 陈辅元
|
70c8e90f2e
|
Update environment configuration to switch OpenAI model from gpt-5.4 to gpt-4o-mini. Introduce _effective_llm_route_from_request function in api_server.py to determine the effective LLM routing based on service keys and model compatibility. Update chat event handling to include LLM routing information in response data. Enhance logging for better traceability of API interactions.
|
2026-04-16 15:49:03 +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
|
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 |
|
|
陈辅元
|
84fe545640
|
first commit
|
2026-04-10 16:52:07 +08:00 |
|