This module lays the essential groundwork for using Chroma. Learners will start by understanding the "why" behind local vector databases and then dive into the "what" of Chroma's architecture and SDK. The module quickly transitions into a hands-on "how-to," guiding learners through the complete installation and setup of a persistent Chroma client. By the end of this module, you will have a fully operational local Chroma instance and your first collection, ready for data.

Ready to go beyond basic vector search? In this intermediate course you’ll build scalable Chroma databases, use metadata for precise filtering, design multi‑collection architectures, and create a Python ETL pipeline that ingests and organizes customer‑support tickets, delivering a production‑ready data‑management engine.

Vector Databases for Machine Learning: Integrate Embeddings and Chroma is an intermediate course for ML engineers and AI practitioners. You’ll build automated ingestion pipelines, connect OpenAI or HuggingFace embeddings to ChromaDB, troubleshoot dimension and encoding errors, and ensure production‑grade reliability for vector search.

Build Chroma Search is an intermediate, project‑based course for developers and aspiring ML engineers. You'll create a semantic search app using vector embeddings and Chroma, index documents with a third‑party model, expose a Flask API, measure MRR and precision@5, and deliver a portfolio‑ready, evaluated solution.

Boost RAG with Chroma is an intermediate, hands‑on course for developers and AI practitioners. You’ll build a Retrieval‑Augmented Generation pipeline using Chroma and LangChain, connect it to an LLM, evaluate hallucination reduction, and deliver a portfolio‑ready, enterprise‑grade generative AI solution.

In this project, you will design and implement a proof-of-concept knowledge base using ChromaDB to enable semantic search over corporate documentation. Running entirely within a cloud-based notebook (requiring no external LLM APIs), you will build a complete pipeline. This project simulates a real-world ML engineering task and produces a fully documented, portfolio-ready deliverable demonstrating your applied vector database skills.