OpenAI

Updated

Integrate an OpenAI LLM into Conversational AI Engine.

OpenAI provides frontier models ranging from lightweight to high-capability.

Sample configuration

The following examples show how to configure OpenAI LLM when starting a conversational AI agent.

from agora_agent import Agent, OpenAI

# client is your configured Agora client
agent = (
    Agent(client)
    .with_stt(...)  # configure your STT vendor
    .with_llm(OpenAI(
        api_key='your-openai-key',  # omit api_key and base_url to use Agora-managed mode
        base_url='https://api.openai.com/v1/chat/completions',
        model='gpt-4o-mini',
        system_messages=[{'role': 'system', 'content': 'You are a helpful chatbot.'}],
        greeting_message='Hello, how can I assist you?',
        failure_message='Please hold on a second.',
        max_history=32,
    ))
    .with_tts(...)  # configure your TTS vendor
)
import { Agent, OpenAI } from 'agora-agents';

// client is your configured Agora client
const agent = new Agent({ client })
  .withStt(/* configure your STT vendor */)
  .withLlm(new OpenAI({
    apiKey: 'your-openai-key',  // omit apiKey and url to use Agora-managed mode
    url: 'https://api.openai.com/v1/chat/completions',
    model: 'gpt-4o-mini',
    systemMessages: [{ role: 'system', content: 'You are a helpful chatbot.' }],
    greetingMessage: 'Hello, how can I assist you?',
    failureMessage: 'Please hold on a second.',
    maxHistory: 32,
  }))
  .withTts(/* configure your TTS vendor */);
import (
    Agora "github.com/AgoraIO/agora-agents-go/v2"
    "github.com/AgoraIO/agora-agents-go/v2/agentkit"
    "github.com/AgoraIO/agora-agents-go/v2/agentkit/vendors"
)

// client is your configured Agora client
agent := agentkit.NewAgent(client).WithStt(/* configure your STT vendor */).
  WithLlm(
    vendors.NewOpenAI(vendors.OpenAIOptions{
        APIKey:  "your-openai-key",  // omit APIKey and BaseURL to use Agora-managed mode
        BaseURL: "https://api.openai.com/v1/chat/completions",
        Model:   "gpt-4o-mini",
        SystemMessages: []map[string]interface{}{
            {"role": "system", "content": "You are a helpful chatbot."},
        },
        GreetingMessage: "Hello, how can I assist you?",
        FailureMessage:  "Please hold on a second.",
        MaxHistory:      Agora.Int(32),
    }),
).WithTts(/* configure your TTS vendor */)
  • Managed mode

    To use an OpenAI LLM with Agora-managed credentials, set credential_mode to "managed" in the llm block. When using managed mode, api_key is not required. You can still use the llm field to configure additional settings such as system_messages and greeting_message. For more information, see Use managed mode.

    "llm": {
      "credential_mode": "managed",
      "vendor": "openai",
      "style": "openai",
      "url": "https://api.openai.com/v1/chat/completions",
      "params": {
        "model": "gpt-4.1-mini"
      },
      "system_messages": [
        {
          "role": "system",
          "content": "You are a helpful chatbot."
        }
      ],
      "max_history": 32,
      "greeting_message": "Hello, how can I assist you?",
      "failure_message": "Please hold on a second."
    }
  • BYOK

    "llm": {
        "url": "https://api.openai.com/v1/chat/completions",
        "api_key": "<your_llm_key>",
        "system_messages": [
          {
            "role": "system",
            "content": "You are a helpful chatbot."
          }
        ],
        "max_history": 32,
        "greeting_message": "Hello, how can I assist you?",
        "failure_message": "Please hold on a second.",
        "params": {
          "model": "gpt-4o-mini"
        }
      }

Key parameters

The following parameters are required when using your own API key (BYOK). When using managed mode, api_key is not required. For more information, see Use managed mode.

llm
ParameterDescription
api_keystring

Create or manage your API key from OpenAI organization settings. Required when using your own API key (BYOK).

urlstring

Use the completions endpoint.

paramsobject
  • model: string

    Refer to OpenAI models for available models. For managed mode, use gpt-4o-mini, gpt-4.1-mini, gpt-5-nano, or gpt-5-mini.

The table extends beyond the current width. Scroll horizontally to view more columns.

For complete llm configuration options, see LLM parameters. For OpenAI-specific options and model capabilities, see the OpenAI API documentation.