Nyckel Dog Breed Classification

The Nyckel Dog Breed Image Classification Flow is designed to automatically classify the breed of a dog from an image URL and provide fun facts about the breed. This flow simplifies the process of sending an image to the Nyckel API for classification, retrieving the breed information, and then enhancing it with fun facts using OpenAI's API. The results are then formatted and stored as records for further use.

This flow is particularly useful in applications such as image analysis, educational content creation, and automated content enrichment.

You can find this template in the Services Catalog under these categories:

AI, Contextual Basics, Enrichment

What's Included

1 Flow
1 Object Type
2 Connections

What You'll Need

No need for an API Key for Nyckel for this demo - we've got an endpoint configured for you
Sign up for Nyckel to get your own access to the Nyckel API and ability to host and train your own models for integration into your Contextual projects
Access to the OpenAI API
API Key for the OpenAI service

Ideas for Using the Nyckel Dog Breed Image Classification Flow

Image Analysis and Classification

Use this flow to automatically classify the breed of dogs from images. This can be particularly helpful for developers building applications in the pet industry or for educational purposes.

Content Enrichment

Generate fun and engaging content based on dog breed classifications. For example, this flow can be used to enrich articles, blogs, or social media posts with interesting facts about various dog breeds.

Educational Tools

Create an interactive learning tool where users can upload dog images and receive detailed information about the breed, including fun facts. This can be a valuable addition to educational apps and websites.

Flow Overview

Flow Start

The flow begins by receiving an image URL, which is for demo and testing, injected as an input when editing the flow or received from an external event.

Convert Image URL to Binary Buffer

The image URL is converted to a binary buffer, preparing it for classification by the Nyckel API.

Send Image URL and Receive Breed Classification

The flow sends the binary image data to the Nyckel API, which processes the image and returns the breed classification.

Send Breed Classification to OpenAI and Receive Fun Facts

The classified breed information is sent to the OpenAI API, which generates fun facts about the breed. The response includes interesting and engaging facts formatted for easy display.

Format Classification and Fun Facts then Create Record

The classification result and the fun facts are combined into a structured format and stored as a new record in Contextual. This ensures that the information is readily accessible for future reference or display.

Error Handling

Any errors encountered during the flow are captured and logged, ensuring that issues can be quickly identified and resolved.

Flow End

The flow concludes once the records have been successfully created or any errors have been logged.

Nyckel Dog Breed Image Classification Flow Details

Inbound Send to Agent Events

Nodes: contextual-start
Purpose: The flow begins by receiving an image URL, either injected directly or received from an external source.

In-Editor Testing

Nodes: Test Prompt, Convert Image URL to Binary Buffer
Purpose: Allows for testing the image URL directly within the editor. The image URL is converted to a binary format that is suitable for the Nyckel API.

Code Example: Convert Image URL to Binary Buffer Function

codemsg.payload = {
    // URL of the dog image to be classified
    dogImage: "https://images.pexels.com/photos/3763313/pexels-photo-3763313.jpeg?auto=compress&cs=tinysrgb&w=1260&h=750&dpr=2"
};
return msg;

Explanation: This function assigns the image URL to msg.payload, preparing it for processing by the flow. The image URL is the input that will be classified by the Nyckel API.

Send Image URL and Receive Breed Classification

Nodes: Prepare Classification Request, Prompt Nyckel, Nyckel Response
Purpose: The binary image is sent to the Nyckel API, which returns a breed classification. This information is logged and passed on for further processing.

Code Example: Prepare Classification Request Function

codemsg.payload = {
    // Set the 'data' field to the image URL for classification
    data: msg.event.dogImage
};
return msg;

Explanation: This function prepares the payload by assigning the image URL to the data field, which is required by the Nyckel API to classify the image.

Send Breed Classification and Receive Fun Facts

Nodes: Prepare "Fun Facts" Request, Prompt OpenAI Chat, OpenAI Chat Response
Purpose: The breed classification is sent to the OpenAI API, which generates fun facts about the breed. The response is logged and formatted for record creation.

Code Example: Prepare "Fun Facts" Request Function

codemsg.payload = {
    model: "gpt-4o-mini",
    messages: [
        {
            role: "system",
            content: "You are an expert on dog breeds. Provide three fun and interesting facts in bulletpoint format."
        },
        {
            role: "user",
            content: `Tell me three fun facts about this dog breed: ${msg.breedClassification.labelName}`
        }
    ]
};
return msg;

Explanation: This function constructs the payload for the OpenAI API, specifying the model and the messages required to generate fun facts about the classified dog breed.

Format Classification and Fun Facts then Create Record

Nodes: Prepare AI Response Data, Create AI Response Record, Create AI Classification Record Log
Purpose: The classification result and fun facts are combined into a structured object and stored as a record. This ensures that the information is easily accessible for further use.

Code Example: Prepare AI Response Data Function

codelet body = {
    dogImage: msg.responseUrl,
    dogBreed: msg.breedClassification.labelName,
    funFacts: msg.funFacts.choices[0].message.content
};
msg.payload = body;
return msg;

Explanation: This function formats the classification and fun facts into a single object, which is then saved as a record. The object includes the image URL, the breed name, and the fun facts.

Error Handling

Nodes: catch, Error Catch Log, contextual-error
Purpose: Captures any errors during the flow, logs them for troubleshooting, and ensures that issues can be promptly addressed.

Flow End

Nodes: contextual-end
Purpose: Completes the flow after the records have been created or any errors have been logged.

Summary of Flow

Flow Start: Begin the flow with an image URL for dog breed classification.
Data Preparation: Convert the image URL to a binary buffer for API interaction.
API Interaction: Send the image to Nyckel for classification and then send the classification to OpenAI for fun facts.
Record Creation: Format and store the classification and fun facts as records.
Error Handling: Capture and log any errors that occur during the process.
Flow End: Conclude the flow after records are created or errors are logged.

This help article provides a comprehensive guide to using the Nyckel Dog Breed Image Classification Flow, detailing the flow's functionality and providing code examples for each major step.

PreviousMistral AI Prompt and Response NextRapidAPI ClassifyAI Text Classification

Last updated 23 days ago