### Compile and Install CoAI from Source

Source: https://github.com/mathematrix/coai/blob/main/README.md

This method involves cloning the CoAI repository, installing Node.js dependencies, building the application, and then compiling the Go binary. The compiled binary can be run directly or managed using services like nohup, systemd, or other service managers. Configuration can be overridden using environment variables.

```shell
git clone https://github.com/Deeptrain-Community/chatnio.git
cd chatnio

cd app
npm install -g pnpm
pnpm install
pnpm build

cd ..
go build -o chatnio

# e.g. using nohup (you can also use systemd or other service manager)
nohup ./chatnio > output.log &

```

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

### Install CoAI using standalone Docker

Source: https://github.com/mathematrix/coai/blob/main/README.md

This lightweight Docker installation is suitable for running CoAI, especially when using external MySQL/RDS services. It requires setting environment variables for database connections, JWT secret, and static file serving. Update instructions involve stopping, removing, and re-pulling the Docker image.

```shell
docker run -d --name chatnio \
   --network host \
   -v ~/config:/config \
   -v ~/logs:/logs \
   -v ~/storage:/storage \
   -e MYSQL_HOST=localhost \
   -e MYSQL_PORT=3306 \
   -e MYSQL_DB=chatnio \
   -e MYSQL_USER=root \
   -e MYSQL_PASSWORD=chatnio123456 \
   -e REDIS_HOST=localhost \
   -e REDIS_PORT=6379 \
   -e SECRET=secret \
   -e SERVE_STATIC=true \
   programzmh/chatnio:latest
```

```shell
docker stop chatnio
docker rm chatnio
docker pull programzmh/chatnio:latest
```

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

### Deploy CoAI using Docker Compose

Source: https://github.com/mathematrix/coai/blob/main/README.md

This method uses Docker Compose for a recommended installation of CoAI. It involves cloning the repository and running the service with docker-compose. Additional options for stable versions and automatic updates with Watchtower are provided. Mount directories for databases and configurations are also specified.

```shell
git clone --depth=1 --branch=main --single-branch https://github.com/Deeptrain-Community/chatnio.git
cd chatnio
docker-compose up -d # Run the service
# To use the stable version, use docker-compose -f docker-compose.stable.yaml up -d instead
# To use Watchtower for automatic updates, use docker-compose -f docker-compose.watch.yaml up -d instead
```

```shell
docker-compose down 
docker-compose pull
docker-compose up -d
```

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

### Configure Billing Rules (Bash)

Source: https://context7.com/mathematrix/coai/llms.txt

Sets up flexible billing rules per model, supporting non-billing, per-request (times-billing), and per-token (token-billing) methods. Examples include token-billing for GPT models, times-billing for image generation, and a free tier for basic models. Supports anonymous access and minimum charge requirements.

```bash
curl -X POST https://your-domain.com/api/admin/charge/set \
  -H "Authorization: Bearer admin-jwt-token" \
  -H "Content-Type: application/json" \
  -d '{
    "id": 0,
    "type": "token-billing",
    "models": ["gpt-4", "gpt-4-turbo"],
    "input": 0.03,
    "output": 0.06,
    "anonymous": false
  }'

# Response
{
  "status": true,
  "id": 5,
  "message": "Charge rule created successfully"
}

# Create times-based billing for image generation
curl -X POST https://your-domain.com/api/admin/charge/set \
  -H "Authorization: Bearer admin-jwt-token" \
  -H "Content-Type: application/json" \
  -d '{
    "id": 0,
    "type": "times-billing",
    "models": ["dall-e-3"],
    "input": 0,
    "output": 0.04,
    "anonymous": true
  }'

# Create free tier for basic models
curl -X POST https://your-domain.com/api/admin/charge/set \
  -H "Authorization: Bearer admin-jwt-token" \
  -H "Content-Type: application/json" \
  -d '{
    "id": 0,
    "type": "non-billing",
    "models": ["gpt-3.5-turbo", "claude-instant"],
    "input": 0,
    "output": 0,
    "anonymous": true
  }'

# List all charge rules
curl -X GET https://your-domain.com/api/admin/charge/list \
  -H "Authorization: Bearer admin-jwt-token"

# Response
{
  "status": true,
  "data": [
    {
      "id": 5,
      "type": "token-billing",
      "models": ["gpt-4", "gpt-4-turbo"],
      "input": 0.03,
      "output": 0.06,
      "anonymous": false
    },
    {
      "id": 6,
      "type": "times-billing",
      "models": ["dall-e-3"],
      "input": 0,
      "output": 0.04,
      "anonymous": true
    },
    {
      "id": 7,
      "type": "non-billing",
      "models": ["gpt-3.5-turbo", "claude-instant"],
      "input": 0,
      "output": 0,
      "anonymous": true
    }
  ]
}
```

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

### GET /api/v1/plans

Source: https://context7.com/mathematrix/coai/llms.txt

Retrieves a list of available subscription plans, including their pricing, features, and usage limits.

```APIDOC
## GET /api/v1/plans

### Description
Retrieve available subscription tiers with pricing and usage limits. Plans support monthly/yearly billing with automatic discounts.

### Method
GET

### Endpoint
/api/v1/plans

### Parameters
None

### Request Example
None

### Response
#### Success Response (200)
- **status** (boolean) - Indicates if the request was successful.
- **data** (array) - An array of subscription plan objects.
  - **level** (integer) - The tier level of the plan.
  - **name** (string) - The name of the plan (e.g., "Basic", "Standard", "Pro").
  - **price** (float) - The monthly price of the plan.
  - **items** (array) - A list of features included in the plan.
    - **id** (string) - The unique identifier for the feature.
    - **name** (string) - The display name of the feature.
    - **icon** (string) - An icon representing the feature.
    - **value** (integer) - The limit or quantity of the feature (e.g., number of calls, images). -1 indicates unlimited.
    - **models** (array) - A list of models associated with this feature.

#### Response Example
```json
{
  "status": true,
  "data": [
    {
      "level": 1,
      "name": "Basic",
      "price": 9.99,
      "items": [
        {
          "id": "gpt4_calls",
          "name": "GPT-4 Calls",
          "icon": "🚀",
          "value": 100,
          "models": ["gpt-4", "gpt-4-turbo"]
        },
        {
          "id": "dalle_images",
          "name": "DALL-E Images",
          "icon": "🎨",
          "value": 50,
          "models": ["dall-e-3"]
        }
      ]
    },
    {
      "level": 2,
      "name": "Standard",
      "price": 19.99,
      "items": [
        {
          "id": "gpt4_calls",
          "name": "GPT-4 Calls",
          "icon": "🚀",
          "value": 500,
          "models": ["gpt-4", "gpt-4-turbo"]
        },
        {
          "id": "dalle_images",
          "name": "DALL-E Images",
          "icon": "🎨",
          "value": 200,
          "models": ["dall-e-3"]
        }
      ]
    },
    {
      "level": 3,
      "name": "Pro",
      "price": 49.99,
      "items": [
        {
          "id": "unlimited",
          "name": "Unlimited Access",
          "icon": "⭐",
          "value": -1,
          "models": ["*"]
        }
      ]
    }
  ]
}
```
```

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

### GET /api/admin/charge/list

Source: https://context7.com/mathematrix/coai/llms.txt

Retrieves a list of all configured billing rules.

```APIDOC
## GET /api/admin/charge/list

### Description
Lists all configured billing rules for AI models.

### Method
GET

### Endpoint
/api/admin/charge/list

### Parameters
None

### Request Example
```bash
curl -X GET https://your-domain.com/api/admin/charge/list \
  -H "Authorization: Bearer admin-jwt-token"
```

### Response
#### Success Response (200)
- **status** (boolean) - Indicates success of the operation.
- **data** (array of objects) - A list of charge rules.
  - **id** (integer) - The unique identifier of the charge rule.
  - **type** (string) - The type of billing rule.
  - **models** (array of strings) - List of models to which this rule applies.
  - **input** (number) - Cost per input token or 0.
  - **output** (number) - Cost per output token/request or 0.
  - **anonymous** (boolean) - Whether anonymous users are allowed.

#### Response Example
```json
{
  "status": true,
  "data": [
    {
      "id": 5,
      "type": "token-billing",
      "models": ["gpt-4", "gpt-4-turbo"],
      "input": 0.03,
      "output": 0.06,
      "anonymous": false
    },
    {
      "id": 6,
      "type": "times-billing",
      "models": ["dall-e-3"],
      "input": 0,
      "output": 0.04,
      "anonymous": true
    },
    {
      "id": 7,
      "type": "non-billing",
      "models": ["gpt-3.5-turbo", "claude-instant"],
      "input": 0,
      "output": 0,
      "anonymous": true
    }
  ]
}
```
```

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

### Get Subscription Plans

Source: https://context7.com/mathematrix/coai/llms.txt

Retrieves available subscription tiers, including pricing and usage limits for different services like GPT-4 calls and DALL-E images. Supports monthly and yearly billing with discounts.

```bash
curl -X GET https://your-domain.com/api/v1/plans \
  -H "Authorization: Bearer your-jwt-token"

# Response
{
  "status": true,
  "data": [
    {
      "level": 1,
      "name": "Basic",
      "price": 9.99,
      "items": [
        {
          "id": "gpt4_calls",
          "name": "GPT-4 Calls",
          "icon": "🚀",
          "value": 100,
          "models": ["gpt-4", "gpt-4-turbo"]
        },
        {
          "id": "dalle_images",
          "name": "DALL-E Images",
          "icon": "🎨",
          "value": 50,
          "models": ["dall-e-3"]
        }
      ]
    },
    {
      "level": 2,
      "name": "Standard",
      "price": 19.99,
      "items": [
        {
          "id": "gpt4_calls",
          "name": "GPT-4 Calls",
          "icon": "🚀",
          "value": 500,
          "models": ["gpt-4", "gpt-4-turbo"]
        },
        {
          "id": "dalle_images",
          "name": "DALL-E Images",
          "icon": "🎨",
          "value": 200,
          "models": ["dall-e-3"]
        }
      ]
    },
    {
      "level": 3,
      "name": "Pro",
      "price": 49.99,
      "items": [
        {
          "id": "unlimited",
          "name": "Unlimited Access",
          "icon": "⭐",
          "value": -1,
          "models": ["*"]
        }
      ]
    }
  ]
}
```

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

### Create AI Provider Channel (Bash)

Source: https://context7.com/mathematrix/coai/llms.txt

Configures a new AI provider channel with support for load balancing, retry logic, model mapping, multiple API keys, priority routing, and user group restrictions. Includes examples for OpenAI and Azure OpenAI, demonstrating proxy and model exclusion settings.

```bash
curl -X POST https://your-domain.com/api/admin/channel/create \
  -H "Authorization: Bearer admin-jwt-token" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "OpenAI GPT-4 Primary",
    "type": "openai",
    "priority": 10,
    "weight": 100,
    "models": ["gpt-4", "gpt-4-turbo", "gpt-4-vision-preview"],
    "retry": 3,
    "secret": "sk-proj-abc123xyz789\nsk-proj-def456uvw012",
    "endpoint": "https://api.openai.com",
    "mapper": "gpt-4>gpt-4-0613\ngpt-4-turbo>gpt-4-turbo-2024-04-09",
    "state": true,
    "group": ["basic", "standard", "pro"],
    "proxy": {
      "proxy_type": 0,
      "proxy": "",
      "username": "",
      "password": ""
    }
  }'

# Response
{
  "status": true,
  "id": 15,
  "message": "Channel created successfully"
}

# Create channel with proxy and model exclusions
curl -X POST https://your-domain.com/api/admin/channel/create \
  -H "Authorization: Bearer admin-jwt-token" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "Azure OpenAI Backup",
    "type": "azure",
    "priority": 5,
    "weight": 50,
    "models": ["gpt-4", "gpt-35-turbo"],
    "retry": 2,
    "secret": "azure-api-key-here",
    "endpoint": "https://your-resource.openai.azure.com",
    "mapper": "!gpt-4-32k>\ngpt-35-turbo>gpt-35-turbo-16k",
    "state": true,
    "group": ["standard", "pro"],
    "proxy": {
      "proxy_type": 1,
      "proxy": "http://proxy.example.com:8080",
      "username": "proxyuser",
      "password": "proxypass"
    }
  }'

# List all channels
curl -X GET https://your-domain.com/api/admin/channel/list \
  -H "Authorization: Bearer admin-jwt-token"

# Response
{
  "status": true,
  "data": [
    {
      "id": 15,
      "name": "OpenAI GPT-4 Primary",
      "type": "openai",
      "priority": 10,
      "weight": 100,
      "models": ["gpt-4", "gpt-4-turbo", "gpt-4-vision-preview"],
      "state": true,
      "group": ["basic", "standard", "pro"]
    },
    {
      "id": 16,
      "name": "Azure OpenAI Backup",
      "type": "azure",
      "priority": 5,
      "weight": 50,
      "models": ["gpt-4", "gpt-35-turbo"],
      "state": true,
      "group": ["standard", "pro"]
    }
  ]
}
```

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

### GET /api/admin/channel/list

Source: https://context7.com/mathematrix/coai/llms.txt

Retrieves a list of all configured AI provider channels.

```APIDOC
## GET /api/admin/channel/list

### Description
Lists all configured AI provider channels.

### Method
GET

### Endpoint
/api/admin/channel/list

### Parameters
None

### Request Example
```bash
curl -X GET https://your-domain.com/api/admin/channel/list \
  -H "Authorization: Bearer admin-jwt-token"
```

### Response
#### Success Response (200)
- **status** (boolean) - Indicates success of the operation.
- **data** (array of objects) - A list of AI channels.
  - **id** (integer) - The unique identifier of the channel.
  - **name** (string) - The name of the AI channel.
  - **type** (string) - The type of the AI provider.
  - **priority** (integer) - The priority of the channel.
  - **weight** (integer) - The weight for load balancing.
  - **models** (array of strings) - List of models supported by this channel.
  - **state** (boolean) - Whether the channel is enabled or disabled.
  - **group** (array of strings) - User groups allowed to access this channel.

#### Response Example
```json
{
  "status": true,
  "data": [
    {
      "id": 15,
      "name": "OpenAI GPT-4 Primary",
      "type": "openai",
      "priority": 10,
      "weight": 100,
      "models": ["gpt-4", "gpt-4-turbo", "gpt-4-vision-preview"],
      "state": true,
      "group": ["basic", "standard", "pro"]
    },
    {
      "id": 16,
      "name": "Azure OpenAI Backup",
      "type": "azure",
      "priority": 5,
      "weight": 50,
      "models": ["gpt-4", "gpt-35-turbo"],
      "state": true,
      "group": ["standard", "pro"]
    }
  ]
}
```
```

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

### Get System Information (JSON Response)

Source: https://context7.com/mathematrix/coai/llms.txt

The response contains various system metrics such as online users, total users, daily and monthly revenue, request counts, active channels, and the error rate.

```json
{
  "status": true,
  "data": {
    "online_users": 45,
    "total_users": 1250,
    "today_revenue": 350.50,
    "monthly_revenue": 8420.75,
    "today_requests": 15420,
    "monthly_requests": 425680,
    "active_channels": 12,
    "error_rate": 0.02
  }
}
```

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

### Get Model Usage Analysis (cURL Request)

Source: https://context7.com/mathematrix/coai/llms.txt

Fetches model usage analytics for a specified time period. Requires an admin JWT token and query parameters for start and end times.

```bash
curl -X GET "https://your-domain.com/api/admin/analytics/model?start_time=2024-01-01&end_time=2024-01-31" \
  -H "Authorization: Bearer admin-jwt-token"
```

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

### Get System Information (cURL Request)

Source: https://context7.com/mathematrix/coai/llms.txt

Retrieves key system analytics, including user counts, revenue, request statistics, active channels, and error rates. Requires an admin JWT token.

```bash
curl -X GET https://your-domain.com/api/admin/analytics/info \
  -H "Authorization: Bearer admin-jwt-token"
```

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

### GET /api/subscription

Source: https://context7.com/mathematrix/coai/llms.txt

Retrieves the current subscription status and usage details for the authenticated user.

```APIDOC
## GET /api/subscription

### Description
Check current subscription status and view usage details for your active plan.

### Method
GET

### Endpoint
/api/subscription

### Parameters
None

### Request Example
None

### Response
#### Success Response (200)
- **status** (boolean) - Indicates if the request was successful.
- **subscription** (object) - Details of the current subscription.
  - **level** (integer) - The level of the current subscription plan.
  - **name** (string) - The name of the current subscription plan.
  - **expired** (string) - The expiration date of the subscription in ISO 8601 format.
  - **usage** (object) - An object detailing the usage of different features within the plan.
    - **feature_id** (object) - Usage details for a specific feature (e.g., "gpt4_calls", "dalle_images").
      - **used** (integer) - The amount of the feature consumed.
      - **limit** (integer) - The total limit for the feature. -1 indicates unlimited.
      - **percentage** (float) - The percentage of the limit that has been used.

#### Response Example
```json
{
  "status": true,
  "subscription": {
    "level": 2,
    "name": "Standard",
    "expired": "2025-01-06T00:00:00Z",
    "usage": {
      "gpt4_calls": {
        "used": 23,
        "limit": 500,
        "percentage": 4.6
      },
      "dalle_images": {
        "used": 8,
        "limit": 200,
        "percentage": 4.0
      }
    }
  }
}
```
```

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

### Get API Key and Use for Chat Completions - Bash

Source: https://context7.com/mathematrix/coai/llms.txt

Retrieves an existing API key or generates a new one for programmatic access. The API key, formatted as `sk-{hash}`, is then used to authenticate requests to the OpenAI-compatible API endpoints, such as chat completions. Dependencies: User authentication.

```bash
curl -X GET https://your-domain.com/api/apikey \
  -H "Authorization: Bearer eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9..."

# Response
{
  "status": true,
  "key": "sk-a1b2c3d4e5f6g7h8i9j0k1l2m3n4o5p6q7r8s9t0u1v2w3x4y5z6a7b8c9d0e1f2"
}

# Use the API key in subsequent requests
curl -X POST https://your-domain.com/api/v1/chat/completions \
  -H "Authorization: Bearer sk-a1b2c3d4e5f6g7h8i9j0k1l2m3n4o5p6q7r8s9t0u1v2w3x4y5z6a7b8c9d0e1f2" \
  -H "Content-Type: application/json" \
  -d '{ "model": "gpt-4", "messages": [{"role": "user", "content": "Hello"}] }'
```

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

### Get Billing Analysis

Source: https://context7.com/mathematrix/coai/llms.txt

Retrieves a billing analysis for a specified time range. This endpoint provides total revenue, subscription revenue, usage revenue, and a daily breakdown.

```APIDOC
## GET /api/admin/analytics/billing

### Description
Retrieves a billing analysis for a specified time range.

### Method
GET

### Endpoint
`/api/admin/analytics/billing`

### Query Parameters
- **start_time** (string) - Required - The start date for the analysis (YYYY-MM-DD).
- **end_time** (string) - Required - The end date for the analysis (YYYY-MM-DD).

### Request Example
```
GET /api/admin/analytics/billing?start_time=2024-01-01&end_time=2024-01-31
```

### Response
#### Success Response (200)
- **status** (boolean) - Indicates if the request was successful.
- **data** (object) - Contains the billing analysis details:
  - **total_revenue** (number) - The total revenue for the period.
  - **subscription_revenue** (number) - The revenue generated from subscriptions.
  - **usage_revenue** (number) - The revenue generated from usage.
  - **daily_breakdown** (array) - An array of objects, each representing a day's revenue and requests:
    - **date** (string) - The date of the breakdown (YYYY-MM-DD).
    - **revenue** (number) - The revenue for that day.
    - **requests** (integer) - The number of requests for that day.

#### Response Example
```json
{
  "status": true,
  "data": {
    "total_revenue": 8420.75,
    "subscription_revenue": 4500.00,
    "usage_revenue": 3920.75,
    "daily_breakdown": [
      {"date": "2024-01-01", "revenue": 250.50, "requests": 12500},
      {"date": "2024-01-02", "revenue": 280.75, "requests": 13200},
      {"date": "2024-01-03", "revenue": 310.25, "requests": 14800}
    ]
  }
}
```
```

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

### Get Billing Analysis API Request

Source: https://context7.com/mathematrix/coai/llms.txt

This API endpoint retrieves billing analytics for a specified time range. It requires an administrator JWT token for authorization. The response includes total revenue, subscription and usage revenue, and a daily breakdown.

```bash
curl -X GET "https://your-domain.com/api/admin/analytics/billing?start_time=2024-01-01&end_time=2024-01-31" \
  -H "Authorization: Bearer admin-jwt-token"
```

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

### GET /api/conversation/load

Source: https://context7.com/mathematrix/coai/llms.txt

Loads a specific conversation by its ID. Requires authentication.

```APIDOC
## GET /api/conversation/load

### Description
Loads a specific conversation by its ID. Requires authentication.

### Method
GET

### Endpoint
/api/conversation/load

### Parameters
#### Query Parameters
- **id** (integer) - Required - The ID of the conversation to load.

#### Request Body
None

### Request Example
```bash
curl -X GET "https://your-domain.com/api/conversation/load?id=1" \
  -H "Authorization: Bearer your-jwt-token"
```

### Response
#### Success Response (200)
- **status** (boolean) - Indicates if the request was successful.
- **data** (object) - Contains the conversation details.
  - **id** (integer) - The unique identifier of the conversation.
  - **name** (string) - The name of the conversation.
  - **messages** (array) - An array of message objects.
    - **role** (string) - The role of the sender (e.g., 'user', 'assistant').
    - **content** (string) - The message content.
    - **timestamp** (string) - The time the message was sent (ISO 8601 format).

#### Response Example
```json
{
  "status": true,
  "data": {
    "id": 1,
    "name": "Quantum Computing Discussion",
    "messages": [
      {
        "role": "user",
        "content": "Explain quantum computing",
        "timestamp": "2024-01-05T10:30:00Z"
      },
      {
        "role": "assistant",
        "content": "Quantum computing is...",
        "timestamp": "2024-01-05T10:30:15Z"
      }
    ]
  }
}
```
```

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

### User Registration API - Bash

Source: https://context7.com/mathematrix/coai/llms.txt

Registers a new user account by first requesting a verification code via email, then submitting the username, password, email, and verification code. Returns a JWT token and initial quota upon successful registration. Dependencies: Email verification service.

```bash
curl -X POST https://your-domain.com/api/verify \
  -H "Content-Type: application/json" \
  -d '{
    "email": "user@example.com"
  }'

# Response: { "status": true }

# Then register with the code
curl -X POST https://your-domain.com/api/register \
  -H "Content-Type: application/json" \
  -d '{
    "username": "newuser",
    "password": "SecurePass123!",
    "email": "user@example.com",
    "code": "123456"
  }'

# Response
{
  "status": true,
  "token": "eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJ1c2VybmFtZSI6Im5ld3VzZXIiLCJwYXNzd29yZCI6Imhhc2giLCJleHAiOjE3MDk5OTk5OTl9.signature",
  "quota": 5.0
}
```

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

### GET /api/conversation/view

Source: https://context7.com/mathematrix/coai/llms.txt

Views a shared conversation using its hash. No authentication required.

```APIDOC
## GET /api/conversation/view

### Description
Views a shared conversation using its hash. No authentication required.

### Method
GET

### Endpoint
/api/conversation/view

### Parameters
#### Query Parameters
- **hash** (string) - Required - The hash of the shared conversation.

#### Request Body
None

### Request Example
```bash
curl -X GET "https://your-domain.com/api/conversation/view?hash=abc123xyz789"
```

### Response
#### Success Response (200)
- **status** (boolean) - Indicates if the request was successful.
- **data** (object) - Contains the conversation details.
  - **name** (string) - The name of the conversation.
  - **messages** (array) - An array of message objects.
    - **role** (string) - The role of the sender (e.g., 'user', 'assistant').
    - **content** (string) - The message content.

#### Response Example
```json
{
  "status": true,
  "data": {
    "name": "My Quantum Computing Discussion",
    "messages": [
      {"role": "user", "content": "Explain quantum computing"},
      {"role": "assistant", "content": "Quantum computing is..."},
      {"role": "user", "content": "What are practical applications?"},
      {"role": "assistant", "content": "Practical applications include..."}
    ]
  }
}
```
```

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

### GET /api/conversation/list

Source: https://context7.com/mathematrix/coai/llms.txt

Retrieves a list of user's conversation history with pagination support.

```APIDOC
## GET /api/conversation/list

### Description
Retrieves a list of user's conversation history. Supports pagination.

### Method
GET

### Endpoint
/api/conversation/list

### Parameters
#### Query Parameters
- **page** (integer) - Optional - The page number to retrieve.
- **limit** (integer) - Optional - The number of conversations per page.

### Request Example
```bash
curl -X GET https://your-domain.com/api/conversation/list \
  -H "Authorization: Bearer your-jwt-token"
```

### Response
#### Success Response (200)
- **status** (boolean) - Indicates success of the operation.
- **data** (array of objects) - A list of conversations.
  - **id** (string) - The unique identifier of the conversation.
  - **title** (string) - The title of the conversation.
  - **createdAt** (string) - The timestamp when the conversation was created.

#### Response Example
```json
{
  "status": true,
  "data": [
    {
      "id": "conv-123abc",
      "title": "My first conversation",
      "createdAt": "2023-10-27T10:00:00Z"
    },
    {
      "id": "conv-456def",
      "title": "AI prompt ideas",
      "createdAt": "2023-10-26T15:30:00Z"
    }
  ]
}
```
```

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

### System Configuration File (config.yaml)

Source: https://context7.com/mathematrix/coai/llms.txt

This file contains the complete system configuration for Chat Nio, including server settings, database connection details (MySQL), Redis configuration, security secrets, and initial user quota. It also includes options to control user registration and relay services.

```yaml
server:
  port: "8000"

serve_static: true
allow_origins: ["https://yourdomain.com"]

secret: "your-jwt-secret-key-min-32-chars"

database:
  type: "mysql"
  host: "localhost"
  port: 3306
  username: "root"
  password: "password"
  database: "chatnio"

redis:
  host: "localhost"
  port: 6379
  password: ""
  db: 0

close_registration: false
close_relay: false
initial_quota: 5.0

```

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

### User Login API - Bash

Source: https://context7.com/mathematrix/coai/llms.txt

Authenticates a user using their username or email and password. Upon successful authentication, it returns a JWT token valid for 30 days and the user's current information, including their quota balance. Dependencies: User database.

```bash
curl -X POST https://your-domain.com/api/login \
  -H "Content-Type: application/json" \
  -d '{
    "username": "newuser",
    "password": "SecurePass123!"
  }'

# Response
{
  "status": true,
  "token": "eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9...",
  "user": {
    "username": "newuser",
    "email": "user@example.com",
    "admin": false,
    "quota": 5.0,
    "subscription": {
      "level": 0,
      "expired": null
    }
  }
}
```

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

### Docker Compose Deployment Configuration

Source: https://context7.com/mathematrix/coai/llms.txt

This Docker Compose file defines the services for deploying the Chat Nio stack, including the main application, MySQL database, and Redis cache. It manages container networking, volumes for persistent data, and environment variables for configuration. Automatic database initialization is handled.

```yaml
version: '3.8'

services:
  chatnio:
    image: programzmh/chatnio:latest
    container_name: chatnio
    ports:
      - "8000:8000"
    volumes:
      - ./config:/config
      - ./logs:/logs
      - ./storage:/storage
    environment:
      MYSQL_HOST: mysql
      MYSQL_PORT: 3306
      MYSQL_DB: chatnio
      MYSQL_USER: root
      MYSQL_PASSWORD: chatnio123456
      REDIS_HOST: redis
      REDIS_PORT: 6379
      SECRET: your-jwt-secret-change-this
      SERVE_STATIC: "true"
    depends_on:
      - mysql
      - redis

  mysql:
    image: mysql:8.0
    container_name: chatnio-mysql
    volumes:
      - ./db:/var/lib/mysql
    environment:
      MYSQL_ROOT_PASSWORD: chatnio123456
      MYSQL_DATABASE: chatnio
    command: --default-authentication-plugin=mysql_native_password

  redis:
    image: redis:alpine
    container_name: chatnio-redis
    volumes:
      - ./redis:/data

# Start services
# docker-compose up -d

# View logs
# docker-compose logs -f chatnio

# Update to latest version
# docker-compose pull && docker-compose up -d
```

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

### Get Error Analysis

Source: https://context7.com/mathematrix/coai/llms.txt

Retrieves an error analysis for a specified duration. This endpoint provides total errors, error rate, and breakdowns by type and channel.

```APIDOC
## GET /api/admin/analytics/error

### Description
Retrieves an error analysis for a specified duration.

### Method
GET

### Endpoint
`/api/admin/analytics/error`

### Query Parameters
- **hours** (integer) - Required - The duration in hours for the error analysis.

### Request Example
```
GET /api/admin/analytics/error?hours=24
```

### Response
#### Success Response (200)
- **status** (boolean) - Indicates if the request was successful.
- **data** (object) - Contains the error analysis details:
  - **total_errors** (integer) - The total number of errors.
  - **error_rate** (number) - The overall error rate.
  - **by_type** (array) - An array of objects detailing errors by type:
    - **type** (string) - The type of error (e.g., "rate_limit").
    - **count** (integer) - The number of errors of this type.
    - **percentage** (number) - The percentage of total errors of this type.
  - **by_channel** (array) - An array of objects detailing errors by channel:
    - **channel** (string) - The channel where errors occurred.
    - **errors** (integer) - The number of errors for this channel.

#### Response Example
```json
{
  "status": true,
  "data": {
    "total_errors": 320,
    "error_rate": 0.021,
    "by_type": [
      {"type": "rate_limit", "count": 150, "percentage": 46.9},
      {"type": "timeout", "count": 85, "percentage": 26.6},
      {"type": "invalid_key", "count": 50, "percentage": 15.6},
      {"type": "server_error", "count": 35, "percentage": 10.9}
    ],
    "by_channel": [
      {"channel": "OpenAI GPT-4 Primary", "errors": 120},
      {"channel": "Azure OpenAI Backup", "errors": 80},
      {"channel": "Claude Primary", "errors": 120}
    ]
  }
}
```
```

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

### POST /api/admin/channel/create

Source: https://context7.com/mathematrix/coai/llms.txt

Configures a new AI provider channel with specified settings like load balancing, retry logic, model mapping, and access restrictions. Supports multiple API keys and priority-based routing.

```APIDOC
## POST /api/admin/channel/create

### Description
Configures a new AI provider channel with load balancing, retry logic, and model mapping. Supports multiple API keys, priority-based routing, and user group restrictions.

### Method
POST

### Endpoint
/api/admin/channel/create

### Parameters
#### Request Body
- **name** (string) - Required - The name of the AI channel.
- **type** (string) - Required - The type of the AI provider (e.g., "openai", "azure").
- **priority** (integer) - Optional - The priority of the channel (higher value means higher priority).
- **weight** (integer) - Optional - The weight for load balancing.
- **models** (array of strings) - Required - List of models supported by this channel.
- **retry** (integer) - Optional - Number of retries on failure.
- **secret** (string) - Required - API key(s) for the provider, separated by newline for multiple keys.
- **endpoint** (string) - Required - The API endpoint for the AI provider.
- **mapper** (string) - Optional - Model mapping rules (e.g., "model_a>model_b").
- **state** (boolean) - Optional - Whether the channel is enabled (true) or disabled (false).
- **group** (array of strings) - Optional - User groups allowed to access this channel.
- **proxy** (object) - Optional - Proxy configuration.
  - **proxy_type** (integer) - Required - Type of proxy (0: None, 1: HTTP, 2: SOCKS4, 3: SOCKS5).
  - **proxy** (string) - Optional - Proxy address.
  - **username** (string) - Optional - Proxy username.
  - **password** (string) - Optional - Proxy password.

### Request Example
```json
{
  "name": "OpenAI GPT-4 Primary",
  "type": "openai",
  "priority": 10,
  "weight": 100,
  "models": ["gpt-4", "gpt-4-turbo", "gpt-4-vision-preview"],
  "retry": 3,
  "secret": "sk-proj-abc123xyz789\nsk-proj-def456uvw012",
  "endpoint": "https://api.openai.com",
  "mapper": "gpt-4>gpt-4-0613\ngpt-4-turbo>gpt-4-turbo-2024-04-09",
  "state": true,
  "group": ["basic", "standard", "pro"],
  "proxy": {
    "proxy_type": 0,
    "proxy": "",
    "username": "",
    "password": ""
  }
}
```

### Response
#### Success Response (200)
- **status** (boolean) - Indicates success of the operation.
- **id** (integer) - The unique identifier of the created channel.
- **message** (string) - A confirmation message.

#### Response Example
```json
{
  "status": true,
  "id": 15,
  "message": "Channel created successfully"
}
```
```

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

### User Registration API

Source: https://context7.com/mathematrix/coai/llms.txt

Allows users to register for a new account. This involves two steps: requesting a verification code via email and then completing registration with the provided code.

```APIDOC
## POST /api/verify

### Description
Requests a verification code to be sent to the specified email address for user registration.

### Method
POST

### Endpoint
/api/verify

### Parameters
#### Request Body
- **email** (string) - Required - The email address to send the verification code to.

### Request Example
```json
{
  "email": "user@example.com"
}
```

### Response
#### Success Response (200)
- **status** (boolean) - Indicates if the verification code request was successful.

#### Response Example
```json
{
  "status": true
}
```

## POST /api/register

### Description
Registers a new user account using a verification code previously sent to their email. Upon successful registration, a JWT token and initial quota are provided.

### Method
POST

### Endpoint
/api/register

### Parameters
#### Request Body
- **username** (string) - Required - The desired username for the new account.
- **password** (string) - Required - The password for the new account.
- **email** (string) - Required - The email address associated with the account.
- **code** (string) - Required - The verification code received via email.

### Request Example
```json
{
  "username": "newuser",
  "password": "SecurePass123!",
  "email": "user@example.com",
  "code": "123456"
}
```

### Response
#### Success Response (200)
- **status** (boolean) - Indicates if the registration was successful.
- **token** (string) - JWT token for user authentication.
- **quota** (float) - The initial quota allocated to the new user.

#### Response Example
```json
{
  "status": true,
  "token": "eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJ1c2VybmFtZSI6Im5ld3VzZXIiLCJwYXNzd29yZCI6Imhhc2giLCJleHAiOjE3MDk5OTk5OTl9.signature",
  "quota": 5.0
}
```
```

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

### Vision/Image Understanding with CoAI API (Bash)

Source: https://context7.com/mathematrix/coai/llms.txt

Demonstrates how to enable multimodal capabilities by sending images with user messages. Images can be provided either as base64-encoded strings or public URLs. This allows the model to analyze and interpret image content. The `gpt-4-vision-preview` model is used for this functionality.

```bash
curl -X POST https://your-domain.com/api/v1/chat/completions \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4-vision-preview",
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "type": "text",
            "text": "What is in this image?"
          },
          {
            "type": "image_url",
            "image_url": {
              "url": "https://example.com/image.jpg"
            }
          }
        ]
      }
    ],
    "max_tokens": 500
  }'
```

```json
{
  "choices": [{
    "message": {
      "role": "assistant",
      "content": "This image shows a beautiful sunset over a mountain range. The sky displays vibrant orange and pink hues, with silhouetted peaks in the foreground..."
    },
    "finish_reason": "stop"
  }],
  "usage": {"prompt_tokens": 1285, "completion_tokens": 89, "total_tokens": 1374}
}
```