Agents use LLMs to decide which actions to take.
Build autonomous AI assistants with LangChain agents.
Agent Types
Zero-shot Agent: Decides without examples
Conversational Agent: For chat applications
ReAct Agent: Reasoning and acting
Creating an Agent
from langchain.agents import initialize_agent, Tool
from langchain.tools import DuckDuckGoSearchRun
search = DuckDuckGoSearchRun()
tools = [Tool(name=”Search”, func=search.run, description=”Search the web”)]
agent = initialize_agent(tools, llm, agent=”zero-shot-react-description”)
agent.run(“What is the weather in Tokyo?”)
Custom Tools
Create your own tools for specific tasks.
Conclusion
Agents enable powerful automation!