 陈辅元
|
3891aae7fe
|
Refactor api_server.py to import environment setup and schema loading from bootstrap.py, enhancing modularity. Introduce a new function in Text2SQLOrchestrator to prioritize VCUserAccessibleFunction in table selection, improving SQL generation accuracy. Update validation logic to enforce restrictions on CJK characters in SQL string literals, ensuring compliance with business rules. Enhance prompts to clarify SQL generation constraints regarding date conditions and CJK usage.
|
2026-04-17 15:15:01 +08:00 |
|
|
陈辅元
|
4ee0ad2eec
|
Refine SQL output formatting in prompts to enforce pure text SQL without Markdown code fences. Allow inline comments using -- and update few-shot selector to reflect these changes in output presentation. Enhance clarity on SQL output requirements for better adherence to standards.
|
2026-04-16 16:40:22 +08:00 |
|
|
陈辅元
|
bff5f85d60
|
Enhance SQL generation and streaming capabilities in the API server. Introduce optional parameters for streaming throttle and SQL stream granularity in NLChatRequest. Implement new functions for iterating SQL generation content pieces and adjusting streaming behavior based on user-defined settings. Update prompts for few-shot SQL adaptation and improve logging for SQL generation processes. Refactor orchestrator methods to support streaming responses and integrate few-shot SQL conditions. Update impact analysis documentation to reflect these changes.
|
2026-04-16 13:48:44 +08:00 |
|
|
陈辅元
|
695356a496
|
加入日志管理
|
2026-04-16 10:53:10 +08:00 |
|
|
陈辅元
|
2d0b1ab36f
|
Refactor embedding configuration to remove local model support, transitioning to a unified remote API approach. Update environment variables and documentation accordingly. Enhance error handling in the orchestrator and related modules to reflect these changes. This update simplifies the embedding process and improves overall system reliability.
|
2026-04-15 09:49:18 +08:00 |
|
|
陈辅元
|
ca8bc5e7de
|
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 |
|
|
陈辅元
|
cc83fe963a
|
0.1.1 暂存
|
2026-04-14 10:28:22 +08:00 |
|