🤖 Create Agents in a Second - with the Best Tools, RAG, Knowledge Graph and Vector Databases

⚡ Everything you need to create an LLM Agent is here. Access a comprehensive suite of tools, prompts, frameworks, and a knowledge hub of LLM models—all in one place to streamline your agent development.

📑 Table of Contents

• Introduction
• Architecture
• Installation
• Usage
  • Package Version
  • Python Interface
  • Source Code Version
• DemoGPT AgentHub
  • Installation
  • Creating Tools
  • Available Tools
  • Creating an Agent
  • Using an Agent
  • Available Agent Types
  • Using ReactAgent
  • Using RAG
  • Combining RAG with Agents
• To-Do
• Contribute
• Citations
• License

🤖 DemoGPT AgentHub

DemoGPT AgentHub is a powerful library that allows you to create, customize, and use AI agents with various tools.

🛠 Installation

To use DemoGPT AgentHub, simply install the main package:

pip install demogpt

🔧 Creating Tools

Creating custom tools is easy:

from demogpt_agenthub.tools import BaseTool
class MyCustomTool(BaseTool):
    def __init__(self):
        self.name = "MyCustomTool"
        self.description = "This tool does something amazing!"
        super().__init__()
    def run(self, query):
        # Implement your tool's functionality here
        return f"Result for: {query}"

Example Usage:

my_tool = MyCustomTool()
agent = ToolCallingAgent(tools=[my_tool], llm=llm, verbose=True)
agent.run("Can you use my custom tool?")

Example Output:

Reasoning:
The user is asking to use the custom tool called MyCustomTool. This tool is described as doing "something amazing", so I will use it to process the query.
Tool call:
MyCustomTool
Tool result:
Result for: Can you use my custom tool?
Answer:
Yes, I successfully used your custom tool! The tool processed your query and returned the following result: "Result for: Can you use my custom tool?"

🧰 Available Tools

DemoGPT AgentHub comes with several built-in tools:

• 🔍 TavilySearchTool
• 🌦 WeatherTool
• 📚 WikipediaTool
• 🐚 BashTool
• 🐍 PythonTool
• 📄 ArxivTool
• 🎥 YouTubeSearchTool
• 💻 StackOverFlowTool
• 🌐 RequestUrlTool
• 🗃 WikiDataTool
• 🏥 PubmedTool

🤖 Creating an Agent

To create an agent:

from demogpt_agenthub.agents import ToolCallingAgent
from demogpt_agenthub.llms import OpenAIChatModel
from demogpt_agenthub.tools import TavilySearchTool, WeatherTool

search_tool = TavilySearchTool()
weather_tool = WeatherTool()
llm = OpenAIChatModel(model_name="gpt-4o-mini")
agent = ToolCallingAgent(tools=[search_tool, weather_tool], llm=llm, verbose=True)

🎮 Using an Agent

Once you've created an agent, use it to ask questions or perform tasks:

query = "What's the weather like in New York today?"
response = agent.run(query)
print(response)

Example Output: