> ## Documentation Index
> Fetch the complete documentation index at: https://docs.portkey.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Files

> Upload files to Portkey and reuse the content in your requests

Portkey supports managing files in two ways:

1. **Provider Files**: Uploading and managing files directly to any provider using the unified signature
2. **Portkey Files**: Uploading files to Portkey and using them for batching/fine-tuning requests with any provider

***

## 1. Provider Files

Upload and manage files directly to providers (OpenAI, Bedrock, etc.) using Portkey's unified API signature. This approach is useful when you need provider-specific file features or want to manage files directly on the provider's platform.

### Supported Providers

* [Anthropic](/integrations/llms/anthropic#files-api)
* [OpenAI](/integrations/llms/openai/files)
* [Bedrock](/integrations/llms/bedrock/files)
* [Azure OpenAI](/integrations/llms/azure-openai/files)
* [Fireworks](/integrations/llms/fireworks/files)
* [Vertex AI](/integrations/llms/vertex-ai/files)

### Quick Example

```bash theme={"system"}
curl -X POST https://api.portkey.ai/v1/files \
  -H "Authorization: Bearer $PORTKEY_API_KEY" \
  -H "x-portkey-provider: openai" \
  -F "purpose=fine-tune" \
  -F "file=@training_data.jsonl"
```

***

## 2. Portkey Files

Upload files to Portkey and reuse them for [batching inference](/product/ai-gateway/batches) with any provider and [fine-tuning](/product/ai-gateway/fine-tuning) with supported providers. This approach is ideal for:

* Testing your data with different foundation models
* Performing A/B testing across multiple providers
* Batch inference with provider-agnostic file management
* Reusing the same file across multiple batch jobs

### File Requirements

* **Format**: JSONL files where each line contains a single request payload

### Uploading Files

<CodeGroup>
  ```bash curl theme={"system"}
  curl -X POST https://api.portkey.ai/v1/files \
    -H "Authorization: Bearer $PORTKEY_API_KEY" \
    -F "purpose=batch" \
    -F "file=@batch_data.jsonl"
  ```

  ```javascript Typescript theme={"system"}
  import Portkey from 'portkey-ai';

  const client = new Portkey({
    apiKey: 'PORTKEY_API_KEY'
  });

  const file = await client.files.create({
    purpose: 'batch',
    file: fs.createReadStream('batch_data.jsonl')
  });

  console.log(file);
  ```

  ```python Python theme={"system"}
  from portkey_ai import Portkey

  client = Portkey(api_key="PORTKEY_API_KEY")

  with open('batch_data.jsonl', 'rb') as f:
      file = client.files.create(
          purpose='batch',
          file=f
      )

  print(file)
  ```
</CodeGroup>

### Listing Files

<CodeGroup>
  ```bash curl theme={"system"}
  curl -X GET https://api.portkey.ai/v1/files \
    -H "Authorization: Bearer $PORTKEY_API_KEY"
  ```

  ```javascript Typescript theme={"system"}
  const files = await client.files.list();
  console.log(files);
  ```

  ```python Python theme={"system"}
  files = client.files.list()
  print(files)
  ```
</CodeGroup>

### Get File Details

<CodeGroup>
  ```bash curl theme={"system"}
  curl -X GET https://api.portkey.ai/v1/files/{file_id} \
    -H "Authorization: Bearer $PORTKEY_API_KEY"
  ```

  ```javascript Typescript theme={"system"}
  const file = await client.files.retrieve('file_abc123');
  console.log(file);
  ```

  ```python Python theme={"system"}
  file = client.files.retrieve('file_abc123')
  print(file)
  ```
</CodeGroup>

### Get File Content

<CodeGroup>
  ```bash curl theme={"system"}
  curl -X GET https://api.portkey.ai/v1/files/{file_id}/content \
    -H "Authorization: Bearer $PORTKEY_API_KEY"
  ```

  ```javascript Typescript theme={"system"}
  const content = await client.files.content('file_abc123');
  console.log(content);
  ```

  ```python Python theme={"system"}
  content = client.files.content('file_abc123')
  print(content)
  ```
</CodeGroup>

***

## File Format Examples

### Batch Inference JSONL Format

Each line should be a valid JSON object representing a single request:

```jsonl theme={"system"}
{"custom_id": "request-1", "method": "POST", "url": "/v1/chat/completions", "body": {"model": "gpt-3.5-turbo-0125", "messages": [{"role": "system", "content": "You are a helpful assistant."},{"role": "user", "content": "Hello world!"}],"max_tokens": 1000}}
{"custom_id": "request-2", "method": "POST", "url": "/v1/chat/completions", "body": {"model": "gpt-3.5-turbo-0125", "messages": [{"role": "system", "content": "You are an unhelpful assistant."},{"role": "user", "content": "Hello world!"}],"max_tokens": 1000}}
```

### Fine-tuning JSONL Format

For fine-tuning, each line should contain training examples:

```jsonl theme={"system"}
{"messages": [{"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "Hello"}, {"role": "assistant", "content": "Hi! How can I help you today?"}]}
{"messages": [{"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "What's 2+2?"}, {"role": "assistant", "content": "2+2 equals 4."}]}
```

***

## Security & Best Practices

* **Encryption**: Files are encrypted at rest using AES-256
* **Access Control**: File access is gated by workspace permissions
* **Provider Upload**: Portkey uploads files to providers using least-privilege credentials

***