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

..

__pycache__

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

__init__.py

0.1.1 暂存

2026-04-14 10:28:22 +08:00

dialog_classifier.py

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

dialog_context.py

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

embedding.py

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

fewshot_chroma_store.py

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

fewshot_selector.py

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

question_locale.py

0.1.1 暂存

2026-04-14 10:28:22 +08:00

sql_parser.py

0.1.1 暂存

2026-04-14 10:28:22 +08:00

validators.py

0.1.1 暂存

2026-04-14 10:28:22 +08:00