陈辅元 85ad31348e Implement follow-up detection in dialog context to prevent context pollution in multi-topic conversations. Introduce is_likely_follow_up function to determine when to inject session history based on user input. Adjust _load_session_text2sql_context to conditionally include context based on follow-up status, enhancing SQL generation accuracy. Update relevant API endpoints to pass user text for improved context handling.

2026-04-15 17:33:07 +08:00

..

embeddings

Implement follow-up detection in dialog context to prevent context pollution in multi-topic conversations. Introduce is_likely_follow_up function to determine when to inject session history based on user input. Adjust _load_session_text2sql_context to conditionally include context based on follow-up status, enhancing SQL generation accuracy. Update relevant API endpoints to pass user text for improved context handling.

2026-04-15 17:33:07 +08:00

Example

first commit

2026-04-10 16:52:07 +08:00

experiences

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.

2026-04-14 18:02:12 +08:00

schemas

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.

2026-04-14 18:02:12 +08:00