News for hackers. Stuff that matters.
Re:PMET: Precise Model Editing in a Transformer by DennisP on Sunday August 27, 2023 @08:20PM (#37288112)
How do you save a document vector and do similarity search with it?
Re:PMET: Precise Model Editing in a Transformer by PaulHoule on Sunday August 27, 2023 @08:42PM (#37288287)
There is this

https://github.com/openai/chatgpt-retrieval-plugin

I just use SBERT which has models I can run locally

https://sbert.net/

Re:PMET: Precise Model Editing in a Transformer by nl on Sunday August 27, 2023 @08:43PM (#37288299)
You encode your document with some kind of embedding, eg HuggingFace Sentence Transformers: https://www.sbert.net/ (probably most commonly used) or OpenAI Embeddings: https://platform.openai.com/docs/guides/embeddings/what-are-... and then use a vector database (Elastic, Postgres, FAISS or whatever) to do a similarity search.