RAG with vector databases: Advanced strategies for AI optimization

Contents

• Introduction Introduction

  • RAG with vector databases: Advanced strategies for AI optimization

    34s
  • What you should know

    3m 22s
  • Setting up your exercise files

    1m 25s
• 1. Optimizing RAG 1. Optimizing RAG

  • Introduction to preprocessing for RAG

    4m 57s
  • Chunking considerations

    5m 12s
  • Chunking examples

    4m 32s
  • Introduction to embeddings

    9m 50s
  • Embedding examples

    2m 57s
  • Metadata

    3m 12s
  • Demo: Chunking

    2m 32s
  • Demo: Metadata

    1m 23s
  • Demo: Embed and store

    2m
  • Demo: Querying

    1m 8s
  • Demo: Adding the LLM

    2m 1s
  • Challenge: Cite your document sources

    47s
  • Solution: Cite your document sources

    59s
  • Challenge: Change the chunk size

    44s
  • Solution: Change the chunk size

    55s
• 2. Image Search with Vector Databases 2. Image Search with Vector Databases

  • Introduction to vector embeddings for images

    2m 8s
  • Vision models 101

    4m 58s
  • Demo: Getting semantic vectors

    57s
  • Demo: Storing image vectors

    1m 10s
  • Demo: Comparing images semantically

    46s
  • Challenge: Find the dog most similar to a cat

    42s
  • Solution: Find the dog most similar to a cat

    1m 46s
• 3. Multimodal RAG with Vector Databases 3. Multimodal RAG with Vector Databases

  • Introduction to the types of multimodality

    2m 23s
  • Ways to do multimodal RAG

    4m 13s
  • Introduction to multimodal embedding models

    3m 4s
  • Demo: Embedding and storing data

    40s
  • Demo: Query images with text

    3m 5s
  • Challenge: Find anomalies in your embeddings

    1m 24s
  • Solution: Find anomalies in your embeddings

    2m 3s
• Conclusion Conclusion

  • Next steps

    26s