Ollama /api/embed Silently Dropped 45% of My Document
On a machine without a GPU, Ollama 0.40.14 loaded qwen3-embedding:0.6b with a 4,096-token context, and /api/embed cut my 7,510-token document down to 4,095 tokens with no error, no warning and no flag in the response. Send "truncate": false so an overlong input fails with HTTP 400, and split docume…
Read the full story at DEV Community — AI ↗
Timeline · 1 report
- 2026-11-15 05:33 · DEV Community — AI
Ollama /api/embed Silently Dropped 45% of My Document