Reduce chunk size to fit all-MiniLM-L6-v2 token limit (256 max)

Verschifft

18. März 2026 um 02:54 UTC

Autor

Kamo

Ausschuss

a794078

Chunk target was 2000 chars (~512 tokens) but the embedding model only accepts 256 tokens, causing 413 validation errors. Reduce to 800 chars (~200 tokens) with 100 char overlap.