Skip to content
Overmind
Get started
API Reference
Jobs

Create job

jobs.create(JobCreateParams**kwargs) -> JobCreateResponse
POST/api/jobs/

Create job

ParametersExpand Collapse
agent: Optional[str]
formatuuid
analyzer_model: Optional[str]
maxLength128
backtest_results: Optional[object]
baseline_score: Optional[float]
formatdouble
best_agent_code: Optional[str]
best_score: Optional[float]
formatdouble
candidates_per_iteration: Optional[int]
maximum9223372036854776000
minimum-9223372036854776000
formatint64
celery_task_id: Optional[str]
maxLength255
data_source: Optional[str]
minLength1
maxLength20
improvement: Optional[float]
formatdouble
job_type: Optional[Literal["inference", "uploaded_outputs_setup", "judge_scoring", 2 more]]
  • inference - Inference
  • uploaded_outputs_setup - Uploaded Outputs Setup
  • judge_scoring - Judge Scoring
  • prompt_tuning - Prompt Tuning
  • model_backtesting - Model Backtesting
Accepts one of the following:
"inference"
"uploaded_outputs_setup"
"judge_scoring"
"prompt_tuning"
"model_backtesting"
num_iterations: Optional[int]
maximum9223372036854776000
minimum-9223372036854776000
formatint64
project: Optional[str]
formatuuid
prompt_slug: Optional[str]
maxLength255
report_markdown: Optional[str]
result: Optional[object]
status: Optional[Literal["pending", "running", "completed", 2 more]]
  • pending - Pending
  • running - Running
  • completed - Completed
  • failed - Failed
  • cancelled - Cancelled
Accepts one of the following:
"pending"
"running"
"completed"
"failed"
"cancelled"
triggered_by: Optional[int]
ReturnsExpand Collapse
class JobCreateResponse: …
id: str
formatuuid
created_at: datetime
formatdate-time
iterations: List[Iteration]
id: str
formatuuid
created_at: datetime
formatdate-time
iteration_name: str
maxLength64
job: str
formatuuid
agent_code: Optional[str]
avg_score: Optional[float]
formatdouble
description: Optional[str]
dimension_scores: Optional[object]
order: Optional[int]
maximum9223372036854776000
minimum-9223372036854776000
formatint64
status: Optional[Literal["keep", "discard"]]
  • keep - Keep
  • discard - Discard
Accepts one of the following:
"keep"
"discard"
updated_at: datetime
formatdate-time
agent: Optional[str]
formatuuid
analyzer_model: Optional[str]
maxLength128
backtest_results: Optional[object]
baseline_score: Optional[float]
formatdouble
best_agent_code: Optional[str]
best_score: Optional[float]
formatdouble
candidates_per_iteration: Optional[int]
maximum9223372036854776000
minimum-9223372036854776000
formatint64
celery_task_id: Optional[str]
maxLength255
data_source: Optional[str]
maxLength20
improvement: Optional[float]
formatdouble
job_type: Optional[Literal["inference", "uploaded_outputs_setup", "judge_scoring", 2 more]]
  • inference - Inference
  • uploaded_outputs_setup - Uploaded Outputs Setup
  • judge_scoring - Judge Scoring
  • prompt_tuning - Prompt Tuning
  • model_backtesting - Model Backtesting
Accepts one of the following:
"inference"
"uploaded_outputs_setup"
"judge_scoring"
"prompt_tuning"
"model_backtesting"
num_iterations: Optional[int]
maximum9223372036854776000
minimum-9223372036854776000
formatint64
project: Optional[str]
formatuuid
prompt_slug: Optional[str]
maxLength255
report_markdown: Optional[str]
result: Optional[object]
status: Optional[Literal["pending", "running", "completed", 2 more]]
  • pending - Pending
  • running - Running
  • completed - Completed
  • failed - Failed
  • cancelled - Cancelled
Accepts one of the following:
"pending"
"running"
"completed"
"failed"
"cancelled"
triggered_by: Optional[int]
Create job
from overmind_lab import OvermindLab

client = OvermindLab()
job = client.jobs.create()
print(job.id)
{
  "id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
  "created_at": "2019-12-27T18:11:19.117Z",
  "iterations": [
    {
      "id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
      "created_at": "2019-12-27T18:11:19.117Z",
      "iteration_name": "iteration_name",
      "job": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
      "agent_code": "agent_code",
      "avg_score": 0,
      "description": "description",
      "dimension_scores": {},
      "order": -9007199254740991,
      "status": "keep"
    }
  ],
  "updated_at": "2019-12-27T18:11:19.117Z",
  "agent": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
  "analyzer_model": "analyzer_model",
  "backtest_results": {},
  "baseline_score": 0,
  "best_agent_code": "best_agent_code",
  "best_score": 0,
  "candidates_per_iteration": -9007199254740991,
  "celery_task_id": "celery_task_id",
  "data_source": "data_source",
  "improvement": 0,
  "job_type": "inference",
  "num_iterations": -9007199254740991,
  "project": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
  "prompt_slug": "prompt_slug",
  "report_markdown": "report_markdown",
  "result": {},
  "status": "pending",
  "triggered_by": 0
}
Returns Examples
{
  "id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
  "created_at": "2019-12-27T18:11:19.117Z",
  "iterations": [
    {
      "id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
      "created_at": "2019-12-27T18:11:19.117Z",
      "iteration_name": "iteration_name",
      "job": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
      "agent_code": "agent_code",
      "avg_score": 0,
      "description": "description",
      "dimension_scores": {},
      "order": -9007199254740991,
      "status": "keep"
    }
  ],
  "updated_at": "2019-12-27T18:11:19.117Z",
  "agent": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
  "analyzer_model": "analyzer_model",
  "backtest_results": {},
  "baseline_score": 0,
  "best_agent_code": "best_agent_code",
  "best_score": 0,
  "candidates_per_iteration": -9007199254740991,
  "celery_task_id": "celery_task_id",
  "data_source": "data_source",
  "improvement": 0,
  "job_type": "inference",
  "num_iterations": -9007199254740991,
  "project": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
  "prompt_slug": "prompt_slug",
  "report_markdown": "report_markdown",
  "result": {},
  "status": "pending",
  "triggered_by": 0
}