Enum EmbedTaskType

Namespace

Glitch9.AIDevKit

Google Only. Task type for embedding content.

public enum EmbedTaskType

Fields

Classification = 4

Optimized for classification tasks. Generates embeddings suitable for input to classification models.

Clustering = 5

Optimized for clustering large volumes of text. Use cases: topic grouping, data analysis.

Document = 2

Optimized for embedding documents to be searched. Use case: storing chat session messages, notes, or document bodies for later retrieval.

SearchQuery = 1

Optimized for embedding search queries. Use case: user inputs a search query like "AI agent storage methods" and you want to match it against documents. Characteristics: trained to produce embeddings suitable for short queries.

SemanticSimilarity = 3

Optimized for computing semantic similarity between two texts. Use cases: question-answer matching, paraphrase detection, duplicate detection.

Unspecified = 0

Default value. The model will choose the best type for the input content.