AddEmbedding adds an embedding node to the parallel. eg. embeddingNode, err := openai.NewEmbedder(ctx, &openai.EmbeddingConfig{ Model: "text-embed

AddEmbeddingNode adds an embedding node and returns it.

AddIndexerNode adds an indexer node to the workflow and returns it.

AddPassthrough adds a passthrough node to the parallel. eg. p.AddPassthrough("output_key01")

AddToolsNode adds a tools node to the parallel. eg. toolsNode, err := compose.NewToolNode(ctx, &compose.ToolsNodeConfig{ Tools: []tool.BaseTool{..

AfterAgent is called after the agent run reaches a successful terminal state. Successful terminal states are: final answer (model response with no too

AppendAgenticModel add a agentic.Model node to the chain. e.g. model, err := openai.NewAgenticModel(ctx, config) if err != nil {...} chain.AppendA

AppendIndexer add an Indexer node to the chain. Indexer is a node that can store documents. e.g. vectorStoreImpl, err := vikingdb.NewVectorStorer(ct

AppendLoader adds a Loader node to the chain. e.g. loader, err := file.NewFileLoader(ctx, &file.FileLoaderConfig{}) if err != nil {...} chain.Appe

AppendToolsNode add a ToolsNode node to the chain. e.g. toolsNode, err := compose.NewToolNode(ctx, &compose.ToolsNodeConfig{ Tools: []tools.BaseTo

BuildAgentCallback builds a callback handler for agent. e.g. callback := BuildAgentCallback(modelHandler, toolHandler) agent, err := react.NewAgent

Chain sets the chain handler for the handler helper, which will be called when the chain is executed.

Close safely closes the StreamReader. It should be called only once, as multiple calls may not work as expected. Notice: always remember to call Close

CollectableLambdaWithOption creates a Lambda with collectable lambda function and options.

ConvLoaderCallbackInput converts the callback input to the loader callback input.

ConvLoaderCallbackOutput converts the callback output to the loader callback output.

ConvTransformerCallbackInput converts the callback input to the transformer callback input.

ConvTransformerCallbackOutput converts the callback output to the transformer callback output.

CopyMap copies a map to a new map.

DSLInfo returns the dsl info of the document. can use doc.WithDSLInfo() to set the dsl info.

DenseVector returns the dense vector of the document. can use doc.WithDenseVector() to set the dense vector.

Edit replaces string occurrences in a file. Returns: - error: Error if file does not exist, OldString is empty, or OldString is not found

ExportGraph exports the underlying graph from MultiAgent, along with the []compose.GraphAddNodeOpt to be used when adding this graph to another graph.

ExtraInfo returns the extra info of the document. can use doc.WithExtraInfo() to set the extra info.

Format returns the agentic messages after rendering by the given formatType. It formats only the user input fields (UserInputText, UserInputImage, Use

FromInterruptContexts converts user-facing interrupt contexts to an interrupt signal.

GetCommonOptions extracts standard [Options] from opts, merging onto base. Implementors must call this inside Store: func (idx *MyIndexer) Store(ctx

GetCommonOptions extract embedding Options from Option list, optionally providing a base Options with default values. eg. defaultModelName := "defau

GetCommonOptions extracts standard [Options] from opts, merging onto base. Implementors must call this to honour caller-provided options: func (r *M

GetImplSpecificOptions returns the implementation-specific options from the given agent options.

GetImplSpecificOptions extracts the implementation specific options from Option list, optionally providing a base options with default values.

GetImplSpecificOptions extracts implementation-specific options from an Option list, merging them onto base. If base is nil, a zero-value T is used.

GetImplSpecificOptions provides Parser author the ability to extract their own custom options from the unified Option type. T: the type of the impl sp

GetImplSpecificOptions extract the implementation specific options from AgentRunOption list, optionally providing a base options with default values.

GetLoaderImplSpecificOptions provides Loader author the ability to extract their own custom options from the unified LoaderOption type. T: the type of

GetParsers returns a copy of the registered parsers. It is safe to modify the returned parsers.

GetTransformerImplSpecificOptions provides Transformer author the ability to extract their own custom options from the unified TransformerOption type.

GetType returns the type of the chat template (Default).

GrepRaw searches for content matching the specified pattern in files. Returns: - []GrepMatch: List of all matching results - error: Error if the sear

InferEnhancedStreamTool creates an [tool.EnhancedStreamableTool] by inferring the parameter JSON schema from type T. The function streams [schema.Tool

InferEnhancedTool creates an [tool.EnhancedInvokableTool] by inferring the parameter JSON schema from type T. The function returns a [schema.ToolResul

InferOptionableStreamTool is like [InferStreamTool] but the function also receives [tool.Option] values passed by ToolsNode at call time.

InferOptionableTool is like [InferTool] but the function also receives [tool.Option] values passed by ToolsNode at call time.

Invoke works like `ping => pong`.

IsCallbacksEnabled checks if the callbacks are enabled for the chat template.

Lambda sets the lambda handler for the handler helper, which will be called when the lambda is executed.

NewAgenticToolsNode creates a new AgenticToolsNode. e.g. conf := &ToolsNodeConfig{ Tools: []tool.BaseTool{invokableTool1, streamableTool2}, } to

NewContentBlockChunk creates a new ContentBlock with the given content and streaming metadata.

NewEnhancedStreamTool creates an [tool.EnhancedStreamableTool] from an explicit [schema.ToolInfo] and a typed streaming function.

NewEnhancedTool creates an [tool.EnhancedInvokableTool] from an explicit [schema.ToolInfo] and a function that returns [schema.ToolResult].

NewExitAction creates an action that signals the agent to exit. NOT RECOMMENDED: Agent transfer with full context sharing between agents has not prov

NewIndexer creates a new parent indexer that handles document splitting and sub-document management. Parameters: - ctx: context for the operation - c

NewMockToolCallingChatModel creates a new mock instance.

NewMockTransformer creates a new mock instance.

NewRetriever creates a new parent retriever that handles retrieving original documents based on sub-document search results. Parameters: - ctx: conte

NewRetriever creates a router retriever. router retriever is useful when you want to retrieve documents from multiple retrievers with different querie

NewStreamChainBranch creates a new ChainBranch instance based on a given stream condition. It takes a generic type T and a StreamGraphBranchCondition

NewTyped constructs and returns the filesystem middleware as a TypedChatModelAgentMiddleware[M]. This is the generic constructor that supports both *

NewTypedFinalizer creates a new TypedFinalizerBuilder. Handlers run in registration order, and the summary message is post-processed as DefaultFinali

RegisterValuesMergeFunc registers a function to merge outputs from multiple nodes when fan-in. It's used to define how to merge for a specific type. F

Score returns the score of the document. can use doc.WithScore() to set the score.