Method GetTopCategories
- Namespace
- LMKit.TextAnalysis
- Assembly
- LM-Kit.NET.dll
GetTopCategories(IList<string>, string, int, bool, CancellationToken)
Classifies the specified plain text into up to a specified maximum number of categories.
public List<int> GetTopCategories(IList<string> categories, string content, int maxCategories, bool normalize = true, CancellationToken cancellationToken = default)
Parameters
categories
IList<string>A list of predefined category names.
content
stringThe plain text to be classified.
maxCategories
intThe maximum number of top categories to return.
normalize
boolOptional. Specifies whether input parameters should be normalized. Default is
true
.cancellationToken
CancellationTokenOptional. A CancellationToken for cancelling the operation.
Returns
Examples
// Synchronous usage:
var categories = new List<string> { "finance", "travel", "entertainment", "politics", "technology" };
string text = "The government unveiled a new technology policy impacting the finance sector.";
// Returns the top 3 categories:
IList<int> topCategories = categorization.GetTopCategories(categories, text, 3);
Console.WriteLine("Top categories:");
foreach (var index in topCategories)
{
Console.WriteLine(categories[index]);
}
GetTopCategories(IList<string>, IList<string>, string, int, bool, CancellationToken)
Classifies the specified plain text into up to a specified maximum number of categories.
public List<int> GetTopCategories(IList<string> categories, IList<string> categoryDescriptions, string content, int maxCategories, bool normalize = true, CancellationToken cancellationToken = default)
Parameters
categories
IList<string>A list of predefined category names.
categoryDescriptions
IList<string>Optional descriptions for each category.
content
stringThe plain text to be classified.
maxCategories
intThe maximum number of top categories to return.
normalize
boolSpecifies whether input parameters should be normalized. Default is
true
.cancellationToken
CancellationTokenCancellationToken for cancelling the operation.
Returns
GetTopCategories(IList<string>, Attachment, int, bool, CancellationToken)
Classifies the content provided as an attachment into up to a specified maximum number of categories. The attachment can contain either plain text or image data. If the attachment is an image requiring vision processing, the underlying language model must support vision input.
public List<int> GetTopCategories(IList<string> categories, Attachment content, int maxCategories, bool normalize = true, CancellationToken cancellationToken = default)
Parameters
categories
IList<string>A list of predefined category names.
content
AttachmentThe attachment to be classified.
maxCategories
intThe maximum number of top categories to return.
normalize
boolSpecifies whether input parameters should be normalized. Default is
true
.cancellationToken
CancellationTokenCancellationToken for cancelling the operation.
Returns
Exceptions
- InvalidModelException
Thrown when the attachment is an image that requires vision input but the underlying language model does not support vision.
GetTopCategories(IList<string>, IList<string>, Attachment, int, bool, CancellationToken)
Classifies the content provided as an attachment into up to a specified maximum number of categories.
public List<int> GetTopCategories(IList<string> categories, IList<string> categoryDescriptions, Attachment content, int maxCategories, bool normalize = true, CancellationToken cancellationToken = default)
Parameters
categories
IList<string>A list of predefined category names.
categoryDescriptions
IList<string>Optional descriptions for each category.
content
AttachmentThe attachment to be classified.
maxCategories
intThe maximum number of top categories to return.
normalize
boolSpecifies whether input parameters should be normalized. Default is
true
.cancellationToken
CancellationTokenCancellationToken for cancelling the operation.
Returns
Exceptions
- InvalidModelException
Thrown when the attachment is an image that requires vision input but the underlying language model does not support vision.