Skip to main content
grasp.study
About
Explore
Pricing
Log in
Try it for free
Back to course
👋
Welcome to a Grasp lesson
Create a free account
to keep studying and create your own study path.
Build AI agent for code generation
·
Module 2
Retrieval-Augmented Generation (RAG) Principles
1
Understanding RAG: Grounding LLMs in Specific Knowledge
Explain the core concept of RAG and its necessity for grounding LLMs in specific knowledge.
2
Text to Vector: Embedding for Semantic Search
Describe how text is converted into numerical vector embeddings for semantic search.
3
Vector Store Fundamentals
Explain the function of a vector store in indexing, storing, and retrieving embeddings.
4
Chunking Strategies for RAG
Apply various chunking strategies to effectively segment long documents for RAG.
Building Your First RAG Pipeline
Orchestrate the fundamental RAG pipeline: retrieve relevant chunks for a query and augment the LLM prompt.
6
Evaluating RAG Output & Diagnosing Failures
Assess the quality of a RAG pipeline's output and diagnose common failure modes.
Previous module
Foundations of AI Agents and LLMs
Next module
The Atlassian AI Ecosystem: Jira, Forge, and Rovo