Extract fields

Paste a messy blob — an email signature, a forwarded intro, a chat message —

README Pruébalo Código

Showcase — Extract fields

Paste a messy blob — an email signature, a forwarded intro, a chat message — and get back a strict JSON object: name, email, phone, company. The model fills what it finds and returns null for the rest instead of guessing, because the schema says those fields are optional, not absent.

Run

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

Open http://localhost:3000.

To run against Gemini instead:

PROVIDER=gemini docker compose up --build

What's where

backend/ai_openai.py — the Contact schema + responses.parse call
backend/ai_gemini.py — same schema, response_schema on the config
backend/main.py — identical FastAPI loader; reads PROVIDER and dispatches
frontend/app/page.tsx — textarea + result (rendered as JSON)
docker-compose.yml — two services, secrets mounted from ./secrets/

run(input: str) -> str returns the validated object serialized to pretty JSON, keeping the contract identical across the week's showcases.

Stop

docker compose down

Ejecútalo en tu máquina

Descarga el proyecto como ZIP y córrelo con Docker. Levanta un backend FastAPI y un frontend Next.js en localhost:3000.

Descargar extract-fields.zip

unzip extract-fields.zip
cd extract-fields
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

Escribe algo, elige un proveedor y ejecuta el mismo código de Código contra la API real. Requiere iniciar sesión.

Entrada

Proveedor

Output

Los mismos módulos que ejecuta el botón Run. El proyecto completo (frontend, Dockerfile, compose) está en el ZIP, pestaña README.

`backend/ai_openai.py`

"""Week 4 - Showcase 1 (OpenAI): pull contact fields out of free text.

A schema in, a clean object out. The model fills what it finds and leaves
the rest null instead of guessing. The run() contract still returns a
string, so we serialize the validated object to pretty JSON for display.
"""
import json
from typing import Optional

from openai import OpenAI
from pydantic import BaseModel

_client = OpenAI()


class Contact(BaseModel):
    name: Optional[str] = None
    email: Optional[str] = None
    phone: Optional[str] = None
    company: Optional[str] = None


def run(text: str) -> str:
    response = _client.responses.parse(
        model="gpt-5.4-nano",
        input="Extract the contact details from this text. Use null for "
              f"anything not present.\n\n{text.strip()}",
        text_format=Contact,
    )
    return json.dumps(response.output_parsed.model_dump(), indent=2)

`backend/ai_gemini.py`

"""Week 4 - Showcase 1 (Gemini): pull contact fields out of free text."""
import json
import os
from typing import Optional

from google import genai
from google.genai import types
from pydantic import BaseModel

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


class Contact(BaseModel):
    name: Optional[str] = None
    email: Optional[str] = None
    phone: Optional[str] = None
    company: Optional[str] = None


def run(text: str) -> str:
    response = _client.models.generate_content(
        model="gemini-3.1-flash-lite",
        contents="Extract the contact details from this text. Use null for "
                 f"anything not present.\n\n{text.strip()}",
        config=types.GenerateContentConfig(
            response_mime_type="application/json",
            response_schema=Contact,
        ),
    )
    return json.dumps(response.parsed.model_dump(), indent=2)