WeKnora/internal/models/embedding
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
..
aliyun.go feat: 新增对多家平台的模型适配 2025-12-29 12:18:42 +08:00
batch.go refactor: Update tenant ID handling across the application 2025-11-25 16:30:54 +08:00
embedder.go feat: support NVIDIA model API 2026-03-13 18:14:08 +08:00
jina.go feat: 新增对多家平台的模型适配 2025-12-29 12:18:42 +08:00
nvidia.go feat: support NVIDIA model API 2026-03-13 18:14:08 +08:00
ollama.go feat: Use num_ctx instead of truncate for embedding truncation 2026-02-04 14:24:01 +08:00
openai.go fix: enforce 7500 char limit in chunker to prevent embedding API errors 2026-03-15 23:59:34 +08:00
volcengine.go feat: 新增对多家平台的模型适配 2025-12-29 12:18:42 +08:00