How to run this route from Python with the Ouro SDK.
API access requires an API key. Create one in Settings → API Keys, then set OURO_API_KEY in your environment. Install the SDK with pip install ouro-py.
POST /materials/structure/relaxParameters and request body schema for this route.
Range: 0 to 1
Force convergence threshold (eV/Å); with cell optimization it also bounds the stress components.
orb-v3-conservative-20-omatorb-v3-conservative-inf-omatorb-v3-direct-20-omatorb-v3-direct-inf-omatorb-v3-conservative-20-mpaorb-v3-conservative-inf-mpaorb-v3-direct-20-mpaorb-v3-direct-inf-mpamace-mp-smallmace-mp-mediummace-mp-largemace-mpa-mediummace-omat-smallmace-omat-mediumchgnetMachine-learning interatomic potential used for energies and forces. Includes Orb v3 OMat/MPA variants, MACE foundation models, and CHGNet.
Range: 1 to 1000
Maximum optimization steps. A run that hits this limit still returns its last geometry, marked as not converged.
Whether to optimize cell parameters using FrechetCellFilter
Hold the input's space group (found at a 0.1 Å tolerance) fixed during the relaxation. Positions are first symmetrized onto it, so small distortions in the input are removed.
Also return the optimization path as an ASE .traj file: every step's geometry with its energy, forces, and (when the cell is optimized) stress.
Skip CIF validity checks (parse failure, empty structure, overlapping atoms closer than 0.5 Å). Use only when you have already validated the structure.
Pass the ID of an Ouro asset for each of these in input_assets. Ouro loads the asset and sends it to the route.
Runs save these to Ouro. Read them by name from action.final_data.
execute returns an action: the record of this run, with its status, response, and any assets it created.
This route is long-running. Start it without waiting, then collect the result when it's done.
By default a failed run comes back as an action with status error. Pass raise_on_error=True to raise an exception instead.
Every run is saved as an action. List yours, or read the logs of a single run. See the Python SDK reference for everything an action carries.
import os
from ouro import Ouro
ouro = Ouro(api_key=os.environ.get("OURO_API_KEY"))
# The ID also works, and stays the same if the route is renamed: "d040d3b6-faad-40cf-9d7c-999a5c769ed8"
route = ouro.routes.retrieve("mmoderwell/relax-a-crystal-structure")
action = route.execute(
body={
"fmax": 0.02,
"model": "orb-v3-conservative-inf-mpa",
"max_steps": 400,
"optimize_cell": True,
"preserve_symmetry": False,
"include_trajectory": False,
"bypass_cif_health_screen": False,
},
input_assets={
"structure": "your-file-id",
},
)
print(action.status) # "success" or "error"
print(action.final_data)
# Assets the run created are keyed by output name
file = action.final_data["file"]
print(file["id"])# Returns as soon as the run is accepted
action = route.execute(
body={
"fmax": 0.02,
"model": "orb-v3-conservative-inf-mpa",
"max_steps": 400,
"optimize_cell": True,
"preserve_symmetry": False,
"include_trajectory": False,
"bypass_cif_health_screen": False,
},
input_assets={
"structure": "your-file-id",
},
wait=False,
)
print(action.id, action.status)
# Later, even from another process
action = ouro.routes.poll_action(str(action.id), poll_interval=5, timeout=1800)
print(action.final_data)from ouro import ExternalServiceError, RouteExecutionError
try:
action = route.execute(
body={
"fmax": 0.02,
"model": "orb-v3-conservative-inf-mpa",
"max_steps": 400,
"optimize_cell": True,
"preserve_symmetry": False,
"include_trajectory": False,
"bypass_cif_health_screen": False,
},
input_assets={
"structure": "your-file-id",
},
raise_on_error=True,
)
except ExternalServiceError as exc:
# The API behind this route failed
print(exc.status_code, exc.retryable)
except RouteExecutionError as exc:
print(exc.action_id, exc.status, exc.response)
except TimeoutError as exc:
# Still running on Ouro; pick it up again later
action = ouro.routes.poll_action(exc.action_id, timeout=None)route = ouro.routes.retrieve("mmoderwell/relax-a-crystal-structure")
# Your runs of this route
actions = route.read_actions()
for action in actions:
print(action.id, action.status, action.created_at)
# One run and its logs
action = ouro.routes.retrieve_action("your-action-id")
for entry in action.read_logs(chronological=True):
print(entry.level, entry.message)Part of service
Materials API
Optimize atomic positions and (optionally) unit-cell parameters of a crystal structure using a configurable machine learning interatomic potential such as Orb, MACE, or CHGNet. Upload a CIF file and receive the relaxed structure as a new CIF; set include_trajectory to also get the optimization path as an ASE .traj file. Supports configurable force-convergence threshold (fmax), maximum optimization steps, and holding the input symmetry fixed; the response reports whether the run converged and its final max force. Rejects CIFs with overlapping atoms unless bypass_cif_health_screen is set.
Execution
Usage
7049 callsView history