> ## Documentation Index
> Fetch the complete documentation index at: https://pype-db52d533.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Image Reference

The ImageReferenceMetric is a multimodal metric designed to evaluate the relevance of images in relation to the accompanying text. It assesses how well the image serves as a reference to the text, serving as a proxy for evaluating the performance of models that generate or select images to support textual content.

### **Required Arguments**

* input: A list containing the textual context or description.
* actual\_output: A list containing the textual description of the image and the image itself. The image is represented as an MLLMImage instance with:
* url: The file path or URL to the image.

### **Optional Arguments**

* threshold: A float representing the minimum passing threshold, defaulted to 0.5.
* model: A string specifying which of OpenAI's GPT models to use, or any custom LLM model of type DeepEvalBaseLLM. Defaulted to 'gpt-4o'.
* include\_reason: A boolean which, when set to True, includes a reason for its evaluation score. Defaulted to True.
* strict\_mode: A boolean which, when set to True, enforces a binary metric score: 1 for perfection, 0 otherwise. It also overrides the current threshold and sets it to 1. Defaulted to False.
* async\_mode: A boolean which, when set to True, enables concurrent execution within the measure() method. Defaulted to True.
* verbose\_mode: A boolean which, when set to True, prints the intermediate steps used to calculate the metric to the console. Defaulted to False.

### Usage Example

```python theme={null}
import sys
import os

from agensight.eval.metrics import ImageReferenceMetric
from agensight.eval.test_case import MLLMTestCase
from agensight.eval.test_case import MLLMImage

input_data = ["This is a report with an image."]
actual_output = ["The following image shows a cat on a windowsill.", MLLMImage(url="/image-path/cat.jpeg")]

metric = ImageReferenceMetric(model="gpt-4o", threshold=0.5)
test_case = MLLMTestCase(input=input_data, actual_output=actual_output)

metric.measure(test_case)
print(f"Score: {metric.score}")
print(f"Reason: {metric.reason}") 
```