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 no GitHubSite
Estrelas
10,309
Forks
910
Issues abertas
19
Último commit
há 5 dias

O que é?

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.

Recursos principais

  • 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.

Tópicos

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

Perguntas frequentes

O que é 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 é gratuito? Qual é a licença?
PixelRAG é open source sob a licença Apache-2.0. Confira os termos da licença antes de usá-lo em produtos comerciais.
PixelRAG ainda é mantido?
Manutenção ativa. O último commit de PixelRAG foi em 14 de out. de 2026.
Para que posso 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.
Onde consigo PixelRAG?
O código-fonte e as instruções de instalação estão no GitHub: https://github.com/StarTrail-org/PixelRAG

Resumo gerado por IA a partir do README do projeto. As estatísticas do GitHub são atualizadas diariamente.

Projetos relacionados