Skip to content

MicroDC Python Client Library

The MicroDC Python Client Library provides a simple, intuitive interface for submitting inference jobs to the MicroDC.ai distributed inference platform.

Package Name: microdc-client | Import Name: microdc | Python: 3.8+

Quick Start

from microdc import Client, LLMComplete

# Initialize client
client = Client(api_key="mDC_499FC19C-686A-47C5-AA93-E619C55EBE98")

# Create and configure a job
job = LLMComplete(model="llama3.3")
job.set_prompt("Why is the sky blue?")

# Submit and wait for results
job_id = client.send_job(job)
client.wait_for_all()

# Get results
result = client.get_job_details(job_id)
print(result.result)

Features

  • Multiple Job Types -- LLM generation, chat, embeddings, and document processing
  • Callback-Based Async -- Background polling with automatic callback invocation
  • File Upload Support -- Upload files and create download tokens for multimodal workflows
  • Automatic Retries -- Exponential backoff for transient errors
  • Type Safe -- Full type hints for IDE autocomplete and static analysis
  • Context Manager -- Clean resource management with with statements

Job Types

Class Purpose Key Method
LLMComplete Single-turn text generation set_prompt()
LLMChat Multi-turn conversations add_user_message()
LLMEmbed Text embeddings add_texts()
DocumentCall Document processing add_file()

Installation

pip install git+https://gitlab.com/microdc/python-client.git

See the Installation Guide for more options.

Next Steps