darksyntrix-sdk 1.0.0

Official Python SDK for DarkSyntrix — A stealth AI gateway orchestrating 24 private model pipelines through a secure Same-Origin proxy architecture.

DarkSyntrix Python SDK

Official Python SDK for the DarkSyntrix AI Gateway — a stealth Same-Origin proxy architecture orchestrating 24 private model pipelines (LLM + media) behind a unified OpenAI-compatible API.

Installation

pip install darksyntrix-sdk

Or install directly from the repository:

pip install git+https://gitlab.com/llm_model/darksyntrix-sdk.git

Quick Start

Synchronous Client

from darksyntrix_sdk import DarkSyntrixClient

client = DarkSyntrixClient(
    base_url="https://your-gateway.app",
    api_key="vr_live_..."
)

# Non-streaming chat
response = client.chat.create(
    model="pulse_conversational_1.5b",
    messages=[{"role": "user", "content": "Hello!"}],
    stream=False
)
print(response.choices[0].message.content)

# Streaming chat
stream = client.chat.create(
    model="pulse_conversational_1.5b",
    messages=[{"role": "user", "content": "Tell me a story"}],
    stream=True
)
for chunk in stream:
    for choice in chunk.choices:
        print(choice.delta.content, end="", flush=True)

client.close()

Async Client

import asyncio
from darksyntrix_sdk import AsyncDarkSyntrixClient

async def main():
    async with AsyncDarkSyntrixClient(
        base_url="https://your-gateway.app",
        api_key="vr_live_..."
    ) as client:
        stream = await client.chat.create(
            model="hyperion_r1_reasoning_7b",
            messages=[{"role": "user", "content": "Solve this step by step: 2+2*2"}],
            stream=True
        )
        async for chunk in stream:
            for choice in chunk.choices:
                print(choice.delta.content, end="", flush=True)

asyncio.run(main())

Authentication & Key Management

from darksyntrix_sdk import DarkSyntrixClient

client = DarkSyntrixClient(base_url="https://your-gateway.app")

# Register a new account
result = client.auth.register("my_user", "secure_pass123")
# Login to get a session token
client.auth.login("my_user", "secure_pass123")

# Create a new API key
new_key = client.keys.create("my_user", "My API key")
print(f"Key: {new_key}")

# List existing keys
for key in client.keys.list("my_user"):
    print(f"{key.id}: {key.description} (active: {key.is_active})")

Media Processing

client = DarkSyntrixClient(
    base_url="https://your-gateway.app",
    api_key="vr_live_..."
)

# Upload a video for processing
url = client.media.upload("path/to/video.mp4", "video.mp4", "video/mp4")

# Process with RIFE frame interpolation
result = client.media.process(
    model="frame_interpolation_rife",
    cloudinary_url=url,
    parameters={"interpolation_factor": 4}
)
print(result)

API Namespaces

Namespace	Description
client.auth	Register & login to obtain API keys / session tokens
client.keys	List, create, and revoke API keys
client.chat	Blocking & streaming chat completions (OpenAI-style)
client.media	Upload files & trigger GPU media processing
client.telemetry	Real-time host metrics & database statistics

Features

• Zero bloat — Only depends on httpx. Uses native Python dataclasses instead of Pydantic.
• Sync + Async — Full mirror API with DarkSyntrixClient (sync) and AsyncDarkSyntrixClient (async).
• SSE Streaming — First-class Server-Sent Events parser for real-time token streaming.
• Connection Pooling — Built-in httpx connection pool with 120s timeout resilience for cold-start containers.
• Full IDE Autocomplete — Typed dataclass response models for ChatCompletionResponse, ChatCompletionChunk, KeyInfo, TelemetryStats.
• Context Manager Support — Use with / async with for automatic connection cleanup.

Supported Models (24 Engines)

Conversational / General Assistant

• pulse_conversational_1.5b — DarkSyntrix Pulse Conversational 1.5B
• aurora_core_gemma_1b — DarkSyntrix AuroraCore Gemma 1B
• apex_conversational_llama_3b — DarkSyntrix Apex Conversational LLaMA 3B
• infinity_phi_instruct_4 — DarkSyntrix Infinity Phi Instruct 4
• sentinel_pulse_qwen_0.5b — DarkSyntrix SentinelPulse Qwen 0.5B
• nebula_core_llama_1b — DarkSyntrix NebulaCore LLaMA 1B
• genesis_smollm_1.7b — DarkSyntrix Genesis SmolLM 1.7B
• nexus_quantum_instruct_mini — DarkSyntrix Nexus Quantum Instruct Mini

Reasoning / Chain-of-Thought

• hyperion_r1_reasoning_7b — DarkSyntrix Hyperion R1 Reasoning 7B
• synapse_r1_reasoning_1.5b — DarkSyntrix Synapse R1 Reasoning 1.5B

Code Generation

• cyber_forge_coder_1.5b — DarkSyntrix CyberForge Coder 1.5B
• matrix_core_coder_3b — DarkSyntrix MatrixCore Coder 3B
• titan_apex_coder_7b — DarkSyntrix TitanApex Coder 7B
• nova_starcoder_3b — DarkSyntrix Nova StarCoder 3B
• vector_gemma_coder_2b — DarkSyntrix VectorGemma Coder 2B
• synapse_coder_deepseek_1.3b — DarkSyntrix SynapseCoder DeepSeek 1.3B
• granite_matrix_coder_3b — DarkSyntrix GraniteMatrix Coder 3B
• micro_pulse_coder_0.5b — DarkSyntrix MicroPulse Coder 0.5B

Media Processing (GPU)

• acoustic_suppression_deepfilter — DarkSyntrix Acoustic Suppression DeepFilterNet
• photographic_restoration_gfpgan — DarkSyntrix Photographic Restoration GFPGAN
• avatar_lipsync_hyperlips — DarkSyntrix Avatar LipSync HyperLips
• generative_cinematic_ltx — DarkSyntrix Generative Cinematic LTX
• super_resolution_esrgan — DarkSyntrix Super Resolution ESRGAN
• frame_interpolation_rife — DarkSyntrix Frame Interpolation RIFE

License

MIT