Project Case Study

Source Stream

Enterprise RAG Ingestion & Search Platform

Ravi Rai
3 min read

Modular Retrieval Augmented Generation platform that ingests PDFs and documentation for semantic search using LangChain, FastAPI, and Qdrant.

Overview#

1

Built a modular Retrieval Augmented Generation platform that ingests local PDFs and recursively crawls documentation websites before chunking, embedding, and indexing content for semantic search.

2

Implemented semantic retrieval using LangChain, Gemini embeddings, and Qdrant Cloud with session isolated vector collections for multi-tenant document indexing.

3

Added query intent routing, prompt injection detection, toxicity filtering, and groundedness evaluation to reduce hallucinations and reject unsafe requests.

4

Built a React frontend with streaming responses, source citations, and an execution trace displaying pipeline stages, latency, and token usage for debugging.

5

Designed a decoupled FastAPI backend exposing REST APIs for document ingestion, retrieval, indexing, and chat workflows following a modular service architecture.

6

Automated testing and deployment with GitHub Actions, deploying the backend to Google Cloud Run and the frontend to Firebase Hosting.

Tech Stack#

Python

Core language

FastAPI

REST API backend

React

Frontend UI

Vite

Build tool

Tailwind CSS

Styling

LangChain

RAG orchestration

Gemini Embeddings

Vector embeddings

Groq

Fast LLM inference

Qdrant Cloud

Vector database

R

REST APIs

Architecture

Pytest

Testing framework

Docker

Containerization

Google Cloud Run

Backend hosting

Firebase Hosting

Frontend hosting

GitHub Actions

Automated pipelines

LLM-as-Judge (Evals)

Evaluation

CI/CD

Continuous integration

Ravi Rai

Ravi Rai

AI Engineer & Full Stack Developer · Germany

Expert in Generative AI, LLMs, and Data Engineering. Passionate about building intelligent, agentic systems and scalable full-stack applications.

More about the author →
© 2026 Ravi Rai. All rights reserved.|Privacy