Enum ModelCapabilities
Flags enum describing the capabilities a model supports in LM-Kit. Multiple values can be combined with bitwise operations to represent models that support several capabilities.
[Flags]
public enum ModelCapabilitiesFields
None = 0Indicates no specific capability is assigned. Useful for initialization or undefined roles.
TextEmbeddings = 1Indicates the model supports text embedding generation. Used for semantic similarity, clustering, and retrieval.
TextGeneration = 2Indicates the model supports general text generation, such as content creation, summarization, and free-form generation.
Chat = 4Indicates the model supports chat-oriented conversation, including dialogue, chatbots, and question answering.
CodeCompletion = 8Indicates the model supports code generation and completion, assisting developers with suggestions and snippet synthesis.
SentimentAnalysis = 16Indicates the model supports sentiment and emotion analysis, including positive, negative, neutral, and specific emotions.
Math = 32Indicates the model supports mathematical reasoning and problem solving, including equation solving, symbolic manipulation, and numerical calculations.
Vision = 64Indicates the model supports vision-language tasks (VLM), combining image and text understanding for multimodal reasoning, recognition, and description generation.
ImageEmbeddings = 128Indicates the model supports image embedding generation, used for image similarity, search, and clustering.
TextReranking = 256Indicates the model supports text reranking, reordering candidate results by relevance or quality (e.g., in RAG/search).
SpeechToText = 512Indicates the model supports speech-to-text transcription.
VoiceActivityDetection = 1024Indicates the model supports voice-activity detection (VAD), distinguishing speech from silence or background noise.
ImageSegmentation = 2048Indicates the model supports image segmentation, partitioning images into regions or objects for analysis and understanding.