flutter_gemma library
Classes
- CorruptionDetectionResult
- Result of corruption detection
- DiagnosticReport
- Diagnostic information for troubleshooting
- EmbeddingModel
- Represents an embedding model instance.
- ErrorHandlingResult
- Result of error handling
- EstimatedDimensions
- Estimated image dimensions
- FlutterGemmaPlugin
- Interface for the FlutterGemma plugin.
- FunctionCallParser
- Unified parser for function calls in all formats:
- FunctionCallResponse
- Gemma3Specs
- Gemma 3 SigLIP vision encoder specifications
- GeneralVisionSpecs
- General vision encoder specifications
- ImageErrorHandler
- Comprehensive error handling and debugging utilities for AI image processing to prevent corruption that causes repeating text patterns in model responses.
- ImageProcessor
- Comprehensive image processing utilities to prevent AI image corruption and ensure proper vision encoder compatibility.
- ImageTokenizer
- Handles proper image tokenization for multimodal AI models to prevent "Prompt contained 0 image tokens but received 1 images" errors and corruption that causes repeating text patterns.
- InferenceChat
- InferenceModel
- Represents an LLM model instance.
- InferenceModelSession
- Session managing response generation from the model.
- Message
- ModelFileManager
- ModelResponse
- Base interface for model responses from InferenceChat Can be either TextResponse, FunctionCallResponse, or ThinkingResponse
- MultimodalImageHandler
- Main integration class for handling multimodal image processing in Flutter Gemma to prevent AI image corruption and repeating text pattern issues.
- MultimodalImageResult
- Result of multimodal image processing
- PlatformService
- ProcessedImage
- Represents a processed image ready for AI model consumption
- ResponseValidationResult
- Result of response validation
- RetrievalResult
- TextResponse
- Text token during streaming
- ThinkingResponse
- Thinking process content from the model
- Tool
- ValidationResult
- Result of image validation
- VectorStoreStats
- VisionEncoderValidator
- Validates images for compatibility with AI vision encoders to prevent corruption that causes models to interpret images as repeating text patterns.
- VisionSpecs
- Base class for vision encoder specifications
Enums
- CorruptionAction
- Actions to take when corruption is detected
- ErrorType
- Types of errors that can occur in image processing
- MessageType
- ModelFileType
- ModelReplacePolicy
- Policy for handling old models when switching to new ones
- ModelType
- PreferredBackend
- ResponseAction
- Actions to take for corrupted responses
- VisionEncoderType
- Vision encoder types with their specifications
Constants
-
supportedLoraRanks
→ const List<
int>
Exceptions / Errors
- ImageProcessingException
- Exception thrown when image processing fails
- ImageTokenizationException
- Exception thrown when image tokenization fails
- VisionEncoderValidationException
- Exception thrown when validation fails