langchain.agents.xml.base
.create_xml_agent¶
- langchain.agents.xml.base.create_xml_agent(llm: BaseLanguageModel, tools: Sequence[BaseTool], prompt: BasePromptTemplate) Runnable [source]¶
Create an agent that uses XML to format its logic.
Examples:
from langchain import hub from langchain_community.chat_models import ChatAnthropic from langchain.agents import AgentExecutor, create_xml_agent prompt = hub.pull("hwchase17/xml-agent-convo") model = ChatAnthropic() tools = ... agent = create_xml_agent(model, tools, prompt) agent_executor = AgentExecutor(agent=agent, tools=tools) agent_executor.invoke({"input": "hi"}) # Use with chat history from langchain_core.messages import AIMessage, HumanMessage agent_executor.invoke( { "input": "what's my name?", # Notice that chat_history is a string # since this prompt is aimed at LLMs, not chat models "chat_history": "Human: My name is Bob
- AI: Hello Bob!”,
}
)
- Args:
llm: LLM to use as the agent. tools: Tools this agent has access to. prompt: The prompt to use, must have input keys of
tools and agent_scratchpad.
- Returns:
A runnable sequence representing an agent. It takes as input all the same input variables as the prompt passed in does. It returns as output either an AgentAction or AgentFinish.