← Registry / Multimodal Conversation
AIM
Text and Image Query
MMC-TIQ-V2.5
Submissions for this AIM must match this definition: the same ports, API profile and internal wiring.
Description
Text and Image Query: answers with text to a text-based question about an image.
Inputs and outputs 2 in · 3 out
Inputs
- InputText OSD-BTO-V1.5 or OSD-TXO-V1.5
- InputVisual OSD-BVO-V1.5 or OSD-VIO-V1.5
Outputs
- OutputSpeech optional OSD-SPO-V1.5
- OutputText OSD-BTO-V1.5 or OSD-TXO-V1.5
- OutputImage OSD-BVO-V1.5 or OSD-VIO-V1.5
Used in 1 AIM
- Answer to Multimodal Question MMC-AMQ-V2.5
Documentation
Implementations 0
None published yet.