Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/mauroperez055/infoJobs/llms.txt

Use this file to discover all available pages before exploring further.

This guide walks you through cloning the InfoJobs DevBoard repository, starting both the Express backend and the React frontend on your machine, verifying the API is working with a live request, and optionally enabling AI-powered job summaries with a locally running Ollama model.
1

Prerequisites

Make sure the following are installed before you begin:
  • Node.js ≥ 18 — required by both the backend and frontend build tooling.
  • npm (bundled with Node.js) or pnpm — for installing dependencies.
  • Ollama (optional) — only needed if you want to use the AI summary feature. Download it from ollama.com.
Confirm your Node.js version:
node --version
# v18.0.0 or higher
2

Clone the repository

Clone the monorepo and navigate into the main full-stack stage:
git clone https://github.com/mauroperez055/infoJobs.git
cd infoJobs/07-inteligencia-artificial
The 07-inteligencia-artificial directory contains two sub-projects: backend/ (Express API) and frontend/ (React app).
3

Start the backend

Install backend dependencies and start the development server:
cd backend
npm install
npm run dev
The API server starts on port 1234 using nodemon for automatic restarts on file changes. You should see output similar to:
Servidor levantado en http://localhost:1234
4

Start the frontend

In a separate terminal, install frontend dependencies and launch the Vite dev server:
cd ../frontend
npm install
npm run dev
Vite opens the app on port 5173 by default. Visit http://localhost:5173 in your browser to see the job board.
5

Verify the API

With the backend running, confirm the jobs endpoint is responding:
curl http://localhost:1234/jobs
A successful response returns a paginated JSON object. Job fields use Spanish names as stored in jobs.json:
{
  "total": 42,
  "limit": 10,
  "offset": 0,
  "data": [
    {
      "id": "7a4d1d8b-1e45-4d8c-9f1a-8c2f9a9121a4",
      "titulo": "Desarrollador de Software Senior",
      "empresa": "Tech Solutions Inc.",
      "ubicacion": "Remoto",
      "descripcion": "Buscamos un ingeniero de software...",
      "data": {
        "technology": ["react", "node", "javascript"],
        "modalidad": "remoto",
        "nivel": "senior"
      },
      "content": {
        "description": "...",
        "responsibilities": "...",
        "requirements": "...",
        "about": "..."
      }
    }
  ]
}
You can also filter results using query parameters:
# Filter by technology (singular param name)
curl "http://localhost:1234/jobs?technology=react"

# Filter by free-text search across titulo and descripcion
curl "http://localhost:1234/jobs?text=senior"

# Paginate with limit and offset
curl "http://localhost:1234/jobs?limit=5&offset=10"
6

(Optional) Enable AI summaries

To use the AI-powered job summary feature, pull the required model and start Ollama in a dedicated terminal:
ollama pull qwen2.5:3b
ollama serve
Ollama runs on localhost:11434 by default. Once it is running, navigate to any job detail page in the frontend and click ✨ Generar resumen con IA — the summary will stream in real time.
The AI endpoint is rate-limited to 5 requests per minute per IP to prevent abuse. If you exceed this limit you will receive a 429 Too Many Requests response and should wait before retrying.

​
Configure the frontend API URL

The frontend reads the backend URL from the VITE_API_URL environment variable. Create a .env file inside the frontend/ directory if the default does not match your setup:
If you are running the backend on the default port 1234, no configuration is needed — the frontend falls back to http://localhost:1234 automatically. Only set this variable if you changed the port or are running the backend on a remote host.
# frontend/.env
VITE_API_URL=http://localhost:1234
After creating or editing the .env file, restart the Vite dev server for the change to take effect.

​
Configure the backend AI model

The backend reads the Ollama model name from the MODEL_AI environment variable, defined in backend/config.js. Create a .env file inside the backend/ directory to override the default: 
# backend/.env
PORT=1234
MODEL_AI=qwen2.5:3b
The default value for MODEL_AI is mistral/devstral-small-2. The AI route (backend/routes/ai.js) currently hard-codes qwen2.5:3b — set this variable if you want to use a different locally available Ollama model. Any model listed by ollama list can be used here.

​
Next steps

Architecture overview

See how the frontend, Express backend, and Ollama AI layer are wired together.

API Reference

Explore all available endpoints, request schemas, and response formats.

Build docs developers (and LLMs) love

Get started for freeTalk to us