Hacker News new | ask | show | jobs
by rmykhajliw 54 days ago
Small approach to use RAG for better result in similarity for related content. The best thing is the process of getting vectors are don't only once, then you can reuse them indefinitely.
1 comments

As obvious it's possible to use local Ollama models instead of ChatGPT , it you have large amount of data. But I love using the same approach even for building linking inside internal documentation, I really helps to keep all the changes updated and related.