Running a Custom Tool and Agent Locally

This is an example of how to run a custom tool and agent locally, independent of GLChat.

This documentation has been deprecated and moved to the GL SDK Gitbook

Prerequisites

This example specifically requires:

• Python v3.11 or v3.12

• Pip

• Git

Installation

# you can use a Conda environment
pip install gllm-agents-binary

Running The Code

All the code used in the following examples can be found in our GitHub repository gen-ai-examples/custom-tool-and-agent.

This example uses hello_tool.py for the tool definition and hello_agent_example.py to run the agent.

Clone from GitHub

git clone https://github.com/GDP-ADMIN/gen-ai-examples.git
cd gen-ai-examples/examples/custom-tool-and-agent

Copy & Paste the Code

• hello_tool.py

  # Tool Definition
  from gllm_agents import BaseTool
  from pydantic import BaseModel, Field
  from typing import Any, Type
  
  class HelloInput(BaseModel):
      name: str = Field(..., description="The name to say hello to")
  
  class SimpleHelloTool(BaseTool):
      """A simple tool that says hello."""
      name: str = "simple_hello_tool"
      description: str = "Greets the user by name."
      args_schema: Type[BaseModel] = HelloInput
  
      def _run(self, name: str, **kwargs: Any) -> str:
          return f"Hello, {name}!"

• hello_agent_example.py

  # Agent Runner Script
  from gllm_agents import Agent
  from langchain_openai import ChatOpenAI
  from hello_tool import SimpleHelloTool
  
  # Initialize components
  llm = ChatOpenAI(model="gpt-4o")
  tool = SimpleHelloTool()
  
  # Create an agent
  agent = Agent(
      name="HelloAgent",
      instruction="You are a helpful assistant that can greet people by name using the provided tool.",
      llm=llm,
      tools=[tool],
      verbose=True
  )
  
  # Run the agent
  query = "Please greet World"
  response = agent.run(query)
  print(response['output'])

Set up your OPENAI_API_KEY

Get your OpenAI API key from https://platform.openai.com/api-keys.

Linux, macOS, or Windows WSL

export OPENAI_API_KEY="sk-..."

Windows Powershell

$env:OPENAI_API_KEY = "sk-..."

Windows Command Prompt

set OPENAI_API_KEY="sk-..."

Execute the script

python hello_agent_example.py

With verbose=True, you will see the agent's thinking process, which may look like this:

> Entering new AgentExecutor chain... Invoking: `simple_hello_tool` with `{'name': 'World'}` Hello, World! > Finished chain. Hello, World!

The key indicators of success:

• The agent initialization completes without errors

• The verbose output shows the tool being invoked

• The final output includes the greeting "Hello, World!"

Troubleshooting

For common issues and their solutions, please refer to the centralized FAQ document.