Multimodal Embedding Service : This is a vibecodded application to serve as an HTTP API for CLIP models like from Jina or OpenAI. It uses the sentence-transformers library with the clip-ViT-B-32 model to generate high-quality, multimodal embeddings for both text and images.
python api docker machine-learning ai deep-learning docker-compose embeddings clip http-service multimodal fastapi sentence-transformers
-
Updated
Dec 24, 2025 - Python