WeKnora/internal/models
ChenRussell 0fe5d67b6a fix: enforce 7500 char limit in chunker to prevent embedding API errors
Prevents 400 Bad Request errors when uploading documents with large
tables or code blocks by adding hard limits in buildUnitsWithProtection
and mergeUnits functions.
2026-03-15 23:59:34 +08:00
..
chat feat: NVIDIA chat model API support custom endpoint 2026-03-13 18:14:08 +08:00
embedding fix: enforce 7500 char limit in chunker to prevent embedding API errors 2026-03-15 23:59:34 +08:00
provider fix: NVIDIA VLM model API default BaseURL 2026-03-13 18:14:08 +08:00
rerank feat: support NVIDIA model API 2026-03-13 18:14:08 +08:00
utils refactor: Update function signatures across multiple files to improve readability by adding context parameters and enhancing code structure 2025-11-28 16:17:52 +08:00
vlm feat: introduce WeKnora Lite edition with lightweight configuration and deployment 2026-03-02 21:21:49 +08:00