Multimodal AI Search Engine — Text & Image Semantic Search réalisé par un freelance en Tunisie | Tunisie Freelance
Multimodal AI Search Engine — Text & Image Semantic Search
data-science
Development of an AI-powered multimodal image search engine using CLIP and FAISS. The system supports both text-to-image and image-to-image semantic search. CLIP generates shared embeddings for text and images, while FAISS performs fast similarity search. A Streamlit interface allows users to enter natural-language queries or upload images to retrieve relevant results.
