Build a RAG Pipeline from Scratch with Python and Claude

pip install anthropic chromadb sentence-transformers pypdf

from pypdf import PdfReader
import re

def load_pdf(path: str) -> list[str]:
    reader = PdfReader(path)
    text = " ".join(page.extract_text() for page in reader.pages)
    # Chunk into ~500 word segments with 50-word overlap
    words = text.split()
    chunks = []
    for i in range(0, len(words), 450):
        chunk = " ".join(words[i:i+500])
        chunks.append(chunk)
    return chunks

import chromadb
from sentence_transformers import SentenceTransformer

model = SentenceTransformer("all-MiniLM-L6-v2")
client = chromadb.Client()
collection = client.create_collection("docs")

chunks = load_pdf("your_document.pdf")
embeddings = model.encode(chunks).tolist()

collection.add(
    documents=chunks,
    embeddings=embeddings,
    ids=[f"chunk_{i}" for i in range(len(chunks))]
)

import anthropic

def rag_query(question: str, top_k: int = 3) -> str:
    # Embed the question
    q_embedding = model.encode([question]).tolist()
    
    # Retrieve relevant chunks
    results = collection.query(query_embeddings=q_embedding, n_results=top_k)
    context = "\n\n".join(results["documents"][0])
    
    # Ask Claude with context
    client = anthropic.Anthropic()
    response = client.messages.create(
        model="claude-sonnet-4-6",
        max_tokens=1024,
        messages=[{
            "role": "user",
            "content": f"""Answer the question based on the context below.
If the answer is not in the context, say "I don't know."

Context:
{context}

Question: {question}"""
        }]
    )
    return response.content[0].text

# Use it
answer = rag_query("What are the main conclusions of the report?")
print(answer)