Shrideep's picture
Create README.md
288d21e verified
|
raw
history blame
639 Bytes
metadata
datasets:
  - chromadb/paul_graham_essay
language:
  - en
tags:
  - RAG
  - Retrieval Augmented Generation
  - llama-index

Summary:

Retrieval Augmented Generation (RAG) is a technique to specialize a language model with a specific knowledge domain by feeding in relevant data so that it can give better answers.

Implemeting RAG(in a nutshell):

1. Ready/ Preprocess your input data:

Language Models see all the data as tokens and vectors. So we want to convert the data to be fed into the same format.

2. Feed the processed data to the Language Model.

3. Indexing the stored data that matches the context of the query.