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
|
df33657099
|
Enhance LLM integration by adding OpenAI client support and enabling dynamic routing between DeepSeek and OpenAI services. Update environment configuration to include LLM_SERVICE_CODE for service selection, and modify API server to accommodate new request parameters for language and model. Implement streaming response improvements for chat interactions, allowing for segmented SSE output. Update documentation and impact analysis to reflect these changes.
|
2026-04-16 09:15:01 +08:00 |
|
陈辅元
|
a55fd18915
|
Enhance impact analysis and configuration for vector persistence and API integration. Update main.spec to clarify data handling for ChromaDB, ensuring vector directories are excluded from packaging. Modify Text2SQLOrchestrator to unify question normalization for consistent SQL generation across languages. Introduce SchemaIndexer improvements for persistent vector storage and optimize embedding retrieval processes. Update documentation and comments for clarity on configuration changes and behavior adjustments.
|
2026-04-15 11:25:19 +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 |
|