RAG From Scratch

from openai import OpenAI
import numpy as np

client = OpenAI()

def chunk(text: str, size: int = 400, overlap: int = 50) -> list[str]:
    words = text.split()
    chunks: list[str] = []
    i = 0
    while i < len(words):
        chunks.append(" ".join(words[i:i+size]))
        i += size - overlap
    return chunks

def embed(texts: list[str]) -> np.ndarray:
    r = client.embeddings.create(model="text-embedding-3-small", input=texts)
    return np.array([d.embedding for d in r.data], dtype=np.float32)

def cosine(a: np.ndarray, b: np.ndarray) -> np.ndarray:
    a_n = a / np.linalg.norm(a, axis=1, keepdims=True)
    b_n = b / np.linalg.norm(b)
    return a_n @ b_n

DOC = open("handbook.txt", encoding="utf-8").read()
CHUNKS = chunk(DOC)
MATRIX = embed(CHUNKS)

def answer(question: str, k: int = 4) -> str:
    q_vec = embed([question])[0]
    scores = cosine(MATRIX, q_vec)
    top = np.argsort(-scores)[:k]
    context = "\n\n---\n\n".join(CHUNKS[i] for i in top)

    r = client.responses.create(
        model="gpt-5",
        input=[
            {"role": "system", "content": "Answer only from the provided context. If unsure, say you don't know."},
            {"role": "user", "content": f"Context:\n{context}\n\nQuestion: {question}"},
        ],
    )
    return r.output_text

print(answer("What is the PTO policy?"))