Project Motivation and Overview
I built this website to create an interactive way to engage with my resume. After conversations with friends I had the idea to use a LLM (Large Language Model) to filter and retrieve relevant information answering all questions in one place.
The current version of the chatbot runs local models through Ollama and interacts with this website through a FastAPI backend. Questions are preprocessed to search for topic areas and skills before searching a local vector-based document retrieval system for relevent context. Responses are guided with prompt engineering with final answers returned to the user (You!)
Key Skills
This project involved a combination of FastAPI for backend development, Ollama for local language model inference, and ChromaDB for vector-based document retrieval. I worked extensively with Python to develop the API and implemented prompt engineering techniques to refine the chatbot’s responses for improved accuracy and relevance. Additionally, I integrated the chatbot with my Webflow website, ensuring seamless user interaction while maintaining structured and precise resume data retrieval.
