Xin Wang 5bc4e24adb Add vision model enhancements and image processing capabilities ...

- 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.

2026-07-08 10:33:44 +08:00

..

brains

Enhance AssistantConfig and pipeline for FastGPT integration

2026-06-16 16:55:51 +08:00

pipecat

Add vision model enhancements and image processing capabilities

2026-07-08 10:33:44 +08:00

__init__.py

Initial commit: AI Video Assistant fullstack platform.

2026-06-08 13:51:28 +08:00

config_resolver.py

Add vision model support and related configurations in Assistant

2026-07-07 21:50:15 +08:00

interface_catalog.py

Add support for image input in model resources and enhance related configurations

2026-07-07 19:41:45 +08:00

masking.py

Refactor backend to support interface-definition driven model resources

2026-06-14 19:36:12 +08:00

model_resource_tester.py

Implement StepFun Realtime service and enhance AssistantConfig

2026-06-14 23:41:40 +08:00

node_specs.py

Update node specifications and enhance GenericNode component

2026-06-15 15:49:58 +08:00

webrtc_ice.py

Add WebRTC TURN configuration and related enhancements

2026-07-06 17:45:53 +08:00

workflow_engine.py

Enhance workflow engine and frontend components with transition speech support

2026-06-15 15:57:05 +08:00