README.md

---
title: Library Card Metadata Extractor
emoji: 📇
colorFrom: blue
colorTo: purple
sdk: gradio
sdk_version: 5.30.0
app_file: app.py
pinned: false
---

# Library Card Metadata Extractor

Extract structured metadata from library catalog cards using Qwen3-VL-30B-A3B-Instruct.

## Features

- Upload an image of a library catalog card
- Automatically extract metadata fields:
  - Title
  - Author/Creator
  - Dates
  - Call Number
  - Physical Description
  - Subjects
  - Notes
- Returns structured JSON output

## Datasets

This demo works with catalog cards from:
- [Rubenstein Manuscript Catalog](https://huggingface.co/datasets/biglam/rubenstein-manuscript-catalog) - Duke University's manuscript catalog cards
- [Boston Public Library Card Catalog](https://huggingface.co/datasets/biglam/bpl-card-catalog) - BPL's rare books catalog cards

## Model

Uses [Qwen3-VL-30B-A3B-Instruct](https://huggingface.co/Qwen/Qwen3-VL-30B-A3B-Instruct), a powerful vision-language model with:
- 30B parameters
- 256K context length
- Advanced OCR capabilities in 32 languages
- Strong visual understanding and reasoning

## Usage

1. Upload an image of a library catalog card
2. Click "Extract Metadata"
3. View the extracted metadata as formatted JSON

Built for the GLAM (Galleries, Libraries, Archives, Museums) community.