# AI

## Execute AI model

`ai.run(strmodel_name, AIRunParams**kwargs)  -> AIRunResponse`

**post** `/accounts/{account_id}/ai/run/{model_name}`

This endpoint provides users with the capability to run specific AI models on-demand.

By submitting the required input data, users can receive real-time predictions or results generated by the chosen AI
model. The endpoint supports various AI model types, ensuring flexibility and adaptability for diverse use cases.

Model specific inputs available in [Cloudflare Docs](https://developers.cloudflare.com/workers-ai/models/).

### Parameters

- `account_id: str`

- `model_name: str`

- `text: str`

  The text that you want to classify

### Returns

- `AIRunResponse`

  An array of classification results for the input text

  - `List[TextClassification]`

    An array of classification results for the input text

    - `label: Optional[str]`

      The classification label assigned to the text (e.g., 'POSITIVE' or 'NEGATIVE')

    - `score: Optional[float]`

      Confidence score indicating the likelihood that the text belongs to the specified label

  - `object`

    The generated image in PNG format

  - `class Audio: …`

    - `audio: Optional[str]`

      The generated audio in MP3 format, base64-encoded

  - `object`

    The generated audio in MP3 format

  - `class TextEmbeddings: …`

    - `data: Optional[List[List[float]]]`

      Embeddings of the requested text values

    - `shape: Optional[List[float]]`

  - `class AutomaticSpeechRecognition: …`

    - `text: str`

      The transcription

    - `vtt: Optional[str]`

    - `word_count: Optional[float]`

    - `words: Optional[List[AutomaticSpeechRecognitionWord]]`

      - `end: Optional[float]`

        The ending second when the word completes

      - `start: Optional[float]`

        The second this word begins in the recording

      - `word: Optional[str]`

  - `List[ImageClassification]`

    - `label: Optional[str]`

      The predicted category or class for the input image based on analysis

    - `score: Optional[float]`

      A confidence value, between 0 and 1, indicating how certain the model is about the predicted label

  - `List[ObjectDetection]`

    An array of detected objects within the input image

    - `box: Optional[ObjectDetectionBox]`

      Coordinates defining the bounding box around the detected object

      - `xmax: Optional[float]`

        The x-coordinate of the bottom-right corner of the bounding box

      - `xmin: Optional[float]`

        The x-coordinate of the top-left corner of the bounding box

      - `ymax: Optional[float]`

        The y-coordinate of the bottom-right corner of the bounding box

      - `ymin: Optional[float]`

        The y-coordinate of the top-left corner of the bounding box

    - `label: Optional[str]`

      The class label or name of the detected object

    - `score: Optional[float]`

      Confidence score indicating the likelihood that the detection is correct

  - `class UnionMember8: …`

    - `response: str`

      The generated text response from the model

    - `tool_calls: Optional[List[UnionMember8ToolCall]]`

      An array of tool calls requests made during the response generation

      - `arguments: Optional[object]`

        The arguments passed to be passed to the tool call request

      - `name: Optional[str]`

        The name of the tool to be called

    - `usage: Optional[UnionMember8Usage]`

      Usage statistics for the inference request

      - `completion_tokens: Optional[float]`

        Total number of tokens in output

      - `prompt_tokens: Optional[float]`

        Total number of tokens in input

      - `total_tokens: Optional[float]`

        Total number of input and output tokens

  - `object`

  - `class Translation: …`

    - `translated_text: Optional[str]`

      The translated text in the target language

  - `class Summarization: …`

    - `summary: Optional[str]`

      The summarized version of the input text

  - `class ImageToText: …`

    - `description: Optional[str]`

  - `class ImageTextToText: …`

    - `description: Optional[str]`

  - `class MultimodalEmbeddings: …`

    - `data: Optional[List[List[float]]]`

    - `shape: Optional[List[float]]`

### Example

```python
import os
from cloudflare import Cloudflare

client = Cloudflare(
    api_token=os.environ.get("CLOUDFLARE_API_TOKEN"),  # This is the default and can be omitted
)
response = client.ai.run(
    model_name="model_name",
    account_id="023e105f4ecef8ad9ca31a8372d0c353",
    text="x",
)
print(response)
```

#### Response

```json
{
  "result": [
    {
      "label": "label",
      "score": 0
    }
  ]
}
```

## Domain Types

### AI Run Response

- `AIRunResponse`

  An array of classification results for the input text

  - `List[TextClassification]`

    An array of classification results for the input text

    - `label: Optional[str]`

      The classification label assigned to the text (e.g., 'POSITIVE' or 'NEGATIVE')

    - `score: Optional[float]`

      Confidence score indicating the likelihood that the text belongs to the specified label

  - `object`

    The generated image in PNG format

  - `class Audio: …`

    - `audio: Optional[str]`

      The generated audio in MP3 format, base64-encoded

  - `object`

    The generated audio in MP3 format

  - `class TextEmbeddings: …`

    - `data: Optional[List[List[float]]]`

      Embeddings of the requested text values

    - `shape: Optional[List[float]]`

  - `class AutomaticSpeechRecognition: …`

    - `text: str`

      The transcription

    - `vtt: Optional[str]`

    - `word_count: Optional[float]`

    - `words: Optional[List[AutomaticSpeechRecognitionWord]]`

      - `end: Optional[float]`

        The ending second when the word completes

      - `start: Optional[float]`

        The second this word begins in the recording

      - `word: Optional[str]`

  - `List[ImageClassification]`

    - `label: Optional[str]`

      The predicted category or class for the input image based on analysis

    - `score: Optional[float]`

      A confidence value, between 0 and 1, indicating how certain the model is about the predicted label

  - `List[ObjectDetection]`

    An array of detected objects within the input image

    - `box: Optional[ObjectDetectionBox]`

      Coordinates defining the bounding box around the detected object

      - `xmax: Optional[float]`

        The x-coordinate of the bottom-right corner of the bounding box

      - `xmin: Optional[float]`

        The x-coordinate of the top-left corner of the bounding box

      - `ymax: Optional[float]`

        The y-coordinate of the bottom-right corner of the bounding box

      - `ymin: Optional[float]`

        The y-coordinate of the top-left corner of the bounding box

    - `label: Optional[str]`

      The class label or name of the detected object

    - `score: Optional[float]`

      Confidence score indicating the likelihood that the detection is correct

  - `class UnionMember8: …`

    - `response: str`

      The generated text response from the model

    - `tool_calls: Optional[List[UnionMember8ToolCall]]`

      An array of tool calls requests made during the response generation

      - `arguments: Optional[object]`

        The arguments passed to be passed to the tool call request

      - `name: Optional[str]`

        The name of the tool to be called

    - `usage: Optional[UnionMember8Usage]`

      Usage statistics for the inference request

      - `completion_tokens: Optional[float]`

        Total number of tokens in output

      - `prompt_tokens: Optional[float]`

        Total number of tokens in input

      - `total_tokens: Optional[float]`

        Total number of input and output tokens

  - `object`

  - `class Translation: …`

    - `translated_text: Optional[str]`

      The translated text in the target language

  - `class Summarization: …`

    - `summary: Optional[str]`

      The summarized version of the input text

  - `class ImageToText: …`

    - `description: Optional[str]`

  - `class ImageTextToText: …`

    - `description: Optional[str]`

  - `class MultimodalEmbeddings: …`

    - `data: Optional[List[List[float]]]`

    - `shape: Optional[List[float]]`

# Finetunes

## List Finetunes

`ai.finetunes.list(FinetuneListParams**kwargs)  -> FinetuneListResponse`

**get** `/accounts/{account_id}/ai/finetunes`

Lists all fine-tuning jobs created by the account, including status and metrics.

### Parameters

- `account_id: str`

### Returns

- `class FinetuneListResponse: …`

  - `id: str`

  - `created_at: datetime`

  - `model: str`

  - `modified_at: datetime`

  - `name: str`

  - `description: Optional[str]`

### Example

```python
import os
from cloudflare import Cloudflare

client = Cloudflare(
    api_token=os.environ.get("CLOUDFLARE_API_TOKEN"),  # This is the default and can be omitted
)
finetunes = client.ai.finetunes.list(
    account_id="023e105f4ecef8ad9ca31a8372d0c353",
)
print(finetunes.id)
```

#### Response

```json
{
  "result": {
    "id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
    "created_at": "2019-12-27T18:11:19.117Z",
    "model": "model",
    "modified_at": "2019-12-27T18:11:19.117Z",
    "name": "name",
    "description": "description"
  },
  "success": true
}
```

## Create a new Finetune

`ai.finetunes.create(FinetuneCreateParams**kwargs)  -> FinetuneCreateResponse`

**post** `/accounts/{account_id}/ai/finetunes`

Creates a new fine-tuning job for a Workers AI model using custom training data.

### Parameters

- `account_id: str`

- `model: str`

- `name: str`

- `description: Optional[str]`

- `public: Optional[bool]`

### Returns

- `class FinetuneCreateResponse: …`

  - `id: str`

  - `created_at: datetime`

  - `model: str`

  - `modified_at: datetime`

  - `name: str`

  - `public: bool`

  - `description: Optional[str]`

### Example

```python
import os
from cloudflare import Cloudflare

client = Cloudflare(
    api_token=os.environ.get("CLOUDFLARE_API_TOKEN"),  # This is the default and can be omitted
)
finetune = client.ai.finetunes.create(
    account_id="023e105f4ecef8ad9ca31a8372d0c353",
    model="model",
    name="name",
)
print(finetune.id)
```

#### Response

```json
{
  "result": {
    "id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
    "created_at": "2019-12-27T18:11:19.117Z",
    "model": "model",
    "modified_at": "2019-12-27T18:11:19.117Z",
    "name": "name",
    "public": true,
    "description": "description"
  },
  "success": true
}
```

## Domain Types

### Finetune List Response

- `class FinetuneListResponse: …`

  - `id: str`

  - `created_at: datetime`

  - `model: str`

  - `modified_at: datetime`

  - `name: str`

  - `description: Optional[str]`

### Finetune Create Response

- `class FinetuneCreateResponse: …`

  - `id: str`

  - `created_at: datetime`

  - `model: str`

  - `modified_at: datetime`

  - `name: str`

  - `public: bool`

  - `description: Optional[str]`

# Assets

## Upload a Finetune Asset

`ai.finetunes.assets.create(strfinetune_id, AssetCreateParams**kwargs)  -> AssetCreateResponse`

**post** `/accounts/{account_id}/ai/finetunes/{finetune_id}/finetune-assets`

Uploads training data assets for a Workers AI fine-tuning job.

### Parameters

- `account_id: str`

- `finetune_id: str`

- `file: Optional[FileTypes]`

- `file_name: Optional[str]`

### Returns

- `class AssetCreateResponse: …`

  - `success: bool`

### Example

```python
import os
from cloudflare import Cloudflare

client = Cloudflare(
    api_token=os.environ.get("CLOUDFLARE_API_TOKEN"),  # This is the default and can be omitted
)
asset = client.ai.finetunes.assets.create(
    finetune_id="bc451aef-f723-4b26-a6b2-901afd2e7a8a",
    account_id="023e105f4ecef8ad9ca31a8372d0c353",
)
print(asset.success)
```

#### Response

```json
{
  "success": true
}
```

## Domain Types

### Asset Create Response

- `class AssetCreateResponse: …`

  - `success: bool`

# Public

## List Public Finetunes

`ai.finetunes.public.list(PublicListParams**kwargs)  -> SyncSinglePage[PublicListResponse]`

**get** `/accounts/{account_id}/ai/finetunes/public`

Lists publicly available fine-tuned models that can be used with Workers AI.

### Parameters

- `account_id: str`

- `limit: Optional[float]`

  Pagination Limit

- `offset: Optional[float]`

  Pagination Offset

- `order_by: Optional[str]`

  Order By Column Name

### Returns

- `class PublicListResponse: …`

  - `id: str`

  - `created_at: datetime`

  - `model: str`

  - `modified_at: datetime`

  - `name: str`

  - `public: bool`

  - `description: Optional[str]`

### Example

```python
import os
from cloudflare import Cloudflare

client = Cloudflare(
    api_token=os.environ.get("CLOUDFLARE_API_TOKEN"),  # This is the default and can be omitted
)
page = client.ai.finetunes.public.list(
    account_id="023e105f4ecef8ad9ca31a8372d0c353",
)
page = page.result[0]
print(page.id)
```

#### Response

```json
{
  "result": [
    {
      "id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
      "created_at": "2019-12-27T18:11:19.117Z",
      "model": "model",
      "modified_at": "2019-12-27T18:11:19.117Z",
      "name": "name",
      "public": true,
      "description": "description"
    }
  ],
  "success": true
}
```

## Domain Types

### Public List Response

- `class PublicListResponse: …`

  - `id: str`

  - `created_at: datetime`

  - `model: str`

  - `modified_at: datetime`

  - `name: str`

  - `public: bool`

  - `description: Optional[str]`

# Authors

## Author Search

`ai.authors.list(AuthorListParams**kwargs)  -> SyncSinglePage[object]`

**get** `/accounts/{account_id}/ai/authors/search`

Searches Workers AI models by author or organization name.

### Parameters

- `account_id: str`

### Returns

- `object`

### Example

```python
import os
from cloudflare import Cloudflare

client = Cloudflare(
    api_token=os.environ.get("CLOUDFLARE_API_TOKEN"),  # This is the default and can be omitted
)
page = client.ai.authors.list(
    account_id="023e105f4ecef8ad9ca31a8372d0c353",
)
page = page.result[0]
print(page)
```

#### Response

```json
{
  "errors": [
    {}
  ],
  "messages": [
    "string"
  ],
  "result": [
    {}
  ],
  "success": true
}
```

# Tasks

## Task Search

`ai.tasks.list(TaskListParams**kwargs)  -> SyncSinglePage[object]`

**get** `/accounts/{account_id}/ai/tasks/search`

Searches Workers AI models by task type (e.g., text-generation, embeddings).

### Parameters

- `account_id: str`

### Returns

- `object`

### Example

```python
import os
from cloudflare import Cloudflare

client = Cloudflare(
    api_token=os.environ.get("CLOUDFLARE_API_TOKEN"),  # This is the default and can be omitted
)
page = client.ai.tasks.list(
    account_id="023e105f4ecef8ad9ca31a8372d0c353",
)
page = page.result[0]
print(page)
```

#### Response

```json
{
  "errors": [
    {}
  ],
  "messages": [
    "string"
  ],
  "result": [
    {}
  ],
  "success": true
}
```

# Models

## Model Search

`ai.models.list(ModelListParams**kwargs)  -> SyncV4PagePaginationArray[object]`

**get** `/accounts/{account_id}/ai/models/search`

Searches Workers AI models by name or description.

### Parameters

- `account_id: str`

- `author: Optional[str]`

  Filter by Author

- `hide_experimental: Optional[bool]`

  Filter to hide experimental models

- `page: Optional[int]`

- `per_page: Optional[int]`

- `search: Optional[str]`

  Search

- `source: Optional[float]`

  Filter by Source Id

- `task: Optional[str]`

  Filter by Task Name

### Returns

- `object`

### Example

```python
import os
from cloudflare import Cloudflare

client = Cloudflare(
    api_token=os.environ.get("CLOUDFLARE_API_TOKEN"),  # This is the default and can be omitted
)
page = client.ai.models.list(
    account_id="023e105f4ecef8ad9ca31a8372d0c353",
)
page = page.result[0]
print(page)
```

#### Response

```json
{
  "errors": [
    {}
  ],
  "messages": [
    "string"
  ],
  "result": [
    {}
  ],
  "success": true
}
```

# Schema

## Get Model Schema

`ai.models.schema.get(SchemaGetParams**kwargs)  -> SchemaGetResponse`

**get** `/accounts/{account_id}/ai/models/schema`

Retrieves the input and output JSON schema definition for a Workers AI model.

### Parameters

- `account_id: str`

- `model: str`

  Model Name

### Returns

- `class SchemaGetResponse: …`

  - `input: Input`

    - `additional_properties: bool`

    - `description: str`

    - `type: str`

  - `output: Output`

    - `additional_properties: bool`

    - `description: str`

    - `type: str`

### Example

```python
import os
from cloudflare import Cloudflare

client = Cloudflare(
    api_token=os.environ.get("CLOUDFLARE_API_TOKEN"),  # This is the default and can be omitted
)
schema = client.ai.models.schema.get(
    account_id="023e105f4ecef8ad9ca31a8372d0c353",
    model="model",
)
print(schema.input)
```

#### Response

```json
{
  "result": {
    "input": {
      "additionalProperties": true,
      "description": "JSON Schema definition for the model's input parameters",
      "type": "object"
    },
    "output": {
      "additionalProperties": true,
      "description": "JSON Schema definition for the model's output format",
      "type": "object"
    }
  },
  "success": true
}
```

## Domain Types

### Schema Get Response

- `class SchemaGetResponse: …`

  - `input: Input`

    - `additional_properties: bool`

    - `description: str`

    - `type: str`

  - `output: Output`

    - `additional_properties: bool`

    - `description: str`

    - `type: str`

# To Markdown

## Convert Files into Markdown

`ai.to_markdown.transform(ToMarkdownTransformParams**kwargs)  -> SyncSinglePage[ToMarkdownTransformResponse]`

**post** `/accounts/{account_id}/ai/tomarkdown`

Converts uploaded files into Markdown format using Workers AI.

### Parameters

- `account_id: str`

- `file: File`

  - `files: SequenceNotStr[FileTypes]`

### Returns

- `class ToMarkdownTransformResponse: …`

  - `data: str`

  - `format: str`

  - `mime_type: str`

  - `name: str`

  - `tokens: str`

### Example

```python
import os
from cloudflare import Cloudflare

client = Cloudflare(
    api_token=os.environ.get("CLOUDFLARE_API_TOKEN"),  # This is the default and can be omitted
)
page = client.ai.to_markdown.transform(
    account_id="023e105f4ecef8ad9ca31a8372d0c353",
    file={
        "files": [b"Example data"]
    },
)
page = page.result[0]
print(page.data)
```

#### Response

```json
{
  "result": [
    {
      "data": "data",
      "format": "format",
      "mimeType": "mimeType",
      "name": "name",
      "tokens": "tokens"
    }
  ],
  "success": true
}
```

## Get all converted formats supported

`ai.to_markdown.supported(ToMarkdownSupportedParams**kwargs)  -> SyncSinglePage[ToMarkdownSupportedResponse]`

**get** `/accounts/{account_id}/ai/tomarkdown/supported`

Lists all file formats supported for conversion to Markdown.

### Parameters

- `account_id: str`

### Returns

- `class ToMarkdownSupportedResponse: …`

  - `extension: str`

  - `mime_type: str`

### Example

```python
import os
from cloudflare import Cloudflare

client = Cloudflare(
    api_token=os.environ.get("CLOUDFLARE_API_TOKEN"),  # This is the default and can be omitted
)
page = client.ai.to_markdown.supported(
    account_id="023e105f4ecef8ad9ca31a8372d0c353",
)
page = page.result[0]
print(page.extension)
```

#### Response

```json
{
  "result": [
    {
      "extension": "extension",
      "mimeType": "mimeType"
    }
  ],
  "success": true
}
```

## Domain Types

### To Markdown Transform Response

- `class ToMarkdownTransformResponse: …`

  - `data: str`

  - `format: str`

  - `mime_type: str`

  - `name: str`

  - `tokens: str`

### To Markdown Supported Response

- `class ToMarkdownSupportedResponse: …`

  - `extension: str`

  - `mime_type: str`