IA en el dispositivo · WebGPU

Busca en tus PDFs directo en tu navegador.

RAG de PDF en el cliente. Extraer, crear embeddings y recuperar — todo en el dispositivo, sin servidores.

WebGPU / WASM
MiniLM embeddings
100 % privado
Por qué RAG Search

Búsqueda semántica. Cero subidas.

Sube PDFs, haz preguntas y obtén respuestas con citas — todo en local.

100 % privado

Tus documentos nunca salen de tu dispositivo. Todo el procesamiento ocurre en local.

Embeddings en el dispositivo

Embeddings de texto generados localmente vía Transformers.js. Sin llamadas API.

Fragmentación y recuperación

Fragmentación automática de texto y búsqueda por similitud vectorial para una recuperación precisa.

Respuestas con citas

Las respuestas incluyen citas de las fuentes para que puedas verificar el contexto.

How it works

Three steps. Zero servers.

  1. 01

    Upload a PDF

    Drop in any text-based PDF. Text is extracted page by page in your browser via pdf.js.

  2. 02

    AI builds the index

    Text is chunked and embedded on-device with all-MiniLM-L6-v2 via WebGPU, stored in an in-memory vector store.

  3. 03

    Ask & retrieve

    Type a question. The top matching passages are ranked by cosine similarity and shown instantly.

Complete guide

About document RAG search

A free “chat with your PDF” tool that builds a semantic search index over your documents entirely in the browser. Instead of keyword matching, it finds passages by meaning — ideal for research papers, contracts, manuals, and long reports where the answer exists but you do not know the exact words to search for.

How it works

pdf.js extracts the text layer of your PDF on-device. The document is split into chunks and embedded with all-MiniLM-L6-v2, a compact sentence transformer running via Transformers.js with WebGPU acceleration; the embeddings live in an in-memory vector store. When you ask a question, your query is embedded with the same model and ranked against every chunk by cosine similarity, returning the top matching passages with page numbers and scores in seconds.

Limits & requirements

The tool reads PDFs with a selectable text layer — scanned, image-only PDFs need OCR first. There is no hard file-size limit, but very large documents scale with your device’s available RAM. Chrome or Edge with WebGPU is recommended for fast indexing; other browsers work via WebAssembly.

Privacy

The model downloads once from the open-source model hub, then indexing and search are 100% local. Confidential documents never touch a server, and nothing about their content is collected.

Soporte

Preguntas, respondidas.

No. Todo se ejecuta en tu navegador. El modelo de embeddings se descarga una vez desde Hugging Face y se guarda en caché localmente — a partir de ahí, la indexación y búsqueda son 100 % en el dispositivo.