Loading...
Loading...
Found 2 Skills
Send images, audio, video, or documents into an AG2 `Agent` alongside text. Pass `ImageInput`, `AudioInput`, `VideoInput`, or `DocumentInput` as positional args to `agent.ask(...)`. Use when the user wants the agent to process non-text input — describe a photo, transcribe audio, summarise a PDF, analyse a video. Covers per-provider support matrix, the four ways to source data (URL / path / bytes / file_id), Gemini-specific YouTube + media-resolution + clipping, OpenAI image-detail, Anthropic prompt-caching on attachments, and `FilesAPI` for upload lifecycle.
Use when another skill needs to resolve an image source into a Sivi media ID (mId) or media URL. Handles 4 input sources — local file upload, direct image URL, product/webpage URL auto-pick, and AI generation — and returns a unified result (mId + mediaUrl). This is a utility skill referenced by composite skills (generate-design, create-a-plus-content, etc.) to avoid duplicating media handling scripts. For brand-scoped asset management with folder saving, see brand-assets. For standalone AI image generation/enhancement, see enhance-media.