Generating an Answer

# How the augmented prompt is structured in a RAG system

def build_rag_prompt(user_question, retrieved_chunks):
    """
    Build the final prompt that is sent to the LLM in a RAG system.
    The prompt includes both the retrieved context and the user's question.
    """
    # Format the retrieved chunks as context
    context_text = ""
    for i, chunk in enumerate(retrieved_chunks, 1):
        context_text += f"Source {i}: {chunk}\n\n"

    # Build the full prompt
    system_message = """You are a helpful assistant. Answer questions based ONLY on 
the provided context. If the answer is not in the context, say 'I don't have 
information about that in my knowledge base.' Do not invent information."""

    user_message = f"""Context (retrieved from our knowledge base):
{context_text}

Question: {user_question}

Answer based only on the context above:"""

    return system_message, user_message

# Example
question = "What is your return policy?"
retrieved = [
    "Our return policy allows returns within 30 days of purchase.",
    "Items must be in original condition with tags attached.",
    "Returns are processed within 5-7 business days.",
]

system, user = build_rag_prompt(question, retrieved)
print("System message:")
print(system)
print()
print("User message (with context):")
print(user)