sunra-client 0.1.5

Python client for sunra.ai

sunra.ai Python Client

This is a Python client library for interacting with ML models deployed on sunra.ai.

Getting Started

To install the client, run:

pip install sunra-client

To use the client, you need to have an API key. You can get one by signing up at sunra.ai. Once you have it, set it as an environment variable:

export SUNRA_KEY=your-api-key

Now you can use the client to interact with your models. Here's an example of how to use it:

import sunra_client

response = sunra_client.subscribe(
    "black-forest-labs/flux-kontext-pro/text-to-image",
    arguments={
      "prompt": "a cute cat, realistic, orange"
    },
    with_logs=True,
    on_enqueue=print,
    on_queue_update=print
)
print(response["images"][0]["url"])

Streaming Responses

You can stream real-time updates as your request is being processed:

import sunra_client

application = "black-forest-labs/flux-kontext-pro/text-to-image"
arguments = {"prompt": "a cute cat, realistic, orange"}

for event in sunra_client.stream(application, arguments):
    print(f"Received event: {event}")

Asynchronous Requests

The client also supports asynchronous requests out of the box. Here's an example:

import asyncio
import sunra_client

async def main():
    response = await sunra_client.subscribe_async(
        "black-forest-labs/flux-kontext-pro/text-to-image",
        arguments={"prompt": "a cute cat, realistic, orange"}
        with_logs=True,
        on_enqueue=print,
        on_queue_update=print
    )
    print(response["images"][0]["url"])

asyncio.run(main())

Queuing Requests

When you want to send a request and keep receiving updates on its status, you can use the submit method:

import asyncio
import sunra_client

async def main():
    response = await sunra_client.submit_async(
        "black-forest-labs/flux-kontext-pro/text-to-image",
        arguments={"prompt": "a cute cat, realistic, orange"}
    )

    async for event in response.iter_events():
        if isinstance(event, sunra_client.Queued):
            print("Queued. Position:", event.position)
        elif isinstance(event, (sunra_client.InProgress, sunra_client.Completed)):
            print(event)

    result = await response.get()
    print(result["images"][0]["url"])

asyncio.run(main())

File Upload Support

The client supports uploading files to sunra.ai:

import sunra_client
from PIL import Image

# Create a sync client
client = sunra_client.SyncClient()

# Upload an image file
image = Image.new("RGB", (100, 100), color="red")
image_url = client.upload_image(image)

# Upload any file from local path
file_url = client.upload_file("path/to/your/file.txt")

# Upload raw data
data_url = client.upload(
    data=b"Hello, World!",
    content_type="text/plain",
    file_name="hello.txt"
)

Error Handling

The client provides proper error handling for common scenarios:

import sunra_client
from sunra_client.client import SunraClientError

try:
    response = sunra_client.subscribe(
        "black-forest-labs/flux-kontext-pro/text-to-image",
        arguments={"prompt": "a cute cat, realistic, orange"},
        with_logs=True,
        on_enqueue=print,
        on_queue_update=print
    )
    print(response["images"][0]["url"])
except SunraClientError as e:
    print(f"Error: {e}")

Credits

This project is derived from:

• fal-ai/fal-js
• fal-ai/fal-java
• fal-ai/fal

and adapted to work with sunra.ai. The original projects are licensed under the MIT/Apache 2.0 License. We extend our gratitude to the original authors for their contributions.