Add embedding generation and vector store integration for RAG pipeline

[alok-kumar0421]

🚀 Feature Request

Problem:
Currently, we have document loading and chunking, but embeddings and vector storage are not implemented.

Proposed Solution:

• Generate embeddings using SentenceTransformers
• Store embeddings in a vector database (ChromaDB)
• Enable efficient similarity search for retrieval

Why needed:

• Required for RAG pipeline
• Enables semantic search over documents

I would like to work on this as the next step Under NSoC.

[alok-kumar0421]

@yash-pouranik
I would like to work on embeddings and vector store as the next step.

[yash-pouranik]

Proceed

[alok-kumar0421]

@yash-pouranik
thanks, i am preparing for next