Vision Agent - PraisonAI

Analyse, describe, compare, and read text from images with the VisionAgent and its dedicated methods.

from praisonaiagents import VisionAgent

agent = VisionAgent()

result = agent.analyze("https://example.com/image.jpg")
print(result)

VisionAgent provides dedicated methods for image understanding tasks like analysis, description, comparison, and text extraction.

How It Works

Quick Start

Install

pip install praisonaiagents litellm
export OPENAI_API_KEY="your-key"

Create Agent

from praisonaiagents import VisionAgent

agent = VisionAgent()

Analyze Image

result = agent.analyze("https://example.com/image.jpg")
print(result)

Methods

analyze()

Analyze an image with optional custom prompt.

from praisonaiagents import VisionAgent

agent = VisionAgent()

# Basic analysis
result = agent.analyze("image.jpg")

# With custom prompt
result = agent.analyze(
    "chart.png",
    prompt="What data does this chart show?"
)

str

required

Image URL or local file path

str

Custom analysis prompt

str

default:"auto"

Detail level: low, high, or auto

describe()

Generate detailed description of an image.

description = agent.describe("photo.jpg")
print(description)

Returns comprehensive description including:

Main subject and composition
Colors, lighting, mood
Background and setting
Text, symbols, notable details

compare()

Compare multiple images.

comparison = agent.compare([
    "before.jpg",
    "after.jpg"
], prompt="What changed?")

List[str]

required

List of image URLs or paths (minimum 2)

extract_text()

Extract text from images (OCR-like).

text = agent.extract_text("document.png", detail="high")
print(text)

Use detail="high" for better text extraction accuracy.

Configuration

Basic
With Config
Dict Config

from praisonaiagents import VisionAgent

agent = VisionAgent(
    name="MyVision",
    llm="gpt-4o",
    verbose=True
)

from praisonaiagents import VisionAgent, VisionConfig

config = VisionConfig(
    detail="high",
    max_tokens=8192,
    timeout=120
)

agent = VisionAgent(vision=config)

agent = VisionAgent(
    vision={
        "detail": "high",
        "max_tokens": 4096
    }
)

VisionConfig Parameters

Parameter	Type	Default	Description
`detail`	str	`"auto"`	Detail level: `low`, `high`, `auto`
`max_tokens`	int	`4096`	Maximum response tokens
`timeout`	int	`60`	Request timeout in seconds

Supported Models

OpenAI

gpt-4o (default)
gpt-4o-mini
gpt-4-turbo

Anthropic

claude-3-5-sonnet-20241022
claude-3-opus-20240229

Google

gemini/gemini-1.5-pro
gemini/gemini-1.5-flash

Examples

Analyze Chart Data

from praisonaiagents import VisionAgent

agent = VisionAgent(llm="gpt-4o")

result = agent.analyze(
    "https://example.com/sales-chart.png",
    prompt="Extract all data points and trends from this chart"
)
print(result)

Compare Product Images

agent = VisionAgent()

comparison = agent.compare([
    "product_v1.jpg",
    "product_v2.jpg",
    "product_v3.jpg"
], prompt="Describe the design evolution across these versions")

Extract Document Text

agent = VisionAgent()

# High detail for better OCR
text = agent.extract_text(
    "scanned_document.png",
    detail="high"
)
print(text)

Async Usage

import asyncio
from praisonaiagents import VisionAgent

async def main():
    agent = VisionAgent()
    result = await agent.aanalyze("image.jpg")
    print(result)

asyncio.run(main())

Comparison with ImageAgent

VisionAgent is for image analysis/understanding.
ImageAgent is for image generation.

Feature	VisionAgent	ImageAgent
Purpose	Analyze images	Generate images
Input	Image URL/path	Text prompt
Output	Text description	Image file/URL
Models	GPT-4o, Claude, Gemini	DALL-E, Stable Diffusion

Best Practices

Pick the method that matches the task

Use analyze for open-ended questions, describe for captions, compare for two images, and text extraction for OCR. The dedicated methods prompt the model more precisely than a raw call.

Use a vision-capable model

VisionAgent needs a multimodal model (GPT-4o, Claude, Gemini). Point it at a text-only model and it cannot see the image.

Give a specific prompt for analysis

analyze(image, prompt="Count the people") beats a bare analyze(image). A focused question yields a focused, useful answer.

Reach for ImageAgent to generate, not analyse

VisionAgent understands existing images. To create new images from a text prompt, use the ImageAgent instead.

Generate images from text prompts.

Extract text from images with OCR.

​How It Works

​Quick Start

​Methods

​Configuration

​VisionConfig Parameters

​Supported Models

OpenAI

Anthropic

Google

​Examples

​Analyze Chart Data

​Compare Product Images

​Extract Document Text

​Async Usage

​Comparison with ImageAgent

​Best Practices

​Related

How It Works

Quick Start

Methods

Configuration

VisionConfig Parameters

Supported Models

Examples

Analyze Chart Data

Compare Product Images

Extract Document Text

Async Usage

Comparison with ImageAgent

Best Practices

Related