multimodal_task
Combine text and images for complex reasoning. Send multimodal conversations to NVIDIA NIM vision models such as Neva and Phi-3.5 Vision.
Instructions
Perform multimodal tasks combining text and images. Send a conversation with mixed text and image content to multimodal models for complex reasoning across modalities.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"messages": "<messages>"
},
"name": "multimodal_task"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| model | No | Multimodal model ID (e.g., nvidia/neva-22b, microsoft/phi-3.5-vision-instruct, meta/llama-3.2-90b-vision-instruct) | |
| top_p | No | ||
| stream | No | ||
| messages | Yes | Conversation messages with optional images. Each message can have text content or an array of text and image_url parts. | |
| max_tokens | No | ||
| temperature | No |