OpenAI PHP

https://github.com/openai-php/client
Admin
A community-maintained PHP API client for interacting with the OpenAI API, supporting various...
Tokens:76,993
Snippets:306
Trust Score:8.9
License:MIT
Update:4 months ago
Show doc for...
Tokens:
Raw
### Install Development Dependencies

Source: https://github.com/openai-php/client/blob/main/CONTRIBUTING.md

Run this command after cloning your fork to install necessary development dependencies.

```bash
composer install
```

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

### Install OpenAI PHP Client

Source: https://github.com/openai-php/client/blob/main/README.md

Install the OpenAI PHP client using Composer. Ensure a PSR-18 client is available or install one like Guzzle.

```bash
composer require openai-php/client
```

```bash
composer require guzzlehttp/guzzle
```

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

### Create a Streamed Run with Function Calls

Source: https://github.com/openai-php/client/blob/main/README.md

This example demonstrates creating a streamed run that can handle function calls. It includes logic to submit tool outputs when the run requires action. Refer to OpenAI Assistant Events for event types.

```php
$stream = $client->threads()->runs()->createStreamed(
    threadId: 'thread_tKFLqzRN9n7MnyKKvc1Q7868',
    parameters: [
        'assistant_id' => 'asst_gxzBkD1wkKEloYqZ410pT5pd',
    ],
);


do{
    foreach($stream as $response){
        $response->event // 'thread.run.created' | 'thread.run.in_progress' | .....
        $response->response // ThreadResponse | ThreadRunResponse | ThreadRunStepResponse | ThreadRunStepDeltaResponse | ThreadMessageResponse | ThreadMessageDeltaResponse

        switch($response->event){
            case 'thread.run.created':
            case 'thread.run.queued':
            case 'thread.run.completed':
            case 'thread.run.cancelling':
                $run = $response->response;
                break;
            case 'thread.run.expired':
            case 'thread.run.cancelled':
            case 'thread.run.failed':
                $run = $response->response;
                break 3;
            case 'thread.run.requires_action':
                // Overwrite the stream with the new stream started by submitting the tool outputs
                $stream = $client->threads()->runs()->submitToolOutputsStreamed(
                    threadId: $run->threadId,
                    runId: $run->id,
                    parameters: [
                        'tool_outputs' => [
                            [
                                'tool_call_id' => 'call_KSg14X7kZF2WDzlPhpQ168Mj',
                                'output' => '12',
                            ]
                        ],
                    ]
                );
                break;
        }
    }
} while ($run->status != "completed")

// ...
```

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

### Create Streamed Chat Completion with Usage Report

Source: https://github.com/openai-php/client/blob/main/README.md

This example shows how to enable usage reporting (token counts) when creating a streamed chat completion. The usage information is only available in the last chunk.

```php
$stream = $client->chat()->createStreamed([
    'model' => 'gpt-4',
    'messages' => [
        ['role' => 'user', 'content' => 'Hello!'],
    ],
    'stream_options'=>[
        'include_usage' => true,
    ]
]);

foreach($stream as $response){
    if($response->usage !== null){
        $response->usage->promptTokens; // 9,
        $response->usage->completionTokens; // 12,
        $response->usage->totalTokens; // 21
    }
}
```

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

### Transcribe Audio Streamed

Source: https://github.com/openai-php/client/blob/main/README.md

This example demonstrates transcribing audio with streaming enabled. It processes audio chunks and yields events as they become available.

```php
$stream = $client->audio()->transcribeStreamed([
    'model' => 'gpt-4o-transcribe',
    'file' => fopen('audio.mp3', 'r'),
]);

foreach ($stream as $event) {
    echo json_encode($event->toArray()); // {"event":"transcript.text.delta","data":{"delta":"The"}}
}
```

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

### List Available Models in PHP

Source: https://github.com/openai-php/client/blob/main/README.md

Use this to get a list of all available models and their basic information. The response includes the object type and an array of model data.

```php
$response = $client->models()->list();

$response->object; // 'list'

foreach ($response->data as $result) {
    $result->id; // 'gpt-3.5-turbo-instruct'
    $result->object; // 'model'
    // ...
}

$response->toArray(); // ['object' => 'list', 'data' => [...]]
```

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

### Assistants API Information

Source: https://github.com/openai-php/client/blob/main/README.md

Information and usage examples for the Assistants API. Note that this API is deprecated and will stop working by August 26, 2026. A 'OpenAI-Beta: assistants=v2' header is required when creating the client manually.

```APIDOC
## Assistants Resource (deprecated)

> [!WARNING]
> OpenAI has deprecated the Assistants API and will stop working by August 26, 2026. https://platform.openai.com/docs/guides/migrate-to-responses#assistants-api

<details>
<summary>Assistants API Information</summary>

> **Note** - If you are creating the client manually from the factory. Make sure you provide the necessary header:
> ```php
> $factory->withHttpHeader('OpenAI-Beta', 'assistants=v2')
> ```

#### `create`

Create an assistant with a model and instructions.

```php
$response = $client->assistants()->create([
    'instructions' => 'You are a personal math tutor. When asked a question, write and run Python code to answer the question.',
    'name' => 'Math Tutor',
    'tools' => [
        [
            'type' => 'code_interpreter',
        ],
    ],
    'model' => 'gpt-4o',
]);

$response->id; // 'asst_gxzBkD1wkKEloYqZ410pT5pd'
$response->object; // 'assistant'
$response->createdAt; // 1623936000
$response->name; // 'Math Tutor'
$response->instructions; // 'You are a personal math tutor. When asked a question, write and run Python code to answer the question.'
$response->model; // 'gpt-4o'
$response->description; // null
$response->tools[0]->type; // 'code_interpreter'
$response->toolResources; // []
$response->metadata; // []
$response->temperature: // null
$response->topP: // null
$response->format: // 'auto'

$response->toArray(); // ['id' => 'asst_gxzBkD1wkKEloYqZ410pT5pd', ...]
```

#### `retrieve`

Retrieves an assistant.

```php
$response = $client->assistants()->retrieve('asst_gxzBkD1wkKEloYqZ410pT5pd');

$response->id; // 'asst_gxzBkD1wkKEloYqZ410pT5pd'
$response->object; // 'assistant'
$response->createdAt; // 1623936000
$response->name; // 'Math Tutor'
$response->instructions; // 'You are a personal math tutor. When asked a question, write and run Python code to answer the question.'
$response->model; // 'gpt-4o'
$response->description; // null
$response->tools[0]->type; // 'code_interpreter'
$response->toolResources; // []
$response->metadata; // []
$response->temperature: // null
$response->topP: // null
$response->format: // 'auto'

$response->toArray(); // ['id' => 'asst_gxzBkD1wkKEloYqZ410pT5pd', ...]
```

#### `modify`

Modifies an assistant.

```php
$response = $client->assistants()->modify('asst_gxzBkD1wkKEloYqZ410pT5pd', [
        'name' => 'New Math Tutor',
    ]);

$response->id; // 'asst_gxzBkD1wkKEloYqZ410pT5pd'
$response->object; // 'assistant'
$response->createdAt; // 1623936000
$response->name; // 'New Math Tutor'
$response->instructions; // 'You are a personal math tutor. When asked a question, write and run Python code to answer the question.'
$response->model; // 'gpt-4o'
$response->description; // null
$response->tools[0]->type; // 'code_interpreter'
$response->toolResources; // []
$response->metadata; // []
$response->temperature: // null
$response->topP: // null
$response->format: // 'auto'

$response->toArray(); // ['id' => 'asst_gxzBkD1wkKEloYqZ410pT5pd', ...]
```

#### `delete`

Delete an assistant.

```php
$response = $client->assistants()->delete('asst_gxzBkD1wkKEloYqZ410pT5pd');

$response->id; // 'asst_gxzBkD1wkKEloYqZ410pT5pd'
$response->object; // 'assistant.deleted'
$response->deleted; // true

$response->toArray(); // ['id' => 'asst_gxzBkD1wkKEloYqZ410pT5pd', ...]
```

#### `list`

Returns a list of assistants.

```php
$response = $client->assistants()->list([
    'limit' => 10,
]);

$response->object; // 'list'
$response->firstId; // 'asst_gxzBkD1wkKEloYqZ410pT5pd'
$response->lastId; // 'asst_reHHtAM0jKLDIxanM6gP6DaR'
$response->hasMore; // true

foreach ($response->data as $result) {
    $result->id; // 'asst_gxzBkD1wkKEloYqZ410pT5pd'
    // ...
}

$response->toArray(); // ['object' => 'list', ...]]
```

</details>
```

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

### retrieve

Source: https://github.com/openai-php/client/blob/main/README.md

Gets information about a specific fine-tune job. This method is part of the deprecated FineTunes API.

```APIDOC
## `retrieve`

### Description
Gets information about a specific fine-tune job.

### Method
GET

### Endpoint
`/v1/fine-tunes/{fine_tune_id}`

### Parameters
#### Path Parameters
- **fine_tune_id** (string) - Required - The ID of the fine-tune job to retrieve.

### Request Example
```php
$response = $client->fineTunes()->retrieve('ft-AF1WoRqd3aJAHsqc9NY7iL8F');
```

### Response
#### Success Response (200)
- **id** (string) - The ID of the fine-tune job.
- **object** (string) - The object type, usually 'fine-tune'.
- **model** (string) - The base model used for fine-tuning.
- **createdAt** (integer) - The timestamp when the fine-tune job was created.
- **fineTunedModel** (string) - The name of the fine-tuned model (if available).
- **organizationId** (string) - The ID of the organization that owns the fine-tune job.
- **resultFiles** (array) - An array of file objects representing the result files.
- **status** (string) - The current status of the fine-tune job.
- **validationFiles** (array) - An array of file objects representing the validation files.
- **trainingFiles** (array) - An array of file objects representing the training files.
- **updatedAt** (integer) - The timestamp when the fine-tune job was last updated.
- **events** (array) - An array of fine-tune event objects.
- **hyperparams** (object) - An object containing the hyperparameters used for fine-tuning.

#### Response Example
```json
{
  "id": "ft-AF1WoRqd3aJAHsqc9NY7iL8F",
  "object": "fine-tune",
  "model": "curie",
  "createdAt": 1614807352,
  "fineTunedModel": "curie => ft-acmeco-2021-03-03-21-44-20",
  "organizationId": "org-jwe45798ASN82s",
  "resultFiles": [
    {
      "id": "file-XjGxS3KTG0uNmNOK362iJua3",
      "object": "file",
      "bytes": 140,
      "createdAt": 1613779657,
      "filename": "mydata.jsonl",
      "purpose": "fine-tune",
      "status": "succeeded",
      "status_details": null
    }
  ],
  "status": "succeeded",
  "validationFiles": [],
  "trainingFiles": [],
  "updatedAt": 1614807865,
  "events": [
    {
      "object": "fine-tune-event",
      "createdAt": 1614807352,
      "level": "info",
      "message": "Job enqueued. Waiting for jobs ahead to complete. Queue number =>  0."
    }
  ],
  "hyperparams": {
    "batchSize": 4,
    "learningRateMultiplier": 0.1,
    "nEpochs": 4,
    "promptLossWeight": 0.1
  }
}
```
```

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

### Create and Run a Thread

Source: https://github.com/openai-php/client/blob/main/README.md

This snippet demonstrates how to create a thread and initiate a run in a single request. It requires an assistant ID and thread details, including messages. The response provides comprehensive information about the run, such as its ID, status, and associated IDs.

```php
$response = $client->threads()->createAndRun(
    [
        'assistant_id' => 'asst_gxzBkD1wkKEloYqZ410pT5pd',
        'thread' => [
            'messages' =>
                [
                    [
                        'role' => 'user',
                        'content' => 'Explain deep learning to a 5 year old.',
                    ],
                ],
        ],
    ],
);

$response->id; // 'run_4RCYyYzX9m41WQicoJtUQAb8'
$response->object; // 'thread.run'
$response->createdAt; // 1623936000
$response->assistantId; // 'asst_gxzBkD1wkKEloYqZ410pT5pd'
$response->threadId; // 'thread_tKFLqzRN9n7MnyKKvc1Q7868'
$response->status; // 'queued'
$response->requiredAction; // null
$response->lastError; // null
$response->startedAt; // null
$response->expiresAt; // 1699622335
$response->cancelledAt; // null
$response->failedAt; // null
$response->completedAt; // null
$response->incompleteDetails; // null
$response->lastError; // null
$response->model; // 'gpt-4o'
$response->instructions; // null
$response->tools; // []
$response->metadata; // []
$response->usage->total_tokens; // 579
$response->temperature; // null
$response->topP; // null
$response->maxPromptTokens; // 1000
$response->maxCompletionTokens; // 1000
$response->truncationStrategy->type; // 'auto'
$response->responseFormat; // 'auto'
$response->toolChoice; // 'auto'

$response->toArray(); // ['id' => 'run_4RCYyYzX9m41WQicoJtUQAb8', ...]
```

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

### list events

Source: https://github.com/openai-php/client/blob/main/README.md

Get fine-grained status updates for a fine-tune job. This method is part of the deprecated FineTunes API.

```APIDOC
## `list events`

### Description
Get fine-grained status updates for a fine-tune job.

### Method
GET

### Endpoint
`/v1/fine-tunes/{fine_tune_id}/events`

### Parameters
#### Path Parameters
- **fine_tune_id** (string) - Required - The ID of the fine-tune job to get events for.

### Request Example
```php
$response = $client->fineTunes()->listEvents('ft-AF1WoRqd3aJAHsqc9NY7iL8F');
```

### Response
#### Success Response (200)
- **object** (string) - The object type, usually 'list'.
- **data** (array) - An array of fine-tune event objects.

Each fine-tune event object in the `data` array contains:
- **object** (string) - The object type, usually 'fine-tune-event'.
- **createdAt** (integer) - The timestamp when the event occurred.
- **level** (string) - The severity level of the event (e.g., 'info').
- **message** (string) - The message describing the event.

#### Response Example
```json
{
  "object": "list",
  "data": [
    {
      "object": "fine-tune-event",
      "createdAt": 1614807352,
      "level": "info",
      "message": "Job enqueued. Waiting for jobs ahead to complete. Queue number =>  0."
    }
  ]
}
```
```

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

### Provide OpenAI-Beta Header

Source: https://github.com/openai-php/client/blob/main/README.md

When creating the client manually from the factory, ensure the 'OpenAI-Beta' header is set to 'assistants=v2'. This is necessary for using the Assistants API.

```php
$factory->withHttpHeader('OpenAI-Beta', 'assistants=v2')
```

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

### list events streamed

Source: https://github.com/openai-php/client/blob/main/README.md

Get streamed fine-grained status updates for a fine-tune job. This method is part of the deprecated FineTunes API.

```APIDOC
## `list events streamed`

### Description
Get streamed fine-grained status updates for a fine-tune job.

### Method
GET

### Endpoint
`/v1/fine-tunes/{fine_tune_id}/events?stream=true`

### Parameters
#### Path Parameters
- **fine_tune_id** (string) - Required - The ID of the fine-tune job to get streamed events for.

#### Query Parameters
- **stream** (boolean) - Required - Set to `true` to enable streaming.

### Request Example
```php
$stream = $client->fineTunes()->listEventsStreamed('ft-y3OpNlc8B5qBVGCCVsLZsDST');

foreach($stream as $response){
    $response->message;
}
```

### Response
#### Success Response (200)
The response is a stream of event objects. Each event object contains:
- **message** (string) - The message describing the event.

#### Response Example
```
1. iteration => 'Created fine-tune: ft-y3OpNlc8B5qBVGCCVsLZsDST'
2. iteration => 'Fine-tune costs $0.00'
...
xx. iteration => 'Uploaded result file: file-ajLKUCMsFPrT633zqwr0eI4l'
xx. iteration => 'Fine-tune succeeded'
```
```

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

### Create an Assistant

Source: https://github.com/openai-php/client/blob/main/README.md

Use this snippet to create a new assistant. Specify the model, instructions, and tools. The response includes the assistant's ID and other details.

```php
$response = $client->assistants()->create([
    'instructions' => 'You are a personal math tutor. When asked a question, write and run Python code to answer the question.',
    'name' => 'Math Tutor',
    'tools' => [
        [
            'type' => 'code_interpreter',
        ],
    ],
    'model' => 'gpt-4o',
]);

$response->id; // 'asst_gxzBkD1wkKEloYqZ410pT5pd'
$response->object; // 'assistant'
$response->createdAt; // 1623936000
$response->name; // 'Math Tutor'
$response->instructions; // 'You are a personal math tutor. When asked a question, write and run Python code to answer the question.'
$response->model; // 'gpt-4o'
$response->description; // null
$response->tools[0]->type; // 'code_interpreter'
$response->toolResources; // []
$response->metadata; // []
$response->temperature: // null
$response->topP: // null
$response->format: // 'auto'

$response->toArray(); // ['id' => 'asst_gxzBkD1wkKEloYqZ410pT5pd', ...]
```

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

### Retrieve a Thread Run Step

Source: https://github.com/openai-php/client/blob/main/README.md

Retrieves a specific run step from a thread. Use this to get details about a single step in a run.

```php
$response = $client->threads()->runs()->steps()->retrieve(
    threadId: 'thread_tKFLqzRN9n7MnyKKvc1Q7868',
    runId: 'run_4RCYyYzX9m41WQicoJtUQAb8',
    stepId: 'step_1spQXgbAabXFm1YXrwiGIMUz',
);

$response->id; // 'step_1spQXgbAabXFm1YXrwiGIMUz'
$response->object; // 'thread.run.step'
$response->createdAt; // 1699564106
$response->runId; // 'run_4RCYyYzX9m41WQicoJtUQAb8'
$response->assistantId; // 'asst_gxzBkD1wkKEloYqZ410pT5pd'
$response->threadId; // 'thread_tKFLqzRN9n7MnyKKvc1Q7868'
$response->type; // 'message_creation'
$response->status; // 'completed'
$response->cancelledAt; // null
$response->completedAt; // 1699564119
$response->expiresAt; // null
$response->failedAt; // null
$response->lastError; // null
$response->stepDetails->type; // 'message_creation'
$response->stepDetails->messageCreation->messageId; // 'msg_i404PxKbB92d0JAmdOIcX7vA'

$response->toArray(); // ['id' => 'step_1spQXgbAabXFm1YXrwiGIMUz', ...]
```

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

### Run All Tests

Source: https://github.com/openai-php/client/blob/main/CONTRIBUTING.md

Execute this command to run the complete test suite for the project.

```bash
composer test
```

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

### Modify a Run

Source: https://github.com/openai-php/client/blob/main/README.md

Use this to modify an existing run, for example, to update its metadata. The run must exist and be in a state where modification is allowed.

```php
$response = $client->threads()->runs()->modify(
    threadId: 'thread_tKFLqzRN9n7MnyKKvc1Q7868',
    runId: 'run_4RCYyYzX9m41WQicoJtUQAb8',
    parameters:  [
        'metadata' => [
            'name' => 'My new run name',
        ],
    ],
);

$response->id; // 'run_4RCYyYzX9m41WQicoJtUQAb8'
$response->object; // 'thread.run'
$response->createdAt; // 1623936000
$response->assistantId; // 'asst_gxzBkD1wkKEloYqZ410pT5pd'
$response->threadId; // 'thread_tKFLqzRN9n7MnyKKvc1Q7868'
$response->status; // 'queued'
$response->startedAt; // null
$response->expiresAt; // 1699622335
$response->cancelledAt; // null
$response->failedAt; // null
$response->completedAt; // null
$response->incompleteDetails; // null
$response->lastError; // null
$response->model; // 'gpt-4o'
$response->instructions; // null
$response->tools; // []
$response->usage->total_tokens; // 579
$response->temperature; // null
$response->topP; // null
$response->maxPromptTokens; // 1000
$response->maxCompletionTokens; // 1000
$response->truncationStrategy->type; // 'auto'
$response->toolChoice; // 'auto'
$response->responseFormat; // 'auto'
$response->metadata; // ['name' => 'My new run name']

$response->toArray(); // ['id' => 'run_4RCYyYzX9m41WQicoJtUQAb8', ...]
```

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

### Completions Resource (legacy) - Create

Source: https://github.com/openai-php/client/blob/main/README.md

Creates a completion for the provided prompt and parameters. Note: This resource is marked as legacy.

```APIDOC
## `create`

### Description
Creates a completion for the provided prompt and parameters.

### Method
POST (inferred)

### Endpoint
/completions

### Parameters
#### Request Body
- **model** (string) - Required - The model to use for completion (e.g., 'gpt-3.5-turbo-instruct').
- **prompt** (string) - Required - The prompt to generate a completion for.
- **max_tokens** (integer) - Optional - The maximum number of tokens to generate.
- **temperature** (number) - Optional - Controls randomness. Lower values make output more focused and deterministic.

### Request Example
```json
{
  "model": "gpt-3.5-turbo-instruct",
  "prompt": "Say this is a test",
  "max_tokens": 6,
  "temperature": 0
}
```

### Response
#### Success Response (200)
- **id** (string) - The ID of the completion.
- **object** (string) - The type of object, e.g., 'text_completion'.
- **created** (integer) - The creation timestamp.
- **model** (string) - The model used for completion.
- **choices** (array) - An array of completion choices.
  - **text** (string) - The generated text.
  - **index** (integer) - The index of the choice.
  - **logprobs** (null) - Log probabilities (currently null).
  - **finishReason** (string) - The reason for finishing (e.g., 'length').
- **usage** (object)
  - **promptTokens** (integer) - The number of tokens in the prompt.
  - **completionTokens** (integer) - The number of tokens in the completion.
  - **totalTokens** (integer) - The total number of tokens.

#### Response Example
```json
{
  "id": "cmpl-uqkvlQyYK7bGYrRHQ0eXlWi7",
  "object": "text_completion",
  "created": 1589478378,
  "model": "gpt-3.5-turbo-instruct",
  "choices": [
    {
      "text": "\n\nThis is a test",
      "index": 0,
      "logprobs": null,
      "finishReason": "length"
    }
  ],
  "usage": {
    "promptTokens": 5,
    "completionTokens": 6,
    "totalTokens": 11
  }
}
```
```

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

### Translate Audio

Source: https://github.com/openai-php/client/blob/main/README.md

Translates audio content into English using the Whisper model. This example uses verbose JSON output and requests segment-level timestamps.

```php
$response = $client->audio()->translate([
    'model' => 'whisper-1',
    'file' => fopen('german.mp3', 'r'),
    'response_format' => 'verbose_json',
]);

$response->task; // 'translate'
$response->language; // 'english'
$response->duration; // 2.95
$response->text; // 'Hello, how are you?'

foreach ($response->segments as $segment) {
    $segment->index; // 0
    $segment->seek; // 0
    $segment->start; // 0.0
    $segment->end; // 4.0
    $segment->text; // 'Hello, how are you?'
    $segment->tokens; // [50364, 2425, 11, 577, 366, 291, 30, 50564]
    $segment->temperature; // 0.0
    $segment->avgLogprob; // -0.45045216878255206
    $segment->compressionRatio; // 0.7037037037037037
    $segment->noSpeechProb; // 0.1076972484588623
    $segment->transient; // false
}

$response->toArray(); // ['task' => 'translate', ...]
```

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

### Create a Vector Store

Source: https://github.com/openai-php/client/blob/main/README.md

Use this snippet to create a new vector store. You must provide file IDs and a name. The response includes details about the created store and its initial status.

```php
$response = $client->vectorStores()->create([
    'file_ids' => [
        'file-fUU0hFRuQ1GzhOweTNeJlCXG',
    ],
    'name' => 'My first Vector Store',
]);

$response->id; // 'vs_vzfQhlTWVUl38QGqQAoQjeDF'
$response->object; // 'vector_store'
$response->createdAt; // 1717703267
$response->name; // 'My first Vector Store'
$response->usageBytes; // 0
$response->fileCounts->inProgress; // 1
$response->fileCounts->completed; // 0
$response->fileCounts->failed; // 0
$response->fileCounts->cancelled; // 0
$response->fileCounts->total; // 1
$response->status; // 'in_progress'
$response->expiresAfter; // null
$response->expiresAt; // null
$response->lastActiveAt; // 1717703267

$response->toArray(); // ['id' => 'vs_vzfQhlTWVUl38QGqQAoQjeDF', ...]
```

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

### Transcribe Audio

Source: https://github.com/openai-php/client/blob/main/README.md

Transcribes audio into text using the Whisper model. This example specifies verbose JSON output and requests segment and word-level timestamps.

```php
$response = $client->audio()->transcribe([
    'model' => 'whisper-1',
    'file' => fopen('audio.mp3', 'r'),
    'response_format' => 'verbose_json',
    'timestamp_granularities' => ['segment', 'word']
]);

$response->task; // 'transcribe'
$response->language; // 'english'
$response->duration; // 2.95
$response->text; // 'Hello, how are you?'

foreach ($response->segments as $segment) {
    $segment->index; // 0
    $segment->seek; // 0
    $segment->start; // 0.0
    $segment->end; // 4.0
    $segment->text; // 'Hello, how are you?'
    $segment->tokens; // [50364, 2425, 11, 577, 366, 291, 30, 50564]
    $segment->temperature; // 0.0
    $segment->avgLogprob; // -0.45045216878255206
    $segment->compressionRatio; // 0.7037037037037037
    $segment->noSpeechProb; // 0.1076972484588623
    $segment->transient; // false
}

foreach ($response->words as $word) {
    $word->word; // 'Hello'
    $word->start; // 0.31
    $word->end; // 0.92
}

$response->toArray(); // ['task' => 'transcribe', ...]
```

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

### Create a Run

Source: https://github.com/openai-php/client/blob/main/README.md

Use this to create a new run for a thread. Ensure you have the thread ID and assistant ID.

```php
$response = $client->threads()->runs()->create(
    threadId: 'thread_tKFLqzRN9n7MnyKKvc1Q7868', 
    parameters: [
        'assistant_id' => 'asst_gxzBkD1wkKEloYqZ410pT5pd',
    ],
);

$response->id; // 'run_4RCYyYzX9m41WQicoJtUQAb8'
$response->object; // 'thread.run'
$response->createdAt; // 1623936000
$response->assistantId; // 'asst_gxzBkD1wkKEloYqZ410pT5pd'
$response->threadId; // 'thread_tKFLqzRN9n7MnyKKvc1Q7868'
$response->status; // 'queued'
$response->startedAt; // null
$response->expiresAt; // 1699622335
$response->cancelledAt; // null
$response->failedAt; // null
$response->completedAt; // null
$response->incompleteDetails; // null
$response->lastError; // null
$response->model; // 'gpt-4o'
$response->instructions; // null
$response->tools; // []
$response->metadata; // []
$response->usage->total_tokens; // 579
$response->temperature; // null
$response->topP; // null
$response->maxPromptTokens; // 1000
$response->maxCompletionTokens; // 1000
$response->truncationStrategy->type; // 'auto'
$response->toolChoice; // 'auto'
$response->responseFormat; // 'auto'

$response->toArray(); // ['id' => 'run_4RCYyYzX9m41WQicoJtUQAb8', ...]
```

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

### create

Source: https://github.com/openai-php/client/blob/main/README.md

Creates a new vector store. You can associate files with the vector store during creation.

```APIDOC
## `create`

### Description
Creates a vector store.

### Method
POST (inferred)

### Endpoint
/vectorStores

### Parameters
#### Request Body
- **file_ids** (array<string>) - Required - A list of file IDs to associate with the vector store.
- **name** (string) - Required - The name of the vector store.

### Request Example
```php
$response = $client->vectorStores()->create([
    'file_ids' => [
        'file-fUU0hFRuQ1GzhOweTNeJlCXG',
    ],
    'name' => 'My first Vector Store',
]);
```

### Response
#### Success Response (200)
- **id** (string) - The unique identifier for the vector store.
- **object** (string) - The type of object, e.g., 'vector_store'.
- **createdAt** (integer) - The Unix timestamp when the vector store was created.
- **name** (string) - The name of the vector store.
- **usageBytes** (integer) - The amount of storage used in bytes.
- **fileCounts** (object) - Counts related to files in the vector store.
  - **inProgress** (integer)
  - **completed** (integer)
  - **failed** (integer)
  - **cancelled** (integer)
  - **total** (integer)
- **status** (string) - The current status of the vector store (e.g., 'in_progress').
- **expiresAfter** (null) - Expiration settings.
- **expiresAt** (null) - Expiration timestamp.
- **lastActiveAt** (integer) - The Unix timestamp when the vector store was last active.

#### Response Example
```php
{
  "id": "vs_vzfQhlTWVUl38QGqQAoQjeDF",
  "object": "vector_store",
  "createdAt": 1717703267,
  "name": "My first Vector Store",
  "usageBytes": 0,
  "fileCounts": {
    "inProgress": 1,
    "completed": 0,
    "failed": 0,
    "cancelled": 0,
    "total": 1
  },
  "status": "in_progress",
  "expiresAfter": null,
  "expiresAt": null,
  "lastActiveAt": 1717703267
}
```
```

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

### create

Source: https://github.com/openai-php/client/blob/main/README.md

Creates a batch. Requires uploading a file first and then referencing its ID.

```APIDOC
## `create`

### Description
Creates a batch. This involves uploading a file containing commands and then creating a batch that references the uploaded file's ID.

### Method
POST (inferred from SDK usage)

### Endpoint
/v1/batches

### Parameters
#### Path Parameters
None

#### Query Parameters
None

#### Request Body
- **input_file_id** (string) - Required - The ID of the file to be used as input for the batch.
- **endpoint** (string) - Required - The API endpoint to use for the batch job (e.g., \'/v1/chat/completions\').
- **completion_window** (string) - Optional - The window for when completions will be delivered (e.g., \'24h\').
- **metadata** (object) - Optional - User-specified key-value pairs to store with the batch.

### Request Example
```php
$fileResponse = $client->files()->upload(
     parameters: [
          'purpose' => 'batch',
          'file' => fopen('commands.jsonl', 'r'),
    ]
);

$fileId = $fileResponse->id;

$response = $client->batches()->create(
    parameters: [
        'input_file_id' => $fileId,
        'endpoint' => '/v1/chat/completions',
        'completion_window' => '24h',
        'metadata' => ['name' => 'My batch name']
    ]
 );
```

### Response
#### Success Response (200)
- **id** (string) - The ID of the batch.
- **object** (string) - The type of object, which is \'batch\'.
- **endpoint** (string) - The API endpoint used for the batch job.
- **errors** (null) - Contains errors if any occurred during batch processing.
- **completionWindow** (string) - The window for when completions will be delivered.
- **status** (string) - The current status of the batch (e.g., \'validating\', \'in_progress\', \'completed\').
- **outputFileId** (string|null) - The ID of the output file if the batch has completed successfully.
- **errorFileId** (string|null) - The ID of the error file if the batch encountered errors.
- **createdAt** (integer) - Unix timestamp of when the batch was created.
- **inProgressAt** (integer|null) - Unix timestamp of when the batch started processing.
- **expiresAt** (integer) - Unix timestamp of when the batch will expire.
- **completedAt** (integer|null) - Unix timestamp of when the batch completed.
- **failedAt** (integer|null) - Unix timestamp of when the batch failed.
- **expiredAt** (integer|null) - Unix timestamp of when the batch expired.
- **requestCounts** (object|null) - Counts of requests processed, completed, and failed.
- **metadata** (object) - User-specified key-value pairs associated with the batch.

#### Response Example
```json
{
  "id": "batch_abc123",
  "object": "batch",
  "endpoint": "/v1/chat/completions",
  "errors": null,
  "completionWindow": "24h",
  "status": "validating",
  "outputFileId": null,
  "errorFileId": null,
  "createdAt": 1714508499,
  "inProgressAt": null,
  "expiresAt": 1714536634,
  "completedAt": null,
  "failedAt": null,
  "expiredAt": null,
  "requestCounts": null,
  "metadata": {"name": "My batch name"}
}
```
```

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

### Upload File and Create Batch

Source: https://github.com/openai-php/client/blob/main/README.md

Uploads a file and then creates a batch job using the uploaded file's ID. Ensure the 'commands.jsonl' file exists and is correctly formatted.

```php
$fileResponse = $client->files()->upload(
     parameters: [
          'purpose' => 'batch',
          'file' => fopen('commands.jsonl', 'r'),
    ]
);

$fileId = $fileResponse->id;

$response = $client->batches()->create(
    parameters: [
        'input_file_id' => $fileId,
        'endpoint' => '/v1/chat/completions',
        'completion_window' => '24h'
    ]
 );

$response->id; // 'batch_abc123'
$response->object; // 'batch'
$response->endpoint; // /v1/chat/completions
$response->errors; // null
$response->completionWindow; // '24h'
$response->status; // 'validating'
$response->outputFileId; // null
$response->errorFileId; // null
$response->createdAt; // 1714508499
$response->inProgressAt; // null
$response->expiresAt; // 1714536634
$response->completedAt; // null
$response->failedAt; // null
$response->expiredAt; // null
$response->requestCounts; // null
$response->metadata; // ['name' => 'My batch name']

$response->toArray(); // ['id' => 'batch_abc123', ...]
```

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

### Configure Custom OpenAI PHP Client

Source: https://github.com/openai-php/client/blob/main/README.md

Configure and create a custom OpenAI PHP client instance with specific settings like API key, organization, base URI, and HTTP client.

```php
$yourApiKey = getenv('YOUR_API_KEY');

$client = OpenAI::factory()
    ->withApiKey($yourApiKey)
    ->withOrganization('your-organization') // default: null
    ->withProject('Your Project') // default: null
    ->withBaseUri('openai.example.com/v1') // default: api.openai.com/v1
    ->withHttpClient($httpClient = new 
GuzzleHttp\Client([])) // default: HTTP client found using PSR-18 HTTP Client Discovery
    ->withHttpHeader('X-My-Header', 'foo')
    ->withQueryParam('my-param', 'bar')
    ->withStreamHandler(fn (RequestInterface $request): ResponseInterface => $httpClient->send($request, [
        'stream' => true // Allows to provide a custom stream handler for the http client.
    ]))
    ->make();
```

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

### Create Legacy Completion

Source: https://github.com/openai-php/client/blob/main/README.md

Use this to create a text completion based on a provided prompt and parameters. Note that this resource is marked as legacy and the Chat resource is recommended instead.

```php
$response = $client->completions()->create([
    'model' => 'gpt-3.5-turbo-instruct',
    'prompt' => 'Say this is a test',
    'max_tokens' => 6,
    'temperature' => 0
]);

$response->id; // 'cmpl-uqkvlQyYK7bGYrRHQ0eXlWi7'
$response->object; // 'text_completion'
$response->created; // 1589478378
$response->model; // 'gpt-3.5-turbo-instruct'

foreach ($response->choices as $choice) {
    $choice->text; // '\n\nThis is a test'
    $choice->index; // 0
    $choice->logprobs; // null
    $choice->finishReason; // 'length' or null
}

$response->usage->promptTokens; // 5,
$response->usage->completionTokens; // 6,
$response->usage->totalTokens; // 11

$response->toArray(); // ['id' => 'cmpl-uqkvlQyYK7bGYrRHQ0eXlWi7', ...]
```

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

### List Run Steps for a Thread

Source: https://github.com/openai-php/client/blob/main/README.md

Returns a list of all run steps belonging to a specific run within a thread. Useful for iterating through the steps of a completed or ongoing run.

```php
$response = $client->threads()->runs()->steps()->list(
    threadId: 'thread_tKFLqzRN9n7MnyKKvc1Q7868',
    runId: 'run_4RCYyYzX9m41WQicoJtUQAb8',
    parameters: [
        'limit' => 10,
    ],
);

$response->object; // 'list'
$response->firstId; // 'step_1spQXgbAabXFm1YXrwiGIMUz'
$response->lastId; // 'step_1spQXgbAabXFm1YXrwiGIMUz'
$response->hasMore; // false

foreach ($response->data as $result) {
    $result->id; // 'step_1spQXgbAabXFm1YXrwiGIMUz'
    // ...
}

$response->toArray(); // ['object' => 'list', ...]]
```

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

### Create a Fine-Tuning Job

Source: https://github.com/openai-php/client/blob/main/README.md

Creates a job that fine-tunes a specified model from a given dataset. Requires training and validation file IDs, model name, and optionally epochs, batch size, learning rate multiplier, prompt loss weight, and classification metrics.

```php
$response = $client->fineTunes()->create([
    'training_file' => 'file-ajSREls59WBbvgSzJSVWxMCB',
    'validation_file' => 'file-XjSREls59WBbvgSzJSVWxMCa',
    'model' => 'curie',
    'n_epochs' => 4,
    'batch_size' => null,
    'learning_rate_multiplier' => null,
    'prompt_loss_weight' => 0.01,
    'compute_classification_metrics' => false,
    'classification_n_classes' => null,
    'classification_positive_class' => null,
    'classification_betas' => [],
    'suffix' => null,
]);

$response->id; // 'ft-AF1WoRqd3aJAHsqc9NY7iL8F'
$response->object; // 'fine-tune'
// ...

$response->toArray(); // ['id' => 'ft-AF1WoRqd3aJAHsqc9NY7iL8F', ...]
```

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

### Basic API Call with OpenAI PHP Client

Source: https://github.com/openai-php/client/blob/main/README.md

Make a basic API call to generate a response using the OpenAI PHP client. Requires an API key set as an environment variable.

```php
$yourApiKey = getenv('YOUR_API_KEY');
$client = OpenAI::client($yourApiKey);

$response = $client->responses()->create([
    'model' => 'gpt-4o',
    'input' => 'Hello!',
]);

echo $response->outputText; // Hello! How can I assist you today?
```
Tokens:
Raw