Classify and Summarize Images
Image Classification is a prompt chain example that demonstrates multi-step workflows for classifying images using AI vision models with promptfoo's testing
Why it matters
Automate the process of classifying images and extracting key information for content analysis and organization.
Outcomes
What it gets done
Classify images based on their content.
Extract relevant details from image classifications.
Summarize findings from image analysis.
Install
Add it to your toolbox
Run in your project directory:
curl -fsSL https://spark.entire.vc/get/pfoo-image-classification | bash Capabilities
What this chain does
Labels or categorizes text, files, or data points.
Pulls structured data fields from unstructured text.
Condenses long documents or threads into key takeaways.
Overview
Image Classification
What it does
Image Classification is a prompt chain example from the promptfoo framework that demonstrates how to build multi-step workflows for classifying images with AI vision models. It shows how to structure prompt chains that process image inputs, orchestrate model calls, and format classification results. The example is executable via the promptfoo CLI.
How it connects
Use this when you need a reference implementation for building image classification workflows with prompt chains, or when you want to learn how promptfoo handles multi-step vision model testing. It's ideal for developers prototyping computer vision features or establishing testing patterns for AI-powered image recognition systems.
Source README
yaml-language-server: $schema=https://promptfoo.dev/config-schema.json
description: Image Classification Example of Fashion MNIST dataset
providers:
- openai:chat:gpt-4o
- openai:chat:gpt-4.1-mini
prompts: - label: Image Classification
raw: file://prompt.js
config:
response_format:
type: json_schema
json_schema:
name: image_classification
schema:
type: object
properties:
classification:
type: string
enum:
[
'T-shirt/top',
'Trouser',
'Pullover',
'Dress',
'Coat',
'Sandal',
'Shirt',
'Sneaker',
'Bag',
'Ankle boot',
]
color:
type: string
features:
type: string
style:
type: string
confidence:
type: integer
reasoning:
type: string
required:
- classification
- color
- features
- style
- confidence
- reasoning
additionalProperties: false
defaultTest:
assert:
- type: is-json
value:
type: object
properties:
classification:
type: string
color:
type: string
features:
type: string
style:
type: string
confidence:
type: integer
reasoning:
type: string
- type: javascript
value: 'output.classification === context.vars.label'
metric: accuracy
tests: file://fashion_mnist_sample_base64.csv
Discussion
Questions & comments · 0
Sign In Sign in to leave a comment.