肖泽涛 0695f6f4cd fix(embedding): use model-level batch_size for provider-specific limits ... Root cause: DashScope embeddings accepts at most 10 inputs per request, but code used fixed batch_size=40, causing 400 Bad Request during indexing. Changes: - add batch_size to EmbedModelInfo with default 40 - set dashscope/text-embedding-v4 batch_size to 10 - persist batch_size in BaseEmbeddingModel and use it as default in batch/abatch encode - update Milvus, evaluation, and upload-graph embedding paths to read model-configured batch_size		2026-02-28 13:09:53 +08:00
..
bad_keywords.txt	fix(docs): 更新 README 和文档路径，添加 MinIO 存储模块文档	2025-09-23 10:48:44 +08:00
info.template.yaml	feat: 更新版本号至 0.5.0-beta	2026-01-24 12:06:49 +08:00
models.py	fix(embedding): use model-level batch_size for provider-specific limits	2026-02-28 13:09:53 +08:00