wip Self-Correcting
Recursive Portfolio Chatbot
A self-correcting RAG agent that answers questions about my background using a LangGraph correction loop — with a 'See Thoughts' toggle showing internal reasoning.
LangGraphVercel AI SDKPostgrespgvectorReact
An “About Me” page on steroids. Instead of a static bio, visitors chat with an agent that retrieves context from my resume, GitHub activity, and project descriptions.
The Correction Loop
The agent uses a LangGraph correction loop:
- Retrieve — fetch context from pgvector embeddings of my resume and GitHub
- Grade — a grader LLM asks: “Does this actually answer the question?”
- Rewrite — if “No”, the query is rewritten and the loop retries
- Respond — only answers the visitor when confident
”See Thoughts” Toggle
A toggle next to the chat exposes the agent’s internal JSON reasoning trace in real time — showing exactly which retrieval step fired, what the grader scored, and why the query was rewritten. This is the transparency feature that makes it a portfolio piece, not just a chatbot.
Tech Choices
- LangGraph for the stateful correction loop
- Vercel AI SDK for streaming responses to the React island
- Postgres + pgvector for semantic memory (resume, GitHub, project writeups)