$ show huggingface/agents-course
This repository is the source code for the Hugging Face Agents Course, a structured educational curriculum teaching the fundamentals and practical implementation of AI agents. The course is organized into units covering agent theory (ReAct, tool calling, observations), framework-specific tutorials (smolagents, LlamaIndex, LangGraph), agentic RAG, observability and evaluation, and a final project based on the GAIA benchmark. The content is delivered as MDX files with embedded code examples, quizzes, and links to interactive notebooks, and is translated into multiple languages (English, Spanish, French, Chinese, Korean, Russian, Vietnamese). While primarily an educational resource, the repository also contains reusable scripts for automated translation of course content and for pushing quiz data to the Hugging Face Hub, as well as CI/CD workflows for building documentation. The codebase is not a production application or a data pipeline, but rather a hybrid of educational content and supporting tooling for course maintenance.
The LLM identified 3 files worth highlighting for reuse:
A self-contained script that uses Hugging Face InferenceClient (DeepSeek-R1) to translate MDX course content into multiple languages. It is parameterized with language-specific modules (e.g., vi.py) and can be extracted and adapted for any multilingual documentation project. Demonstrates a clean ETL pattern for automated content translation.
A script that reads structured quiz data from JSON files and pushes it to the Hugging Face Hub for use in interactive quiz Spaces. It is reusable for any assessment deployment workflow and demonstrates a simple, idempotent data push pattern.
A JSON file containing multiple-choice quiz questions with choices, correct answers, and explanations. This data format is a reusable template for creating and deploying assessments in educational courses, and can be easily adapted for other subjects.