Enhance your email assistant by integrating external documents and context. Learn to use Retrieval-Augmented Generation (RAG) to make agent responses more informed and personalized.
Overview
Syllabus
- Unit 1: Introducing Documents and Context for RAG
- Creating Your First Context Document
- Reading External Documents
- Preparing Documents for RAG Systems
- Inspecting the Context Document
- Unit 2: Chunking Documents for Efficient Retrieval
- Splitting our Context Document
- Splitting the Document with a Medium Chunk Size
- Visualizing Chunk Boundaries and Overlaps
- Fixing the Chunking Error
- Unit 3: Embedding Chunks and Storing in a Vector Database
- Creating Text Embeddings
- Initializing the Database
- Preparing the Database Index
- Writing to the Vector Database
- Adding Metadata to the Database
- Unit 4: Querying for Relevant Context with Embeddings
- Embedding a Singular String
- Finding Relevant Email Context
- Semantic Search for Context
- Unit 5: Integrating Retrieved Context into Agent Responses
- Creating a Vector Query Tool
- Adding the Query Tool to our Agent
- Informing our Agent of the Tool
- Using our RAG-Powered Agent
Related Courses
-
Retrieval Augmented Generation (RAG) with LangChain
-
Foundations of Retrieval Augmented Generation (RAG) Systems
-
Large Language Models (LLMs) and Retrieval Augmented Generation (RAG)
-
Building a RAG-Powered Chatbot with LangChain and TypeScript
-
Retrieval Augmented Generation (RAG)
-
Foundations of Retrieval Augmented Generation Systems with Rust
4.0
Related Articles
-
12 Best Retrieval-Augmented Generation (RAG) Courses in 2026
-
[2026] Unlock 2000+ Free Certificates: Master Tech & Soft Skills with CodeSignal Learn
-
Become a Supercommunicator: Practical Skills for Better Conversations
-
CodeSignal – The Duolingo of Coding Practice
-
6 Best AI Agent Courses for Beginners and Non-Coders in 2026
-
9 Best Vector Database Courses to Implement AI’s Searchable Memory
