Enables LLMs to analyze images via OpenAI-compatible multimodal models, supporting local files, base64, and URLs with safety validation and model selection.
Enables MCP-compatible agents to analyze images via NVIDIA NIM vision models, supporting file paths, URLs, or base64 input to return actionable textual descriptions.
Enables reading images (diagrams, screenshots) directly via the model's own vision, with no external API key needed, and can extract embedded images from .doc/MHTML documents.