News for hackers. Stuff that matters.
Re:Ask HN: Is RAG the Future of LLMs? by choilive on Sunday April 14, 2024 @06:58PM (#40035247)
I think that "next level" would essentially be a RAG referential information system that gets data via search engines or databases. Maybe we will have the "google search" equivalent completely intended for LLM clients where all data is stored, searched, and returned via vector embeddings, but it could tap on exabytes of information.
Re:Ask HN: Is RAG the Future of LLMs? by 0x008 on Monday April 15, 2024 @05:00AM (#40038241)
That is actually already what is happening, tools like llama_index are trying to provide all the necessary integrations.