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

# Multi-Modal Agent CLI

> Command-line interface for multi-modal agents

# Multi-Modal Agent CLI

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

## 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