lite library
A lightweight entry point for Genkit.
Use this library for simple scripts or applications that need to perform generation tasks (using generate or generateStream) without setting up the full Genkit framework or reflection server.
This is useful for quick prototyping or simple LLM interactions.
Classes
- $AgentAbortRequest
- $AgentAbortResponse
- $AgentErrorInfo
- $AgentInit
- $AgentInput
- $AgentMetadata
- $AgentOutput
- $AgentResult
- $AgentResume
- $AgentStreamChunk
- $Artifact
- $BaseDataPoint
- $Candidate
- $CustomPart
- $DataPart
- $DocumentData
- $Embedding
- $EmbedRequest
- $EmbedResponse
- $EvalFnResponse
- $EvalRequest
- $GenerateActionOptions
- $GenerateActionOutputConfig
- $GenerateRequest
- $GenerateResponse
- $GenerateResumeOptions
- $GenerationUsage
- $GetSnapshotDataInput
- $JsonPatchOperation
- $Media
- $MediaPart
- $Message
- $MiddlewareRef
- $ModelInfo
- $ModelRequest
- $ModelResponse
- $ModelResponseChunk
- $Operation
- $OutputConfig
- $Part
- $ReasoningPart
- $ReflectionCancelActionParams
- $ReflectionCancelActionResponse
- $ReflectionConfigureParams
- $ReflectionEndInputStreamParams
- $ReflectionListActionsResponse
- $ReflectionListValuesParams
- $ReflectionListValuesResponse
- $ReflectionRegisterParams
- $ReflectionRunActionParams
- $ReflectionRunActionStateParams
- $ReflectionSendInputStreamChunkParams
- $ReflectionStreamChunkParams
- $ResourcePart
- $Score
- $SessionSnapshot
- $SessionState
- $TextPart
- $ToolDefinition
- $ToolRequest
- $ToolRequestPart
- $ToolResponse
- $ToolResponsePart
- $TurnEnd
- AgentAbortRequest
- AgentAbortResponse
- AgentErrorInfo
- AgentInit
- AgentInput
- AgentMetadata
- AgentOutput
- AgentResult
- AgentResume
- AgentStreamChunk
- Artifact
- BaseDataPoint
- Candidate
- CustomPart
- DataPart
- DocumentData
- Embedding
- EmbedRequest
- EmbedResponse
- EvalFnResponse
- EvalFnResponseEvaluation
- EvalRequest
- GenerateActionOptions
- GenerateActionOutputConfig
- GenerateActionOutputConfigInstructions
- GenerateRequest
- GenerateResponse
- GenerateResumeOptions
- GenerationUsage
- GetSnapshotDataInput
- JsonPatchOperation
- Media
- MediaPart
- Message
- MiddlewareRef
- ModelInfo
- ModelRequest
- ModelResponse
- ModelResponseChunk
- Operation
- OutputConfig
- Part
- ReasoningPart
- ReflectionCancelActionParams
- ReflectionCancelActionResponse
- ReflectionConfigureParams
- ReflectionEndInputStreamParams
- ReflectionListActionsResponse
- ReflectionListValuesParams
- ReflectionListValuesResponse
- ReflectionRegisterParams
- ReflectionRunActionParams
- ReflectionRunActionStateParams
- ReflectionSendInputStreamChunkParams
- ReflectionStreamChunkParams
- ResourcePart
- Score
- ScoreScore
- SessionSnapshot
- SessionState
- TextPart
- ToolDefinition
- ToolRequest
- ToolRequestPart
- ToolResponse
- ToolResponsePart
- TurnEnd
Extension Types
Extensions
- MessageExtension on Message
- ModelResponseChunkExtension on ModelResponseChunk
- ModelResponseExtension on ModelResponse
- PartExtension on Part
- Extension methods for Part.
- ToolRequestPartExtension on ToolRequestPart
- Extension methods for ToolRequestPart.
Functions
-
generate<
C> ({String? system, String? prompt, List< Message> ? messages, required Model<C> model, C? config, List<Tool> ? tools, List<String> ? toolNames, String? toolChoice, bool? returnToolRequests, int? maxTurns, SchemanticType? outputSchema, String? outputFormat, bool? outputConstrained, String? outputInstructions, bool? outputNoInstructions, String? outputContentType, Map<String, dynamic> ? context, StreamingCallback<GenerateResponseChunk> ? onChunk, List<GenerateMiddleware> ? use, List<InterruptResponse> ? interruptRespond, List<ToolRequestPart> ? interruptRestart}) → Future<GenerateResponseHelper> -
generateStream<
C> ({required Model< C> model, String? system, String? prompt, List<Message> ? messages, C? config, List<Tool> ? tools, List<String> ? toolNames, String? toolChoice, bool? returnToolRequests, int? maxTurns, SchemanticType? outputSchema, String? outputFormat, bool? outputConstrained, String? outputInstructions, bool? outputNoInstructions, String? outputContentType, Map<String, dynamic> ? context, List<GenerateMiddleware> ? use, List<InterruptResponse> ? interruptRespond, List<ToolRequestPart> ? interruptRestart}) → ActionStream<GenerateResponseChunk, GenerateResponseHelper> -
remoteModel(
{required String name, required String url, FutureOr< Map< headers(Map<String, String> ?>String, dynamic> context)?, ModelInfo? modelInfo, Client? httpClient}) → Model - Defines a remote Genkit model.