5bc4e24adb
- Update `requirements.txt` to include Pillow for image handling. - Refactor vision model validation logic in `voice_webrtc.py` to improve error handling for unsupported image input. - Introduce new functions in `pipeline.py` for image data processing and analysis using vision models. - Implement `VisionCaptureProcessor` to manage video frame requests for auxiliary vision model analysis. - Enhance the pipeline to support image input requests and integrate vision model responses into the processing flow.
23 lines
775 B
Plaintext
23 lines
775 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]==1.3.0
|
|
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
|
|
|
|
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
|
|
asyncpg
|
|
greenlet # SQLAlchemy 异步运行时必需(部分平台不会自动带上)
|