Claude Anthropic

Claude from Anthropic provides helpful, harmless, and honest AI assistance with strong reasoning capabilities and natural conversational abilities.

The following example shows a starting llm parameter configuration you can use when you Start a conversational AI agent.

_19

"llm": {

_19

"url": "https://api.anthropic.com/v1/messages",

_19

"api_key": "<api_key>",

_19

"headers": "{\"anthropic-version\":\"2023-06-01\"}",

_19

"system_messages": [

_19

{

_19

"role": "user",

_19

"content": "You are a Conversational AI Agent, developed by Agora."

_19

}

_19

],

_19

"max_history": 32,

_19

"greeting_message": "Good to see you!",

_19

"failure_message": "Hold on a second.",

_19

"params": {

_19

"model": "claude-3-5-haiku-latest",

_19

"max_tokens": 1024

_19

},

_19

"style": "anthropic"

_19

}

• api_key: Get your API key from Anthropic Console.
• url: Use Anthropic's messages endpoint.
• headers: Must include anthropic-version header for API compatibility.
• model: Refer to Claude models for available models.
• max_tokens: Must specify maximum tokens in the response.
• style: Set to "anthropic" to use Claude's message format.

For advanced configuration options, model capabilities, and detailed parameter descriptions, see the Claude API documentation.