all-MiniLM-L6-v2 Silently Truncates at 256 Tokens: 38% of My Chunks
The question was simple: "How do I rotate the staging API key?" The answer was in my runbook index, word for word. My RAG pipeline returned a passage about rotating log files instead. I opened the chunk that should have won. The answer was there, in the last third of it. The embedding model had nev…
Read the full story at DEV Community — Machine Learning ↗
Timeline · 1 report
- 2026-11-08 07:14 · DEV Community — Machine Learning
all-MiniLM-L6-v2 Silently Truncates at 256 Tokens: 38% of My Chunks