This project extends a Retrieval-Augmented Generation (RAG) pipeline into a stateful, conversational assistant using LangChain, LangGraph, and OpenAI’s GPT-4o-mini. Designed for the MSDS 442 course at Northwestern University, it builds on previous modules by introducing agent reasoning, memory persistence, and multi-step retrieval workflows.

This reinforces the principle that AI systems are most powerful when embedded into structured, state-aware workflows, not standalone black boxes. LangGraph offers a clean architecture to reason over conversational history, perform multi-step tool calls, and allow LLMs to act as autonomous decision-makers.

Features

Key Insight

Agents are ideal for dynamic and ambiguous queries. This project illustrates how LLMs can be embedded in intelligent systems that retrieve, reason, and respond across evolving conversations, making them more like collaborative assistants than static tools.

View the source code on GitHub

View on GitHub →