modified bullet points in intro

Author: malaikannan

_posts/2024-08-31-VectorDB.md

@@ -8,9 +8,9 @@ In the world of Large Language Models (LLMs), vector databases play a pivotal ro
 
 How RAG Works:
 
-User Query: A user submits a query or prompt to the RAG system.
-Information Retrieval: The system retrieves relevant information from a knowledge base based on the query. VectorDBs play a key role in this. Embeddings aka vectors are stored in VectorDB and retrieval is done using similarity measures. 
-Language Model Generation: The retrieved information is fed into a language model, which generates a response based on the query and the retrieved context.
+- User Query: A user submits a query or prompt to the RAG system.
+- Information Retrieval: The system retrieves relevant information from a knowledge base based on the query. VectorDBs play a key role in this. Embeddings aka vectors are stored in VectorDB and retrieval is done using similarity measures. 
+- Language Model Generation: The retrieved information is fed into a language model, which generates a response based on the query and the retrieved context.
 
 In this blog series, we will delve into the intricacies of vector databases, exploring their underlying principles, key features, and real-world applications. We will also discuss the advantages they offer over traditional databases and how they are transforming the way we store, manage, and retrieve data.