In this blog, I describe creating InferGPT, a personalized chatbot, using Python, FastAPI, and React without the use of LangChain. Our backend handles complex queries with a multi-agent system and Neo4j database, aiming to provide tailored responses.

The Scott Logic Blog offers insights, thought leadership, and technical expertise across various domains including software development, UX design, and financial services technology. Developers can explore articles on emerging technologies, industry trends, and software engineering best practices. Additionally, the blog covers case studies, project insights, and client success stories, providing  perspectives for technology professionals and enthusiasts.

Scott Logic

Developers are working on InferGPT, a personalized chatbot that knows its users and offers tailored responses. Instead of relying on LangChain, the team opted for React, FastAPI, and Neo4j to create a multi-agent system where each agent solves specific tasks using a large language model (LLM) and various tools. The backend design emphasizes minimizing LLM overuse, with traditional strategies connecting agents. This project aims to enhance the chatbot's engagement by inferring user preferences and involves iterative testing and future improvements in user interaction and agent creation.

Building a Multi Agent Chatbot Without LangChain