Semantic Search and Information Retrieval using GenAI

Course details

Generative AI is a win for traditional search technologies, especially when you use its power in tandem. This technical course designed for data professionals shows you how to design, implement, and evaluate sophisticated search solutions that combine knowledge graphs, AI, and traditional search technologies. Learn how to make architectural decisions, implement security measures, and establish effective KPIs for enterprise-scale search systems. Along the way, instructor Ashleigh Faith emphasizes practical implementation, security considerations, and performance optimization while providing hands-on experience with modern search architectures.

Concepts

0. Introduction

01 - The power of semantic search and information retrieval
02 - What you need to know for the course

1. Selecting Search

03 - Use case - Two Trees Olive Oil
04 - What kind of search do you need
05 - Deciding if you need a vector database, a knowledge graph, or both
06 - What about non-LLM AI for semantic search

2. Building Blocks of Semantic Search

07 - What is information retrieval
08 - What is semantic search
09 - What are knowledge graphs, and how are they used in semantic search
10 - What are vector embeddings

3. Enhancing Semantic Search

11 - What is semantic similarity
12 - How is semantic similarity calculated
13 - Weights, boosts, and blocks
14 - User and localization data
15 - Walking the graph
16 - Other factors for semantic similarity
17 - Search performance in semantic search
18 - Automated and human search relevancy assessment

4. Optimizing Data and Entities for Semantic Search

19 - Text and document quality
20 - Entity recognition and disambiguation
21 - Alternative search methods

5. Mastering Semantic Search with AI, Human Feedback, and Key Data

22 - Where does search fit in an AI or data pipeline
23 - How can AI use both vector and graph data for semantic search
24 - How can key performance indicators (KPIs) be used in semantic search

6. Bridging Text and Graphs for Smarter Semantic Search

25 - Loading our sample model and data into Stardog
26 - Building a graph query
27 - Query options
28 - Using graph data to ground an AI response
29 - Comparison GraphRAG grounding alone vs. RAG with semantic knowledge graphs

Conclusion

30 - Continuing your learning journey