Long-Context LLMs vs. RAG: Rivals or Allies?

Weaviate Podcast hosted UC Berkeley PhD Siddharth Gollapudi to discuss whether long-context LLMs and RAG compete or complement each other, including how the 0.6B model BlockSearch tackles million-token retrieval.

2026-10-01 ~ 2026-10-01 · 2 related posts

• BlockSearch: a 0.6B in-context retriever rivals dense retrieval at million-token scale — CShorten30 · 2026-10-01
• Weaviate Podcast: UC Berkeley PhD on whether long-context LLMs kill or improve RAG — CShorten30 · 2026-10-01