Hacker News Reader

Suppose I would want to run something like this on corpus of documents I have and I'm not really a machine learning expert, any recommendation for a library/boilerplate/starting point?

View on HN

This tutorial uses an off-the-shelf ML model (Average Word Embeddings) and a managed vector index for document search: https://www.pinecone.io/docs/examples/semantic-text-search/

Even if you choose another model or method for storing and searching through the vector embeddings, the order of operations will be approximately the same.

I haven't used it yet, but https://github.com/semi-technologies/weaviate is a vector search engine that does embeddings and search. I don't know if they have succeeded, but the goal seems to be to make embedding and searching vectors easy enough to not need to be an ML expert.

Reply on news.ycombinator.com