multimodal-search repositories

Trending repositories tagged multimodal-search, ranked by trending score. Updated daily.

  1. 1
    Just-A-Freshman/VimgFind

    本地搜图工具:图片搜索、以图搜图、以文搜图、相似图片搜索、图片检索、本地图片检索、离线图片搜索、本地图片搜索、找相似图片、相册搜索、电脑搜图、看图找图——Windows 离线 AI 图像检索,毫秒级响应。Local image search / reverse image search / text-to-image search / photo search for Windows: offline, HNSW, Chinese-CLIP, no setup.

    GitHub · HTML · 28 stars · 4 forks · +1 stars in 24 hours · Trending score 0.45

  2. 2
    iDiagoValeta/localOllamaRAG

    MonkeyGrab: a local, multilingual (ES/CA/EN) RAG system for PDFs. MinerU parsing, hybrid BM25 + FAISS retrieval with cross-encoder reranking, and generation with open models via Ollama. Flask + React web app and Windows desktop build; no data leaves your machine.

    GitHub · Python · 16 stars · 1 forks · 0 stars in 24 hours · Trending score 0.39

  3. 3
    treygrainger/ai-powered-search

    The codebase for the book "AI-Powered Search" (Manning Publications, 2025) and associated "AI-Powered Search: Modern Retrieval for Humans & Agents" Maven course

    GitHub · Jupyter Notebook · 423 stars · 132 forks · 0 stars in 24 hours · Trending score 0.30

  4. 4
    B0yko/tern

    Search a video archive by what was said, what was on screen, or what the scene looked like.

    GitHub · Python · 118 stars · 1 forks · −72 stars in 24 hours · Trending score 0.06

  5. 5
    li-xiu-qi/MaterialSeeker

    本地优先的创作者素材库:视频、图片、音频与文本统一管理和检索。支持 SQLite FTS5 关键词搜索、EmbeddingGemma 2 语义搜索、文字搜图片与视频关键帧的跨模态搜索,以及中文 ASR、句级时间戳、场景检测与 AI 画面描述。Local-first creator asset search with FTS5, semantic and cross-modal retrieval.

    GitHub · TypeScript · 6 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00