Back to Portfolio
Adaptive RAG System
Generative AI
Intelligent RAG system with query routing, document grading, hallucination detection, and multiple UI options — built with LangGraph.
The Challenge
Standard RAG pipelines lack intelligence about when to retrieve, how to grade document relevance, and whether generated answers contain hallucinations.
The Solution
Built an adaptive RAG system using LangGraph that intelligently routes queries, grades retrieved documents for relevance, detects hallucinations in generated answers, and falls back to web search when needed.
Tech Stack
LangGraphLangChainChromaDBTavilyStreamlitGradioFlask
Key Features
- Intelligent query routing
- Document relevance grading
- Hallucination detection
- Web search fallback
- Multiple UI options (Streamlit, Gradio, Flask)
Demo
Related Projects
BusinessChat.io
BusinessChat.io — RAG & Agentic Chatbot
LLM-based chatbot with RAG and agentic flows for a business communication platform.
Generative AI
LangGraphRAGLLM APIs
View Case Study →
Agentic RAG
5-node workflow with document grading and query rewriting using LangGraph.
Generative AI
LangGraphLangChainFlask
Live Video Event Alert
VLM-based real-time video monitoring and alerting system.
Generative AIComputer Vision
NVIDIA NIMsGradioOpenCV