Class LangChainRunnerFactory

Factory for creating LangChain runners (chat completion and agent).

Hierarchy

AIProvider
- LangChainRunnerFactory

Index

Constructors

Properties

Methods

createAgent createAgentGraph createModel _ensureInstrumented

Constructors

constructor

new LangChainRunnerFactory(logger?): LangChainRunnerFactory
Parameters
- Optional logger: LDLogger
  Optional
Returns LangChainRunnerFactory
Overrides AIProvider.constructor
- Defined in ai-providers/server-ai-langchain/src/LangChainRunnerFactory.ts:21

Properties

`Protected` `Optional` _logger

_logger?: LDLogger

Methods

createAgent

createAgent(config, tools?): Promise<LangChainAgentRunner>
Create an agent runner from an agent AI configuration.

Uses LangChain's createAgent to build a compiled agent graph that handles the tool-calling loop internally. Tool definitions are sourced from config.model.parameters.tools and matched against the supplied tools registry.
Parameters
- config: LDAIAgentConfig
- Optional tools: ToolRegistry
  Optional
Returns Promise<LangChainAgentRunner>
Overrides AIProvider.createAgent
- Defined in ai-providers/server-ai-langchain/src/LangChainRunnerFactory.ts:51

createAgentGraph

createAgentGraph(_graphDef, _tools?): Promise<undefined | AgentGraphRunner>
Create an AgentGraphRunner for an agent graph definition.

Override in provider subclasses to return a configured AgentGraphRunner. Default implementation returns undefined.
Parameters
- _graphDef: AgentGraphDefinition
- Optional _tools: ToolRegistry
  Optional
Returns Promise<undefined | AgentGraphRunner>
Promise resolving to an AgentGraphRunner, or undefined if this provider does not support graph execution.
Inherited from AIProvider.createAgentGraph
- Defined in sdk/server-ai/dist/index.d.ts:1236

createModel

createModel(config, multiTurn?): Promise<LangChainModelRunner>
Create a model runner from a completion AI configuration.
Parameters
- config: LDAICompletionConfig
  
  The completion (or judge) AI configuration.
- multiTurn: boolean = true
  
  Whether the runner should accumulate conversation history across successive run() calls. Defaults to true (chat semantics). Pass false for stateless runners such as judges.
Returns Promise<LangChainModelRunner>
Overrides AIProvider.createModel
- Defined in ai-providers/server-ai-langchain/src/LangChainRunnerFactory.ts:35

`Static` `Private` _ensureInstrumented

_ensureInstrumented(logger?): Promise<void>
Automatically patches the ESM LangChain module for OpenTelemetry tracing when a TracerProvider is active and @traceloop/instrumentation-langchain is installed.
Parameters
- Optional logger: LDLogger
  Optional
Returns Promise<void>
- Defined in ai-providers/server-ai-langchain/src/LangChainRunnerFactory.ts:79

Generated using TypeDoc