RAG with local embeddings
Build a small file-based retrieval pipeline and measure whether evidence is found before judging generated answers. Requires Node.js 22+, JavaScript and local Ollama. Download a local embedding model and text model; verify their licenses and hardware fit. No cloud API is required; hardware, electricity and rented infrastructure still have costs.
Course outline
Free lessons: 2What you will learn
- Create a traceable corpus
- Chunk without losing meaning
- Generate and store local embeddings
- Retrieve and inspect ranked evidence
- Generate answers with checked citations
- Evaluate retrieval and maintain the index
Frequently asked questions
How is learning structured?
Lessons in this course: 6. Work through explanations, complete practical assignments and check understanding with quizzes. Lesson topics are listed in the course outline.
What can I try for free?
Open lessons: 2. They are marked in the course outline. You can read open materials before registering; an account is needed to save progress across devices.
Which languages can I study in?
Ukrainian, Russian, English and Italian. Switching language preserves course progress for a registered user.