🐍 DynaSpark Python Client

Installation

Install the package using pip:

pip install dynaspark

Quick Start

Here's a simple example to get you started:

from dynaspark import DynaSpark

# Initialize client (no API key needed)
ds = DynaSpark()

# Generate text
response = ds.generate_response("What is artificial intelligence?")
print(response.get('response', ''))

# Generate image
image_url = ds.generate_image("A beautiful sunset over mountains")
print(f"Generated image: {image_url}")

# Generate audio response
audio_data = ds.generate_audio_response("Hello, this is a test!")
ds.save_audio(audio_data, "response.mp3")

Authentication

Currently, no API key is required to use the DynaSpark API. However, you can specify your own API key if needed:

from dynaspark import DynaSpark

# Initialize with custom API key (optional)
ds = DynaSpark(api_key="your_api_key")

Client Initialization

Initialize a new DynaSpark client instance.

Parameters:

Text Generation

Generate text responses using various models and parameters.

Parameters:

# Basic usage
response = ds.generate_response("What is Python?")

# Advanced usage with parameters
response = ds.generate_response(
    "Write a poem about technology",
    model="mistral",
    temperature=0.8,
    top_p=0.9,
    presence_penalty=0.6,
    frequency_penalty=0.6
)

Image Generation

Generate images from text descriptions.

Parameters:

# Basic usage
image_url = ds.generate_image("A serene mountain landscape")

# Advanced usage
image_url = ds.generate_image(
    "A futuristic city with flying cars",
    width=1024,
    height=768,
    model="flux",
    nologo=True,
    wm="DynaSpark"
)

Audio Generation

Generate audio responses from prompt using various voices.

Parameters:

Available Voices:

# Basic usage
audio_data = ds.generate_audio_response("Hello, this is a test!")

# With different voice
audio_data = ds.generate_audio_response(
    "This is a test with a different voice.",
    voice="nova"
)

# Save to file
ds.save_audio(audio_data, "response.mp3")

Error Handling

The client provides custom exceptions for better error handling:

from dynaspark import DynaSpark, DynaSparkError

ds = DynaSpark()

try:
    response = ds.generate_response("Hello")
    print(response.get('response', ''))
except DynaSparkError as e:
    print(f"API Error: {e}")
except ValueError as e:
    print(f"Invalid Parameter: {e}")
except Exception as e:
    print(f"Unexpected Error: {e}")

Common Exceptions:

Rate Limiting

The API implements rate limiting to ensure fair usage. The client automatically handles rate limits and provides information about your current usage:

# Get rate limit information
rate_limit = ds.get_rate_limit()
print(f"Remaining requests: {rate_limit.remaining}")
print(f"Reset time: {rate_limit.reset_time}")

Streaming Responses

For long text generations, you can use streaming to get responses as they're generated:

# Stream a response
for chunk in ds.generate_response(
    "Write a long story",
    stream=True
):
    print(chunk, end='', flush=True)

Text Generation Examples

response = ds.generate_response(
    "You are a helpful assistant. Explain quantum computing.",
    model="mistral",
    temperature=0.7
)
print(response['response'])

response = ds.generate_response(
    "Write a Python function to sort a list of dictionaries by a key",
    model="qwen-coder",
    temperature=0.2
)
print(response['response'])

Image Generation Examples

image_url = ds.generate_image(
    "A cute cat playing with yarn",
    model="flux"
)
print(f"Image URL: {image_url}")

image_url = ds.generate_image(
    "A detailed landscape of mountains at sunset",
    width=1024,
    height=768,
    model="turbo"
)
print(f"Image URL: {image_url}")

Audio Generation Examples

audio_data = ds.generate_audio_response(
    "Welcome to DynaSpark! This is a test of the audio generation.",
    voice="alloy"
)
ds.save_audio(audio_data, "welcome.mp3")

# Generate audio with different voices
voices = ["alloy", "echo", "nova"]
for i, voice in enumerate(voices):
    audio_data = ds.generate_audio_response(
        f"This is voice {voice}",
        voice=voice
    )
    ds.save_audio(audio_data, f"voice_{i}.mp3")