Enhance dialog context handling for Text2SQL queries by integrating session history. Introduce new methods for summarizing previous assistant messages and determining if the last interaction was a data query. Update environment configuration for embedding options and improve error handling in SQL generation. Add user-facing delivery messages for successful SQL execution. This update supports more coherent follow-up questions and improves user experience in conversational interactions.

This commit is contained in:
陈辅元
2026-04-14 18:02:12 +08:00
parent 026d3bf88c
commit ca8bc5e7de
87 changed files with 5808 additions and 6351 deletions
+1 -1
View File
@@ -17,7 +17,7 @@ class Settings(BaseSettings):
max_tokens: int = 4096
# Embedding配置
embedding_model_path: str = "./data/models/Qwen3-Embedding-0.6B"
embedding_model_path: str = "" # 仅本地 Embedding 时使用;默认走远程 API
vector_dim: int = 2048
use_local_embedding: bool = True