Back to feed
Dev.to
Dev.to
7/19/2026
How I Built a RAG Chatbot Into My Portfolio with LangGraph, PGVector & MCP

How I Built a RAG Chatbot Into My Portfolio with LangGraph, PGVector & MCP

Short summary

Rehbar Khan breaks down how he built an AI terminal chatbot for his portfolio using LangGraph, pgvector on Neon Postgres, and GitHub MCP for live data. The architecture uses a score-threshold retriever to prevent hallucinations, a LangGraph StateGraph for tool routing, and Redis for session memory. Code snippets cover chunking, retrieval, graph construction, and MCP client setup.

  • •RAG chatbot architecture with LangGraph, pgvector, and MCP integration
  • •Score-threshold retrieval drops irrelevant matches to prevent hallucinations
  • •GitHub MCP tool fetches live activity; Redis handles conversation memory

Generated with AI, which can make mistakes.

#ai-tools#ai-agents#open-source
Read full article at Dev.to

Is this a good recommendation for you?

Comments

Failed to load comments. Please try again.

Explore more

Anatomy of a Full RAG Application: Every Concept, One Self-Hosted Stack
Dev.to
The original title is "RAG in Laravel: Embeddings and pgvector for a Knowledge-Base Bot"
Dev.to
I Built a Simple RAG App with LangChain, OpenAI, and Pinecone
Dev.to
How I Built a RAG-Powered Conversational Assistant for Odoo ERP
Dev.to