WeKnora/internal/models/embedding
begoniezhao 5082460cc0 fix(embedding): remove hardcoded TruncatePromptTokens in BatchEmbed
Remove the hardcoded TruncatePromptTokens: 512 limit from WeKnoraCloud
BatchEmbed to allow the API to use its default truncation behavior,
avoiding unexpected truncation of longer input texts.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-14 16:29:49 +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
azure_openai.go fix: gate Azure OpenAI dimensions support 2026-04-09 19:19:25 +08:00
azure_openai_test.go fix: gate Azure OpenAI dimensions support 2026-04-09 19:19:25 +08:00
batch.go refactor: Update tenant ID handling across the application 2025-11-25 16:30:54 +08:00
embedder.go feat: integrate ChatBot provider and docreader 2026-04-13 17:47:24 +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: gate Azure OpenAI dimensions support 2026-04-09 19:19:25 +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
weknoracloud.go fix(embedding): remove hardcoded TruncatePromptTokens in BatchEmbed 2026-04-14 16:29:49 +08:00