Create README.md
Browse files
README.md
CHANGED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
datasets:
|
| 3 |
+
- chromadb/paul_graham_essay
|
| 4 |
+
language:
|
| 5 |
+
- en
|
| 6 |
+
tags:
|
| 7 |
+
- RAG
|
| 8 |
+
- Retrieval Augmented Generation
|
| 9 |
+
- llama-index
|
| 10 |
+
---
|
| 11 |
+
# Summary:
|
| 12 |
+
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.
|
| 13 |
+
# Implemeting RAG(in a nutshell):
|
| 14 |
+
### 1. Ready/ Preprocess your input data:
|
| 15 |
+
Language Models see all the data as tokens and vectors. So we want to convert the data to be fed into the same format.
|
| 16 |
+
### 2. Feed the processed data to the Language Model.
|
| 17 |
+
### 3. Indexing the stored data that matches the context of the query.
|