Open-source course repository for building a Second Brain AI assistant using LLMs, RAG, and agents. Provides two Python applications: offline data pipelines and online inference, with multiple integrations and 6 modules.
Collecting history — the radar snapshots this repo daily. The trend line appears after 3 days of data (1 so far).
What it is
This is an open-source course repository intended to teach building a production-ready agentic RAG and LLM system using LLMOps and ML systems best practices. The course comprises 6 modules and aims to help readers build an end-to-end AI assistant that interacts with a personal knowledge base (the Second Brain).
How it works
The project describes two Python applications: offline ML pipelines (data pipelines, RAG, fine-tuning, etc.) and an online inference pipeline (the Second Brain AI assistant). It emphasizes pipeline orchestration and tracking with ZenML, RAG architectures, and production-oriented practices. The README lists tools and integrations across OpenAI, Hugging Face, MongoDB, ZenML, Opik, Comet, Unsloth, and ZenML for orchestration and evaluation.
Getting started
Getting started guidance points to per-application documentation:
- Offline ML Pipelines (data pipelines, RAG, fine-tuning, etc.) -> apps/second-brain-offline
- Online Inference Pipeline (Second Brain AI assistant) -> apps/second-brain-online
The repository notes that the course is open-source and free, with some cost considerations for tools like OpenAI API and Hugging Face endpoints. It also mentions that you can download Notion data from a public S3 bucket for ease of use.
Recent releases
Latest releases: none.
Traction
Stars: 2948. Forks: 511. Open issues: 6.
License
MIT