Building Your First RAG System with Python and OpenAI

This tutorial guides you through building a Retrieval Augmented Generation (RAG) system using Python and OpenAI. RAG enhances AI responses by retrieving relevant information from your documents before generating an answer – essentially, letting the AI "study" beforehand.

What You'll Learn:

• Building a RAG system from scratch.
• Document preparation and processing for RAG.
• Utilizing OpenAI embeddings.
• Creating a basic retrieval system.
• Integrating with the OpenAI API.

Project Structure:

<code>rag-project/
│
├── src/
│   ├── __init__.py
│   ├── document_loader.py
│   ├── text_processor.py
│   ├── embeddings_manager.py
│   ├── retrieval_system.py
│   └── rag_system.py
│
├── data/
│   └── documents/
│
├── requirements.txt
├── test.py
├── README.md
└── .env</code>

Step 1: Environment Setup:

1. Create a virtual environment: python -m venv venv (On Windows: venvScriptsactivate)
2. Activate it: source venv/bin/activate
3. Install packages: pip install openai python-dotenv numpy pandas
4. Create requirements.txt:

<code>openai==1.12.0
python-dotenv==1.0.0
numpy==1.24.3
pandas==2.1.0</code>

5. Configure .env:

<code>OPENAI_API_KEY=your_api_key_here</code>

Step 2: Document Loading (src/document_loader.py):

import os
from typing import List

class DocumentLoader:
    def __init__(self, documents_path: str):
        self.documents_path = documents_path

    def load_documents(self) -> List[str]:
        documents = []
        for filename in os.listdir(self.documents_path):
            if filename.endswith('.txt'):
                with open(os.path.join(self.documents_path, filename), 'r') as file:
                    documents.append(file.read())
        return documents

Step 3: Text Processing (src/text_processor.py):

from typing import List

class TextProcessor:
    def __init__(self, chunk_size: int = 1000):
        self.chunk_size = chunk_size

    def split_into_chunks(self, text: str) -> List[str]:
        words = text.split()
        chunks = []
        current_chunk = []
        current_size = 0

        for word in words:
            if current_size + len(word) > self.chunk_size:
                chunks.append(' '.join(current_chunk))
                current_chunk = [word]
                current_size = len(word)
            else:
                current_chunk.append(word)
                current_size += len(word) + 1

        if current_chunk:
            chunks.append(' '.join(current_chunk))

        return chunks

Step 4: Embeddings Creation (src/embeddings_manager.py):

from typing import List
import openai
import numpy as np

class EmbeddingsManager:
    def __init__(self, api_key: str):
        openai.api_key = api_key

    def create_embeddings(self, texts: List[str]) -> List[np.ndarray]:
        embeddings = []
        for text in texts:
            response = openai.embeddings.create(
                model="text-embedding-ada-002",
                input=text
            )
            embeddings.append(np.array(response.data[0].embedding))
        return embeddings

Step 5: Retrieval System (src/retrieval_system.py):

import numpy as np
from typing import List, Tuple

class RetrievalSystem:
    def __init__(self, chunks: List[str], embeddings: List[np.ndarray]):
        self.chunks = chunks
        self.embeddings = embeddings

    def find_similar_chunks(self, query_embedding: np.ndarray, top_k: int = 3) -> List[Tuple[str, float]]:
        similarities = []
        for i, embedding in enumerate(self.embeddings):
            similarity = np.dot(query_embedding, embedding) / (
                np.linalg.norm(query_embedding) * np.linalg.norm(embedding)
            )
            similarities.append((self.chunks[i], similarity))

        return sorted(similarities, key=lambda x: x[1], reverse=True)[:top_k]

Step 6: OpenAI Integration (src/rag_system.py):

import os
from dotenv import load_dotenv
from typing import List
import openai

from .document_loader import DocumentLoader
from .text_processor import TextProcessor
from .embeddings_manager import EmbeddingsManager
from .retrieval_system import RetrievalSystem

class RAGSystem:
    def __init__(self):
        load_dotenv()
        self.api_key = os.getenv('OPENAI_API_KEY')
        self.loader = DocumentLoader('data/documents')
        self.processor = TextProcessor()
        self.embeddings_manager = EmbeddingsManager(self.api_key)

        # Initialize system
        self.initialize_system()

    def initialize_system(self):
        # Load and process documents
        documents = self.loader.load_documents()
        self.chunks = []
        for doc in documents:
            self.chunks.extend(self.processor.split_into_chunks(doc))

        # Create embeddings
        self.embeddings = self.embeddings_manager.create_embeddings(self.chunks)

        # Initialize retrieval system
        self.retrieval_system = RetrievalSystem(self.chunks, self.embeddings)

    def answer_question(self, question: str) -> str:
        # Get question embedding
        question_embedding = self.embeddings_manager.create_embeddings([question])[0]

        # Get relevant chunks
        relevant_chunks = self.retrieval_system.find_similar_chunks(question_embedding)

        # Prepare context
        context = "\n".join([chunk[0] for chunk in relevant_chunks])

        # Create prompt
        prompt = f"""Context: {context}\n\nQuestion: {question}\n\nAnswer:"""

        # Get response from OpenAI
        response = openai.chat.completions.create(
            model="gpt-4-turbo-preview",
            messages=[
                {"role": "system", "content": "You are a helpful assistant. Use the provided context to answer the question."},
                {"role": "user", "content": prompt}
            ]
        )

        return response.choices[0].message.content

Step 7: System Usage (test.py):

Place sample .txt documents in data/documents. Then, run test.py:

# test.py
from src.rag_system import RAGSystem

# Initialize the RAG system
rag = RAGSystem()

# Ask a question
question = "What was the answer to the guardian’s riddle, and how did it help Kai?" #Replace with your question based on your documents
answer = rag.answer_question(question)
print(answer)

Conclusion:

This provides a foundational RAG system. Future improvements could include enhanced chunking, embedding caching, error handling, refined prompt engineering, and vector database integration. Remember to manage your OpenAI API key securely and monitor usage.

The above is the detailed content of Building Your First RAG System with Python and OpenAI. For more information, please follow other related articles on the PHP Chinese website!