Early LLMs had context windows of approximately 4K tokens, which was too small to fit entire documents, forcing reliance on RAG systems.
factualpending
Speaker
Unidentified Speaker — Is RAG Still Needed? Choosing the Best Approach for LLMs [UabBYexBD4k]Evidence Quote
“Early LLMs had context windows that could maybe store like 4K of tokens. You couldn't fit a novel in there, let alone a corporate knowledge base. You basically had to use RAG.”
Created: 8/13/2026, 7:43:56 AM
Your notes
Loading notes...