from mka1 import SDK, models


with SDK(
    bearer_auth="<YOUR_BEARER_TOKEN_HERE>",
) as sdk:

    res = sdk.llm.evals.create_run(suite_id="eval_suite_aa87e2b1112a455b8deabed784372198", models=[
        "auto",
    ], judge_model="auto", embedding_model="auto", generation=models.EvalGenerationConfig(
        temperature=0,
        max_gen_toks=512,
        until=[
            "<|endoftext|>",
        ],
        do_sample=False,
        chat_template_kwargs={
            "enable_thinking": False,
        },
        timeout_seconds=120,
        max_retries=2,
        max_empty_retries=1,
    ), concurrency=4, metadata={
        "purpose": "mvp",
    })

    # Handle response
    print(res)

{
  "id": "eval_run_aa87e2b1112a455b8deabed784372198",
  "object": "eval.run",
  "suite_id": "eval_suite_aa87e2b1112a455b8deabed784372198",
  "suite_version": 1,
  "suite_version_id": "eval_sver_aa87e2b1112a455b8deabed784372198",
  "status": "in_progress",
  "models": [
    "auto"
  ],
  "task_ids": null,
  "judge_model": "auto",
  "embedding_model": "auto",
  "generation": {
    "temperature": 0,
    "max_output_tokens": 512
  },
  "request_counts": {
    "total": 100,
    "completed": 10,
    "failed": 0
  },
  "metrics": null,
  "error": null,
  "artifact_file_ids": [],
  "metadata": {
    "purpose": "mvp"
  },
  "created_at": 1704067200,
  "started_at": 1704067210,
  "completed_at": null,
  "cancelled_at": null,
  "failed_at": null
}