Combine AI Models for Image Search using ONNX and Milvus

What this post added

This post details a method for performing image search by combining multiple AI models (VGG16, ResNet50) using ONNX for feature vector generation and Milvus for vector retrieval. It provides Python code snippets for converting Keras models to ONNX format, extracting feature vectors using ONNX runtime, storing these vectors in Milvus collections, and performing similarity searches using Euclidean distance. It also mentions the use of Redis for mapping vector IDs to image paths in the context of Milvus 1.1.