Repolode
Enviar
StarTrail-org

StarTrail-org/PixelRAG

Open-source pipeline that renders web pages and PDFs as screenshots and retrieves them visually, so tables and charts survive for RAG.

Ver en GitHubSitio web
Estrellas
10,309
Forks
910
Issues abiertos
19
Último commit
hace 5 días

¿Qué es?

PixelRAG treats documents as images rather than text. It renders web pages, PDFs and images into screenshot tiles, embeds them with a Qwen3-VL-Embedding model, and searches a FAISS or Qdrant index. Because layout, tables, charts and infographics are kept intact, a reader model can answer questions that text-chunk pipelines lose when HTML is parsed.

The project ships several pieces: the pixelshot CLI for capture via Playwright/CDP, the pixelrag umbrella command for chunking, embedding, index building and a FastAPI search server, and a LoRA fine-tuning recipe in a separate train/ project. A hosted search API over a pre-built index of 8.28M Wikipedia pages is available, and the same rendering can be used by Claude Code or opencode through a plugin.

Funciones clave

  • 01Renders web pages and PDFs into screenshot tiles with pixelshot.
  • 02Embeds page images with a Qwen3-VL-Embedding model that can be LoRA fine-tuned.
  • 03Builds FAISS or Qdrant indexes and serves search through a FastAPI endpoint.
  • 04Supports image queries for visual search.
  • 05Runs on Linux with CUDA and on macOS with Apple Silicon MPS.

Casos de uso

  • Answering questions over documents where tables and charts carry the key numbers.
  • Letting an AI coding agent read a web page as an image instead of raw HTML.
  • Indexing a private collection of PDFs for visual search on a local machine.

Temas

#rag#multimodal#vision#vector-search#embeddings#screenshot#faiss#qdrant#agent#ai

Preguntas frecuentes

¿Qué es PixelRAG?
Open-source pipeline that renders web pages and PDFs as screenshots and retrieves them visually, so tables and charts survive for RAG. PixelRAG treats documents as images rather than text. It renders web pages, PDFs and images into screenshot tiles, embeds them with a Qwen3-VL-Embedding model, and searches a FAISS or Qdrant index. Because layout, tables, charts and infographics are kept intact, a reader model can answer questions that text-chunk pipelines lose when HTML is parsed.
¿PixelRAG es gratuito? ¿Qué licencia tiene?
PixelRAG es open source bajo la licencia Apache-2.0. Revisa los términos de la licencia antes de usarlo en productos comerciales.
¿PixelRAG sigue mantenido?
Mantenimiento activo. El último commit de PixelRAG fue el 14 oct 2026.
¿Para qué puedo usar PixelRAG?
Answering questions over documents where tables and charts carry the key numbers. Letting an AI coding agent read a web page as an image instead of raw HTML. Indexing a private collection of PDFs for visual search on a local machine.
¿Dónde consigo PixelRAG?
El código fuente y las instrucciones de instalación están en GitHub: https://github.com/StarTrail-org/PixelRAG

Resumen generado por IA a partir del README del proyecto. Las estadísticas de GitHub se actualizan a diario.

Proyectos relacionados