RAG Project – Module 1 (Agentic AI Developer Certification)

Project Overview
This project implements a Retrieval-Augmented Generation (RAG) system as part of the ReadyTensor Agentic AI Developer Certification.
The goal was to combine document retrieval with large language model (LLM) generation to improve response accuracy and context-awareness.

Objectives

• Build a system that can retrieve relevant context from a document store.
• Connect the retriever with a LLM for answer generation.
• Demonstrate how RAG improves response accuracy compared to LLM-only outputs.
• Provide a working implementation with clear documentation and reproducibility.

Tech Stack

• Python 3.10+
• LangChain for RAG pipeline
• OpenAI API / Hugging Face models
• FAISS for vector search
• Streamlit (optional, for simple demo UI)
• GitHub for version control & submission

System Architecture

graph TD
    A[User Query] --> B[Retriever]
    B --> C[Vector DB - FAISS]
    C --> D[Relevant Context]
    D --> E[LLM Generator]
    E --> F[Final Answer]

| Header 1 | Header 2 |
| --- | --- |
| Cell 1 | Cell 2 |
| Cell 3 | Cell 4 |

- [x] Task 1
- [ ] Task 2
- [ ] Task 3






<!-- RT_DIVIDER -->

<!-- RT_DIVIDER -->