top | item 34510271

(no title)

TomatoTomato | 3 years ago

How are you getting the book text into gpt3?

discuss

order

leobg|3 years ago

You don’t. You cut it into snippets. For those you create embeddings which allow you to rank them by semantic similarity to a query. You then prompt GPT3 with the question plus, say, the three most relevant snippets from the book.

The most difficult thing about the process is preventing the model from making stuff up.

kreas|3 years ago

This is exactly what I'm working on! My project is taking Zoom conversation, using pyannote for speaker diarisation, whisper for transcription, pinecone.io for semantic search, then feeding that into GPT-3 so we can ask questions about conversation.

For us this is super useful because it's not unusual for our discover sessions to last days and we're all terrible at taking notes.

As a nerd, my brain is already buzzing on ways that I could use this for my groups D&D campaigns.

d4rkp4ttern|3 years ago

How do you create the embeddings? Is there a GPT3 API that returns a paragraph’s embedding vector?