AI Resume Chat with LLM and RAG (Portfolio Assistant)

Built a sitemap-driven portfolio assistant that answers recruiter questions with grounded, source-linked responses. This project demonstrates practical execution from architecture and implementation to measurable delivery outcomes.

Personal ProjectsYear 2026

Project Overview

Objective

Built a sitemap-driven portfolio assistant that answers recruiter questions with grounded, source-linked responses.

Stack

Next.jsTypeScriptOpenAI APItext-embedding-3-smallFAISSGPT-4o-miniGPT-4.1GPT-5

Delivery highlights

  • Developed an AI-powered assistant that answers recruiter questions about my resume and portfolio using Next.js, TypeScript, OpenAI API, LLMs, and vector search. The system crawls content from all portfolio pages through the sitemap, extracts and cleans the text, and splits it into chunks before generating embeddings using OpenAI textembedding-3-small, which are stored in a vector database for fast semantic retrieval. When a user submits a question, the query is converted into an embedding and matched with the most relevant content using top-k retrieval, after which a selectable LLM (GPT-4o-mini, GPT-4.1, GPT-5) generates a summarized answer grounded only in the retrieved context. The response also includes source references and relevance information, allowing users to trace the answer back to the original portfolio content for better transparency and reliability.
Link DemoBack to Topic ProjectsBack to All Projects

Related Projects

3 items

AI Document Question Answering System with RAG and LLM

Personal ProjectsYear: 2026

Built PDF upload and natural language QA system with retrieval-augmented generation.

AI Meeting Transcription, Summarization & Q&A System (RAG + LLM):

Personal ProjectsYear: 2026

Built an end-to-end system for meeting transcription, summarization, and context-aware Q&A using Whisper, Qdrant, and LLMs, with FastAPI + React for real-time processing and interactive querying.

AI Document Search & Question Answering System (RAG)

Personal ProjectsYear: 2026

Built a multimodal AI system for document, audio, and image understanding with natural language question answering using retrieval-augmented generation (RAG).