Anthropic Agent

Overview

The AnthropicAgent is a powerful and flexible agent class in the Multi-Agent Orchestrator System. It leverages the Anthropic API to interact with various Large Language Models (LLMs) provided by Anthropic, such as Claude. This agent can handle a wide range of processing tasks, making it suitable for diverse applications such as conversational AI, question-answering systems, and more.

Key Features

• Integration with Anthropic’s API
• Support for multiple LLM models available on Anthropic’s platform
• Streaming and non-streaming response options
• Customizable inference configuration
• Ability to set and update custom system prompts
• Optional integration with retrieval systems for enhanced context
• Support for Tool use within the conversation flow

Creating a AnthropicAgent

By default, the AnthropicAgent uses the claude-3-5-sonnet-20240620 model.

Basic Example

To create a new Anthropic Agent with only the required parameters, use the following code:

TypeScript

import { AnthropicAgent } from 'multi-agent-orchestrator';

const agent = new AnthropicAgent({
  name: 'Tech Agent',
  description: 'Specializes in technology areas including software development, \
  hardware, AI, cybersecurity, blockchain, cloud computing, \
  emerging tech innovations,and pricing/costs related to \
  technology products and services.',
  apiKey: 'your-anthropic-api-key-here'
});

Python

In this basic example, only the name, description and apiKey are provided, which are the only required parameters for creating a AnthropicAgent.

Advanced Example

For more complex use cases, you can create a Anthropic Agent with all available options. All parameters except name, description and apiKey or client are optional:

TypeScript

import { AnthropicAgent, AnthropicAgentOptions, ParticipantRole } from 'multi-agent-orchestrator';
import { Retriever } from '../retrievers/retriever';

const options: AnthropicAgentOptions = {
  name: 'My Advanced Anthropic Agent',
  description: 'A versatile agent for complex NLP tasks',
  apiKey: 'your-anthropic-api-key-here',
  modelId: 'claude-3-opus-20240229',
  streaming: true,
  inferenceConfig: {
    maxTokens: 1000,
    temperature: 0.7,
    topP: 0.9,
    stopSequences: ['Human:', 'AI:']
  },
  retriever: new Retriever(), // Assuming you have a Retriever class implemented
  toolConfig: {
    tool: [
      {
        name: "Weather_Tool",
        description: "Get the current weather for a given location, based on its WGS84 coordinates.",
        input_schema: {
            type: "object",
            properties: {
                latitude: {
                    type: "string",
                    description: "Geographical WGS84 latitude of the location.",
                },
                longitude: {
                    type: "string",
                    description: "Geographical WGS84 longitude of the location.",
                },
            },
            required: ["latitude", "longitude"],
        }
      }
    ],
    useToolHandler: (response, conversation) => {
      // Process tool response
      // Return processed response
      return {role: ParticipantRole.USER, content: {
                "type": "tool_result",
                "tool_use_id": "tool_user_id",
                "content": "Response from the tool"
            }}
    }
  }
};

const agent = new AnthropicAgent(options);

Python

Option Explanations

• name and description: Identify and describe the agent’s purpose.
• apiKey: Your Anthropic API key for authentication.
• modelId: Specifies the LLM model to use (e.g., Claude 3 Sonnet).
• streaming: Enables streaming responses for real-time output.
• inferenceConfig: Fine-tunes the model’s output characteristics.
• retriever: Integrates a retrieval system for enhanced context.
• toolConfig: Defines tools the agent can use and how to handle their responses.

Setting a New Prompt

You can dynamically set or update the system prompt for the agent:

TypeScript

agent.setSystemPrompt(
  `You are an AI assistant specialized in {{DOMAIN}}.
   Your main goal is to {{GOAL}}.
   Always maintain a {{TONE}} tone in your responses.`,
  {
    DOMAIN: "cybersecurity",
    GOAL: "help users understand and mitigate potential security threats",
    TONE: "professional and reassuring"
  }
);

Python

agent.set_system_prompt(
    """You are an AI assistant specialized in {{DOMAIN}}.
       Your main goal is to {{GOAL}}.
       Always maintain a {{TONE}} tone in your responses.""",
    {
        "DOMAIN": "cybersecurity",
        "GOAL": "help users understand and mitigate potential security threats",
        "TONE": "professional and reassuring"
    }
)

This method allows you to dynamically change the agent’s behavior and focus without creating a new instance.

Adding the Agent to the Orchestrator

To integrate the Anthropic Agent into your orchestrator, follow these steps:

1. First, ensure you have created an instance of the orchestrator:

TypeScript

import { MultiAgentOrchestrator } from "multi-agent-orchestrator";

const orchestrator = new MultiAgentOrchestrator();

Python

from multi_agent_orchestrator.orchestrator import MultiAgentOrchestrator

orchestrator = MultiAgentOrchestrator()

2. Then, add the agent to the orchestrator:

TypeScript

orchestrator.addAgent(agent);

Python

orchestrator.add_agent(agent)

3. Now you can use the orchestrator to route requests to the appropriate agent, including your Anthropic agent:

TypeScript

const response = await orchestrator.routeRequest(
  "What is the base rate interest for 30 years?",
  "user123",
  "session456"
);

Python

response = await orchestrator.route_request(
    "What is the base rate interest for 30 years?",
    "user123",
    "session456"
)

---

By leveraging the AnthropicAgent, you can create sophisticated, context-aware AI agents capable of handling a wide range of tasks and interactions, all powered by the latest LLM models available through Anthropic’s platform.