Method GetBestCategoryAsync

Namespace

LMKit.TextAnalysis

Assembly

LM-Kit.NET.dll

GetBestCategoryAsync(IList<string>, string, bool, CancellationToken)

Asynchronously classifies the specified plain text into one of the predefined categories.

public Task<int> GetBestCategoryAsync(IList<string> categories, string content, bool normalize = true, CancellationToken cancellationToken = default)

Parameters

categories IList<string>

A list of predefined category names. Each entry should describe the corresponding category.

content string

The plain text to be classified.

normalize bool

Optional. Indicates whether input parameters should be normalized. The default is true.

cancellationToken CancellationToken

Optional. A CancellationToken for handling cancellation requests.

Returns

Task<int>

A task representing the asynchronous operation. The task result contains the index of the best matching category in the categories list, or -1 if no category can be associated with the provided text.

Examples

using LMKit.Model;
using LMKit.TextAnalysis;
using System;
using System.Collections.Generic;
using Tasks;

class Example
{
    static async Task Main()
    {
        LM model = LM.LoadFromModelID("llama-3.1");

        Categorization categorization = new Categorization(model);
        var categories = new List<string> { "animals", "technology", "music" };
        string text = "A newly discovered frog species can glow in the dark.";

        int bestCategoryIndex = await categorization.GetBestCategoryAsync(categories, text);

        if (bestCategoryIndex != -1)
        {
            Console.WriteLine($"Category: {categories[bestCategoryIndex]}");
        }
        else
        {
            Console.WriteLine("No suitable category found.");
        }

        Console.WriteLine($"Confidence: {categorization.Confidence}");
    }
}

Exceptions

OperationCanceledException

Thrown if the operation is canceled via the cancellationToken.

GetBestCategoryAsync(IList<string>, Attachment, bool, CancellationToken)

Asynchronously classifies the content provided as an attachment into one of the predefined categories. The attachment may contain either plain text or image data. For image attachments that require vision processing, ensure that the underlying language model supports vision input.

public Task<int> GetBestCategoryAsync(IList<string> categories, Attachment content, bool normalize = true, CancellationToken cancellationToken = default)

Parameters

categories IList<string>

A list of predefined category names.

content Attachment

The attachment to be classified, representing either plain text or image content.

normalize bool

Optional. Indicates whether input parameters should be normalized. The default is true.

cancellationToken CancellationToken

Optional. A CancellationToken for handling cancellation requests.

Returns

Task<int>

A task representing the asynchronous operation. The task result contains the index of the best matching category in the categories list, or -1 if no suitable category can be determined.

Exceptions

InvalidModelException

Thrown when the attachment is an image requiring vision processing but the underlying language model lacks vision support.