specific-ai 0.1.11

specific.ai python sdk

Specific AI Python SDK

This SDK supports two main workflows:

• Platform automation: manage Tasks, Assets (datasets/benchmarks), Trainings, and Models
• Inference: run inference on deployed Specific AI models

For copy‑paste‑ready deep dives, see optune-sdk/examples/platform/.

Installation

pip install specific-ai

Authentication & configuration

Set these environment variables:

• SPECIFIC_AI_API_KEY: API key / bearer token for the platform backend
• SPECIFIC_AI_BASE_URL: platform backend base URL (default in examples: https://platform.specific.ai/)

Optional:

• SPECIFIC_AI_TASK_ID: current task id. You can create a new task or see the current task_id in the platform url. for example - the following url: https://platform.specific.ai/model-setup?usecaseId=68bedd42667aca8d3086e536 the task_id is '68bedd42667aca8d3086e536'
• SPECIFIC_AI_TASK_TYPE: task type string (e.g. ClassificationResponse)

5-line quickstart (platform)

import os
from specific_ai import SpecificAIClient

client = SpecificAIClient(base_url=os.getenv("SPECIFIC_AI_BASE_URL", "http://localhost:8000"), api_key=os.environ["SPECIFIC_AI_API_KEY"])
task_id = client.tasks.list()[0].iter_tasks()[0].task_id
print(client.models.get_metrics(task_id=task_id).versions)

Deep dive examples

Located in optune-sdk/examples/platform/:

• 01_task_management.py
• 02_asset_management.py
• 03_training_workflows.py
• 04_model_deployment.py

Support

Contact [e-mail].