Files
scripts/pdf-extractor/README.md
T
ealmeida e7adb65d40 docs(okf): frontmatter OKF + rich abstracts nas descriptions
Normalizacao OKF dos .md: type/title/description/timestamp/layer +
descriptions factuais (rich abstracts). Apenas .md tracked; corpos intactos.
Parte da aplicacao OKF a /Dados/Dev (28-06-2026).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-28 22:55:40 +01:00

34 lines
689 B
Markdown

---
type: Reference
title: Readme
description: >-
Extrai texto de PDFs e converte para Markdown usando AI (OpenRouter/Mistral)
timestamp: 2026-02-07T02:52:04.015182+00:00
layer: wiki
---
# pdf-extractor - PDF to Markdown with AI
Extrai texto de PDFs e converte para Markdown usando AI (OpenRouter/Mistral).
## Setup
```bash
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt
cp .env.example .env
# Editar .env com API key OpenRouter
```
## Uso
```bash
# Colocar PDFs na pasta input/
mkdir -p input output
cp meu-ficheiro.pdf input/
python pdfmd.py
# Output em output/
```
## Configuracao
`.env`:
- `OPENROUTER_API_KEY` - Chave API OpenRouter (obrigatorio)