As a developer, I want to explore and implement Retrieval Augmented Generation (RAG) to enhance my web application (VG grade only).

This issue covers the implementation of the RAG functionality required for a VG grade. It includes:

• Data from the chosen dataset is processed into embeddings using a pre-trained model.
• The generated embeddings are successfully stored in a vector database.
• A user interface (e.g., a search bar) is implemented to allow users to submit queries.
• The application retrieves relevant information from the vector database based on user queries.
• An LLM (Large Language Model) is integrated to process retrieved information and generate responses. This can be achieved by using an external LLM API (e.g., OpenAI API) or by deploying a self-hosted open-source LLM (e.g., using Ollama).
• The retrieved information is displayed clearly in the web application.

Frameworks like LangChain or Agno can be used to streamline the RAG pipeline