On Hybrid Search with Qdrant

Re:On Hybrid Search with Qdrant by trengrj on Tuesday March 07, 2023 @08:11AM (#35054923)

Adding a cross-encoder to your app means including pytorch/transformers and a model as a dependency. For people using OpenAI or Cohere embedding apis and lightweight infrastructure this can be a big pain.

[ Parent | on HN ]

Re:On Hybrid Search with Qdrant by generall on Tuesday March 07, 2023 @08:13AM (#35054940)

Proposed architecture doesn't limit you to use self-hosted transformers only, you can use OpenAI just as easily. And you don't need a to install a "module" for that

[ Parent | on HN ]