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:

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.

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

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.

export 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.

PreviousCustom Tool and Agent NextRunning a Custom Tool and Agent in GLChat

Last updated 9 months ago

hashtagInstallation

hashtagRunning The Code

hashtagSet up your OPENAI_API_KEY

hashtagGet your OpenAI API key from https://platform.openai.com/api-keysarrow-up-right.

hashtagExecute the script

Installation

Running The Code

Set up your `OPENAI_API_KEY`

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

Execute the script