Retrieval augmented generation with Wolfram Language

DOWNLOAD-DESKTOP-NOTEBOOK.nb (533 KB)

16 Likes

news-congrads-kkluyshnik-02-04-19.jpg – you have earned Featured Contributor Badge 2015-11-02_10-07-11.png
Your exceptional post has been selected for our editorial column Staff Picks http://wolfr.am/StaffPicks and Your Profile is now distinguished by a Featured Contributor Badge and is displayed on the Featured Contributor Board. Thank you!

1 Like

Great post! It’s always nice to see the technology applied to real world cases.

Just one comment: the default feature extractor for CreateSemanticSearchIndex (“SentenceBERT”) is a local model that runs on your machine.
CreateVectorDatabase does not require any external service either.

It’s true that more advanced embedding models are typically not free or not cheap to run locally but we are looking into supporting more way to run your LLM of choice.

Stay tuned!

4 Likes
3 Likes