Block a user
ed9621dfe0
Update VOICE_CONFIG to use new FastGPT state-enabled configuration and add TEXT_DELTA log group for websocket responses.
3357585443
Add response state configuration to FastGPT XFYun JSON file, enabling state tracking with customizable parameters for improved interaction management.
ad232fdbd9
Add configuration files for FastGPT with XFYun services, including STT, TTS, and audio filtering settings. Introduce new JSON files for different service configurations and enhance logging for text delta responses in the web application.
c4a53b5205
Add voice activity detection and interruption handling configurations to FastGPT and XFYun JSON files. Enhance interruption short replies with additional phrases for improved user interaction.
97deca0f57
Update LLM configuration to support FastGPT integration. Modify requirements to include fastgpt-python-sdk, enhance greeting messages, and adjust LLM service creation to handle app_id. Implement welcome text fetching for FastGPT and improve context handling in the pipeline based on LLM provider. Update related configurations and properties for better integration.
3dfff0c937
Add AssistantContextSyncProcessor to manage LLM context synchronization during assistant interruptions. Update ProductTextStreamProcessor to track last streamed text and modify pipeline to integrate new context sync functionality. Enhance tests to verify context sync behavior for interrupted assistant turns.
b14ef64665
Add configuration files for FastGPT and Xfyun voice services, enhancing LLM service capabilities. Update LLMConfig to include chat_id, variables, detail, and timeout settings. Refactor create_llm_service to support FastGPT integration and adjust pipeline to handle chat_id and greeting prompts. Implement context synchronization for interrupted assistant turns in text streaming.
e7a8cb1faa
Enhance text stream processing by adding synchronization for interrupted assistant turns. Introduce sync_streamed_assistant_context to align LLM context with UI text, and modify ProductTextStreamProcessor to handle interrupted text. Update pipeline to utilize the new functionality for managing assistant turn interruptions.
2edcb51805
Add chat_id, variables, detail, timeout_sec, and send_system_prompt to LLMConfig; update create_llm_service to accept new parameters and handle FastGPT integration. Modify pipeline to utilize chat_id and adjust message handling based on provider settings.
f301af396d
Update AGENTS.md with additional context on implementation and modify pipeline.py to include assistant aggregator in the processing flow.