Files
ai-video-fullstack/backend/services
Xin Wang b749d2e075 Enhance text input processing and LLM interaction in the backend
- Refactor TextInputProcessor to handle immediate and silent text inputs, improving user experience during voice interactions.
- Introduce PassthroughLLMAssistantAggregator to manage LLM responses while preserving context for downstream TTS processing.
- Update event handling for text input and client readiness, ensuring timely updates to the conversation context.
- Modify run_pipeline to integrate new aggregators and streamline message handling, enhancing overall pipeline efficiency.
- Improve message ordering in useVoicePreview to ensure accurate display of chat messages based on timestamps.
2026-06-14 22:12:56 +08:00
..