> ## Documentation Index
> Fetch the complete documentation index at: https://praison.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Multi-Modal Agent CLI

> Command-line interface for multi-modal agents

Work with images, PDFs, and files from the command line.

```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
graph LR
    User([User]) --> CLI[CLI]
    CLI --> Svc[Multi-Modal Agent]

    classDef agent fill:#8B0000,stroke:#7C90A0,color:#fff
    classDef tool fill:#189AB4,stroke:#7C90A0,color:#fff

    class Svc agent
    class User,CLI tool
    classDef agent fill:#8B0000,color:#fff
    classDef tool fill:#189AB4,color:#fff

```

## Quick Start

**1. Simple Usage**

```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
praisonai-ts image analyze https://example.com/image.jpg --prompt "What do you see?"
```

**2. With Configuration**

```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
praisonai-ts image analyze ./photo.png --model gpt-4o --prompt "Describe this image"
```

## Commands

### Analyze Image

```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
# Analyze image from URL
praisonai-ts image analyze https://example.com/image.jpg \
  --prompt "What do you see?"

# Analyze local image
praisonai-ts image analyze ./photo.png \
  --prompt "Describe this image in detail"

# With specific model
praisonai-ts image analyze ./image.jpg \
  --model gpt-4o \
  --prompt "What objects are in this image?"
```

### Generate Image

```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
# Generate image with DALL-E
praisonai-ts image generate "A sunset over mountains" \
  --model dall-e-3 \
  --size 1024x1024 \
  --output ./sunset.png

# With quality setting
praisonai-ts image generate "Futuristic city" \
  --quality hd \
  --style vivid
```

### Process PDF

```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
# Summarize PDF
praisonai-ts pdf summarize ./document.pdf

# Extract text
praisonai-ts pdf extract ./document.pdf --output text.txt

# Ask questions about PDF
praisonai-ts pdf query ./document.pdf \
  --prompt "What are the main findings?"
```

## Options

| Option | Type | Default | Description |
| - | - | - | - |
| `--model` | string | `gpt-4o` | Model to use |
| `--prompt` | string | - | Analysis prompt |
| `--output` | string | - | Output file path |
| `--size` | string | `1024x1024` | Image size |
| `--quality` | string | `standard` | Image quality |
| `--json` | boolean | `false` | JSON output |

## Examples

### Batch Image Analysis

```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
# Analyze multiple images
praisonai-ts image analyze ./images/*.jpg \
  --prompt "Categorize this image" \
  --output results.json \
  --json
```

### Compare Images

```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
# Compare two images
praisonai-ts image compare ./image1.jpg ./image2.jpg \
  --prompt "What are the differences?"
```

### Interactive Vision Chat

```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
# Start vision chat session
praisonai-ts chat --vision \
  --model gpt-4o \
  --instructions "You are a helpful image analyst"
```

## Environment Variables

| Variable | Required | Description |
| - | - | - |
| `OPENAI_API_KEY` | Yes | For GPT-4o and DALL-E |
| `ANTHROPIC_API_KEY` | For Claude | Claude vision |

## Related Commands

* `praisonai-ts image list-models` - List vision models
* `praisonai-ts image history` - View generation history

## Related

> [card] [Multimodal Agent](https://praison.ai/docs/js/multimodal-agent.md)
>
> Multimodal Agent overview

> [card] [Vision](https://praison.ai/docs/js/vision.md)
>
> Vision overview


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.