Hacker News Reader

Quite similar result than fine tuned gpt with embeddings no?

This example isn't using gpt embeddings but it could. It's using local Hugging Face models (FLAN-T5) with a context provided by a vector store (Faiss).

If I would like to use small but trusted knowledge models with some big language model regardles how silly is the second to get verifiable answers only - are those the ways for doing this ? - or better shall I look for some other approaches - maybe like this one: https://openreview.net/forum?id=Plr5l7r0jY6 Language model with Plug-in Knowldge Memory ?

The goal of this approach is to answer questions with a datasource. The referenced example runs a vector database query to build the context and then runs a prompt to ask the question.

Answer the following question using only the context below. Say 'no answer' when the question can't be answered. Question: {question} Context: {context}

Not sure this prompt works for all scenarios and models. But it can easily be changed and is a starting point.

Reply on news.ycombinator.com