Building Applications with Vector Databases - Syllabus

• Introduction
  • Overview of vector databases and their applications
  • Using embeddings for similarity and RAG applications
• Semantic Search
  • Creating a search tool focusing on content meaning
  • Implementation with a user Q/A dataset
• Retrieval Augmented Generation (RAG)
  • Enhancing LLMs by integrating external content
  • Example with Wikipedia data for improved responses
• Recommender Systems
  • Combining semantic search and RAG for recommendations
  • Example application with news articles
• Hybrid Search
  • Building a multimodal search app combining text and images
  • Application example with eCommerce data
• Facial Similarity Search
  • Creating an app to compare facial features
  • Implementation example using public figure database
• Anomaly Detection
  • Building an app to identify unusual patterns in data
  • Example with network communication logs
• Conclusion
  • Summary of applications and future ideas
  • Exploring additional use cases for vector databases