Generative AI RAG Pipeline using LLaMA & FAISS

Inspiration: The project was inspired by the growing need for efficient, privacy-preserving AI systems that can answer questions based on personal or domain-specific documents without relying on external APIs.

What it does: This Generative AI RAG Pipeline processes user-provided documents (text and PDF files), converts them into vector embeddings, stores them in a FAISS index for fast similarity search, retrieves relevant context based on queries, and generates natural language answers using a local LLaMA model via Ollama.

How I built it: I built the system using Python with key libraries: LangChain for the RAG pipeline, Sentence Transformers for embeddings, FAISS for vector storage, PyPDF for document parsing, and Ollama for running LLaMA locally.

Built With

• api
• faiss
• faiss-(for-vector-storage-and-search)
• langchain
• llama
• llamaindex
• llamaindex-(for-indexing)
• llm
• pypdf
• pypdf-(for-document-parsing)
• python
• sentence-transformers-(for-embeddings)