Scalable Rag Pipeline

Enterprise Agentic RAG Platform

   

Table of Contents

1. System Overview
2. RAG Methodologies & Agentic Logic
3. Prerequisites & Tooling
4. Phase 1: Infrastructure Initialization (Terraform)
5. Phase 2: Cluster Bootstrapping (Kubernetes)
6. Phase 3: The Data Plane (Ray & Databases)
7. Phase 4: The Control Plane (API Deployment)
8. Phase 5: Data Ingestion Pipeline
9. Validation & Testing
10. Cost Optimization & Scaling
11. Troubleshooting

1. System Overview

This repository contains the source code and Infrastructure-as-Code (IaC) definitions for a production-grade **Retrieval-Augmented Generation (RAG)** system. Unlike standard RAG implementations, this platform utilizes an **Agentic Architecture** (via LangGraph) to perform multi-step reasoning, query expansion, and hybrid retrieval (Vector + Knowledge Graph).

High-Level Architecture

The system is decoupled into two primary processing planes:

1. Control Plane (The Brain): Handles HTTP requests, state management, agent orchestration, and business logic. Runs on low-cost CPU nodes.
2. Data Plane (The Muscle): Handles heavy compute tasks including LLM Inference, Embedding generation, and Graph Extraction. Runs on autoscaling GPU nodes via Ray.

<