Update main()

Call chat_loop at the end of main() to hand off to the interactive session

💻

Writing code and entering commands is only available on desktop. Open this page on a larger screen to complete this chapter.

Two phases, one program

main() now has two distinct phases:

Setup — parse the folder argument, resolve the cache path, create the client, and either load embeddings from cache or index the folder and save a new cache.
Run — hand off to chat_loop, which stays alive until the user quits.

One line at the end of main() connects the two phases. The loop runs until Ctrl+C or until you add an explicit quit command in a later lesson.

Instructions

At the end of main(), after the if cached / else block, call chat_loop(client, chunks, embeddings).

← Previous Chapter Next Chapter →

import json
import os
import sys
import time
import numpy as np
from dotenv import load_dotenv
from google import genai
from google.genai import types
from files import index_folder

def create_client():
    load_dotenv()
    api_key = os.getenv("GEMINI_API_KEY")
    client = genai.Client(api_key=api_key)
    return client

def embed_text(client, text):
    result = client.models.embed_content(model="gemini-embedding-001", contents=text, config=types.EmbedContentConfig(task_type="RETRIEVAL_DOCUMENT"))
    return result.embeddings[0].values

def embed_all_chunks(client, texts):
    BATCH_SIZE = 90
    embeddings = []
    for i in range(0, len(texts), BATCH_SIZE):
        batch = texts[i : i + BATCH_SIZE]
        for text in batch:
            embeddings.append(embed_text(client, text))
        if i + BATCH_SIZE < len(texts):
            print("Rate limit pause — waiting 60 seconds...")
            time.sleep(60)
    return embeddings

def cosine_similarity(vec_a, vec_b):
    dot = np.dot(vec_a, vec_b)
    norm = np.linalg.norm(vec_a) * np.linalg.norm(vec_b)
    return dot / norm

def search(client, query, chunks, embeddings, top_k=3):
    result = client.models.embed_content(model="gemini-embedding-001", contents=query, config=types.EmbedContentConfig(task_type="RETRIEVAL_QUERY"))
    query_vector = result.embeddings[0].values
    scores = [(cosine_similarity(query_vector, emb), chunk) for emb, chunk in zip(embeddings, chunks)]
    scores.sort(key=lambda x: x[0], reverse=True)
    return [chunk for _, chunk in scores[:top_k]]

def build_prompt(question, context_chunks, file_list=None):
    context = "\n\n".join(chunk["text"] for chunk in context_chunks)
    files_line = ""
    if file_list:
        files_line = f"You have access to these files: {', '.join(file_list)}\n"
    return (
        f"{files_line}"
        "You are a helpful assistant. Answer the question using only the context below.\n"
        "If the answer is not in the context, say \"I don't know.\"\n\n"
        f"Context:\n{context}\n\n"
        f"Question:\n{question}"
    )

def generate_answer(client, prompt):
    response = client.models.generate_content(model="gemini-2.5-flash", contents=prompt)
    return response.text

def save_embeddings(chunks, embeddings, cache_path):
    data = {"chunks": chunks, "embeddings": embeddings}
    with open(cache_path, "w") as f:
        json.dump(data, f)

def load_embeddings(cache_path):
    if not os.path.exists(cache_path):
        return None
    with open(cache_path) as f:
        data = json.load(f)
    return data["chunks"], data["embeddings"]

def chat_loop(client, chunks, embeddings):
    file_list = sorted(set(chunk["source"] for chunk in chunks))
    print("Assistant ready. Type your question, or /help for commands.\n")
    while True:
        question = input("You: ").strip()
        if not question:
            continue
        top_chunks = search(client, question, chunks, embeddings)
        prompt = build_prompt(question, top_chunks, file_list)
        answer = generate_answer(client, prompt)
        print(f"Assistant: {answer}")

def main():
    if len(sys.argv) < 2:
        print("Usage: python app.py <folder>")
        sys.exit(1)
    folder = sys.argv[1]
    cache_path = folder.rstrip("/\\") + ".cache.json"
    client = create_client()
    cached = load_embeddings(cache_path)
    if cached:
        chunks, embeddings = cached
        print(f"Loaded cache from {cache_path}")
    else:
        print(f"Indexing {folder}...")
        chunks = index_folder(folder)
        texts = [chunk["text"] for chunk in chunks]
        file_count = len(set(chunk["source"] for chunk in chunks))
        print(f"Indexed {len(chunks)} chunks from {file_count} files.")
        embeddings = embed_all_chunks(client, texts)
        save_embeddings(chunks, embeddings, cache_path)
        print(f"Cache saved to {cache_path}")
    # Step 1:

if __name__ == "__main__":
    main()

Update main()

Two phases, one program

Instructions

Interactive Code Editor