_API_KEY env var)
            model: GPT model to use (default: gpt-4o)
            embedding_model: Embedding model to use (default: text-embedding-3-small)
        """
        self.api_key = api_key or os.environ.get("OPENAI_API_KEY", "")
        if not self.api_key:
            raise ValueError("OpenAI API key is required. Set it as OPENAI_API_KEY environment variable or pass it to the constructor.")
        
        self.client = openai.OpenAI(api_key=self.api_key)
        self.model = model
        self.embedding_model = embedding_model
    
    def generate_text(
        self, 
        prompt: str,
        max_tokens: int = 512,
        temperature: float = 0.7,
        top_p: float = 0.9,
        stream: bool = False
    ) -> Union[str, Any]:
        """
        Generate text using the GPT-4o model.
        
        Args:
            prompt: Input text prompt
            max_tokens: Maximum number of tokens to generate
            temperature: Sampling temperature
            top_p: Top-p sampling parameter
            stream: Whether to stream the response
            
        Returns:
            Generated text response or stream
        """
        try:
            messages = [{"role": "user", "content": prompt}]
            
            response = self.client.chat.completions.create(
                model=self.model,
                messages=messages,
                max_tokens=max_tokens,
                temperature=temperature,
                top_p=top_p,
                stream=stream
            )
            
            if stream:
                return response
            else:
                return response.choices[0].message.content
                
        except Exception as e:
            print(f"Error generating text: {str(e)}")
            return f"Error: {str(e)}"
    
    def generate_embeddings(
        self, 
        texts: Union[str, List[str]]
    ) -> List[List[float]]:
        """
        Generate embeddings for text using the embedding model.
        
        Args:
            texts: Single text or list of texts to embed
            
        Returns:
            List of embedding vectors
        """
        # Ensure texts is a list
        if isinstance(texts, str):
            texts = [texts]
        
        try:
            response = self.client.embeddings.create(
                model=self.embedding_model,
                input=texts
            )
            
            # Extract embeddings from response
            embeddings = [item.embedding for item in response.data]
            return embeddings
            
        except Exception as e:
            print(f"Error generating embeddings: {str(e)}")
            # Return empty embeddings as fallback
            return [[0.0] * 1536] * len(texts)


# Example RAG prompt template for Norwegian
def create_rag_prompt(query: str, context: List[str]) -> str:
    """
    Create a RAG prompt with retrieved context for GPT-4o.
    
    Args:
        query: User query
        context: List of retrieved document chunks
        
    Returns:
        Formatted prompt with context
    """
    context_text = "\n\n".join([f"Dokument {i+1}:\n{chunk}" for i, chunk in enumerate(context)])
    
    prompt = f"""Du er en hjelpsom assistent som svarer på norsk. Bruk følgende kontekst for å svare på spørsmålet.
    
KONTEKST:
{context_text}

SPØRSMÅL:
{query}

SVAR:
"""
    return prompt