Ask HN: How do I train a custom LLM/ChatGPT on my own documents in Dec 2023?

Re:Ask HN: How do I train a custom LLM/ChatGPT on my own doc... by simonw on Monday December 25, 2023 @11:07AM (#38763697)

I've been trying out an interesting embedding model that knows how to treat text as a question be as a phrase about the world, and embeds the question such that it's likely to end up close to phrases that might answer that question: https://til.simonwillison.net/llms/embed-paragraphs

Embedding and chunking large amounts of documents is expensive though, in both compute and storage.

The other trick I've been planning to explore is using an LLM to turn the user's question into a small number of normal FTS search queries and then run those to try and get context data.

[ Parent | on HN ]

Re:Ask HN: How do I train a custom LLM/ChatGPT on my own doc... by akrymski on Monday December 25, 2023 @12:08PM (#38764212)

> The other trick I've been planning to explore is using an LLM to turn the user's question into a small number of normal FTS search queries and then run those to try and get context data.

I have also been working on this. I still fail to see why this approach isn't the default frankly. There's little benefit to vector databases.

[ Parent | on HN ]