### Get Image to Video Models (cURL, Java, JavaScript, PHP, Python)

Source: https://docs.akool.com/ai-tools-suite/aimodel

This snippet demonstrates how to fetch a list of available image-to-video models from the Akool API. It includes examples for making the GET request using cURL, Java, JavaScript, PHP, and Python. The API requires an 'x-api-key' header for authentication. The response contains metadata about each model, including its type, description, supported resolutions, and pricing information.

```cURL
curl --location 'https://openapi.akool.com/api/open/v4/aigModel/list?types[]=1501' \
--header 'x-api-key: {{API Key}}'
```

```Java
OkHttpClient client = new OkHttpClient().newBuilder()
  .build();
Request request = new Request.Builder()
    .url("https://openapi.akool.com/api/open/v4/aigModel/list?types[]=1501")
    .method("GET", null)
    .addHeader("x-api-key", "{{API Key}}")
    .build();
Response response = client.newCall(request).execute();
```

```JavaScript
const myHeaders = new Headers();
myHeaders.append("x-api-key", "{{API Key}}");

const requestOptions = {
  method: "GET",
  headers: myHeaders,
  redirect: "follow"
};

fetch("https://openapi.akool.com/api/open/v4/aigModel/list?types[]=1501", requestOptions)
  .then((response) => response.text())
  .then((result) => console.log(result))
  .catch((error) => console.error(error));
```

```PHP
<?php
  $client = new Client();
  $headers = [
    'x-api-key' =>'{{API Key}}'
  ];
  $request = new Request('GET', 'https://openapi.akool.com/api/open/v4/aigModel/list?types[]=1501', $headers);
  $res = $client->sendAsync($request)->wait();
  echo $res->getBody();
?>
```

```Python
import requests

url = "https://openapi.akool.com/api/open/v4/aigModel/list?types[]=1501"

headers = {
  'x-api-key':'{{API Key}}'
}

response = requests.request("GET", url, headers=headers)
print(response.text)
```

--------------------------------

### Install Streaming Avatar SDKs

Source: https://docs.akool.com/implementation-guide/streaming-avatar

Commands to install the necessary SDK packages for Agora, LiveKit, or TRTC via npm or yarn.

```bash
npm install agora-rtc-sdk-ng
# or
yarn add agora-rtc-sdk-ng
```

```bash
npm install livekit-client
# or
yarn add livekit-client
```

```bash
npm install trtc-sdk-v5
# or
yarn add trtc-sdk-v5
```

--------------------------------

### Publish and Control Audio Stream (TRTC)

Source: https://docs.akool.com/implementation-guide/streaming-avatar

This example shows how to manage local audio streams with the TRTC SDK. It includes functions to start and stop audio capture, as well as mute and unmute the local audio. The `setupAudioInteraction` function provides methods to control the audio state, ensuring proper handling of audio publishing and unpublishing.

```typescript
async function publishAudio(client: TRTC) {
    try {
      // Start local audio capture
      await client.startLocalAudio({
        quality: TRTC.TRTCAudioQualityDefault
      });
      
      console.log("Audio publishing successful");
      return true;
    } catch (error) {
      console.error("Error publishing audio:", error);
      throw error;
    }
  }

  // Example usage with audio controls
  async function setupAudioInteraction(client: TRTC) {
    let isAudioEnabled = false;
    
    // Start audio
    async function startAudio() {
      try {
        await publishAudio(client);
        isAudioEnabled = true;
      } catch (error) {
        console.error("Failed to start audio:", error);
      }
    }

    // Stop audio
    async function stopAudio() {
      if (isAudioEnabled) {
        try {
          await client.stopLocalAudio();
          isAudioEnabled = false;
        } catch (error) {
          console.error("Failed to stop audio:", error);
        }
      }
    }

    // Mute/unmute audio
    function toggleAudio(muted: boolean) {
      if (isAudioEnabled) {
        client.muteLocalAudio(muted);
      }
    }

    return {
      startAudio,
      stopAudio,
      toggleAudio
    };
  }
```

--------------------------------

### Initialize Avatar with Audio Controls (Agora)

Source: https://docs.akool.com/implementation-guide/streaming-avatar

This snippet demonstrates the complete integration of audio functionality when initializing a streaming avatar with the Agora SDK. It shows how to initialize the avatar, set up audio controls, start audio, toggle mute states, and finally stop the audio stream, providing a clear example of the audio interaction lifecycle.

```typescript
async function initializeWithAudio() {
    try {
      // Initialize avatar
      const client = await initializeStreamingAvatar();
      
      // Setup audio controls
      const audioControls = await setupAudioInteraction(client);
      
      // Start audio when needed
      await audioControls.startAudio();
      
      // Example of muting/unmuting
      audioControls.toggleAudio(true); // mute
      audioControls.toggleAudio(false); // unmute
      
      // Stop audio when done
      await audioControls.stopAudio();
      
    } catch (error) {
      console.error("Error initializing with audio:", error);
    }
  }
```

--------------------------------

### Delete Knowledge Base Request Examples

Source: https://docs.akool.com/ai-tools-suite/knowledge-base

Provides examples of how to make a DELETE request to the Akool API to delete a knowledge base, shown in cURL, Java, Javascript, PHP, and Python. These examples illustrate how to set headers, content type, and the request body.

```bash
curl --location --request DELETE 'https://openapi.akool.com/api/open/v4/knowledge/delete' \
--header 'x-api-key: {{API Key}}' \
--header 'Content-Type: application/json' \
--data '{
  "id": "64f8a1b2c3d4e5f6a7b8c9d0"
}'
```

```java
OkHttpClient client = new OkHttpClient().newBuilder()
  .build();
MediaType mediaType = MediaType.parse("application/json");
RequestBody body = RequestBody.create(mediaType, "{\n  \"id\": \"64f8a1b2c3d4e5f6a7b8c9d0\"\n}");
Request request = new Request.Builder()
  .url("https://openapi.akool.com/api/open/v4/knowledge/delete")
  .method("DELETE", body)
  .addHeader("x-api-key", "{{API Key}}")
  .addHeader("Content-Type", "application/json")
  .build();
Response response = client.newCall(request).execute();
```

```javascript
const myHeaders = new Headers();
myHeaders.append("x-api-key", "{{API Key}}");
myHeaders.append("Content-Type", "application/json");

const raw = JSON.stringify({
  "id": "64f8a1b2c3d4e5f6a7b8c9d0"
});

const requestOptions = {
  method: "DELETE",
  headers: myHeaders,
  body: raw,
  redirect: "follow"
};

fetch("https://openapi.akool.com/api/open/v4/knowledge/delete", requestOptions)
  .then((response) => response.text())
  .then((result) => console.log(result))
  .catch((error) => console.error(error));
```

```php
<?php
$client = new Client();
$headers = [
  'x-api-key' =>'{{API Key}}',
  'Content-Type' => 'application/json'
];
$body = '{
  "id": "64f8a1b2c3d4e5f6a7b8c9d0"
}';
$request = new Request('DELETE', 'https://openapi.akool.com/api/open/v4/knowledge/delete', $headers, $body);
$res = $client->sendAsync($request)->wait();
echo $res->getBody();
?>
```

```python
import requests
import json

url = "https://openapi.akool.com/api/open/v4/knowledge/delete"

payload = json.dumps({
  "id": "64f8a1b2c3d4e5f6a7b8c9d0"
})
headers = {
  'x-api-key':'{{API Key}}',
  'Content-Type': 'application/json'
}

response = requests.request("DELETE", url, headers=headers, data=payload)
print(response.text)
```

--------------------------------

### Initialize Akool Streaming Avatar SDK in Browser

Source: https://docs.akool.com/sdk/jssdk-start

Demonstrates how to include the SDK via CDN, initialize the GenericAgoraSDK, and handle remote video stream subscriptions. It also shows the process for joining a channel and starting a chat session.

```html
<script src="https://unpkg.com/akool-streaming-avatar-sdk"></script>
<script>
  const agoraSDK = new AkoolStreamingAvatar.GenericAgoraSDK({ mode: "rtc", codec: "vp8" });

  agoraSDK.on({
    onUserPublished: async (user, mediaType) => {
      if (mediaType === 'video') {
        const remoteTrack = await agoraSDK.getClient().subscribe(user, mediaType);
        remoteTrack?.play('remote-video');
      }
    }
  });

  async function initializeSDK() {
    await agoraSDK.joinChannel({
      agora_app_id: "YOUR_APP_ID",
      agora_channel: "YOUR_CHANNEL", 
      agora_token: "YOUR_TOKEN",
      agora_uid: 12345
    });

    await agoraSDK.joinChat({
      vid: "YOUR_VOICE_ID",
      lang: "en", 
      mode: 2
    });
  }

  initializeSDK().catch(console.error);
</script>
```

--------------------------------

### Get Video Info by Model ID - JavaScript

Source: https://docs.akool.com/ai-tools-suite/lip-sync

This JavaScript example demonstrates fetching video information by video_model_id using the Fetch API. It includes setting the necessary headers with an API key for authentication.

```javascript
const myHeaders = new Headers();
myHeaders.append("x-api-key", "{{API Key}}");

const requestOptions = {
  method: "GET",
  headers: myHeaders,
  redirect: "follow",
};

fetch(
  "http://openapi.akool.com/api/open/v3/content/video/infobymodelid?video_model_id=66160f989dfc997ac289037b",
  requestOptions
)
  .then((response) => response.text())
  .then((result) => console.log(result))
  .catch((error) => console.error(error));
```

--------------------------------

### Initialize and Use Akool Streaming Avatar SDK

Source: https://docs.akool.com/sdk/jssdk-start

Demonstrates how to instantiate the SDK, register event handlers, join an Agora channel, and send messages to the avatar.

```javascript
import { GenericAgoraSDK } from 'akool-streaming-avatar-sdk';

const agoraSDK = new GenericAgoraSDK({ mode: "rtc", codec: "vp8" });

agoraSDK.on({
  onStreamMessage: (uid, message) => console.log("Received:", uid, message),
  onUserPublished: async (user, mediaType) => {
    const remoteTrack = await agoraSDK.getClient().subscribe(user, mediaType);
    remoteTrack?.play(mediaType === 'video' ? 'remote-video' : undefined);
  }
});

const akoolSession = await fetch('your-backend-url');
const { data: { credentials } } = await akoolSession.json();

await agoraSDK.joinChannel({
  agora_app_id: credentials.agora_app_id,
  agora_channel: credentials.agora_channel,
  agora_token: credentials.agora_token,
  agora_uid: credentials.agora_uid
});

await agoraSDK.joinChat({ vid: "voice-id", lang: "en", mode: 2 });
await agoraSDK.sendMessage("Hello, world!");
```

--------------------------------

### Publish and Control Audio Stream (LiveKit)

Source: https://docs.akool.com/implementation-guide/streaming-avatar

This code illustrates how to create and publish a local audio track using the LiveKit client SDK. It provides functions to initiate audio, terminate it, and toggle mute status. The `setupAudioInteraction` function returns an object with methods to control the audio stream within a LiveKit room.

```typescript
import { createLocalAudioTrack } from 'livekit-client';

async function publishAudio(room: Room) {
    // Create a microphone audio track
    const audioTrack = await createLocalAudioTrack();
    
    try {
      // Publish the audio track to the room
      await room.localParticipant.publishTrack(audioTrack);
      console.log("Audio publishing successful");
      
      return audioTrack;
    } catch (error) {
      console.error("Error publishing audio:", error);
      throw error;
    }
  }

  // Example usage with audio controls
  async function setupAudioInteraction(room: Room) {
    let audioTrack;
    
    // Start audio
    async function startAudio() {
      try {
        audioTrack = await publishAudio(room);
      } catch (error) {
        console.error("Failed to start audio:", error);
      }
    }

    // Stop audio
    async function stopAudio() {
      if (audioTrack) {
        // Stop and unpublish the audio track
        audioTrack.stop();
        await room.localParticipant.unpublishTrack(audioTrack);
        audioTrack = null;
      }
    }

    // Mute/unmute audio
    function toggleAudio(muted: boolean) {
      if (audioTrack) {
        audioTrack.setMuted(muted);
      }
    }

    return {
      startAudio,
      stopAudio,
      toggleAudio
    };
  }
```

--------------------------------

### Get Avatar Detail API Request Examples

Source: https://docs.akool.com/ai-tools-suite/talking-avatar

Demonstrates how to fetch detailed information about an avatar using the Akool API. This endpoint requires an avatar ID and supports authorization via x-api-key or Authorization header. The response includes avatar status, URL, and other metadata.

```bash
curl --location 'https://openapi.akool.com/api/open/v3/avatar/detail?id=66a1a02d591ad336275eda62' \
--header 'x-api-key: {{API Key}}'
```

```java
OkHttpClient client = new OkHttpClient().newBuilder()
  .build();
MediaType mediaType = MediaType.parse("text/plain");
RequestBody body = RequestBody.create(mediaType, "");
Request request = new Request.Builder()
  .url("https://openapi.akool.com/api/open/v3/avatar/detail?id=66a1a02d591ad336275eda62")
  .method("GET", body)
  .addHeader("x-api-key", "{{API Key}}")
  .build();
Response response = client.newCall(request).execute();
```

```javascript
const myHeaders = new Headers();
myHeaders.append("x-api-key", "{{API Key}}");

const requestOptions = {
  method: "GET",
  headers: myHeaders,
  redirect: "follow",
};

fetch(
  "https://openapi.akool.com/api/open/v3/avatar/detail?id=66a1a02d591ad336275eda62,
  requestOptions
)
  .then((response) => response.text())
  .then((result) => console.log(result))
  .catch((error) => console.error(error));
```

```php
<?php
$client = new Client();
$headers = [
  'x-api-key' => '{{API Key}}'
];
$request = new Request('GET', 'https://openapi.akool.com/api/open/v3/avatar/detail?66a1a02d591ad336275eda62', $headers);
$res = $client->sendAsync($request)->wait();
echo $res->getBody();
```

```python
import requests

url = "https://openapi.akool.com/api/open/v3/avatar/detail?id=66a1a02d591ad336275eda62"

payload = {}
headers = {
  'x-api-key': '{{API Key}}'
}

response = requests.request("GET", url, headers=headers, data=payload)

print(response.text)
```

--------------------------------

### SDK Initialization and Session Management

Source: https://docs.akool.com/sdk/jssdk-api

Methods for initializing the SDK, joining channels, and managing the streaming avatar session lifecycle.

```APIDOC
## SDK Initialization and Session Management

### Description
This section covers the initialization of the GenericAgoraSDK, joining a communication channel, and starting the avatar chat session.

### Method
POST /joinChannel, POST /joinChat

### Parameters
#### Request Body (joinChannel)
- **agora_app_id** (string) - Required - The Agora App ID.
- **agora_channel** (string) - Required - The channel name.
- **agora_token** (string) - Required - The temporary token for authentication.
- **agora_uid** (number) - Required - Unique user ID.

#### Request Body (joinChat)
- **vid** (string) - Required - The voice ID for the avatar.
- **lang** (string) - Required - Language code (e.g., 'en').
- **mode** (number) - Required - Interaction mode.

### Request Example
{
  "agora_app_id": "your_app_id",
  "agora_channel": "channel_name",
  "agora_token": "token_string",
  "agora_uid": 12345
}

### Response
#### Success Response (200)
- **status** (string) - Success message indicating session initialization.
```

--------------------------------

### POST /api/open/v4/knowledge/create

Source: https://docs.akool.com/ai-tools-suite/knowledge-base

Creates a new knowledge base with the provided name, prologue, prompt, documents, and URLs.

```APIDOC
## POST /api/open/v4/knowledge/create

### Description
Creates a new knowledge base with the provided name, prologue, prompt, documents, and URLs.

### Method
POST

### Endpoint
/api/open/v4/knowledge/create

### Parameters
#### Request Body
- **name** (string) - Required - The name of the knowledge base.
- **prologue** (string) - Required - The introductory message for the AI assistant.
- **prompt** (string) - Required - The prompt to guide the AI assistant's responses.
- **docs** (array of objects) - Optional - A list of documents to include in the knowledge base.
  - **name** (string) - Required - The name of the document.
  - **url** (string) - Required - The URL of the document.
  - **size** (integer) - Required - The size of the document in bytes.
- **urls** (array of strings) - Optional - A list of URLs to include in the knowledge base.

### Request Example
```json
{
  "name": "Customer Support KB",
  "prologue": "Hello, I am your AI assistant. How can I help you?",
  "prompt": "You are a professional AI assistant. Please answer questions based on the provided documents.",
  "docs": [
    {
      "name": "user_manual.pdf",
      "url": "https://example.com/user_manual.pdf",
      "size": 1024000
    }
  ],
  "urls": [
    "https://example.com/help",
    "https://example.com/faq"
  ]
}
```

### Response
#### Success Response (200)
- **code** (integer) - The status code of the response.
- **msg** (string) - The message describing the response.
- **data** (object) - The data returned by the API.
  - **_id** (string) - The unique identifier of the knowledge base.
  - **team_id** (string) - The ID of the team associated with the knowledge base.
  - **uid** (integer) - The user ID.
  - **user_type** (integer) - The type of user.
  - **from** (integer) - The source of the knowledge base creation.
  - **name** (string) - The name of the knowledge base.
  - **prologue** (string) - The introductory message for the AI assistant.
  - **prompt** (string) - The prompt to guide the AI assistant's responses.
  - **docs** (array of objects) - A list of documents included in the knowledge base.
  - **urls** (array of strings) - A list of URLs included in the knowledge base.
  - **create_time** (integer) - The timestamp when the knowledge base was created.
  - **update_time** (integer) - The timestamp when the knowledge base was last updated.

#### Response Example
```json
{
  "code": 1000,
  "msg": "OK",
  "data": {
    "_id": "64f8a1b2c3d4e5f6a7b8c9d0",
    "team_id": "team_123456",
    "uid": 789,
    "user_type": 2,
    "from": 2,
    "name": "Customer Support KB",
    "prologue": "Hello, I am your AI assistant. How can I help you?",
    "prompt": "You are a professional AI assistant. Please answer questions based on the provided documents.",
    "docs": [
      {
        "name": "user_manual.pdf",
        "url": "https://example.com/user_manual.pdf",
        "size": 1024000
      }
    ],
    "urls": [
      "https://example.com/help",
      "https://example.com/faq"
    ],
    "create_time": 1640995200000,
    "update_time": 1640995200000
  }
}
```
```

--------------------------------

### List Voices API Request (Multiple Languages)

Source: https://docs.akool.com/ai-tools-suite/voiceLab

This snippet demonstrates how to make a GET request to the Akool API's /api/open/v4/voice/list endpoint to retrieve a list of voices. It includes examples for cURL, Java, JavaScript, PHP, and Python, showing how to set parameters such as type, page, size, style, gender, and name, as well as the required API key.

```Bash
curl --location 'https://openapi.akool.com/api/open/v4/voice/list?type=1&page=1&size=10&style=Calm,Authoritative&gender=Male&name=MyVoice' \
--header 'x-api-key: {{API Key}}'
```

```Java
OkHttpClient client = new OkHttpClient().newBuilder()
  .build();
MediaType mediaType = MediaType.parse("text/plain");
RequestBody body = RequestBody.create(mediaType, "");
Request request = new Request.Builder()
  .url("https://openapi.akool.com/api/open/v4/voice/list?type=1&page=1&size=10&style=Calm,Authoritative&gender=Male&name=MyVoice")
  .method("GET", body)
  .addHeader("x-api-key", "{{API Key}}")
  .build();
Response response = client.newCall(request).execute();
```

```Javascript
const myHeaders = new Headers();
myHeaders.append("x-api-key", "{{API Key}}");

const requestOptions = {
  method: "GET",
  headers: myHeaders,
  redirect: "follow"
};

fetch("https://openapi.akool.com/api/open/v4/voice/list?type=1&page=1&size=10&style=Calm,Authoritative&gender=Male&name=MyVoice", requestOptions)
  .then((response) => response.text())
  .then((result) => console.log(result))
  .catch((error) => console.error(error));
```

```PHP
<?php
$client = new Client();
$headers = [
  'x-api-key' =>'{{API Key}}'
];
$request = new Request('GET', 'https://openapi.akool.com/api/open/v4/voice/list?type=1&page=1&size=10&style=Calm,Authoritative&gender=Male&name=MyVoice', $headers);
$res = $client->sendAsync($request)->wait();
echo $res->getBody();
?>
```

```Python
import requests

url = "https://openapi.akool.com/api/open/v4/voice/list"

payload = {}
headers = {
  'x-api-key':'{{API Key}}'
}

params = {
  'type': '1',
  'page': '1',
  'size': '10',
  'style': 'Calm,Authoritative',
  'gender': 'Male',
  'name': 'MyVoice'
}

response = requests.request("GET", url, headers=headers, data=payload, params=params)

print(response.text)
```

--------------------------------

### Get Language List

Source: https://docs.akool.com/ai-tools-suite/video-translation

Get a list of supported languages for video translation.

```APIDOC
## GET /ai-tools-suite/video-translation/get-languages

### Description
Fetches a list of all languages supported by the video translation service.

### Method
GET

### Endpoint
/ai-tools-suite/video-translation/get-languages

### Response
#### Success Response (200)
- **languages** (array) - A list of supported language objects.
  - **code** (string) - The language code (e.g., "en", "es").
  - **name** (string) - The name of the language (e.g., "English", "Spanish").
  - **voice_ids** (array) - A list of available voice IDs for this language.

#### Response Example
```json
{
  "languages": [
    {
      "code": "en",
      "name": "English",
      "voice_ids": ["voice-en-1", "voice-en-2"]
    },
    {
      "code": "es",
      "name": "Spanish",
      "voice_ids": ["voice-es-1"]
    }
  ]
}
```
```

--------------------------------

### Create Knowledge Base with Akool API (JavaScript)

Source: https://docs.akool.com/ai-tools-suite/knowledge-base

Demonstrates how to create a knowledge base using the Akool API with a JavaScript fetch request. It includes setting headers, constructing a JSON payload with knowledge base details, and handling the response.

```javascript
myHeaders.append("Content-Type", "application/json");

const raw = JSON.stringify({
  "name": "Customer Support KB",
  "prologue": "Hello, I am your AI assistant. How can I help you?",
  "prompt": "You are a professional AI assistant. Please answer questions based on the provided documents.",
  "docs": [
    {
      "name": "user_manual.pdf",
      "url": "https://example.com/user_manual.pdf",
      "size": 1024000
    }
  ],
  "urls": [
    "https://example.com/help",
    "https://example.com/faq"
  ]
});

const requestOptions = {
  method: "POST",
  headers: myHeaders,
  body: raw,
  redirect: "follow"
};

fetch("https://openapi.akool.com/api/open/v4/knowledge/create", requestOptions)
  .then((response) => response.text())
  .then((result) => console.log(result))
  .catch((error) => console.error(error));
```

--------------------------------

### Create Knowledge Base with Akool API (Python)

Source: https://docs.akool.com/ai-tools-suite/knowledge-base

Shows how to create a knowledge base using the Akool API in Python. This example uses the `requests` library to send a POST request with an API key, content type, and a JSON payload.

```python
import requests
import json

url = "https://openapi.akool.com/api/open/v4/knowledge/create"

payload = json.dumps({
  "name": "Customer Support KB",
  "prologue": "Hello, I am your AI assistant. How can I help you?",
  "prompt": "You are a professional AI assistant. Please answer questions based on the provided documents.",
  "docs": [
    {
      "name": "user_manual.pdf",
      "url": "https://example.com/user_manual.pdf",
      "size": 1024000
    }
  ],
  "urls": [
    "https://example.com/help",
    "https://example.com/faq"
  ]
})
headers = {
  'x-api-key':'{{API Key}}',
  'Content-Type': 'application/json'
}

response = requests.request("POST", url, headers=headers, data=payload)
print(response.text)
```

--------------------------------

### Get User Credit Info API

Source: https://docs.akool.com/ai-tools-suite/faceswap

Get faceswap user credit information.

```APIDOC
## GET /ai-tools-suite/faceswap/get-credit

### Description
Retrieves the current credit balance and usage information for the authenticated user.

### Method
GET

### Endpoint
/ai-tools-suite/faceswap/get-credit

### Parameters
(No parameters required, uses authentication token)

### Request Example
```
GET /ai-tools-suite/faceswap/get-credit
```

### Response
#### Success Response (200)
- **code** (integer) - Response code (1000 for success).
- **message** (string) - Success message.
- **credits** (object) - Object containing credit information:
  - **balance** (integer) - Remaining credits.
  - **used** (integer) - Credits used.
  - **total** (integer) - Total credits allocated.

#### Response Example
```json
{
  "code": 1000,
  "message": "Success",
  "credits": {
    "balance": 500,
    "used": 150,
    "total": 650
  }
}
```
```

--------------------------------

### Retrieve Knowledge Base Details (HTTP, cURL, Java, JavaScript, PHP, Python)

Source: https://docs.akool.com/ai-tools-suite/knowledge-base

This snippet demonstrates how to fetch detailed information about a specific knowledge base using its ID. It includes examples for making the GET request via HTTP, cURL, Java, JavaScript, PHP, and Python. Authentication is handled using an 'x-api-key' header. The API returns a JSON object containing the knowledge base details or an error code.

```HTTP
GET https://openapi.akool.com/api/open/v4/knowledge/detail?id=64f8a1b2c3d4e5f6a7b8c9d0
```

```cURL
curl --location 'https://openapi.akool.com/api/open/v4/knowledge/detail?id=64f8a1b2c3d4e5f6a7b8c9d0' \
--header 'x-api-key: {{API Key}}'
```

```Java
OkHttpClient client = new OkHttpClient().newBuilder()
  .build();
Request request = new Request.Builder()
  .url("https://openapi.akool.com/api/open/v4/knowledge/detail?id=64f8a1b2c3d4e5f6a7b8c9d0")
  .method("GET", null)
  .addHeader("x-api-key", "{{API Key}}")
  .build();
Response response = client.newCall(request).execute();
```

```JavaScript
const myHeaders = new Headers();
myHeaders.append("x-api-key", "{{API Key}}");

const requestOptions = {
  method: "GET",
  headers: myHeaders,
  redirect: "follow"
};

fetch("https://openapi.akool.com/api/open/v4/knowledge/detail?id=64f8a1b2c3d4e5f6a7b8c9d0", requestOptions)
  .then((response) => response.text())
  .then((result) => console.log(result))
  .catch((error) => console.error(error));
```

```PHP
<?php
$client = new Client();
$headers = [
  'x-api-key' =>'{{API Key}}'
];
$request = new Request('GET', 'https://openapi.akool.com/api/open/v4/knowledge/detail?id=64f8a1b2c3d4e5f6a7b8c9d0', $headers);
$res = $client->sendAsync($request)->wait();
echo $res->getBody();
```

```Python
import requests

url = "https://openapi.akool.com/api/open/v4/knowledge/detail?id=64f8a1b2c3d4e5f6a7b8c9d0"

headers = {
  'x-api-key':'{{API Key}}'
}

response = requests.request("GET", url, headers=headers)
print(response.text)
```

--------------------------------

### Create Knowledge Base API Implementation

Source: https://docs.akool.com/ai-tools-suite/knowledge-base

Demonstrates how to create a new knowledge base using the Akool API. The endpoint accepts a JSON body containing configuration details and requires an API key for authentication.

```bash
curl --location 'https://openapi.akool.com/api/open/v4/knowledge/create' \
--header 'x-api-key: {{API Key}}' \
--header 'Content-Type: application/json' \
--data '{
  "name": "Customer Support KB",
  "prologue": "Hello, I am your AI assistant. How can I help you?",
  "prompt": "You are a professional AI assistant. Please answer questions based on the provided documents.",
  "docs": [
    {
      "name": "user_manual.pdf",
      "url": "https://example.com/user_manual.pdf",
      "size": 1024000
    }
  ],
  "urls": [
    "https://example.com/help",
    "https://example.com/faq"
  ]
}'
```

```java
OkHttpClient client = new OkHttpClient().newBuilder()
  .build();
MediaType mediaType = MediaType.parse("application/json");
RequestBody body = RequestBody.create(mediaType, "{\n  \"name\": \"Customer Support KB\",\n  \"prologue\": \"Hello, I am your AI assistant. How can I help you?\",\n  \"prompt\": \"You are a professional AI assistant. Please answer questions based on the provided documents.\",\n  \"docs\": [\n    {\n      \"name\": \"user_manual.pdf\",\n      \"url\": \"https://example.com/user_manual.pdf\",\n      \"size\": 1024000\n    }\n  ],\n  \"urls\": [\n    \"https://example.com/help\",\n    \"https://example.com/faq\"\n  ]\n}");
Request request = new Request.Builder()
  .url("https://openapi.akool.com/api/open/v4/knowledge/create")
  .method("POST", body)
  .addHeader("x-api-key", "{{API Key}}")
  .addHeader("Content-Type", "application/json")
  .build();
Response response = client.newCall(request).execute();
```

```javascript
const myHeaders = new Headers();
myHeaders.append("x-api-key", "{{API Key}}");
```

--------------------------------

### Create Knowledge Base and Use in Avatar Session (Bash)

Source: https://docs.akool.com/ai-tools-suite/knowledge-base

This bash script demonstrates a complete workflow for integrating a knowledge base with a Streaming Avatar. It includes two `curl` commands: the first creates a new knowledge base with specified documents and URLs, and the second uses the obtained knowledge ID to create a streaming avatar session.

```bash
# 1. Create a knowledge base
curl -X POST "https://openapi.akool.com/api/open/v4/knowledge/create" \
  -H "x-api-key: {{API Key}}" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "Customer Support KB",
    "prologue": "Hello, I am your customer support assistant. How can I help you today?",
    "prompt": "You are a helpful customer support assistant. Use the provided documents to answer questions accurately.",
    "docs": [
      {
        "name": "user_guide.pdf",
        "url": "https://example.com/user_guide.pdf",
        "size": 1024000
      }
    ],
    "urls": [
      "https://example.com/help",
      "https://example.com/faq"
    ]
  }'

# 2. Use the knowledge base in a streaming avatar session
curl -X POST "https://openapi.akool.com/api/open/v4/liveAvatar/session/create" \
  -H "x-api-key: {{API Key}}" \
  -H "Content-Type: application/json" \
  -d '{
    "avatar_id": "your_avatar_id",
    "knowledge_id": "KNOWLEDGE_ID_FROM_STEP_1"
  }'
```

--------------------------------

### Get Video Info by Model ID - PHP

Source: https://docs.akool.com/ai-tools-suite/lip-sync

This PHP snippet illustrates how to retrieve video information using the video_model_id. It makes a GET request with the required x-api-key header.

```php
<?php
$client = new Client();
$headers = [
  'x-api-key' =>'{{API Key}}'
];
$request = new Request('GET', 'http://openapi.akool.com/api/open/v3/content/video/infobymodelid?video_model_id=66160f989dfc997ac289037b', $headers);
$res = $client->sendAsync($request)->wait();
echo $res->getBody();
```

--------------------------------

### Initialize and Manage Akool Streaming Avatar SDK

Source: https://docs.akool.com/sdk/jssdk-api

Demonstrates the full lifecycle of the Akool SDK including initialization, event listener setup, channel joining, and media control functions. It requires valid Agora credentials and handles asynchronous operations for session management.

```javascript
import { GenericAgoraSDK } from 'akool-streaming-avatar-sdk';
const agoraSDK = new GenericAgoraSDK({ mode: "rtc", codec: "vp8" });
agoraSDK.on({
  onStreamMessage: (uid, message) => console.log("Received message from", uid, ":", message),
  onException: (error) => console.error("An exception occurred:", error),
  onMessageReceived: (message) => updateMessageDisplay(message),
  onMessageUpdated: (message) => updateExistingMessage(message),
  onNetworkStatsUpdated: (stats) => updateNetworkQuality(stats),
  onTokenWillExpire: () => refreshToken(),
  onTokenDidExpire: () => handleTokenExpiry(),
  onUserPublished: async (user, mediaType) => {
    const remoteTrack = await agoraSDK.getClient().subscribe(user, mediaType);
    remoteTrack?.play(mediaType === 'video' ? 'remote-video-container' : undefined);
  }
});
async function initializeSession() {
  const response = await fetch('/api/get-agora-credentials');
  const credentials = await response.json();
  await agoraSDK.joinChannel({ agora_app_id: credentials.agora_app_id, agora_channel: credentials.agora_channel, agora_token: credentials.agora_token, agora_uid: credentials.agora_uid });
  await agoraSDK.joinChat({ vid: "your-voice-id", lang: "en", mode: 2 });
}
async function sendMessage(content) { await agoraSDK.sendMessage(content); }
async function toggleMicrophone() { await agoraSDK.toggleMic(); }
async function cleanup() { await agoraSDK.closeStreaming(); }
```

--------------------------------

### Install Akool Streaming Avatar SDK

Source: https://docs.akool.com/sdk/jssdk-start

Methods for adding the SDK to your project via NPM or CDN.

```bash
npm install akool-streaming-avatar-sdk
```

```html
<!-- Using unpkg -->
<script src="https://unpkg.com/akool-streaming-avatar-sdk"></script>

<!-- Using jsDelivr -->
<script src="https://cdn.jsdelivr.net/npm/akool-streaming-avatar-sdk"></script>
```

--------------------------------

### Get Video Info by Model ID - Python

Source: https://docs.akool.com/ai-tools-suite/lip-sync

This Python code uses the requests library to fetch video details by video_model_id. It sends a GET request with the API key in the headers.

```python
import requests

url = "http://openapi.akool.com/api/open/v3/content/video/infobymodelid?video_model_id=66160f989dfc997ac289037b"

payload = {}
headers = {
  'x-api-key':'{{API Key}}'
}

response = requests.request("GET", url, headers=headers, data=payload)

print(response.text)
```

--------------------------------

### Get Streaming Avatar Detail OpenAPI Definition

Source: https://docs.akool.com/ai-tools-suite/live-avatar/detail

The OpenAPI specification for the GET request to retrieve streaming avatar details. It defines the endpoint, required avatar_id parameter, and the schema for the successful response.

```yaml
paths:
  /api/open/v4/liveAvatar/avatar/detail:
    get:
      tags:
        - Avatar Management
      summary: Get Streaming Avatar Detail
      parameters:
        - name: avatar_id
          in: query
          required: true
          schema:
            type: string
      responses:
        '200':
          description: Avatar details
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/AvatarDetail'
```

--------------------------------

### Initialize Client/Room

Source: https://docs.akool.com/implementation-guide/streaming-avatar

Initializes the client or room for different providers (Agora, LiveKit, TRTC) with provided credentials.

```APIDOC
## Initialize Client/Room

### Description
Initializes the client or room for different providers (Agora, LiveKit, TRTC) with provided credentials.

### Method
Asynchronous function

### Endpoint
N/A (Client-side initialization)

### Parameters
- **credentials** (object) - Required - Object containing provider-specific credentials.
  - **agora_app_id** (string) - Required for Agora
  - **agora_channel** (string) - Required for Agora
  - **agora_token** (string) - Required for Agora
  - **agora_uid** (string) - Required for Agora
  - **livekit_url** (string) - Required for LiveKit
  - **livekit_token** (string) - Required for LiveKit
  - **trtc_app_id** (string) - Required for TRTC
  - **trtc_room_id** (string) - Required for TRTC
  - **trtc_user_id** (string) - Required for TRTC
  - **trtc_user_sig** (string) - Required for TRTC

### Request Example
```json
{
  "agora_app_id": "YOUR_AGORA_APP_ID",
  "agora_channel": "YOUR_AGORA_CHANNEL",
  "agora_token": "YOUR_AGORA_TOKEN",
  "agora_uid": "YOUR_AGORA_UID"
}
```

### Response
- **client** (object) - The initialized client object (AgoraRTC.Client or TRTC).
- **room** (object) - The initialized room object (LiveKit Room).

### Response Example
```json
// Returns an initialized client or room object based on the provider
```
```

--------------------------------

### Get Video Info by Model ID - Java

Source: https://docs.akool.com/ai-tools-suite/lip-sync

This Java code snippet shows how to make a GET request to retrieve video information using the video_model_id. It utilizes the OkHttpClient library and requires an API key.

```java
OkHttpClient client = new OkHttpClient().newBuilder()
  .build();
MediaType mediaType = MediaType.parse("text/plain");
RequestBody body = RequestBody.create(mediaType, "");
Request request = new Request.Builder()
  .url("http://openapi.akool.com/api/open/v3/content/video/infobymodelid?video_model_id=66160f989dfc997ac289037b")
  .method("GET", body)
  .addHeader("x-api-key", "{{API Key}}")
  .build();
Response response = client.newCall(request).execute();
```

--------------------------------

### Best Practices

Source: https://docs.akool.com/ai-tools-suite/face-detection/detect-faces

General recommendations for using the Akool API effectively.

```APIDOC
## Best Practices

*   **URL Requirements**: Use HTTPS, ensure publicly accessible.
*   **Video num_frames**: Short videos (5-10), Medium (10-20), Long (20-50).
*   **Performance**: Use `single_face=true` when only one face is needed.
```

--------------------------------

### Get Available Effects - Python

Source: https://docs.akool.com/ai-tools-suite/image2video

This Python snippet shows how to fetch available video effects using the requests library. It performs a GET request to the Akool API endpoint, providing the 'x-api-key' in the request headers for authentication. The response text is then printed.

```python
import requests

url = "https://openapi.akool.com/api/open/v4/image2Video/effects"

headers = {
  'x-api-key':'{{API Key}}'
}

response = requests.request("GET", url, headers=headers)
print(response.text)
```

--------------------------------

### Setup HTML Structure for Avatar

Source: https://docs.akool.com/sdk/jssdk-start

Basic HTML boilerplate required to render the video stream and interact with the avatar.

```html
<!DOCTYPE html>
<html lang="en">
  <head>
    <meta charset="UTF-8" />
    <meta name="viewport" content="width=device-width, initial-scale=1.0" />
    <title>Akool Streaming Avatar Demo</title>
  </head>
  <body>
    <div id="app">
      <h1>Streaming Avatar Demo</h1>
      <div id="remote-video" style="width: 640px; height: 480px;"></div>
      <button id="join-btn">Join Channel</button>
      <button id="send-msg-btn">Send Message</button>
      <input type="text" id="message-input" placeholder="Type your message..." />
    </div>
  </body>
</html>
```

--------------------------------

### Publish and Control Audio Stream (Agora)

Source: https://docs.akool.com/implementation-guide/streaming-avatar

This snippet demonstrates how to create, publish, and manage a local microphone audio track using the Agora SDK. It includes functions to start, stop, and mute/unmute the audio, handling potential errors during these operations. The `setupAudioInteraction` function returns controls for managing the audio stream.

```typescript
async function publishAudio(client: IAgoraRTCClient) {
    // Create a microphone audio track
    const audioTrack = await AgoraRTC.createMicrophoneAudioTrack();
    
    try {
      // Publish the audio track to the channel
      await client.publish(audioTrack);
      console.log("Audio publishing successful");
      
      return audioTrack;
    } catch (error) {
      console.error("Error publishing audio:", error);
      throw error;
    }
  }

  // Example usage with audio controls
  async function setupAudioInteraction(client: IAgoraRTCClient) {
    let audioTrack;
    
    // Start audio
    async function startAudio() {
      try {
        audioTrack = await publishAudio(client);
      } catch (error) {
        console.error("Failed to start audio:", error);
      }
    }

    // Stop audio
    async function stopAudio() {
      if (audioTrack) {
        // Stop and close the audio track
        audioTrack.stop();
        audioTrack.close();
        await client.unpublish(audioTrack);
        audioTrack = null;
      }
    }

    // Mute/unmute audio
    function toggleAudio(muted: boolean) {
      if (audioTrack) {
        if (muted) {
          audioTrack.setEnabled(false);
        } else {
          audioTrack.setEnabled(true);
        }
      }
    }

    return {
      startAudio,
      stopAudio,
      toggleAudio
    };
  }
```

--------------------------------

### Get Available Effects - PHP

Source: https://docs.akool.com/ai-tools-suite/image2video

This PHP code snippet demonstrates how to retrieve available video effects using the Guzzle HTTP client. It sends a GET request to the Akool API, including the 'x-api-key' in the headers for authentication. The response body is then printed.

```php
<?php
$client = new Client();
$headers = [
  'x-api-key' =>'{{API Key}}'
];
$request = new Request('GET', 'https://openapi.akool.com/api/open/v4/image2Video/effects', $headers);
$res = $client->sendAsync($request)->wait();
echo $res->getBody();
?>
```

--------------------------------

### Akool TypeScript Client Initialization and Event Handling

Source: https://docs.akool.com/ai-tools-suite/live-avatar

Demonstrates how to initialize an AgoraRTC client in TypeScript and set up an event listener for stream messages. This is a foundational step for real-time communication within the Akool project.

```typescript
const client: IAgoraRTCClient = AgoraRTC.createClient({
    mode: 'rtc',
    codec: 'vp8',
  });

  client.join(agora_app_id, agora_channel, agora_token, agora_uid);

  client.on('stream-message', (message: Uint8Array | string) => {
    console.log('received: %s', message);
  });
```