Weaviate Podcast The Future of Search with Nils Reimers and Erika Cardenas - Weaviate Podcast #97!
18 snips
Jun 11, 2024 Join the 97th Weaviate Podcast with Nils Reimers and Erika Cardenas as they delve into AI-powered search technology. Topics include Compass embeddings, multi-aspect chunking, ColBERT, RAG Evaluation, and more. Discover the challenges and solutions in embeddings, LLMs, smart chunking strategies, evaluating chatbots, and optimizing vector databases with quantization methods.
AI Snips
Chapters
Transcript
Episode notes
Embeddings as Soup
- Standard embeddings struggle with longer texts, becoming an unspecific "soup" of blended information.
- This makes finding precise details difficult, as crucial nuances get lost in the mix.
Multi-Aspect Embeddings
- "Compass," Cohere's new embedding model, uses a multi-aspect approach, creating a knowledge graph of dense embeddings.
- This allows for finer searches by representing different aspects of an item separately.
Apple Annual Report Example
- Nils Reimers uses the "Apple annual report" example to illustrate the limitations of chunking in embeddings.
- Chunking can create out-of-context issues, where important information is missed.