7 results for “topic:multi-modal-search”
Search photos on Unsplash based on OpenAI's CLIP model, support search with joint image+text queries and attention visualization.
A vector database for querying meaningfully similar data.
Cobweb is a multi-modal journey planner offering a server based REST API and a light frontend.
Cherrry Javascript SDK
CSE508-Information Retrieval course project on Multi modal search using deep learning.
Small Python scraping + LLM pipeline with strict resource/output caps. Works with Ollama (local) or Hugging Face Inference.
FrameFinderLE is an advanced image and video frame retrieval system that enhances CLIP's image-text pairing with hashtag refinement and user feedback, offering an intuitive search experience.