Pipit: Building a 100% On-Device AI Universal Search Engine for Android (<50ms, Open Source)

说明与用途

Pipit 是一个开源的 Android 本地 AI 搜索引擎，支持 PDF、收据、截图、相册、消息、联系人、视频、音频和应用的统一搜索，延迟低于 50 ms，完全离线运行。

问题

Finding content on smartphones is difficult because stock search only checks filenames and cloud search uploads private files.

结果

Pipit delivers a unified, offline search across seven domains with sub‑50 ms latency, eliminating the need for cloud uploads.

工作流

• Index local media using Google ML Kit OCR for PDFs and receipts
• Extract visual features for semantic image search
• Store embeddings in a local database
• Query unified search bar with natural language
• Return results from all domains within 50 ms

证据

Smartphones hold our entire digital lives: thousands of photos, receipts, work PDFs, voice notes, and gate codes buried in messages.

来源

Yet finding anything is painful because stock search only checks cryptic filenames like IMG_20240914.jpg or Scan_Doc_09.pdf.

来源

Pipit 🐦 — an open-source, on-device AI universal search engine for Android.

来源

Deep Content OCR: Searches inside PDFs, receipts, and screenshots using on-device Google ML Kit.

来源

Semantic Visual Search: Natural language search across your gallery ("yellow vintage car", "handwritten grocery list").

来源

Unified Search Bar: 7 domains in one place (Photos, PDFs, Messages, Contacts, Video, Audio, Apps).

来源

100% Offline & Air-Gapped: Runs quantized Google LiteRT multimodal models directly on your phone's silicon. Zero cloud, zero tracking.

来源

Sub-50ms Latency: Accelerated via local Vulkan GPU/NPU delegates.

来源

Source code and release APKs are available on GitHub: Repository: https://github.com/sanjay434343/Pipit

来源