Developer Tutorial: Building LLM Tool-Calling Agents with LangChain and Groq

A developer tutorial published on DEV Community walks through setting up a Python virtual environment and integrating Groq's cloud LLM infrastructure with LangChain to build a tool-calling agent. The guide demonstrates how to define custom tools — such as a weather lookup and a number adder — using LangChain's @tool decorator and bind them to a Groq-hosted language model. The agent follows a two-step invocation pattern: the model first decides whether to call a tool or answer directly, then uses the tool's output to generate a final response. Messages are managed as a Python list, allowing tool results to be appended before a second model call produces the answer. The tutorial also includes a sample requirements file listing key dependencies such as langchain-groq, fastapi, chromadb, and httpx.