📘 Description
This project demonstrates a modular approach to building a multilingual translator using the LangChain framework and OpenAI’s GPT-4o-mini model. Designed for the MSDS 442 course at Northwestern University, the script highlights secure API integration, prompt engineering, and real-time language translation using large language models (LLMs).

More importantly, this project reinforces the idea that ChatGPT’s GUI is not designed to program business process workflows. Instead, we must create explicit reasoning and action workflows — like flowcharts or algorithms — to guide AI agents. This is why we leverage frameworks such as LangChain, LangGraph, or LlamaIndex, which act as bridges between our agent logic and the backend LLMs (e.g., OpenAI, Replicate, or Ollama).

📘 Description

This project builds on Module 1 by showcasing a modular agent framework using OpenAI’s GPT-4o-mini for multi-step problem-solving. Created for MSDS 442 at Northwestern, it follows a structured reasoning loop—Thought, Action, PAUSE, Observation—and integrates tools like LangChain for dynamic data retrieval and calculations. The project highlights how well-structured workflows enable AI agents to reason clearly and handle complex tasks beyond simple Q&A.

📘 Description

This project showcases the creation of a stateful, memory-enabled AI agent using the LangGraph framework from LangChain. Built as part of MSDS 442 at Northwestern, this tutorial walks through how to wire up a language model, connect external tools (like search), stream responses, and persist memory across conversation threads — all in one cohesive agent pipeline.

⸻

🔧 Features

• LLM Integration: GPT-4o-mini via LangChain’s OpenAI wrapper
• Tool Calling: Integrated with Tavily’s search API for live web results
• ReAct Agent Framework: Uses LangGraph’s create_react_agent() to reason + act in steps
• Memory Management: Threaded memory via MemorySaver for multi-turn conversation flow
• Streaming UX: Live stream of responses and tokens for enhanced interactivity
• Conversation Control: Scoped sessions using thread_id to simulate new or continued chats

⸻

📘 Description

This project showcases the creation of a stateful, memory-enabled AI agent using the LangGraph framework from LangChain. Built as part of MSDS 442 at Northwestern, this tutorial walks through how to wire up a language model, connect external tools (like search), stream responses, and persist memory across conversation threads — all in one cohesive agent pipeline.

⸻

🔧 Features

• LLM Integration: GPT-4o-mini via LangChain’s OpenAI wrapper
• Tool Calling: Integrated with Tavily’s search API for live web results
• ReAct Agent Framework: Uses create_react_agent() to reason + act in steps
• Memory Management: Threaded memory via MemorySaver for multi-turn conversation flow
• Streaming UX: Live stream of responses and tokens for enhanced interactivity
• Conversation Control: Scoped sessions using thread_id to simulate new or continued chats

⸻