Skip to content

io.helidon.integrations.langchain4j.AgentsConfig

Description

Configuration for a single LangChain4j agent

Configuration options

KeyTypeDefaultDescription
chat-modelStringName of the dev.langchain4j.model.chat.ChatModel service to use for this agent
mcp-clientsList<String>Names of dev.langchain4j.mcp.client.McpClient services to use for MCP-backed tools
input-guardrailsList<Class>Input guardrail classes to apply to the agent
content-retrieverStringName of the dev.langchain4j.rag.content.retriever.ContentRetriever service to use for this agent
descriptionStringDescription of the agent
toolsList<Class>Tool service classes to register with the agent
chat-memoryStringName of the dev.langchain4j.memory.ChatMemory service to use for this agent
enabledBooleantrueIf set to false, agent will not be available even if configured
execute-tools-concurrentlyBooleanIf true, the agent's tools can be invoked in a concurrent manner
chat-memory-providerStringName of the dev.langchain4j.memory.chat.ChatMemoryProvider service to use for this agent
tool-providerStringName of the dev.langchain4j.service.tool.ToolProvider service to use for this agent
asyncBooleanIf true, the agent will be invoked in an asynchronous manner, allowing the workflow to continue without waiting for the agent's result
output-keyStringKey of the output variable that will be used to store the result of the agent's invocation
retrieval-augmentorStringName of the dev.langchain4j.rag.RetrievalAugmentor service to use for this agent
output-guardrailsList<Class>Output guardrail classes to apply to the agent
nameStringAgent identifier used to label the agent in workflows and/or agent registries

Usages


See the manifest for all available types.