支持音频视频数据检索吗

[SKYMIRRORA]

Is your feature request related to a problem? Please describe.
Manually searching through audio/video files (e.g., finding specific speech or scenes) is very time-consuming.
Describe the solution you'd like
Support audio/video content retrieval: extract text from audio, recognize objects/scenes in video, and enable keyword search with timestamp jumping.
Describe alternatives you've considered
Using third-party tools for pre-processing, but it’s inefficient and requires extra integration.
Additional context
Valuable for media management, online education, legal evidence analysis, etc.

[mssssss123]

Thank you for your feedback. At the moment, we only support text- and image-based RAG. We will add support for more modalities in future updates.