### Install Vapi Python SDK

Source: https://github.com/vapiai/server-sdk-python/blob/main/README.md

Install the Vapi server SDK package using pip. This command fetches and installs the latest version of the library from PyPI.

```sh
pip install vapi_server_sdk
```

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

### Create Assistant with Vapi Python SDK

Source: https://github.com/vapiai/server-sdk-python/blob/main/reference.md

Provides a basic example of creating an assistant using the Vapi Python SDK. This operation requires an initialized Vapi client with a valid authentication token. Further customization options for assistant creation are available but not shown in this basic example.

```python
from vapi import Vapi

client = Vapi(
    token="YOUR_TOKEN",
)
client.assistants.create()
```

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

### Initialize and Use Async Vapi Client (Python)

Source: https://github.com/vapiai/server-sdk-python/blob/main/README.md

Shows how to create an asynchronous Vapi client for non-blocking API calls. It includes an example of running an async function to create a call using the client.

```python
import asyncio

from vapi import AsyncVapi

client = AsyncVapi(
    token="YOUR_TOKEN",
)


async def main() -> None:
    await client.calls.create()


asyncio.run(main())
```

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

### List Tools using Vapi Python SDK

Source: https://github.com/vapiai/server-sdk-python/blob/main/reference.md

This code example demonstrates how to list available tools using the Vapi Python SDK. It initializes the Vapi client and calls the list method for tools. Optional parameters allow filtering the results by creation or update timestamps, and controlling the number of items returned.

```python
from vapi import Vapi
import datetime as dt

client = Vapi(
    token="YOUR_TOKEN",
)
client.tools.list()
# Example with parameters:
# client.tools.list(
#     limit=50,
#     created_at_gt=dt.datetime(2023, 1, 1),
#     updated_at_lt=dt.datetime(2023, 12, 31)
# )
```

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

### Initialize Async Vapi Client (Python)

Source: https://context7.com/vapiai/server-sdk-python/llms.txt

Shows how to initialize the asynchronous Vapi client for non-blocking operations. This is suitable for async applications where I/O operations should not block the event loop. Includes an example of fetching assistants.

```python
import asyncio
from vapi import AsyncVapi

async def main():
    client = AsyncVapi(token="your_api_token_here")

    # Perform async operations
    assistants = await client.assistants.list()

    # Process results
    for assistant in assistants:
        print(f"Assistant: {assistant.name}")

asyncio.run(main())
```

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

### Create Voice Assistant (Python)

Source: https://context7.com/vapiai/server-sdk-python/llms.txt

Example of creating a new AI voice assistant using the Vapi Python SDK. This snippet demonstrates configuring the assistant's name, initial message, AI model, voice, transcriber, call duration, background sound, end call phrases, and webhook server URL.

```python
from vapi import Vapi

client = Vapi(token="your_api_token_here")

assistant = client.assistants.create(
    name="Customer Support Agent",
    first_message="Hello! How can I help you today?",
    model={
        "provider": "openai",
        "model": "gpt-4",
        "messages": [
            {
                "role": "system",
                "content": "You are a friendly customer support agent. Be helpful and concise."
            }
        ],
        "temperature": 0.7
    },
    voice={
        "provider": "11labs",
        "voiceId": "rachel"
    },
    transcriber={
        "provider": "deepgram",
        "model": "nova-2",
        "language": "en"
    },
    max_duration_seconds=600,
    background_sound="office",
    end_call_phrases=["goodbye", "have a nice day"],
    server={
        "url": "https://your-webhook-url.com/vapi"
    }
)

print(f"Created assistant: {assistant.id}")
```

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

### Create Squad with Members in Python

Source: https://github.com/vapiai/server-sdk-python/blob/main/reference.md

Create a new squad by specifying a list of assistant members. The first member in the list becomes the starting assistant. Optional name and member overrides can be applied globally across all squad members.

```python
from vapi import SquadMemberDto, Vapi

client = Vapi(
    token="YOUR_TOKEN",
)
client.squads.create(
    members=[SquadMemberDto()],
    name="string",
    members_overrides=AssistantOverrides(...),
    request_options=RequestOptions(...)
)
```

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

### Tools API

Source: https://github.com/vapiai/server-sdk-python/blob/main/reference.md

APIs for managing tools, including listing, creating, getting, and deleting them.

```APIDOC
## GET /tools

### Description
Retrieves a list of available tools.

### Method
GET

### Endpoint
`/tools`

### Parameters
#### Query Parameters
- **limit** (float) - Optional - The maximum number of items to return. Defaults to 100.
- **created_at_gt** (datetime) - Optional - Filters tools created after the specified date.
- **created_at_lt** (datetime) - Optional - Filters tools created before the specified date.
- **created_at_ge** (datetime) - Optional - Filters tools created on or after the specified date.
- **created_at_le** (datetime) - Optional - Filters tools created on or before the specified date.
- **updated_at_gt** (datetime) - Optional - Filters tools updated after the specified date.
- **updated_at_lt** (datetime) - Optional - Filters tools updated before the specified date.
- **updated_at_ge** (datetime) - Optional - Filters tools updated on or after the specified date.
- **updated_at_le** (datetime) - Optional - Filters tools updated on or before the specified date.

#### Request Body
None

### Response
#### Success Response (200)
- **tools** (array) - A list of tool objects.

### Request Example
```python
from vapi import Vapi

client = Vapi(token="YOUR_TOKEN")
client.tools.list(limit=50)
```

### Response Example
```json
{
  "tools": [
    {
      "id": "tool_abc",
      "name": "Example Tool"
    }
  ]
}
```
```

```APIDOC
## POST /tools

### Description
Creates a new tool.

### Method
POST

### Endpoint
`/tools`

### Parameters
#### Request Body
- **request** (CreateToolsRequest) - Required - The details for creating the tool.

### Response
#### Success Response (200)
- **created_tool** (object) - The details of the newly created tool.

### Request Example
```python
from vapi import CreateApiRequestToolDto, Vapi

client = Vapi(token="YOUR_TOKEN")
client.tools.create(request=CreateApiRequestToolDto(method="POST", url="url"))
```

### Response Example
```json
{
  "created_tool": {
    "id": "tool_xyz",
    "name": "New Tool"
  }
}
```
```

```APIDOC
## GET /tools/{id}

### Description
Retrieves details of a specific tool.

### Method
GET

### Endpoint
`/tools/{id}`

### Parameters
#### Path Parameters
- **id** (str) - Required - The unique identifier of the tool.

#### Request Body
None

### Response
#### Success Response (200)
- **tool_details** (object) - Details of the tool.

### Request Example
```python
from vapi import Vapi

client = Vapi(token="YOUR_TOKEN")
client.tools.get(id="id")
```

### Response Example
```json
{
  "tool_details": {
    "id": "tool_abc",
    "name": "Example Tool"
  }
}
```
```

```APIDOC
## DELETE /tools/{id}

### Description
Deletes a specific tool.

### Method
DELETE

### Endpoint
`/tools/{id}`

### Parameters
#### Path Parameters
- **id** (str) - Required - The unique identifier of the tool to delete.

#### Request Body
None

### Response
#### Success Response (200)
- **message** (str) - Confirmation message of deletion.

### Request Example
```python
from vapi import Vapi

client = Vapi(token="YOUR_TOKEN")
client.tools.delete(id="id")
```

### Response Example
```json
{
  "message": "Tool deleted successfully."
}
```
```

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

### Vapi Python SDK: List Phone Numbers

Source: https://github.com/vapiai/server-sdk-python/blob/main/reference.md

Provides an example of how to list available phone numbers using the Vapi Python SDK. It demonstrates initializing the Vapi client with a token and calling the list method on the phone_numbers client.

```python
from vapi import Vapi

client = Vapi(
    token="YOUR_TOKEN",
)
client.phone_numbers.list()
```

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

### GET /campaigns

Source: https://github.com/vapiai/server-sdk-python/blob/main/reference.md

Retrieves a list of campaigns, with options for filtering, pagination, and sorting.

```APIDOC
## GET /campaigns

### Description
Retrieves a list of campaigns, with options for filtering, pagination, and sorting.

### Method
GET

### Endpoint
/campaigns

### Parameters
#### Query Parameters
- **id** (Optional[str]) - Filters campaigns by ID.
- **status** (Optional[CampaignControllerFindAllRequestStatus]) - Filters campaigns by status.
- **page** (Optional[float]) - The page number to return. Defaults to 1.
- **sort_order** (Optional[CampaignControllerFindAllRequestSortOrder]) - The sort order for pagination. Defaults to 'DESC'.
- **limit** (Optional[float]) - The maximum number of items to return. Defaults to 100.
- **created_at_gt** (Optional[datetime]) - Returns items where the createdAt is greater than the specified value.
- **created_at_lt** (Optional[datetime]) - Returns items where the createdAt is less than the specified value.
- **created_at_ge** (Optional[datetime]) - Returns items where the createdAt is greater than or equal to the specified value.
- **created_at_le** (Optional[datetime]) - Returns items where the createdAt is less than or equal to the specified value.
- **updated_at_gt** (Optional[datetime]) - Returns items where the updatedAt is greater than the specified value.
- **updated_at_lt** (Optional[datetime]) - Returns items where the updatedAt is less than the specified value.
- **updated_at_ge** (Optional[datetime]) - Returns items where the updatedAt is greater than or equal to the specified value.
- **updated_at_le** (Optional[datetime]) - Returns items where the updatedAt is less than or equal to the specified value.
- **request_options** (Optional[RequestOptions]) - Request-specific configuration.

### Response
#### Success Response (200 OK)
- **data** (Array) - A list of campaign objects.
  - Each campaign object may contain fields like id, name, status, etc.
- **page** (float) - The current page number.
- **limit** (float) - The number of items per page.
- **total** (float) - The total number of campaigns available.

#### Response Example
```json
{
  "data": [
    {
      "id": "campaignId1",
      "name": "Q2 Sales Campaign",
      "status": "running"
    },
    {
      "id": "campaignId2",
      "name": "Q3 Marketing Push",
      "status": "completed"
    }
  ],
  "page": 1,
  "limit": 10,
  "total": 2
}
```
```

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

### List Vapi Sessions using Python SDK

Source: https://github.com/vapiai/server-sdk-python/blob/main/reference.md

This code example shows how to retrieve a list of all Vapi sessions using the Python SDK. It requires authentication with a Vapi token. This function does not take any specific parameters other than the client initialization.

```python
from vapi import Vapi

client = Vapi(
    token="YOUR_TOKEN",
)
client.sessions.list()
```

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

### Create Campaign for Batch Calling

Source: https://context7.com/vapiai/server-sdk-python/llms.txt

Sets up a new campaign designed for scheduled batch calling operations. Requires campaign name, assistant ID, phone number ID, customer list, and a schedule plan with start time and time zone. Returns the created campaign's ID and status.

```python
from vapi import Vapi

client = Vapi(token="your_api_token_here")

campaign = client.campaigns.create(
    name="Q4 Product Survey",
    assistant_id="assistant_id_here",
    phone_number_id="phone_number_id_here",
    customers=[
        {"number": "+14155551111", "name": "Customer A"},
        {"number": "+14155552222", "name": "Customer B"}
    ],
    schedule_plan={
        "start_time": "2024-12-01T09:00:00Z",
        "time_zone": "America/New_York"
    }
)

print(f"Campaign created: {campaign.id}")
print(f"Status: {campaign.status}")
```

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

### Create Structured Output Schema

Source: https://context7.com/vapiai/server-sdk-python/llms.txt

Defines a schema for structured outputs to extract specific data from conversations. This example creates a schema named 'Appointment Details' to capture date, time, service, and customer name, specifying required fields and data formats. Dependencies: `Vapi` client.

```python
from vapi import Vapi

client = Vapi(token="your_api_token_here")

# Create structured output schema
structured_output = client.structured_outputs.create(
    name="Appointment Details",
    schema={
        "type": "object",
        "properties": {
            "date": {"type": "string", "format": "date"},
            "time": {"type": "string"},
            "service": {"type": "string"},
            "customer_name": {"type": "string"}
        },
        "required": ["date", "time", "service"]
    },
    description="Extract appointment details from customer conversation"
)

print(f"Structured output created: {structured_output.id}")
```

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

### Update Assistant Configuration (Python)

Source: https://context7.com/vapiai/server-sdk-python/llms.txt

Provides an example of how to update the configuration of an existing voice assistant using its ID. This allows for dynamic adjustments to the assistant's behavior, such as changing its initial message, AI model, or call termination messages.

```python
from vapi import Vapi

client = Vapi(token="your_api_token_here")

updated_assistant = client.assistants.update(
    id="assistant_id_here",
    first_message="Hi there! I'm your updated assistant.",
    model={
        "provider": "openai",
        "model": "gpt-4-turbo",
        "temperature": 0.8
    },
    voicemail_message="Sorry we missed you. Please leave a message.",
    end_call_message="Thank you for calling. Goodbye!"
)

print(f"Updated assistant: {updated_assistant.id}")
```

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

### Configure Request Options and Retries

Source: https://context7.com/vapiai/server-sdk-python/llms.txt

Shows how to configure default request options like timeout for the Vapi client and override them for specific requests. This example sets a default timeout and then customizes the timeout and maximum retries for an assistant creation call using `request_options`. Dependencies: `Vapi`.

```python
from vapi import Vapi

client = Vapi(
    token="your_api_token_here",
    timeout=60.0  # Default timeout for all requests
)

# Override timeout and retries for specific request
assistant = client.assistants.create(
    name="Test Assistant",
    request_options={
        "timeout_in_seconds": 120,  # 2 minute timeout for this request
        "max_retries": 3  # Retry up to 3 times
    }
)

print(f"Assistant created: {assistant.id}")
```

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

### Get Tool by ID using Vapi Python SDK

Source: https://github.com/vapiai/server-sdk-python/blob/main/reference.md

This code example demonstrates retrieving a specific tool by its ID using the Vapi Python SDK. After initializing the client with an authentication token, the `get` method is called with the tool's unique identifier. This operation is useful for fetching details of a particular tool.

```python
from vapi import Vapi

client = Vapi(
    token="YOUR_TOKEN",
)
client.tools.get(
    id="id",
)
```

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

### Initialize Vapi Client (Python)

Source: https://context7.com/vapiai/server-sdk-python/llms.txt

Demonstrates how to initialize the synchronous Vapi client. It covers basic initialization with a token, as well as advanced configurations for custom timeouts, environments, and integrating with httpx for proxy support.

```python
from vapi import Vapi

# Basic synchronous client
client = Vapi(token="your_api_token_here")

# Client with custom timeout and environment
from vapi import VapiEnvironment

client = Vapi(
    token="your_api_token_here",
    environment=VapiEnvironment.DEFAULT,
    timeout=30.0
)

# Client with custom httpx configuration for proxy support
import httpx

client = Vapi(
    token="your_api_token_here",
    httpx_client=httpx.Client(
        proxies="http://proxy.example.com:8080",
        transport=httpx.HTTPTransport(local_address="0.0.0.0")
    )
)
```

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

### Initialize and Use Vapi Client (Python)

Source: https://github.com/vapiai/server-sdk-python/blob/main/README.md

Demonstrates how to instantiate the synchronous Vapi client with an authentication token and make a basic call to create a call. Ensure you replace 'YOUR_TOKEN' with your actual API token.

```python
from vapi import Vapi

client = Vapi(
    token="YOUR_TOKEN",
)
client.calls.create()
```

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

### GET Eval Controller Get Paginated

Source: https://github.com/vapiai/server-sdk-python/blob/main/reference.md

Retrieves paginated eval results from the system. This endpoint returns a paginated list of evaluations with optional filtering and sorting parameters.

```APIDOC
## GET /eval

### Description
Retrieves a paginated list of evaluations from the system.

### Method
GET

### Endpoint
`/eval`

### Parameters
#### Query Parameters
- Pagination parameters (page, limit, etc.) - Optional - Control pagination of results

#### Request Options
- **request_options** (typing.Optional[RequestOptions]) - Optional - Request-specific configuration

### Usage Example
```python
from vapi import Vapi

client = Vapi(
    token="YOUR_TOKEN",
)
client.eval.eval_controller_get_paginated()
```

### Response
#### Success Response (200)
- **items** (array) - List of evaluation objects
- **total** (number) - Total count of evaluations
- **page** (number) - Current page number
- **limit** (number) - Items per page
```

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

### GET /provider-resources - Get Provider Resources Paginated

Source: https://github.com/vapiai/server-sdk-python/blob/main/reference.md

Retrieves paginated provider resources with filtering by provider and resource name. Used to access and manage external provider resources.

```APIDOC
## GET /provider-resources

### Description
Retrieves a paginated list of provider resources filtered by provider type and resource name. Supports pagination for managing large resource sets.

### Method
GET

### Endpoint
`/provider-resources`

### Parameters

#### Query Parameters
- **provider** (string) - Required - Provider identifier (e.g., "11labs" for ElevenLabs)
- **resource_name** (string) - Required - Name of the resource to retrieve (e.g., "pronunciation-dictionary")
- **page** (float) - Optional - Page number for pagination. Defaults to 1
- **limit** (float) - Optional - Maximum number of items to return. Defaults to 100
- **request_options** (RequestOptions) - Optional - Request-specific configuration

### Request Example
```python
from vapi import Vapi

client = Vapi(
    token="YOUR_TOKEN",
)
client.provider_resources.provider_resource_controller_get_provider_resources_paginated(
    provider="11labs",
    resource_name="pronunciation-dictionary",
)
```

### Response
#### Success Response (200)
- **items** (array) - List of provider resource objects
- **page** (float) - Current page number
- **limit** (float) - Number of items per page
- **total** (float) - Total number of resources available
- **provider** (string) - Provider identifier
- **resource_name** (string) - Resource name
```

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

### Structured Output Suggestions

Source: https://github.com/vapiai/server-sdk-python/blob/main/reference.md

Analyzes assistant configuration and generates contextual structured output recommendations.

```APIDOC
## POST /structured_outputs/suggest

### Description
Analyzes assistant configuration and generates contextual structured output recommendations.

### Method
POST

### Endpoint
/structured_outputs/suggest

### Parameters
#### Query Parameters
- **assistant_id** (str) - Required - The assistant ID to analyze and generate suggestions for
- **count** (float) - Optional - Number of suggestions to generate
- **exclude_ids** (Sequence[str]) - Optional - Existing structured output IDs to exclude from suggestions
- **seed** (float) - Optional - Iteration/seed for generating diverse suggestions (0 = first generation, 1+ = regenerations with increasing specificity)
- **request_options** (RequestOptions) - Optional - Request-specific configuration.

### Request Example
```json
{
  "assistant_id": "550e8400-e29b-41d4-a716-446655440000"
}
```

### Response
#### Success Response (200)
- **suggestions** (list) - A list of suggested structured outputs

#### Response Example
```json
{
  "suggestions": [
    {
      "id": "string",
      "name": "string",
      "description": "string"
    }
  ]
}
```
```

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

### GET /campaigns/{id}

Source: https://github.com/vapiai/server-sdk-python/blob/main/reference.md

Retrieves a specific campaign by its ID.

```APIDOC
## GET /campaigns/{id}

### Description
Retrieves a specific campaign by its ID.

### Method
GET

### Endpoint
/campaigns/{id}

### Parameters
#### Path Parameters
- **id** (str) - Required - The unique identifier of the campaign to retrieve.

#### Query Parameters
- **request_options** (Optional[RequestOptions]) - Request-specific configuration.

### Response
#### Success Response (200 OK)
- **id** (str) - The unique identifier for the campaign.
- **name** (str) - The name of the campaign.
- **status** (str) - The current status of the campaign.
- **...other campaign details**

#### Response Example
```json
{
  "id": "campaignId",
  "name": "Q2 Sales Campaign",
  "status": "running",
  "createdAt": "2023-10-27T10:00:00Z",
  "updatedAt": "2023-10-27T10:05:00Z"
}
```
```

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

### GET /chats/{id}

Source: https://github.com/vapiai/server-sdk-python/blob/main/reference.md

Retrieves a specific chat by its ID.

```APIDOC
## GET /chats/{id}

### Description
Retrieves the details of a specific chat using its unique identifier.

### Method
GET

### Endpoint
/chats/{id}

### Parameters
#### Path Parameters
- **id** (str) - Required - The unique identifier of the chat to retrieve.

#### Query Parameters
- **request_options** (Optional[RequestOptions]) - Request-specific configuration.

### Response
#### Success Response (200)
- **chat_details** (object) - An object containing the details of the chat.

#### Response Example
```json
{
  "chat_id": "chat_abcdef123456",
  "status": "active",
  "created_at": "2023-10-27T10:00:00Z"
}
```
```

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

### Initialize Vapi Client in Python

Source: https://github.com/vapiai/server-sdk-python/blob/main/reference.md

Demonstrates how to initialize the Vapi client with an API token. This is the first step before interacting with the Vapi API.

```python
from vapi import Vapi

client = Vapi(
    token="YOUR_TOKEN",
)
```

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

### GET /provider-resources/{id}

Source: https://github.com/vapiai/server-sdk-python/blob/main/reference.md

Retrieves a specific provider resource by its ID.

```APIDOC
## GET /provider-resources/{id}

### Description
Retrieves a specific provider resource by its ID.

### Method
GET

### Endpoint
/provider-resources/{id}

### Parameters
#### Path Parameters
- **id** (str) - Required - The ID of the provider resource to retrieve.

#### Query Parameters
- **provider** (ProviderResourceControllerGetProviderResourceRequestProvider) - Required - The provider (e.g., 11labs)
- **resource_name** (ProviderResourceControllerGetProviderResourceRequestResourceName) - Required - The resource name (e.g., pronunciation-dictionary)
- **request_options** (typing.Optional[RequestOptions]) - Optional - Request-specific configuration.

### Response
#### Success Response (200)
- **id** (str) - The ID of the provider resource.
- **provider** (str) - The provider of the resource.
- **resource_name** (str) - The name of the resource.
- **createdAt** (str) - The timestamp when the resource was created.
- **updatedAt** (str) - The timestamp when the resource was last updated.

#### Response Example
```json
{
  "id": "resource-id-123",
  "provider": "11labs",
  "resource_name": "pronunciation-dictionary",
  "createdAt": "2023-10-27T10:00:00Z",
  "updatedAt": "2023-10-27T10:00:00Z"
}
```
```

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

### GET /eval/runs

Source: https://github.com/vapiai/server-sdk-python/blob/main/reference.md

Retrieves a paginated list of all evaluation runs, with options for filtering and sorting.

```APIDOC
## GET /eval/runs

### Description
Retrieves a paginated list of evaluation runs.

### Method
GET

### Endpoint
/eval/runs

### Parameters
#### Query Parameters
- **id** (Optional[str]) - Optional - Filter by evaluation run ID.
- **page** (Optional[float]) - Optional - The page number to retrieve. Defaults to 1.
- **sort_order** (Optional[EvalControllerGetRunsPaginatedRequestSortOrder]) - Optional - The sort order for pagination. Defaults to 'DESC'.
- **limit** (Optional[float]) - Optional - The maximum number of items to return per page. Defaults to 100.
- **created_at_gt** (Optional[datetime]) - Optional - Filter for runs created after a specific datetime.
- **created_at_lt** (Optional[datetime]) - Optional - Filter for runs created before a specific datetime.
- **created_at_ge** (Optional[datetime]) - Optional - Filter for runs created on or after a specific datetime.
- **created_at_le** (Optional[datetime]) - Optional - Filter for runs created on or before a specific datetime.
- **updated_at_gt** (Optional[datetime]) - Optional - Filter for runs updated after a specific datetime.
- **updated_at_lt** (Optional[datetime]) - Optional - Filter for runs updated before a specific datetime.
- **updated_at_ge** (Optional[datetime]) - Optional - Filter for runs updated on or after a specific datetime.
- **updated_at_le** (Optional[datetime]) - Optional - Filter for runs updated on or before a specific datetime.
- **request_options** (Optional[RequestOptions]) - Optional - Request-specific configuration.

### Request Example
```python
client.eval.eval_controller_get_runs_paginated(limit=50, sort_order='ASC')
```

### Response
#### Success Response (200)
- **runs** (List[object]) - A list of evaluation runs.
- **total** (int) - The total number of evaluation runs available.

#### Response Example
```json
{
  "runs": [
    {
      "runId": "run_abc789",
      "status": "completed",
      "createdAt": "2023-10-27T10:00:00Z"
    },
    {
      "runId": "run_def456",
      "status": "failed",
      "createdAt": "2023-10-26T15:30:00Z"
    }
  ],
  "total": 2
}
```
```

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

### Create Session in Python

Source: https://github.com/vapiai/server-sdk-python/blob/main/reference.md

Demonstrates how to initiate a session using the Vapi Python SDK. This function allows for the creation of new sessions, potentially with various configurations passed as arguments.

```python
from vapi import Vapi

client = Vapi(
    token="YOUR_TOKEN",
)
client.sessions.create()
```

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

### GET /eval/run/{id}

Source: https://github.com/vapiai/server-sdk-python/blob/main/reference.md

Retrieves the details of a specific evaluation run using its ID.

```APIDOC
## GET /eval/run/{id}

### Description
Retrieves the details of a specific evaluation run.

### Method
GET

### Endpoint
/eval/run/{id}

### Parameters
#### Path Parameters
- **id** (str) - Required - The ID of the evaluation run to retrieve.

#### Query Parameters
- **request_options** (Optional[RequestOptions]) - Optional - Request-specific configuration.

### Request Example
```python
client.eval.eval_controller_get_run(id="run_abc789")
```

### Response
#### Success Response (200)
- **runId** (str) - The ID of the evaluation run.
- **status** (str) - The current status of the evaluation run.
- **results** (object) - The results of the evaluation.

#### Response Example
```json
{
  "runId": "run_abc789",
  "status": "completed",
  "results": {
    "score": 0.95,
    "feedback": "The model performed well."
  }
}
```
```

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

### Create Campaign with Vapi SDK

Source: https://github.com/vapiai/server-sdk-python/blob/main/reference.md

Demonstrates how to create a new campaign using the Vapi Python SDK. Requires campaign name, phone number ID, and customer details. Optionally accepts assistant or workflow IDs, scheduling plans, and request options.

```python
from vapi import CreateCustomerDto, Vapi

client = Vapi(
    token="YOUR_TOKEN",
)
client.campaigns.campaign_controller_create(
    name="Q2 Sales Campaign",
    phone_number_id="phoneNumberId",
    customers=[CreateCustomerDto()],
)
```

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

### Generate Structured Output Recommendations (Python)

Source: https://github.com/vapiai/server-sdk-python/blob/main/reference.md

Analyzes assistant configuration and generates contextual structured output recommendations. Requires an assistant ID and optionally accepts count, exclude_ids, seed, and request_options for fine-tuning the suggestions.

```python
from vapi import Vapi

client = Vapi(
    token="YOUR_TOKEN",
)
client.structured_outputs.structured_output_controller_suggest(
    assistant_id="550e8400-e29b-41d4-a716-446655440000",
)
```

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

### Get Session API

Source: https://github.com/vapiai/server-sdk-python/blob/main/reference.md

Retrieves details for a specific session using its unique identifier.

```APIDOC
## GET /sessions/{id}

### Description
Retrieves a specific session by its ID.

### Method
GET

### Endpoint
/sessions/{id}

### Parameters
#### Path Parameters
- **id** (string) - Required - The unique identifier of the session.

#### Query Parameters
- **request_options** (RequestOptions) - Optional - Request-specific configuration.

### Request Example
```python
client.sessions.get(id="sess_xyz789")
```

### Response
#### Success Response (200)
- **id** (string) - The unique identifier for the session.
- **name** (string) - The name of the session.
- **status** (string) - The status of the session.

#### Response Example
```json
{
  "id": "sess_xyz789",
  "name": "My new session",
  "status": "active"
}
```
```

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

### Create Assistant Parameters

Source: https://github.com/vapiai/server-sdk-python/blob/main/reference.md

This section details the parameters available for configuring an assistant's behavior, including transcriber, model, voice, messaging, and integration settings.

```APIDOC
## Create Assistant Parameters

### Description
This endpoint allows for the creation and configuration of an assistant with various customizable parameters.

### Method
POST

### Endpoint
/assistants

### Parameters
#### Request Body
- **transcriber** (CreateAssistantDtoTranscriber) - Optional - Options for the assistant's transcriber.
- **model** (CreateAssistantDtoModel) - Optional - Options for the assistant's LLM.
- **voice** (CreateAssistantDtoVoice) - Optional - Options for the assistant's voice.
- **first_message** (str) - Optional - The initial message the assistant will speak. Can also be a URL to an audio file. If unspecified, the assistant waits for user input.
- **first_message_interruptions_enabled** (bool) - Optional - Controls whether interruptions are allowed for the first message.
- **first_message_mode** (CreateAssistantDtoFirstMessageMode) - Optional - Defines the mode for the first message. Defaults to 'assistant-speaks-first'. Options include:
    - 'assistant-speaks-first': Assistant speaks first.
    - 'assistant-waits-for-user': Assistant waits for user to speak first.
    - 'assistant-speaks-first-with-model-generated-message': Assistant speaks first with a model-generated message based on conversation state.
- **voicemail_detection** (CreateAssistantDtoVoicemailDetection) - Optional - Settings to configure or disable voicemail detection. Can also be configured using model.tools=[VoicemailTool]. Disabled by default.
- **client_messages** (Sequence[CreateAssistantDtoClientMessagesItem]) - Optional - Messages to be sent to Client SDKs. Defaults to a comprehensive list including 'conversation-update', 'function-call', etc.
- **server_messages** (Sequence[CreateAssistantDtoServerMessagesItem]) - Optional - Messages to be sent to the Server URL. Defaults to a list including 'conversation-update', 'end-of-call-report', etc.
- **max_duration_seconds** (float) - Optional - The maximum duration of the call in seconds. Defaults to 600 (10 minutes).
- **background_sound** (CreateAssistantDtoBackgroundSound) - Optional - The background sound for the call. Defaults to 'office' for phone calls and 'off' for web calls. Can also be a URL to a custom audio file.
- **model_output_in_messages_enabled** (bool) - Optional - Determines if the model's output is used in conversation history instead of the assistant's transcribed speech. Defaults to `false` (in beta).
- **transport_configurations** (Sequence[TransportConfigurationTwilio]) - Optional - Configurations for transport providers like Twilio.
- **observability_plan** (LangfuseObservabilityPlan) - Optional - The observability plan for assistant calls. Currently, only Langfuse is supported.
- **credentials** (Sequence[CreateAssistantDtoCredentialsItem]) - Optional - Dynamic credentials to be used for assistant calls. Overrides existing credentials.
- **hooks** (Sequence[CreateAssistantDtoHooksItem]) - Optional - A set of actions to be performed on certain events.
- **name** (str) - Optional - The name of the assistant. Required for transferring between assistants.
- **voicemail_message** (str) - Optional - The message the assistant will speak if the call is forwarded to voicemail. If unspecified, the call will hang up.

### Request Example
```json
{
  "transcriber": {"type": "google"},
  "model": {"provider": "openai", "model": "gpt-4o"},
  "voice": {"provider": "elevenlabs", "voice_id": "21m00Tcm4T8xjWf2Vd27"},
  "first_message": "Hello, how can I help you today?",
  "max_duration_seconds": 1200,
  "name": "Support Assistant"
}
```

### Response
#### Success Response (200)
- **assistant_id** (str) - The unique identifier of the created assistant.

#### Response Example
```json
{
  "assistant_id": "asst_123abc456def"
}
```
```

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

### Phone Numbers API

Source: https://github.com/vapiai/server-sdk-python/blob/main/reference.md

APIs for managing phone numbers, including getting, deleting, and updating them.

```APIDOC
## GET /phone_numbers/{id}

### Description
Retrieves details of a specific phone number.

### Method
GET

### Endpoint
`/phone_numbers/{id}`

### Parameters
#### Path Parameters
- **id** (str) - Required - The unique identifier of the phone number.

#### Request Body
None

### Response
#### Success Response (200)
- **phone_number_details** (object) - Details of the phone number.

### Request Example
```python
from vapi import Vapi

client = Vapi(token="YOUR_TOKEN")
client.phone_numbers.get(id="id")
```

### Response Example
```json
{
  "phone_number_details": {
    "id": "pn_123",
    "number": "+15551234567"
  }
}
```
```

```APIDOC
## DELETE /phone_numbers/{id}

### Description
Deletes a specific phone number.

### Method
DELETE

### Endpoint
`/phone_numbers/{id}`

### Parameters
#### Path Parameters
- **id** (str) - Required - The unique identifier of the phone number to delete.

#### Request Body
None

### Response
#### Success Response (200)
- **message** (str) - Confirmation message of deletion.

### Request Example
```python
from vapi import Vapi

client = Vapi(token="YOUR_TOKEN")
client.phone_numbers.delete(id="id")
```

### Response Example
```json
{
  "message": "Phone number deleted successfully."
}
```
```

```APIDOC
## PUT /phone_numbers/{id}

### Description
Updates an existing phone number.

### Method
PUT

### Endpoint
`/phone_numbers/{id}`

### Parameters
#### Path Parameters
- **id** (str) - Required - The unique identifier of the phone number to update.

#### Request Body
- **request** (UpdateByoPhoneNumberDto) - Required - The data to update the phone number with.

### Response
#### Success Response (200)
- **updated_phone_number** (object) - The updated phone number details.

### Request Example
```python
from vapi import UpdateByoPhoneNumberDto, Vapi

client = Vapi(token="YOUR_TOKEN")
client.phone_numbers.update(id="id", request=UpdateByoPhoneNumberDto())
```

### Response Example
```json
{
  "updated_phone_number": {
    "id": "pn_123",
    "number": "+15551234567",
    "status": "active"
  }
}
```
```

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

### Create File - Python

Source: https://github.com/vapiai/server-sdk-python/blob/main/reference.md

Creates a new file. Requires a Vapi client initialized with a token. The primary input is the 'file' object, conforming to core.File.

```python
from vapi import Vapi

client = Vapi(
    token="YOUR_TOKEN",
)
client.files.create()

```

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

### GET /phone_numbers

Source: https://github.com/vapiai/server-sdk-python/blob/main/reference.md

Retrieves a paginated list of phone numbers. Supports filtering, sorting, and pagination parameters.

```APIDOC
## GET /phone_numbers

### Description
Retrieves a paginated list of phone numbers. Supports filtering, sorting, and pagination parameters.

### Method
GET

### Endpoint
/phone_numbers

### Parameters
#### Query Parameters
- **search** (typing.Optional[str]) - Optional - Searches phone numbers by name, number, or SIP URI (partial match, case-insensitive).
- **page** (typing.Optional[float]) - Optional - The page number to return. Defaults to 1.
- **sort_order** (typing.Optional[PhoneNumberControllerFindAllPaginatedRequestSortOrder]) - Optional - The sort order for pagination. Defaults to 'DESC'.
- **limit** (typing.Optional[float]) - Optional - The maximum number of items to return. Defaults to 100.
- **created_at_gt** (typing.Optional[dt.datetime]) - Optional - Returns items where `createdAt` is greater than the specified value.
- **created_at_lt** (typing.Optional[dt.datetime]) - Optional - Returns items where `createdAt` is less than the specified value.
- **created_at_ge** (typing.Optional[dt.datetime]) - Optional - Returns items where `createdAt` is greater than or equal to the specified value.
- **created_at_le** (typing.Optional[dt.datetime]) - Optional - Returns items where `createdAt` is less than or equal to the specified value.
- **updated_at_gt** (typing.Optional[dt.datetime]) - Optional - Returns items where `updatedAt` is greater than the specified value.
- **updated_at_lt** (typing.Optional[dt.datetime]) - Optional - Returns items where `updatedAt` is less than the specified value.
- **updated_at_ge** (typing.Optional[dt.datetime]) - Optional - Returns items where `updatedAt` is greater than or equal to the specified value.
- **updated_at_le** (typing.Optional[dt.datetime]) - Optional - Returns items where `updatedAt` is less than or equal to the specified value.
- **request_options** (typing.Optional[RequestOptions]) - Optional - Request-specific configuration.

### Request Example
```python
from vapi import Vapi

client = Vapi(token="YOUR_TOKEN")
client.phone_numbers.phone_number_controller_find_all_paginated()
```

### Response
#### Success Response (200)
(Details of the phone number list would be provided here if available in the source)

#### Response Example
```json
{
  "example": "response body"
}
```
```

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

### GET /provider-resources

Source: https://github.com/vapiai/server-sdk-python/blob/main/reference.md

Retrieves a paginated list of provider resources. Supports filtering by ID, creation/update timestamps, and sorting.

```APIDOC
## GET /provider-resources

### Description
Retrieves a paginated list of provider resources. Supports filtering by ID, creation/update timestamps, and sorting.

### Method
GET

### Endpoint
/provider-resources

### Parameters
#### Query Parameters
- **provider** (ProviderResourceControllerGetProviderResourcesPaginatedRequestProvider) - Required - The provider (e.g., 11labs)
- **resource_name** (ProviderResourceControllerGetProviderResourcesPaginatedRequestResourceName) - Required - The resource name (e.g., pronunciation-dictionary)
- **id** (typing.Optional[str]) - Optional - Filters resources by their ID.
- **resource_id** (typing.Optional[str]) - Optional - Filters resources by their resource ID.
- **page** (typing.Optional[float]) - Optional - The page number to return. Defaults to 1.
- **sort_order** (typing.Optional[ProviderResourceControllerGetProviderResourcesPaginatedRequestSortOrder]) - Optional - The sort order for pagination. Defaults to 'DESC'.
- **limit** (typing.Optional[float]) - Optional - The maximum number of items to return. Defaults to 100.
- **created_at_gt** (typing.Optional[dt.datetime]) - Optional - Returns items where the createdAt is greater than the specified value.
- **created_at_lt** (typing.Optional[dt.datetime]) - Optional - Returns items where the createdAt is less than the specified value.
- **created_at_ge** (typing.Optional[dt.datetime]) - Optional - Returns items where the createdAt is greater than or equal to the specified value.
- **created_at_le** (typing.Optional[dt.datetime]) - Optional - Returns items where the createdAt is less than or equal to the specified value.
- **updated_at_gt** (typing.Optional[dt.datetime]) - Optional - Returns items where the updatedAt is greater than the specified value.
- **updated_at_lt** (typing.Optional[dt.datetime]) - Optional - Returns items where the updatedAt is less than the specified value.
- **updated_at_ge** (typing.Optional[dt.datetime]) - Optional - Returns items where the updatedAt is greater than or equal to the specified value.
- **updated_at_le** (typing.Optional[dt.datetime]) - Optional - Returns items where the updatedAt is less than or equal to the specified value.
- **request_options** (typing.Optional[RequestOptions]) - Optional - Request-specific configuration.

### Response
#### Success Response (200)
- **data** (list) - A list of provider resources.
- **pageInfo** (object) - Pagination information.

#### Response Example
```json
{
  "data": [
    {
      "id": "resource-id-123",
      "provider": "11labs",
      "resource_name": "pronunciation-dictionary",
      "createdAt": "2023-10-27T10:00:00Z",
      "updatedAt": "2023-10-27T10:00:00Z"
    }
  ],
  "pageInfo": {
    "hasNextPage": true,
    "endCursor": "cursor-abc"
  }
}
```
```

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

### GET /phone_numbers/{id}

Source: https://github.com/vapiai/server-sdk-python/blob/main/reference.md

Retrieves a specific phone number by its ID. This endpoint is implied by the `client.phone_numbers.get(...)` usage.

```APIDOC
## GET /phone_numbers/{id}

### Description
Retrieves a specific phone number by its ID.

### Method
GET

### Endpoint
/phone_numbers/{id}

### Parameters
#### Path Parameters
- **id** (str) - Required - The unique identifier of the phone number.

#### Query Parameters
- **request_options** (typing.Optional[RequestOptions]) - Optional - Request-specific configuration.

### Request Example
```python
from vapi import Vapi

client = Vapi(token="YOUR_TOKEN")
# Assuming 'phoneNumberId' is the ID of the phone number you want to retrieve
client.phone_numbers.get("phoneNumberId") 
```

### Response
#### Success Response (200)
(Details of the specific phone number object would be listed here if available in the source)

#### Response Example
```json
{
  "example": "response body"
}
```
```

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

### Upload and List Files

Source: https://context7.com/vapiai/server-sdk-python/llms.txt

Demonstrates file management operations, including uploading a local file (e.g., a PDF) and then listing all uploaded files. It uses `client.files.create` for uploads and `client.files.list` for retrieval. Requires a file path and `Vapi` client.

```python
from vapi import Vapi

client = Vapi(token="your_api_token_here")

# Upload a file
with open("knowledge_base.pdf", "rb") as f:
    file = client.files.create(
        file=f,
        name="Knowledge Base Document"
    )

print(f"File uploaded: {file.id}")

# List all files
files = client.files.list(limit=100)

for file in files:
    print(f"File: {file.name}, Size: {file.size} bytes")
```

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

### GET /evals/{id}

Source: https://github.com/vapiai/server-sdk-python/blob/main/reference.md

Retrieves a specific evaluation by its ID. Requires the evaluation ID as a path parameter and allows for optional request options.

```APIDOC
## GET /evals/{id}

### Description
Retrieves a specific evaluation by its ID. Requires the evaluation ID as a path parameter and allows for optional request options.

### Method
GET

### Endpoint
/evals/{id}

### Parameters
#### Path Parameters
- **id** (str) - Required - The unique identifier of the evaluation to retrieve.

#### Query Parameters
- **request_options** (Optional[RequestOptions]) - Optional - Request-specific configuration.

### Response
#### Success Response (200)
- **id** (str) - The ID of the evaluation.
- **name** (str) - The name of the evaluation.
- **description** (str) - The description of the evaluation.
- **type** (str) - The type of the evaluation.
- **messages** (Array) - The messages associated with the evaluation.
- **created_at** (str) - The timestamp when the evaluation was created.
- **updated_at** (str) - The timestamp when the evaluation was last updated.

#### Response Example
```json
{
  "id": "eval_id_123",
  "name": "My First Eval",
  "description": "Evaluating the initial greeting.",
  "type": "chat.mockConversation",
  "messages": [
    {
      "role": "assistant",
      "content": "Hello! How can I help you today?"
    }
  ],
  "created_at": "2023-10-27T10:00:00Z",
  "updated_at": "2023-10-27T10:00:00Z"
}
```
```