Skip to content

RAG and Semantic Search

40 hoursIntermediate7 modules

3 of 7 modules with a published syllabus

0 of 7 modules recorded

Syllabus

Covers the whole path from text to a grounded answer: text as data, embeddings and semantic search, end-to-end RAG — a module shared with Agentic AI — and classification/NER. The application layer comes in through AI APIs and prompt engineering, and the rigour through evaluating AI systems, without which a RAG system is not verifiable. Data collection and cleaning is included because the corpus is half the problem.

Modules of this programme

The same objects as the full curriculum. A module opened from any programme that contains it is the same module, with the same syllabus and the same status.

  • CORE-104Syllabus published

    Data: collection and cleaning

    Content
    Pandas, CSV/JSON/APIs, missing data, EDA
    Hands-on
    Clean and explore a real, messy dataset

    estimated price0 of 1 module published

  • NLP-101Syllabus published

    Text as data (tokens, cleaning, regex)

    Detailed syllabus not written yet

  • NLP-201Syllabus published

    Embeddings and semantic search

    Detailed syllabus not written yet

  • NLP-202Syllabus published

    End-to-end RAG (shared with Agentic AI)

    Detailed syllabus not written yet

  • NLP-203Syllabus published

    Classification and NER

    Detailed syllabus not written yet

  • CORE-205Syllabus published

    AI APIs and prompt engineering

    Content
    OpenAI/Anthropic/OSS, function calling, cost
    Hands-on
    A CLI app that calls an LLM through an API

    estimated price0 of 1 module published

  • CORE-304Syllabus published

    Evaluating AI systems

    Content
    Benchmarks, LLM evals, A/B testing, red teaming
    Hands-on
    Build an eval suite for an application

    estimated price0 of 1 module published

Not everything fits into 40 hours. State of the art, distributed training, interpretability, edge deployment and the five integrative projects exist only inside the complete tracks: Tracks