22 lines
No EOL
969 B
Markdown
22 lines
No EOL
969 B
Markdown
Demo 06 - RAG Part 2
|
|
===============================================
|
|
|
|
Retrieval Augmented Generation (RAG) is a way to extend the knowledge of the LLM used in the AI service.
|
|
|
|
The RAG pattern is composed of two parts:
|
|
* Ingestion: This is the part that stores data in the knowledge base.
|
|
* Augmentation: This is the part that adds the retrieved information to the input of the LLM.
|
|
|
|
|
|
# Embedding model
|
|
One of the core components of the RAG pattern is the embedding model. The embedding model is used to transform the
|
|
text into numerical vectors. These vectors are used to compare the text and find the most relevant segments.
|
|
|
|
# Vector store
|
|
In the previous step, we used an in memory store. Now we will use a persistent store to keep the embeddings between restarts.
|
|
|
|
# Ingesting documents into the vector store
|
|
While you are editing the `src/main/resources/application.properties` file, add the following configuration:
|
|
```
|
|
rag.location=src/main/resources/rag
|
|
``` |