RetrievalAugmentedGeneration-Projects

Is a collection of RAG projects.

Project-1:

Built a Retrieval-Augmented Generation (RAG) pipeline from scratch, and it is called Chat with a PDF.

The problem RAG solves: LLMs like Claude/GPT don't have access to your documents. RAG fixes this by:

1. Splitting your PDF into small chunks
2. Embedding each chunk (converting text → numbers that capture meaning)
3. Storing those embeddings in a vector database
4. When you ask a question → finding the most relevant chunks → sending them to an LLM as context
5. The LLM answers based on your document — not just its training data

Think of it like giving the LLM a "cheat sheet" pulled from your PDF before it answers.