This series aims to demystify embeddings and show you how to use them in your projects. The first blog post taught you how to use and scale up open-source embedding models, pick an existing model, current evaluation methods, and the state of the ecosystem. This second blog post will dive deeper into embeddings and explain the differences between bi-encoders and cross-encoders. Then, we’ll dive into retrieving and re-ranking: we’ll build a tool to answer questions about 400 AI papers. We...
