Dify

Dify is an open-source LLM application development platform that provides a unified API for multiple LLM providers with workflow orchestration and advanced features.

Setup and Configuration

To integrate Dify with Agora Conversational AI, install the plugin, configure your Agora project, and create an endpoint:

Install the Dify plugin
1. Log in to the Dify Console.
2. Click on Plugins in the top navigation bar to open the Marketplace.
3. Search for the Agora Conversational AI plugin.
4. Click Install to install the plugin.
5. After installation, confirm that the plugin status is Active in the Installed Plugins list.
Configure the Agora Console
1. Log in to the Agora Console.
2. Create a new project or select an existing one.
3. Enable the Conversational AI feature within the selected project.
4. Record the following information for later use:
  - App ID (unique project identifier)
  - Certificate (optional, if enabled for enhanced security)
5. Navigate to the RESTful API page and generate an API Key and API Secret (required for HTTP Basic Authentication).
Create an Endpoint in Dify
1. In the Dify console's left-hand navigation panel, click on the Agora Conversational AI plugin you just installed.
2. Click Create a new API endpoint to open the configuration page.
3. Fill in the following details:
  - App ID (copied from the Agora Console)
  - API Key and Secret (copied from the Agora Console)
  - TTS (Text-to-Speech) configuration (e.g., Azure or ElevenLabs)
Save and note the endpoint details
1. Save the endpoint configuration. Dify generates an Endpoint URL.
2. Note down this Endpoint URL and API Key for use in the llm configuration.

Sample configuration

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

from agora_agent import Agent, Dify

# client is your configured Agora client
agent = (
    Agent(client)
    .with_stt(...)  # configure your STT vendor
    .with_llm(Dify(
        api_key='your-dify-api-key',
        url='https://xxxxxx.ai-plugin.io/convoai/dify-completion',
        model='default',
        system_messages=[{'role': 'system', 'content': 'You are a helpful voice assistant.'}],
        greeting_message='Hello, how can I assist you today?',
        failure_message='Hold on a moment.',
        max_history=32,
    ))
    .with_tts(...)  # configure your TTS vendor
)

import { Agent, Dify } from 'agora-agents';

// client is your configured Agora client
const agent = new Agent({ client })
  .withStt(/* configure your STT vendor */)
  .withLlm(new Dify({
    apiKey: 'your-dify-api-key',
    url: 'https://xxxxxx.ai-plugin.io/convoai/dify-completion',
    model: 'default',
    systemMessages: [{ role: 'system', content: 'You are a helpful voice assistant.' }],
    greetingMessage: 'Hello, how can I assist you today?',
    failureMessage: 'Hold on a moment.',
    maxHistory: 32,
  }))
  .withTts(/* configure your TTS vendor */);

import "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.NewDify(vendors.DifyOptions{
        APIKey: "your-dify-api-key",
        URL:    "https://xxxxxx.ai-plugin.io/convoai/dify-completion",
        Model:  "default",
        SystemMessages: []map[string]interface{}{
            {"role": "system", "content": "You are a helpful voice assistant."},
        },
        GreetingMessage: "Hello, how can I assist you today?",
        FailureMessage:  "Hold on a moment.",
        MaxHistory:      agora.Int(32),
    }),
).WithTts(/* configure your TTS vendor */)

Use the following llm configuration in your request:

"llm": {
   "url": "https://xxxxxx.ai-plugin.io/convoai/dify-completion",
   "api_key": "<same_api_key_as_in_endpoint_setup>",
   "system_messages": [
       {
           "role": "system",
           "content": "You are a helpful voice assistant."
       }
   ],
   "max_history": 32,
   "greeting_message": "Hello, how can I assist you today?",
   "failure_message": "Hold on a moment.",
   "params": {
       "model": "default"
   },
   "style": "dify"
}

Key parameters

llmrequired

api_keystring

required

Use the same API key configured in your Dify endpoint setup.

urlstring

required

Use the custom endpoint URL from your Dify marketplace integration.

stylestring

required

Set to dify to use Dify's message format and workflow processing.

paramsobject

required

modelstring

required

Set to default to use the model configured in your Dify application.

For advanced configuration options, workflow setup, and detailed parameter descriptions, see the Agora Conversational AI - Dify Marketplace documentation.

Setup and Configuration

Sample configuration

Key parameters

Contact Us

Contact Us