GitHub - michaelfeil/infinity: Infinity is a high-throughput, low-latency REST API for serving vector embeddings, supporting a wide range of sentence-transformer models and frameworks.
How would you build a modern Search Engine using Embeddings and Transformer models? Here is an article on how @wilsonzlin build a web search engine in two months, capable of indexing 280 million pages with 3 billion embeddings.
The Ingest process (simplified):
1. Crawl raw HTML page and normalize to... See more
Building a web search engine from scratch in two months with 3 billion neural embeddings
blog.wilsonl.in
