Files
ai-video-fullstack/backend/requirements.txt
Xin Wang 01c563a3e7 Add turn configuration support for assistants
- Introduce a new `turnConfig` field in `AssistantConfig` and `Assistant` models to manage user interaction settings.
- Implement `TurnConfig`, `BargeInConfig`, `VadConfig`, and `TurnDetectionConfig` schemas to define turn management strategies.
- Update the backend to handle turn configuration in the database and during assistant operations.
- Enhance frontend components with a `TurnConfigEditor` for configuring turn settings, including VAD and barge-in strategies.
- Modify existing pages to integrate turn configuration, improving user experience and interaction capabilities.
2026-07-12 11:08:19 +08:00

27 lines
865 B
Plaintext

# 薄后端依赖。语音引擎用 pipecat 官方库。
# webrtc -> SmallWebRTCTransport / SmallWebRTCConnection + aiortc
# silero -> 本地 VAD(判断用户说话起止),语音必备
# openai -> OpenAI 兼容的 LLM/STT/TTS 客户端(DeepSeek、SenseVoice、CosyVoice 都走它)
pipecat-ai[webrtc,websocket,silero,openai]==1.4.0
Pillow>=11.1.0,<13
# FastGPT 类型助手:本地 SDK(包 /api/v1/chat/completions 流式 + chatId 会话)
fastgpt-client @ file:///Users/wangx/Code/AI-VideoAssistant-Project/fastgpt-python-sdk
# Dify 类型助手:异步流式 Runtime API SDK
dify-client-python==1.0.3
fastapi
httpx
uvicorn[standard]
python-dotenv
pydantic
loguru
websockets>=13
# 存储:Postgres(SQLAlchemy 2.0 异步 + asyncpg 驱动)
sqlalchemy[asyncio]>=2.0
alembic>=1.13
asyncpg
greenlet # SQLAlchemy 异步运行时必需(部分平台不会自动带上)