Multimodal RAG

A linear, one-concept-per-lesson path through Multimodal RAG, retrieval-augmented generation extended to cover images as well as text, built from scratch with no framework, from your first multimodal generate_content call to a complete FastAPI service that returns cited answers grounded in both text and images. 26 lessons · 3 tiers.

Prerequisites: Completion of Naive RAG, or already comfortable with embeddings, cosine similarity, and top-k retrieval - this course reuses that pipeline unchanged for text and adds one new idea, captioning-then-embed, for images.

Lessons use Google's Gemini free tier (gemini-embedding-001 for embeddings, gemini-3.5-flash-lite for chat and captioning, the latter via native multimodal image input), the same models as this site's other RAG courses. No Docker and no database through most of the course; the Advanced tier graduates the mixed store to a local ChromaDB instance, still no server or account required.

Built directly on google-genai, Gemini's native multimodal SDK - the captioning-then-embed step this course adds runs entirely through its image-input API.