• 2 Posts
  • 436 Comments
Joined 2 years ago
cake
Cake day: June 10th, 2023

help-circle

  • Retrieval-augmented generation (RAG) is a technique that enables large language models (LLMs) to retrieve and incorporate new information. With RAG, LLMs do not respond to user queries until they refer to a specified set of documents. These documents supplement information from the LLM’s pre-existing training data. This allows LLMs to use domain-specific and/or updated information that is not available in the training data. For example, this helps LLM-based chatbots access internal company data or generate responses based on authoritative sources.

    From Retrieval-augmented generation.

    Specifically here, I imagine the idea is to talk to the chatbot about what’s in your documents.
















  • Yep.

    If you can do it, you can sometimes use that skill to quickly compare whether two adjacent vertical images are identical. If they are, you will just see a single version of the image as normal. If they are different, you will easily see a ‘fuzzy’ part of the image that won’t resolve and stay still (hard to describe, it’s like when I try to read text in a dream).

    A practical application I use now and then is when I want to compare two columns of data on a screen. Use the magic eye technique to overlap the columns and any differences will be immediately obvious, even with a lot of data.