Smart Study Assistant: Turn Notes Into a Study Pack

Smart Study Assistant is a beginner-friendly project that helps students quickly convert raw study material into structured learning content. Users can paste notes or textbook text, and the system transforms it into concise summaries, key points, and practice questions.

The tool leverages an LLM to understand the input content and extract the most important ideas, making it easier to revise and retain information. It also generates quiz-style questions to reinforce learning and support active recall.

Built using Python and the OpenAI API, this project demonstrates how large language models can be applied to education use cases. It focuses on simplifying study workflows by turning unstructured text into organized, exam-ready material in a single step.

Purpose: help you study faster than rereading long notes from start to finish.

Typical use: before a quiz, paste one dense paragraph and skim the summary and questions the model writes for you.

Key features:

• One text box for your source notes.
• One button to ask for a study pack.
• Answer split into clear parts: summary, key points, quiz.
• A simple warning if the box is empty, and an error line if the API fails.

Quick example: if you paste two sentences about photosynthesis, you might get a short summary, a few bullet facts, and quiz questions about chloroplasts and light reactions—with suggested answers.

Overall flow

User enters notes
      ↓
Clicks button
      ↓
App sends notes to AI
      ↓
AI generates:
  - Summary
  - Key points
  - Quiz
      ↓
Displayed on screen

Step-by-Step Implementation

1. Set up the project
   • Install Python
   • Create a new project folder
   • Create and activate a virtual environment
2. Install dependencies
   • Install required packages:
     • Streamlit
     • OpenAI Python SDK
     • httpx
     • truststore (helps fix SSL issues on some systems, especially macOS)
3. Build the UI
   • Create a simple Streamlit page with:
     • A title
     • A text area for notes
     • A button to trigger processing
4. Secure your API key
   • Store your OpenAI API key in .streamlit/secrets.toml
   • Never hardcode the API key in your script
5. Handle user interaction
   • On button click:
     • Read the input text
     • Send it to the OpenAI model with a clear system prompt
6. Display results
   • Show the AI-generated response using st.markdown()
   • Ensure the output is structured (Summary, Key Points, Quiz)
7. Add error handling
   • Show a warning if the input box is empty
   • Use try/except to handle API or network errors gracefully

Code Implementation

# Smart Study Assistant — minimal Streamlit + OpenAI example.
# Save as app.py, add OPENAI_API_KEY to .streamlit/secrets.toml, then run: streamlit run app.py

import ssl
import httpx
import streamlit as st
import truststore
from openai import OpenAI

# Browser tab title and layout
st.set_page_config(page_title="Smart Study Assistant", layout="centered")
st.title("Smart Study Assistant")
st.caption("Paste notes below. You will get a summary, key points, and a short quiz.")

# On some macOS/Python setups, default cert verification fails; use the OS trust store.
_ssl_ctx = truststore.SSLContext(ssl.PROTOCOL_TLS_CLIENT)
_http = httpx.Client(timeout=120.0, verify=_ssl_ctx)

# Create the OpenAI client using a secret key (never paste keys into this file).
client = OpenAI(
    api_key=st.secrets["OPENAI_API_KEY"],
    http_client=_http
    )
_chat_model = "gpt-4o-mini"

# Large text box where the student pastes notes
notes = st.text_area(
    "Your notes",
    height=220,
    placeholder="Example: paste a paragraph from a textbook or lecture…",
)

# Main action button
if st.button("Generate study pack", type="primary"):
    # Guard: empty notes should not call the API
    if not notes.strip():
        st.warning("Please paste some text first.")
    else:
        # Show a spinner while the network request runs
        with st.spinner("Calling the model…"):
            try:
                response = client.chat.completions.create(
                    model=_chat_model,
                    messages=[
                        {
                            "role": "system",
                            "content": (
                                "You help students study. Reply with exactly three sections. "
                                "Use these headings on their own lines: Summary, Key points, Quiz. "
                                "Under Quiz, write a few questions and then a line starting with Answers:."
                            ),
                        },
                        {"role": "user", "content": notes},
                    ],
                )
                text = (response.choices[0].message.content or "").strip()
                st.markdown(text)
            except Exception as err:
                st.error(f"Something went wrong: {err}")

Demo

📖 How the Code Works (Step-by-Step)