you are viewing a single comment's thread
view the rest of the comments
[–] 3 points 3 months ago* (last edited 3 months ago)

This is how RAG pipelines work. You chunk up text and then embed it, which gives you a vector representation of the text. You store that in a database keys in the vector Then when you want to inject relevant information for a prompt, you embed the prompt to get a vector, and then dump the a handful of most similar chunks into context to provide additional information.

So this semantic similarity question has been in my mind for a while to answer the question of what names would be the most "intuitive" for an LLM.

Does it work? shrug I guess we'll find out.

  • source
  • parent