Course ES
← back to chapter

Long summarize

Paste an article, transcript, or report and get a TL;DR plus key points. Long context makes summarization trivial — the whole text goes in at once, no chunking or map-reduce.

Showcase — Long summarize

Paste an article, transcript, or report and get a TL;DR plus key points. Long context makes summarization trivial — the whole text goes in at once, no chunking or map-reduce.

Run

bash bootstrap-secrets.sh              # reads ../../../../.env, writes secrets/
docker compose up --build              # default: PROVIDER=openai

Open http://localhost:3000. Gemini: PROVIDER=gemini docker compose up --build.

What's where

  • backend/ai_openai.py / backend/ai_gemini.py — a TL;DR-plus-bullets summary of the pasted passage.
  • frontend/app/page.tsx — passage box, summary out.

Stop

docker compose down

Run locally

Download the project as a ZIP and run it with Docker. Brings up a FastAPI backend + Next.js frontend on localhost:3000.

Download long-summarize.zip

unzip long-summarize.zip
cd long-summarize
bash bootstrap-secrets.sh   # one-time: pulls API keys into ./secrets
docker compose up --build   # default provider: openai
# or:  PROVIDER=gemini docker compose up --build

Type some input, pick a provider, and run the same code shown in Source against the live API. Sign-in required.


  

The same modules the Run button hits. The whole project (frontend, Dockerfile, compose) is in the ZIP under README.

backend/ai_openai.py

"""Showcase 2 (OpenAI): summarize a long passage.

Paste an article, transcript, or report and get a TL;DR plus key points. Long
context makes this trivial — the whole text goes in, no chunking or map-reduce.
"""
from openai import OpenAI

_client = OpenAI()

_MODEL = "gpt-5.4-nano"


def run(text: str) -> str:
    doc = text.strip()
    if len(doc) < 100:
        return "Paste a longer passage (an article, transcript, or report) to summarize."
    response = _client.responses.create(
        model=_MODEL,
        instructions=(
            "Summarize the passage the user provides. Output exactly: a one-line "
            "'TL;DR:' summary, then 3-6 '- ' bullet key points. No preamble."
        ),
        input=[{"role": "user", "content": doc}],
    )
    return response.output_text

backend/ai_gemini.py

"""Showcase 2 (Gemini): summarize a long passage.

Same TL;DR-plus-bullets summary, on Gemini.
"""
import os

from google import genai
from google.genai import types

_client = genai.Client(api_key=os.environ["GEMINI_API_KEY"])

_MODEL = "gemini-3.1-flash-lite"


def run(text: str) -> str:
    doc = text.strip()
    if len(doc) < 100:
        return "Paste a longer passage (an article, transcript, or report) to summarize."
    response = _client.models.generate_content(
        model=_MODEL,
        contents=[types.Content(role="user", parts=[types.Part(text=doc)])],
        config=types.GenerateContentConfig(
            system_instruction=(
                "Summarize the passage the user provides. Output exactly: a one-line "
                "'TL;DR:' summary, then 3-6 '- ' bullet key points. No preamble."
            ),
        ),
    )
    return response.text or ""

Project files

  • .gitignore
  • README.es.md
  • README.md
  • backend/Dockerfile
  • backend/ai_gemini.py
  • backend/ai_openai.py
  • backend/main.py
  • backend/requirements.txt
  • bootstrap-secrets.sh
  • docker-compose.yml
  • frontend/Dockerfile
  • frontend/app/layout.tsx
  • frontend/app/page.tsx
  • frontend/next.config.ts
  • frontend/package.json
  • frontend/tsconfig.json