SDK Documentation

Krutrim Cloud SDK Guide (Python)

1. Overview

The Krutrim Python SDK (krutrim-cloud) provides a simple and consistent interface to interact with various AI and infrastructure services offered by Krutrim Cloud. It supports synchronous and asynchronous workflows, allowing developers to integrate image generation, text completion, and speech services into their applications with ease.

Supported Python Versions: 3.10 – 3.12 Package: https://pypi.org/project/krutrim-cloud

---

2. Installation

Install the SDK via pip:

pip install krutrim-cloud

System Dependencies

Some modules require ffmpeg and ffprobe to be available in your environment:

# macOS (with Homebrew)
brew install ffmpeg

# Ubuntu/Debian
sudo apt-get install ffmpeg

---

3. Authentication

You need an API key to authenticate your requests. This can be provided as an environment variable or passed directly into the client.

Environment Variable (Recommended)

export KRUTRIM_CLOUD_API_KEY="your_api_key_here"

Manual Key Injection

from krutrim_cloud import KrutrimCloud
client = KrutrimCloud(api_key="your_api_key_here")

---

4. Client Initialization

Synchronous Client

from krutrim_cloud import KrutrimCloud
client = KrutrimCloud()

Asynchronous Client

from krutrim_cloud import KrutrimCloudAsync
client = KrutrimCloudAsync()

---

5. Core Functionalities

5.1 Image Generation (Diffusion)

response = client.images.generations.diffusion(
    model_name="diffusion1XL",
    image_height=1024,
    image_width=1024,
    prompt="a cyberpunk cityscape at night"
)

print(response.generated_images)

5.2 Text Completion

response = client.texts.completions.bhashini(
    prompt="Write a short story about a robot and a child.",
    language="en"
)
print(response.generated_text)

5.3 Speech APIs (DIS / Bhashik Speech)

response = client.speech.tts.bhashik(
    text="Namaste, Krutrim Cloud!",
    voice="hi_female_1"
)

with open("output.mp3", "wb") as f:
    f.write(response.audio)

---

6. Error Handling

API responses may raise exceptions for invalid input, network issues, or internal errors.

Basic handling:

try:
    response = client.texts.completions.bhashini(prompt="Hello")
except Exception as e:
    print(f"Error: {str(e)}")

---

7. Using Async Workflows

import asyncio
from krutrim_cloud import KrutrimCloudAsync

async def run():
    client = KrutrimCloudAsync()
    result = await client.images.generations.diffusion(
        model_name="diffusion1XL",
        image_height=512,
        image_width=512,
        prompt="a futuristic AI city"
    )
    print(result.generated_images)

asyncio.run(run())

---

8. Examples & Sample Projects

Explore example notebooks and scripts:

• Basic Inference

• [Fine-Tuning (Coming Soon)]

• [CLI Wrapper (WIP)]

---

9. Versioning & Updates

To upgrade the SDK:

pip install --upgrade krutrim-cloud

Check the GitHub repo for changelogs and release notes.

---

10. Support & Contribution

• For issues, submit a GitHub Issue here

• For API key access, contact the Krutrim team

• For feedback or enhancements, reach out via your internal Slack or community portal

---