ai

package
v0.5.2 Latest Latest
Warning

This package is not in the latest version of its module.

Go to latest Published: Apr 18, 2025 License: Apache-2.0Imports: 28 Imported by: 20

Documentation

Index

Constants

View Source
const (  OutputFormatText string = "text"  OutputFormatJSON string = "json"  OutputFormatJSONL string = "jsonl"  OutputFormatMedia string = "media"  OutputFormatArray string = "array"  OutputFormatEnum string = "enum" )

Variables

View Source
var DEFAULT_FORMATS = []Formatter{  jsonFormatter{}, jsonlFormatter{}, textFormatter{}, arrayFormatter{}, enumFormatter{}, }

Default formats get automatically registered on registry init

Functions

func ConfigureFormatsadded inv0.5.0

func ConfigureFormats(reg *registry.Registry)

ConfigureFormats registers default formats in the registry

func DefineFormatadded inv0.5.0

func DefineFormat(r *registry.Registry, name string, formatter Formatter)

DefineFormat defines and registers a new Formatter.

func DefineGenerateActionadded inv0.3.0

func DefineGenerateAction(ctx context.Context, r *registry.Registry) *generateAction

DefineGenerateAction defines a utility generate action.

func GenerateTextadded inv0.1.0

func GenerateText(ctx context.Context, r *registry.Registry, opts ...GenerateOption) (string, error)

GenerateText run generate request for this model. Returns generated text only.

func Indexadded inv0.1.0

func Index(ctx context.Context, r Indexer, opts ...IndexerOption) error

Index calls the indexer with the provided options.

func LoadPromptDiradded inv0.3.0

func LoadPromptDir(r *registry.Registry, dir string, namespace string) error

LoadPromptDir loads prompts and partials from the input directory for the given namespace.

Types

type AugmentWithContextOptionsadded inv0.3.0

type AugmentWithContextOptions struct {  Preface *string// Preceding text to place before the rendered context documents. ItemTemplate func(d Document, index int, options *AugmentWithContextOptions) string// A function to render a document into a text part to be included in the message. CitationKey *string// Metadata key to use for citation reference. Pass `nil` to provide no citations.}

AugmentWithContextOptions configures how a request is augmented with context.

type BaseDataPointadded inv0.3.0

type BaseDataPoint struct {  Context map[string]any `json:"context,omitempty"`  Input map[string]any `json:"input,omitempty"`  Output map[string]any `json:"output,omitempty"`  Reference map[string]any `json:"reference,omitempty"`  TestCaseID string `json:"testCaseId,omitempty"`  TraceIDs []string `json:"traceIds,omitempty"` }

type BaseEvalDataPointadded inv0.3.0

type BaseEvalDataPoint struct {  Context map[string]any `json:"context,omitempty"`  Input map[string]any `json:"input,omitempty"`  Output map[string]any `json:"output,omitempty"`  Reference map[string]any `json:"reference,omitempty"`  TestCaseID string `json:"testCaseId,omitempty"`  TraceIDs []string `json:"traceIds,omitempty"` }

type CandidateErroradded inv0.3.0

type CandidateError struct {  Code CandidateErrorCode `json:"code,omitempty"`  Index float64 `json:"index,omitempty"`  Message string `json:"message,omitempty"` }

type CandidateErrorCodeadded inv0.3.0

type CandidateErrorCode string
const (  CandidateErrorCodeBlocked CandidateErrorCode = "blocked"  CandidateErrorCodeOther CandidateErrorCode = "other"  CandidateErrorCodeUnknown CandidateErrorCode = "unknown" )

type CommonGenOptionadded inv0.5.0

type CommonGenOption interface { // contains filtered or unexported methods }

func WithMaxTurnsadded inv0.3.0

func WithMaxTurns(maxTurns int) CommonGenOption

WithMaxTurns sets the maximum number of tool call iterations before erroring. A tool call happens when tools are provided in the request and a model decides to call one or more as a response. Each round trip, including multiple tools in parallel, counts as one turn.

func WithMessagesadded inv0.1.0

func WithMessages(messages ...*Message) CommonGenOption

WithMessages sets the messages. These messages will be sandwiched between the system and user prompts.

func WithMessagesFnadded inv0.3.0

func WithMessagesFn(fn MessagesFn) CommonGenOption

WithMessagesFn sets the request messages to the result of the function. These messages will be sandwiched between the system and user messages.

func WithMiddlewareadded inv0.3.0

func WithMiddleware(middleware ...ModelMiddleware) CommonGenOption

WithMiddleware sets middleware to apply to the model request.

func WithModeladded inv0.3.0

func WithModel(model ModelArg) CommonGenOption

WithModel sets a resolvable model reference to use for generation.

func WithModelNameadded inv0.3.0

func WithModelName(name string) CommonGenOption

WithModelName sets the model name to call for generation. The model name will be resolved to a Model and may error if the reference is invalid.

func WithReturnToolRequestsadded inv0.3.0

func WithReturnToolRequests(returnReqs bool) CommonGenOption

WithReturnToolRequests configures whether to return tool requests instead of making the tool calls and continuing the generation.

func WithToolChoiceadded inv0.3.0

func WithToolChoice(toolChoice ToolChoice) CommonGenOption

WithToolChoice configures whether by default tool calls are required, disabled, or optional for the prompt.

func WithToolsadded inv0.1.0

func WithTools(tools ...ToolRef) CommonGenOption

WithTools sets the tools to use for the generate request.

type CommonRerankerOptionsadded inv0.3.0

type CommonRerankerOptions struct { // Number of documents to rerank K float64 `json:"k,omitempty"` }

type CommonRetrieverOptionsadded inv0.3.0

type CommonRetrieverOptions struct { // Number of documents to retrieve K float64 `json:"k,omitempty"` }

type ConfigOptionadded inv0.5.0

type ConfigOption interface { // contains filtered or unexported methods }

ConfigOption is an option for model configuration.

func WithConfigadded inv0.1.0

func WithConfig(config any) ConfigOption

WithConfig sets the configuration.

type ConstrainedSupportadded inv0.3.0

type ConstrainedSupport string
const (  ConstrainedSupportNone ConstrainedSupport = "none"  ConstrainedSupportAll ConstrainedSupport = "all"  ConstrainedSupportNoTools ConstrainedSupport = "no-tools" )

type Document

type Document struct { // The data that is part of this document. Content []*Part `json:"content,omitempty"` // The metadata for this document. Metadata map[string]any `json:"metadata,omitempty"` }

A Document is a piece of data that can be embedded, indexed, or retrieved. It includes metadata. It can contain multiple parts.

func DocumentFromText

func DocumentFromText(text string, metadata map[string]any) *Document

DocumentFromText returns a Document containing a single plain text part. This takes ownership of the metadata map.

type DocumentOptionadded inv0.5.0

type DocumentOption interface { // contains filtered or unexported methods }

DocumentOption is an option for providing context or input documents. It applies only to Generate and Prompt.Execute.

func WithDocsadded inv0.3.0

func WithDocs(docs ...*Document) DocumentOption

WithDocs sets the documents to be used as context for generation or as input to an embedder.

func WithTextDocsadded inv0.5.0

func WithTextDocs(text ...string) DocumentOption

WithTextDocs sets the text to be used as context documents for generation or as input to an embedder.

type DownloadMediaOptionsadded inv0.3.0

type DownloadMediaOptions struct {  MaxBytes int64// Maximum number of bytes to download. Filter func(part *Part) bool// Filter to apply to parts that are media URLs.}

DownloadMediaOptions configures how media is downloaded in the DownloadRequestMedia middleware.

type EmbedRequest

type EmbedRequest struct {  Input []*Document `json:"input,omitempty"`  Options any `json:"options,omitempty"` }

type EmbedResponseadded inv0.0.2

type EmbedResponse struct {  Embeddings []*Embedding `json:"embeddings,omitempty"` }

func Embedadded inv0.1.0

func Embed(ctx context.Context, e Embedder, opts ...EmbedderOption) (*EmbedResponse, error)

Embed invokes the embedder with provided options.

type Embedder

type Embedder interface { // Name returns the registry name of the embedder. Name() string// Embed embeds to content as part of the [EmbedRequest]. Embed(ctx context.Context, req *EmbedRequest) (*EmbedResponse, error) }

Embedder represents an embedder that can perform content embedding.

func DefineEmbedder

func DefineEmbedder( r *registry.Registry, provider, name string, embed func(context.Context, *EmbedRequest) (*EmbedResponse, error), ) Embedder

DefineEmbedder registers the given embed function as an action, and returns an Embedder that runs it.

func LookupEmbedder

func LookupEmbedder(r *registry.Registry, provider, name string) Embedder

LookupEmbedder looks up an Embedder registered by DefineEmbedder. It returns nil if the embedder was not defined.

type EmbedderOptionadded inv0.5.0

type EmbedderOption interface { // contains filtered or unexported methods }

EmbedderOption is an option for configuring an embedder request. It applies only to Embed.

type Embeddingadded inv0.3.0

type Embedding struct {  Embedding []float32 `json:"embedding,omitempty"`  Metadata map[string]any `json:"metadata,omitempty"` }

type EvalFnResponseadded inv0.3.0

type EvalFnResponse struct {  Evaluation any `json:"evaluation,omitempty"`  SampleIndex float64 `json:"sampleIndex,omitempty"`  SpanID string `json:"spanId,omitempty"`  TestCaseID string `json:"testCaseId,omitempty"`  TraceID string `json:"traceId,omitempty"` }

type EvalRequestadded inv0.3.0

type EvalRequest struct {  Dataset []*BaseDataPoint `json:"dataset,omitempty"`  EvalRunID string `json:"evalRunId,omitempty"`  Options any `json:"options,omitempty"` }

type EvalResponseadded inv0.3.0

type EvalResponse []any

type EvalStatusEnumadded inv0.3.0

type EvalStatusEnum string
const (  EvalStatusEnumUNKNOWN EvalStatusEnum = "UNKNOWN"  EvalStatusEnumPASS EvalStatusEnum = "PASS"  EvalStatusEnumFAIL EvalStatusEnum = "FAIL" )

type EvaluationResultadded inv0.3.0

type EvaluationResult struct {  TestCaseId string `json:"testCaseId"`  TraceID string `json:"traceId,omitempty"`  SpanID string `json:"spanId,omitempty"`  Evaluation []Score `json:"evaluation"` }

EvaluationResult is the result of running the evaluator on a single Example. An evaluator may provide multiple scores simultaneously (e.g. if they are using an API to score on multiple criteria)

type Evaluatoradded inv0.3.0

type Evaluator interface { // Name returns the name of the evaluator. Name() string// Evaluates a dataset. Evaluate(ctx context.Context, req *EvaluatorRequest) (*EvaluatorResponse, error) }

Evaluator represents a evaluator action.

func DefineBatchEvaluatoradded inv0.3.0

func DefineBatchEvaluator(r *registry.Registry, provider, name string, options *EvaluatorOptions, batchEval func(context.Context, *EvaluatorRequest) (*EvaluatorResponse, error)) (Evaluator, error)

DefineBatchEvaluator registers the given evaluator function as an action, and returns a Evaluator that runs it. This method provide the full EvaluatorRequest to the callback function, giving more flexibilty to the user for processing the data, such as batching or parallelization.

func DefineEvaluatoradded inv0.3.0

func DefineEvaluator(r *registry.Registry, provider, name string, options *EvaluatorOptions, eval func(context.Context, *EvaluatorCallbackRequest) (*EvaluatorCallbackResponse, error)) (Evaluator, error)

DefineEvaluator registers the given evaluator function as an action, and returns a Evaluator that runs it. This method process the input dataset one-by-one.

func LookupEvaluatoradded inv0.3.0

func LookupEvaluator(r *registry.Registry, provider, name string) Evaluator

LookupEvaluator looks up an Evaluator registered by DefineEvaluator. It returns nil if the evaluator was not defined.

type EvaluatorCallbackRequestadded inv0.3.0

type EvaluatorCallbackRequest struct {  Input Example `json:"input"`  Options any `json:"options,omitempty"` }

EvaluatorCallbackRequest is the data we pass to the callback function provided in defineEvaluator. The Options field is specific to the actual evaluator implementation.

type EvaluatorCallbackResponseadded inv0.3.0

type EvaluatorCallbackResponse = EvaluationResult

EvaluatorCallbackResponse is the result on evaluating a single Example

type EvaluatorOptionadded inv0.5.0

type EvaluatorOption interface { // contains filtered or unexported methods }

EvaluatorOption is an option for providing a dataset to evaluate. It applies only to [Evaluator.Evaluate].

func WithDatasetadded inv0.5.0

func WithDataset(examples ...*Example) EvaluatorOption

WithDataset sets the dataset to do evaluation on.

func WithIDadded inv0.5.0

func WithID(ID string) EvaluatorOption

WithID sets the ID of the evaluation to uniquely identify it.

type EvaluatorOptionsadded inv0.3.0

type EvaluatorOptions struct {  DisplayName string `json:"displayName"`  Definition string `json:"definition"`  IsBilled bool `json:"isBilled,omitempty"` }

type EvaluatorRequestadded inv0.3.0

type EvaluatorRequest struct {  Dataset []*Example `json:"dataset"`  EvaluationId string `json:"evalRunId"`  Options any `json:"options,omitempty"` }

EvaluatorRequest is the data we pass to evaluate a dataset. The Options field is specific to the actual evaluator implementation.

type EvaluatorResponseadded inv0.3.0

type EvaluatorResponse = []EvaluationResult

EvaluatorResponse is a collection of EvaluationResult structs, it represents the result on the entire input dataset.

func Evaluateadded inv0.3.0

func Evaluate(ctx context.Context, r Evaluator, opts ...EvaluatorOption) (*EvaluatorResponse, error)

Evaluate calls the retrivers with provided options.

type Exampleadded inv0.3.0

type Example struct {  TestCaseId string `json:"testCaseId,omitempty"`  Input any `json:"input"`  Output any `json:"output,omitempty"`  Context []any `json:"context,omitempty"`  Reference any `json:"reference,omitempty"`  TraceIds []string `json:"traceIds,omitempty"` }

Example is a single example that requires evaluation

type ExecutionOptionadded inv0.3.0

type ExecutionOption interface { // contains filtered or unexported methods }

ExecutionOption is an option for the execution of a prompt or generate request. It applies only to Generate() and prompt.Execute().

func WithStreamingadded inv0.1.0

func WithStreaming(callback ModelStreamCallback) ExecutionOption

WithStreaming sets the stream callback for the generate request. A callback is a function that is called with each chunk of the generated response before the final response is returned.

type FinishReason

type FinishReason string
const (  FinishReasonStop FinishReason = "stop"  FinishReasonLength FinishReason = "length"  FinishReasonBlocked FinishReason = "blocked"  FinishReasonInterrupted FinishReason = "interrupted"  FinishReasonOther FinishReason = "other"  FinishReasonUnknown FinishReason = "unknown" )

type FormatHandleradded inv0.5.0

type FormatHandler interface { // ParseMessage parses the message and returns a new formatted message. ParseMessage(message *Message) (*Message, error) // Instructions returns the formatter instructions to embed in the prompt. Instructions() string// Config returns the output config for the model request. Config() ModelOutputConfig }

FormatHandler represents the handler part of the Formatter interface.

type Formatteradded inv0.5.0

type Formatter interface { // Name returns the name of the formatter. Name() string// Handler returns the handler for the formatter. Handler(schema map[string]any) (FormatHandler, error) }

Formatter represents the Formatter interface.

type GenerateActionOptionsadded inv0.3.0

type GenerateActionOptions struct {  Config any `json:"config,omitempty"`  Docs []*Document `json:"docs,omitempty"`  MaxTurns int `json:"maxTurns,omitempty"`  Messages []*Message `json:"messages,omitempty"`  Model string `json:"model,omitempty"`  Output *GenerateActionOutputConfig `json:"output,omitempty"`  Resume *GenerateActionResume `json:"resume,omitempty"`  ReturnToolRequests bool `json:"returnToolRequests,omitempty"`  ToolChoice ToolChoice `json:"toolChoice,omitempty"`  Tools []string `json:"tools,omitempty"` }

type GenerateActionOutputConfigadded inv0.3.0

type GenerateActionOutputConfig struct {  Constrained bool `json:"constrained,omitempty"`  ContentType string `json:"contentType,omitempty"`  Format string `json:"format,omitempty"`  Instructions *string `json:"instructions,omitempty"`  JsonSchema map[string]any `json:"jsonSchema,omitempty"` }

type GenerateActionResumeadded inv0.3.0

type GenerateActionResume struct {  Metadata map[string]any `json:"metadata,omitempty"`  Respond []*toolResponsePart `json:"respond,omitempty"`  Restart []*toolRequestPart `json:"restart,omitempty"` }

type GenerateOptionadded inv0.1.0

type GenerateOption interface { // contains filtered or unexported methods }

GenerateOption is an option for generating a model response. It applies only to Generate().

type GenerationCommonConfig

type GenerationCommonConfig struct {  MaxOutputTokens int `json:"maxOutputTokens,omitempty"`  StopSequences []string `json:"stopSequences,omitempty"`  Temperature float64 `json:"temperature,omitempty"`  TopK int `json:"topK,omitempty"`  TopP float64 `json:"topP,omitempty"`  Version string `json:"version,omitempty"` }

GenerationCommonConfig holds configuration for generation.

type GenerationUsage

type GenerationUsage struct {  Custom map[string]float64 `json:"custom,omitempty"`  InputAudioFiles float64 `json:"inputAudioFiles,omitempty"`  InputCharacters int `json:"inputCharacters,omitempty"`  InputImages int `json:"inputImages,omitempty"`  InputTokens int `json:"inputTokens,omitempty"`  InputVideos float64 `json:"inputVideos,omitempty"`  OutputAudioFiles float64 `json:"outputAudioFiles,omitempty"`  OutputCharacters int `json:"outputCharacters,omitempty"`  OutputImages int `json:"outputImages,omitempty"`  OutputTokens int `json:"outputTokens,omitempty"`  OutputVideos float64 `json:"outputVideos,omitempty"`  TotalTokens int `json:"totalTokens,omitempty"` }

GenerationUsage provides information about the generation process.

type GenkitErroradded inv0.3.0

type GenkitError struct {  Data *GenkitErrorData `json:"data,omitempty"`  Details any `json:"details,omitempty"`  Message string `json:"message,omitempty"`  Stack string `json:"stack,omitempty"` }

type GenkitErrorDataadded inv0.3.0

type GenkitErrorData struct {  GenkitErrorDetails *GenkitErrorDetails `json:"genkitErrorDetails,omitempty"`  GenkitErrorMessage string `json:"genkitErrorMessage,omitempty"` }

type GenkitErrorDetailsadded inv0.3.0

type GenkitErrorDetails struct {  Stack string `json:"stack,omitempty"`  TraceID string `json:"traceId,omitempty"` }

type Indexer

type Indexer interface { // Name returns the name of the indexer. Name() string// Index executes the indexing request. Index(ctx context.Context, req *IndexerRequest) error }

Indexer represents a document indexer.

func DefineIndexer

func DefineIndexer(r *registry.Registry, provider, name string, fn IndexerFunc) Indexer

DefineIndexer registers the given index function as an action, and returns an Indexer that runs it.

func LookupIndexer

func LookupIndexer(r *registry.Registry, provider, name string) Indexer

LookupIndexer looks up an Indexer registered by DefineIndexer. It returns nil if the model was not defined.

type IndexerFuncadded inv0.5.0

type IndexerFunc = func(context.Context, *IndexerRequest) error

type IndexerOptionadded inv0.1.0

type IndexerOption interface { // contains filtered or unexported methods }

IndexerOption is an option for configuring an embedder request. It applies only to Index.

type IndexerRequest

type IndexerRequest struct {  Documents []*Document `json:"documents"`  Options any `json:"options,omitempty"` }

IndexerRequest is the data we pass to add documents to the database. The Options field is specific to the actual retriever implementation.

type InterruptOptionsadded inv0.3.0

type InterruptOptions struct {  Metadata map[string]any}

InterruptOptions provides configuration for tool interruption.

type Mediaadded inv0.3.0

type Media struct {  ContentType string `json:"contentType,omitempty"`  Url string `json:"url,omitempty"` }

type Message

type Message struct {  Content []*Part `json:"content,omitempty"`  Metadata map[string]any `json:"metadata,omitempty"`  Role Role `json:"role,omitempty"` }

Message is the contents of a model response.

func NewMessage

func NewMessage(role Role, metadata map[string]any, parts ...*Part) *Message

NewMessage creates a new Message with the provided role, metadata and parts. Use NewTextMessage if you have a text-only message.

func NewModelMessage

func NewModelMessage(parts ...*Part) *Message

NewModelMessage creates a new Message with role "model" and provided parts. Use NewModelTextMessage if you have a text-only message.

func NewModelTextMessage

func NewModelTextMessage(text string) *Message

NewUserTextMessage creates a new Message with role "model" and content with a single text part with the content of provided text.

func NewSystemMessage

func NewSystemMessage(parts ...*Part) *Message

NewSystemMessage creates a new Message with role "system" and provided parts. Use NewSystemTextMessage if you have a text-only message.

func NewSystemTextMessage

func NewSystemTextMessage(text string) *Message

NewUserTextMessage creates a new Message with role "system" and content with a single text part with the content of provided text.

func NewTextMessage

func NewTextMessage(role Role, text string) *Message

NewTextMessage creates a new Message with the provided role and content with a single part containint provided text.

func NewUserMessage

func NewUserMessage(parts ...*Part) *Message

NewUserMessage creates a new Message with role "user" and provided parts. Use NewUserTextMessage if you have a text-only message.

func NewUserMessageWithMetadataadded inv0.3.0

func NewUserMessageWithMetadata(metadata map[string]any, parts ...*Part) *Message

NewUserMessageWithMetadata creates a new Message with role "user" with provided metadata and parts. Use NewUserTextMessage if you have a text-only message.

func NewUserTextMessage

func NewUserTextMessage(text string) *Message

NewUserTextMessage creates a new Message with role "user" and content with a single text part with the content of provided text.

func (*Message) Textadded inv0.3.0

func (m *Message) Text() string

Text returns the contents of a Message as a string. It returns an empty string if the message has no content.

func (*Message) WithCacheNameadded inv0.3.0

func (m *Message) WithCacheName(n string) *Message

WithCacheName adds cache name to use in the generate request

func (*Message) WithCacheTTLadded inv0.3.0

func (m *Message) WithCacheTTL(ttlSeconds int) *Message

WithCacheTTL adds cache TTL configuration for the desired message

type MessagesFnadded inv0.5.0

type MessagesFn = func(context.Context, any) ([]*Message, error)

MessagesFn is a function that generates messages.

type Model

type Model interface { // Name returns the registry name of the model. Name() string// Generate applies the [Model] to provided request, handling tool requests and handles streaming. Generate(ctx context.Context, req *ModelRequest, cb ModelStreamCallback) (*ModelResponse, error) }

Model represents a model that can generate content based on a request.

func DefineModel

func DefineModel(r *registry.Registry, provider, name string, info *ModelInfo, fn ModelFunc) Model

DefineModel registers the given generate function as an action, and returns a Model that runs it.

func LookupModel

func LookupModel(r *registry.Registry, provider, name string) Model

LookupModel looks up a Model registered by DefineModel. It returns nil if the model was not defined.

func LookupModelByNameadded inv0.3.0

func LookupModelByName(r *registry.Registry, modelName string) (Model, error)

LookupModelByName looks up a Model registered by DefineModel. It returns an error if the model was not defined.

type ModelArgadded inv0.5.0

type ModelArg interface {  Name() string}

ModelArg is the interface for model arguments.

type ModelFuncadded inv0.3.0

type ModelFunc = core.StreamingFunc[*ModelRequest, *ModelResponse, *ModelResponseChunk]

ModelFunc is a streaming function that takes in a ModelRequest and generates a ModelResponse, optionally streaming ModelResponseChunks.

type ModelInfo

type ModelInfo struct {  ConfigSchema map[string]any `json:"configSchema,omitempty"`  Label string `json:"label,omitempty"`  Stage ModelStage `json:"stage,omitempty"`  Supports *ModelSupports `json:"supports,omitempty"`  Versions []string `json:"versions,omitempty"` }

type ModelMiddlewareadded inv0.3.0

type ModelMiddleware = core.Middleware[*ModelRequest, *ModelResponse, *ModelResponseChunk]

ModelMiddleware is middleware for model generate requests that takes in a ModelFunc, does something, then returns another ModelFunc.

func DownloadRequestMediaadded inv0.3.0

func DownloadRequestMedia(options *DownloadMediaOptions) ModelMiddleware

DownloadRequestMedia downloads media from a URL and replaces the media part with a base64 encoded string.

type ModelOutputConfigadded inv0.3.0

type ModelOutputConfig struct {  Constrained bool `json:"constrained,omitempty"`  ContentType string `json:"contentType,omitempty"`  Format string `json:"format,omitempty"`  Schema map[string]any `json:"schema,omitempty"` }

OutputConfig describes the structure that the model's output should conform to. If Format is OutputFormatJSON, then Schema can describe the desired form of the generated JSON.

type ModelRefadded inv0.5.0

type ModelRef struct { // contains filtered or unexported fields }

ModelRef is a struct to hold model name and configuration.

func NewModelRefadded inv0.5.0

func NewModelRef(name string, config any) ModelRef

NewModelRef creates a new ModelRef with the given name and configuration.

func (ModelRef) Configadded inv0.5.0

func (m ModelRef) Config() any

ModelConfig returns the configuration of a ModelRef.

func (ModelRef) Nameadded inv0.5.0

func (m ModelRef) Name() string

Name returns the name of the ModelRef.

type ModelRequestadded inv0.3.0

type ModelRequest struct {  Config any `json:"config,omitempty"`  Docs []*Document `json:"docs,omitempty"`  Messages []*Message `json:"messages,omitempty"` // Output describes the desired response format. Output *ModelOutputConfig `json:"output,omitempty"`  ToolChoice ToolChoice `json:"toolChoice,omitempty"` // Tools lists the available tools that the model can ask the client to run. Tools []*ToolDefinition `json:"tools,omitempty"` }

A ModelRequest is a request to generate completions from a model.

func NewModelRequestadded inv0.3.0

func NewModelRequest(config any, messages ...*Message) *ModelRequest

NewModelRequest create a new ModelRequest with provided config and messages.

type ModelResponseadded inv0.3.0

type ModelResponse struct {  Custom any `json:"custom,omitempty"`  FinishMessage string `json:"finishMessage,omitempty"`  FinishReason FinishReason `json:"finishReason,omitempty"` // LatencyMs is the time the request took in milliseconds. LatencyMs float64 `json:"latencyMs,omitempty"`  Message *Message `json:"message,omitempty"` // Request is the [ModelRequest] struct used to trigger this response. Request *ModelRequest `json:"request,omitempty"` // Usage describes how many resources were used by this generation request. Usage *GenerationUsage `json:"usage,omitempty"` }

A ModelResponse is a model's response to a ModelRequest.

func Generateadded inv0.1.0

func Generate(ctx context.Context, r *registry.Registry, opts ...GenerateOption) (*ModelResponse, error)

Generate generates a model response based on the provided options.

func GenerateDataadded inv0.1.0

func GenerateData[Out any](ctx context.Context, r *registry.Registry, opts ...GenerateOption) (*Out, *ModelResponse, error)

Generate run generate request for this model. Returns ModelResponse struct. TODO: Stream GenerateData with partial JSON

func GenerateWithRequestadded inv0.3.0

func GenerateWithRequest(ctx context.Context, r *registry.Registry, opts *GenerateActionOptions, mw []ModelMiddleware, cb ModelStreamCallback) (*ModelResponse, error)

GenerateWithRequest is the central generation implementation for ai.Generate(), prompt.Execute(), and the GenerateAction direct call.

func (*ModelResponse) Historyadded inv0.3.0

func (mr *ModelResponse) History() []*Message

History returns messages from the request combined with the response message to represent the conversation history.

func (*ModelResponse) Outputadded inv0.3.0

func (mr *ModelResponse) Output(v any) error

Output unmarshals structured JSON output into the provided struct pointer.

func (*ModelResponse) Textadded inv0.3.0

func (gr *ModelResponse) Text() string

Text returns the contents of the first candidate in a ModelResponse as a string. It returns an empty string if there are no candidates or if the candidate has no message.

func (*ModelResponse) ToolRequestsadded inv0.5.0

func (mr *ModelResponse) ToolRequests() ([]*ToolRequest, error)

ToolRequests returns the tool requests from the response.

type ModelResponseChunkadded inv0.3.0

type ModelResponseChunk struct {  Aggregated bool `json:"aggregated,omitempty"`  Content []*Part `json:"content,omitempty"`  Custom any `json:"custom,omitempty"`  Index int `json:"index,omitempty"`  Role Role `json:"role,omitempty"` }

A ModelResponseChunk is the portion of the ModelResponse that is passed to a streaming callback.

func (*ModelResponseChunk) Textadded inv0.3.0

func (c *ModelResponseChunk) Text() string

Text returns the text content of the ModelResponseChunk as a string. It returns an error if there is no Content in the response chunk.

type ModelStageadded inv0.3.0

type ModelStage string
const (  ModelStageFeatured ModelStage = "featured"  ModelStageStable ModelStage = "stable"  ModelStageUnstable ModelStage = "unstable"  ModelStageLegacy ModelStage = "legacy"  ModelStageDeprecated ModelStage = "deprecated" )

type ModelStreamCallbackadded inv0.3.0

type ModelStreamCallback = func(context.Context, *ModelResponseChunk) error

ModelStreamCallback is a stream callback of a ModelAction.

type ModelSupportsadded inv0.3.0

type ModelSupports struct {  Constrained ConstrainedSupport `json:"constrained,omitempty"`  ContentType []string `json:"contentType,omitempty"`  Context bool `json:"context,omitempty"`  Media bool `json:"media,omitempty"`  Multiturn bool `json:"multiturn,omitempty"`  Output []string `json:"output,omitempty"`  SystemRole bool `json:"systemRole,omitempty"`  ToolChoice bool `json:"toolChoice,omitempty"`  Tools bool `json:"tools,omitempty"` }

type OutputOptionadded inv0.3.0

type OutputOption interface { // contains filtered or unexported methods }

OutputOption is an option for the output of a prompt or generate request. It applies only to DefinePrompt() and Generate().

func WithCustomConstrainedOutputadded inv0.5.0

func WithCustomConstrainedOutput() OutputOption

WithCustomConstrainedOutput opts out of using the model's native constrained output generation.

By default, the system will use the model's native constrained output capabilities when available. When this option is set, or when the model doesn't support native constraints, the system will use custom implementation to guide the model toward producing properly formatted output.

func WithOutputFormatadded inv0.1.0

func WithOutputFormat(format string) OutputOption

WithOutputFormat sets the format of the output.

func WithOutputInstructionsadded inv0.5.0

func WithOutputInstructions(instructions string) OutputOption

WithOutputInstructions sets custom instructions for constraining output format in the prompt.

When WithOutputType is used without this option, default instructions will be automatically set. If you provide empty instructions, no instructions will be added to the prompt.

This will automatically set WithCustomConstrainedOutput.

func WithOutputTypeadded inv0.3.0

func WithOutputType(output any) OutputOption

WithOutputType sets the schema and format of the output based on the value provided.

type Part

type Part struct {  Kind PartKind `json:"kind,omitempty"`  ContentType string `json:"contentType,omitempty"` // valid for kind==blob Text string `json:"text,omitempty"` // valid for kind∈{text,blob} ToolRequest *ToolRequest `json:"toolRequest,omitempty"` // valid for kind==partToolRequest ToolResponse *ToolResponse `json:"toolResponse,omitempty"` // valid for kind==partToolResponse Custom map[string]any `json:"custom,omitempty"` // valid for plugin-specific custom parts Metadata map[string]any `json:"metadata,omitempty"` // valid for all kinds}

A Part is one part of a Document. This may be plain text or it may be a URL (possibly a "data:" URL with embedded data).

func NewCustomPartadded inv0.5.1

func NewCustomPart(customData map[string]any) *Part

NewCustomPart returns a Part containing custom plugin-specific data.

func NewDataPart

func NewDataPart(contents string) *Part

NewDataPart returns a Part containing raw string data.

func NewJSONPart

func NewJSONPart(text string) *Part

NewJSONPart returns a Part containing JSON.

func NewMediaPart

func NewMediaPart(mimeType, contents string) *Part

NewMediaPart returns a Part containing structured data described by the given mimeType.

func NewTextPart

func NewTextPart(text string) *Part

NewTextPart returns a Part containing text.

func NewToolRequestPart

func NewToolRequestPart(r *ToolRequest) *Part

NewToolRequestPart returns a Part containing a request from the model to the client to run a Tool. (Only genkit plugins should need to use this function.)

func NewToolResponsePart

func NewToolResponsePart(r *ToolResponse) *Part

NewToolResponsePart returns a Part containing the results of applying a Tool that the model requested.

func (*Part) IsCustomadded inv0.5.1

func (p *Part) IsCustom() bool

IsCustom reports whether the Part contains custom plugin-specific data.

func (*Part) IsData

func (p *Part) IsData() bool

IsData reports whether the Part contains unstructured data.

func (*Part) IsMedia

func (p *Part) IsMedia() bool

IsMedia reports whether the Part contains structured media data.

func (*Part) IsText

func (p *Part) IsText() bool

IsText reports whether the Part contains plain text.

func (*Part) IsToolRequest

func (p *Part) IsToolRequest() bool

IsToolRequest reports whether the Part contains a request to run a tool.

func (*Part) IsToolResponse

func (p *Part) IsToolResponse() bool

IsToolResponse reports whether the Part contains the result of running a tool.

func (Part) JSONSchemaAlias

func (Part) JSONSchemaAlias() any

JSONSchemaAlias tells the JSON schema reflection code to use a different type for the schema for this type. This is needed because the JSON marshaling of Part uses a schema that matches the TypeScript code, rather than the natural JSON marshaling. This matters because the current JSON validation code works by marshaling the JSON.

func (*Part) MarshalJSON

func (p *Part) MarshalJSON() ([]byte, error)

MarshalJSON is called by the JSON marshaler to write out a Part.

func (*Part) UnmarshalJSON

func (p *Part) UnmarshalJSON(b []byte) error

UnmarshalJSON is called by the JSON unmarshaler to read a Part.

func (*Part) UnmarshalYAMLadded inv0.3.0

func (p *Part) UnmarshalYAML(value *yaml.Node) error

UnmarshalYAML implements yaml.Unmarshaler for Part.

type PartKind

type PartKind int8
const (  PartText PartKind = iota PartMedia  PartData  PartToolRequest  PartToolResponse  PartCustom )

type PathMetadataadded inv0.3.0

type PathMetadata struct {  Error string `json:"error,omitempty"`  Latency float64 `json:"latency,omitempty"`  Path string `json:"path,omitempty"`  Status string `json:"status,omitempty"` }

type Prompt

type Prompt struct { // contains filtered or unexported fields }

Prompt is a prompt template that can be executed to generate a model response.

func DefinePrompt

func DefinePrompt(r *registry.Registry, name string, opts ...PromptOption) (*Prompt, error)

DefinePrompt creates and registers a new Prompt.

func LoadPromptadded inv0.3.0

func LoadPrompt(r *registry.Registry, dir, filename, namespace string) (*Prompt, error)

LoadPrompt loads a single prompt into the registry.

func LookupPrompt

func LookupPrompt(r *registry.Registry, name string) *Prompt

LookupPrompt looks up a Prompt registered by DefinePrompt. It returns nil if the prompt was not defined.

func (*Prompt) Executeadded inv0.3.0

func (p *Prompt) Execute(ctx context.Context, opts ...PromptExecuteOption) (*ModelResponse, error)

Execute renders a prompt, does variable substitution and passes the rendered template to the AI model specified by the prompt.

func (*Prompt) Nameadded inv0.3.0

func (p *Prompt) Name() string

Name returns the name of the prompt.

func (*Prompt) Render

func (p *Prompt) Render(ctx context.Context, input any) (*GenerateActionOptions, error)

Render renders the prompt template based on user input.

type PromptExecuteOptionadded inv0.5.0

type PromptExecuteOption interface { // contains filtered or unexported methods }

PromptExecuteOption is an option for executing a prompt. It applies only to Prompt.Execute.

func WithInputadded inv0.3.0

func WithInput(input any) PromptExecuteOption

WithInput sets the input for the prompt request. Input must conform to the prompt's input schema and can either be a map[string]any or a struct of the same type.

type PromptFnadded inv0.5.0

type PromptFn = func(context.Context, any) (string, error)

PromptFn is a function that generates a prompt.

type PromptOptionadded inv0.3.0

type PromptOption interface { // contains filtered or unexported methods }

PromptOption is an option for defining a prompt. It applies only to DefinePrompt().

func WithDescriptionadded inv0.3.0

func WithDescription(description string) PromptOption

WithDescription sets the description of the prompt.

func WithInputTypeadded inv0.3.0

func WithInputType(input any) PromptOption

WithInputType uses the type provided to derive the input schema. The inputted value will serve as the default input if no input is given at generation time. Only supports structs and map[string]any types.

func WithMetadataadded inv0.3.0

func WithMetadata(metadata map[string]any) PromptOption

WithMetadata sets arbitrary metadata for the prompt.

type PromptingOptionadded inv0.3.0

type PromptingOption interface { // contains filtered or unexported methods }

PromptingOption is an option for the system and user prompts of a prompt or generate request. It applies only to DefinePrompt() and Generate().

func WithPromptadded inv0.5.0

func WithPrompt(text string, args ...any) PromptingOption

WithPrompt sets the user prompt message. The user prompt is always the last message in the list.

func WithPromptFnadded inv0.3.0

func WithPromptFn(fn PromptFn) PromptingOption

WithPromptFn sets the function that generates the user prompt message. The user prompt is always the last message in the list.

func WithSystemadded inv0.5.0

func WithSystem(text string, args ...any) PromptingOption

WithSystem sets the system prompt message. The system prompt is always the first message in the list.

func WithSystemFnadded inv0.3.0

func WithSystemFn(fn PromptFn) PromptingOption

WithSystemFn sets the function that generates the system prompt message. The system prompt is always the first message in the list.

type RankedDocumentDataadded inv0.3.0

type RankedDocumentData struct {  Content []*Part `json:"content,omitempty"`  Metadata *RankedDocumentMetadata `json:"metadata,omitempty"` }

type RankedDocumentMetadataadded inv0.3.0

type RankedDocumentMetadata struct {  Score float64 `json:"score,omitempty"` }

type RerankerRequestadded inv0.3.0

type RerankerRequest struct {  Documents []*Document `json:"documents,omitempty"`  Options any `json:"options,omitempty"`  Query *Document `json:"query,omitempty"` }

type RerankerResponseadded inv0.3.0

type RerankerResponse struct {  Documents []*RankedDocumentData `json:"documents,omitempty"` }

type Retriever

type Retriever interface { // Name returns the name of the retriever. Name() string// Retrieve retrieves the documents. Retrieve(ctx context.Context, req *RetrieverRequest) (*RetrieverResponse, error) }

Retriever represents a document retriever.

func DefineRetriever

func DefineRetriever(r *registry.Registry, provider, name string, fn RetrieverFunc) Retriever

DefineRetriever registers the given retrieve function as an action, and returns a Retriever that runs it.

func LookupRetriever

func LookupRetriever(r *registry.Registry, provider, name string) Retriever

LookupRetriever looks up a Retriever registered by DefineRetriever. It returns nil if the retriever was not defined.

type RetrieverFuncadded inv0.5.0

type RetrieverFunc = func(context.Context, *RetrieverRequest) (*RetrieverResponse, error)

type RetrieverOptionadded inv0.5.0

type RetrieverOption interface { // contains filtered or unexported methods }

RetrieverOption is an option for configuring a retriever request. It applies only to [Retriever.Retrieve].

type RetrieverRequest

type RetrieverRequest struct {  Options any `json:"options,omitempty"`  Query *Document `json:"query,omitempty"` }

type RetrieverResponse

type RetrieverResponse struct {  Documents []*Document `json:"documents,omitempty"` }

func Retrieveadded inv0.1.0

func Retrieve(ctx context.Context, r Retriever, opts ...RetrieverOption) (*RetrieverResponse, error)

Retrieve calls the retriever with the provided options.

type Role

type Role string

Role indicates which entity is responsible for the content of a message. 

const ( // RoleSystem indicates this message is user-independent context. RoleSystem Role = "system" // RoleUser indicates this message was generated by the client. RoleUser Role = "user" // RoleModel indicates this message was generated by the model during a previous interaction. RoleModel Role = "model" // RoleTool indicates this message was generated by a local tool, likely triggered by a request// from the model in one of its previous responses. RoleTool Role = "tool" )

type Scoreadded inv0.3.0

type Score struct {  Id string `json:"id,omitempty"`  Score any `json:"score,omitempty"`  Status string `json:"status,omitempty" jsonschema:"enum=UNKNOWN,enum=FAIL,enum=PASS"`  Error string `json:"error,omitempty"`  Details map[string]any `json:"details,omitempty"` }

Score is the evaluation score that represents the result of an evaluator. This struct includes information such as the score (numeric, string or other types), the reasoning provided for this score (if any), the score status (if any) and other details.

type ScoreDetailsadded inv0.3.0

type ScoreDetails struct {  Reasoning string `json:"reasoning,omitempty"` }

type ScoreStatusadded inv0.3.0

type ScoreStatus int

ScoreStatus is an enum used to indicate if a Score has passed or failed. This drives additional features in tooling / the Dev UI. 

const (  ScoreStatusUnknown ScoreStatus = iota ScoreStatusFail  ScoreStatusPass )

func (ScoreStatus) Stringadded inv0.3.0

func (ss ScoreStatus) String() string

type Tool

type Tool interface { // Name returns the name of the tool. Name() string// Definition returns ToolDefinition for for this tool. Definition() *ToolDefinition// RunRaw runs this tool using the provided raw input. RunRaw(ctx context.Context, input any) (any, error) }

Tool represents an instance of a tool.

func DefineTool

func DefineTool[In, Out any](r *registry.Registry, name, description string, fn func(ctx *ToolContext, input In) (Out, error)) Tool

DefineTool defines a tool function with interrupt capability

func LookupTooladded inv0.1.0

func LookupTool(r *registry.Registry, name string) Tool

LookupTool looks up the tool in the registry by provided name and returns it.

type ToolChoiceadded inv0.3.0

type ToolChoice string
const (  ToolChoiceAuto ToolChoice = "auto"  ToolChoiceRequired ToolChoice = "required"  ToolChoiceNone ToolChoice = "none" )

type ToolConfigadded inv0.3.0

type ToolConfig struct {  MaxTurns int// Maximum number of tool call iterations before erroring. ReturnToolRequests bool// Whether to return tool requests instead of making the tool calls and continuing the generation.}

ToolConfig handles configuration around tool calls during generation.

type ToolContextadded inv0.3.0

type ToolContext struct { context.Context// Interrupt is a function that can be used to interrupt the tool execution.// Interrupting tool execution returns the control to the caller with the// total model response so far. Interrupt func(opts *InterruptOptions) error }

ToolContext provides context and utility functions for tool execution.

type ToolDefadded inv0.1.0

type ToolDef[In, Out any] core.ActionDef[In, Out, struct{}]

A ToolDef is an implementation of a single tool.

func (*ToolDef[In, Out]) Definitionadded inv0.1.0

func (t *ToolDef[In, Out]) Definition() *ToolDefinition

Definition returns ToolDefinition for for this tool.

func (*ToolDef[In, Out]) Nameadded inv0.3.0

func (t *ToolDef[In, Out]) Name() string

Name returns the name of the tool.

func (*ToolDef[In, Out]) RunRawadded inv0.1.0

func (t *ToolDef[In, Out]) RunRaw(ctx context.Context, input any) (any, error)

RunRaw runs this tool using the provided raw map format data (JSON parsed as map[string]any).

type ToolDefinition

type ToolDefinition struct {  Description string `json:"description,omitempty"` // Valid JSON Schema representing the input of the tool. InputSchema map[string]any `json:"inputSchema,omitempty"` // additional metadata for this tool definition Metadata map[string]any `json:"metadata,omitempty"`  Name string `json:"name,omitempty"` // Valid JSON Schema describing the output of the tool. OutputSchema map[string]any `json:"outputSchema,omitempty"` }

A ToolDefinition describes a tool.

type ToolInterruptErroradded inv0.3.0

type ToolInterruptError struct {  Metadata map[string]any}

ToolInterruptError represents an intentional interruption of tool execution.

func (*ToolInterruptError) Erroradded inv0.3.0

func (e *ToolInterruptError) Error() string

type ToolNameadded inv0.3.0

type ToolName string

ToolName is a distinct type for a tool name. It is meant to be passed where a ToolRef is expected but no Tool is had.

func (ToolName) Nameadded inv0.3.0

func (t ToolName) Name() string

Name returns the name of the tool.

type ToolRefadded inv0.3.0

type ToolRef interface {  Name() string}

ToolRef is a reference to a tool.

type ToolRequest

type ToolRequest struct { // Input is a JSON object describing the input values to the tool.// An example might be map[string]any{"country":"USA", "president":3}. Input any `json:"input,omitempty"`  Name string `json:"name,omitempty"`  Ref string `json:"ref,omitempty"` }

A ToolRequest is a message from the model to the client that it should run a specific tool and pass a ToolResponse to the model on the next chat request it makes. Any ToolRequest will correspond to some ToolDefinition previously sent by the client.

type ToolResponse

type ToolResponse struct {  Name string `json:"name,omitempty"` // Output is a JSON object describing the results of running the tool.// An example might be map[string]any{"name":"Thomas Jefferson", "born":1743}. Output any `json:"output,omitempty"`  Ref string `json:"ref,omitempty"` }

A ToolResponse is a message from the client to the model containing the results of running a specific tool on the arguments passed to the client by the model in a ToolRequest.

type TraceMetadataadded inv0.3.0

type TraceMetadata struct {  FeatureName string `json:"featureName,omitempty"`  Paths []*PathMetadata `json:"paths,omitempty"`  Timestamp float64 `json:"timestamp,omitempty"` }

Source Files

View all Source files
go.dev uses cookies from Google to deliver and enhance the quality of its services and to analyze traffic. Learn more.
close