def test_workflow_submission_auto_review(indico, force_complete,
org_annotate_dataset,
org_annotate_model_group):
client = IndicoClient()
wfs = client.call(ListWorkflows(dataset_ids=[org_annotate_dataset.id]))
wf = max(wfs, key=lambda w: w.id)
wf = client.call(
UpdateWorkflowSettings(wf, enable_review=True,
enable_auto_review=True))
assert wf.review_enabled and wf.auto_review_enabled
_file = str(Path(__file__).parents[1]) + "/data/org-sample.pdf"
sub_ids = client.call(WorkflowSubmission(workflow_id=wf.id, files=[_file]))
subs = client.call(WaitForSubmissions(sub_ids, timeout=120))
sub = subs[0]
assert sub.status == "PENDING_AUTO_REVIEW"
raw_result = client.call(RetrieveStorageObject(sub.result_file))
changes = raw_result["results"]["document"]["results"]
for model, preds in changes.items():
if isinstance(preds, dict):
preds["accepted"] = True
elif isinstance(preds, list):
for pred in preds:
pred["accepted"] = True
job = client.call(
SubmitReview(sub.id, changes=changes, force_complete=force_complete))
job = client.call(JobStatus(job.id))
submission = client.call(GetSubmission(sub.id))
assert submission.status == "COMPLETE" if force_complete else "PENDING_REVIEW"
def test_workflow_submission(indico, airlines_dataset,
airlines_model_group: ModelGroup, _input):
client = IndicoClient()
wfs = client.call(ListWorkflows(dataset_ids=[airlines_dataset.id]))
wf = max(wfs, key=lambda w: w.id)
submission_ids = client.call(
WorkflowSubmission(workflow_id=wf.id, **_input))
submission_id = submission_ids[0]
assert submission_id is not None
with pytest.raises(IndicoInputError):
client.call(SubmissionResult(submission_id, "FAILED"))
with pytest.raises(IndicoInputError):
client.call(SubmissionResult(submission_id, "INVALID_STATUS"))
result_url = client.call(
SubmissionResult(submission_id, "COMPLETE", wait=True))
result = client.call(RetrieveStorageObject(result_url.result))
assert isinstance(result, dict)
assert result["submission_id"] == submission_id
assert result["file_version"] == 1
client.call(UpdateSubmission(submission_id, retrieved=True))
sub = client.call(GetSubmission(submission_id))
assert isinstance(sub, Submission)
assert sub.retrieved is True
def test_workflow_submission_missing_workflow(indico):
client = IndicoClient()
dataset_filepath = str(Path(__file__).parents[1]) + "/data/mock.pdf"
with pytest.raises(IndicoError):
client.call(WorkflowSubmission(workflow_id=0,
files=[dataset_filepath]))
def test_list_workflow_submission_retrieved(indico, airlines_dataset,
airlines_model_group: ModelGroup):
client = IndicoClient()
wfs = client.call(ListWorkflows(dataset_ids=[airlines_dataset.id]))
wf = max(wfs, key=lambda w: w.id)
dataset_filepath = str(Path(__file__).parents[1]) + "/data/mock.pdf"
submission_ids = client.call(
WorkflowSubmission(workflow_id=wf.id, files=[dataset_filepath]))
submission_id = submission_ids[0]
assert submission_id is not None
client.call(SubmissionResult(submission_id, "COMPLETE", wait=True))
client.call(UpdateSubmission(submission_id, retrieved=True))
submissions = client.call(
ListSubmissions(
filters=SubmissionFilter(retrieved=True, status="COMPLETE")))
assert all([s.retrieved for s in submissions])
assert submission_id in [s.id for s in submissions]
submissions = client.call(
ListSubmissions(filters=SubmissionFilter(retrieved=False)))
assert all([not s.retrieved for s in submissions])
assert submission_id not in [s.id for s in submissions]
def test_workflow_submission_mixed_args(indico, airlines_dataset):
client = IndicoClient()
wfs = client.call(ListWorkflows(dataset_ids=[airlines_dataset.id]))
wf = max(wfs, key=lambda w: w.id)
_file = str(Path(__file__).parents[1]) + "/data/mock.pdf"
url = PUBLIC_URL + "mock.pdf"
with pytest.raises(IndicoInputError):
client.call(
WorkflowSubmission(workflow_id=wf.id, files=[_file], urls=[url]))
def test_workflow_job(indico, airlines_dataset,
airlines_model_group: ModelGroup):
client = IndicoClient()
wfs = client.call(ListWorkflows(dataset_ids=[airlines_dataset.id]))
wf = max(wfs, key=lambda w: w.id)
dataset_filepath = str(Path(__file__).parents[1]) + "/data/mock.pdf"
jobs = client.call(
WorkflowSubmission(workflow_id=wf.id,
files=[dataset_filepath],
submission=False))
job = jobs[0]
assert job.id is not None
job = client.call(JobStatus(id=job.id, wait=True))
assert job.status == "SUCCESS"
assert job.ready is True
assert isinstance(job.result["url"], str)
result = client.call(RetrieveStorageObject(job.result))
assert isinstance(result, dict)
def test_workflow_submission_versioned(indico, airlines_dataset,
airlines_model_group: ModelGroup,
_input):
client = IndicoClient()
wfs = client.call(ListWorkflows(dataset_ids=[airlines_dataset.id]))
wf = max(wfs, key=lambda w: w.id)
submission_ids = client.call(
WorkflowSubmission(workflow_id=wf.id,
result_version="LATEST",
**_input))
assert len(submission_ids) == len(next(iter(_input.values())))
submission_id = submission_ids[0]
assert submission_id is not None
submissions = client.call(WaitForSubmissions(submission_id))
result = client.call(RetrieveStorageObject(submissions[0].result_file))
assert isinstance(result, dict)
assert result["file_version"] == 2
assert len(result["submission_results"]) == 1
assert result["submission_results"][0]["input_filename"] == "mock.pdf"
# Use your dataset's id to call it's associated workflow
dataset_id = 6826
my_config = IndicoConfig(
host="app.indico.io", api_token_path="./path/to/indico_api_token.txt"
)
client = IndicoClient(config=my_config)
# Return a list of workflows for this dataset id or an empty list if there are none
workflows = client.call(ListWorkflows(dataset_ids=[dataset_id]))
if workflows:
# Send a document through the workflow
# Get back one Job per file
jobs = client.call(
WorkflowSubmission(
workflow_id=workflows[0].id,
files=["./path/to/sample.pdf"],
submission=False,
)
)
job = jobs[0]
# Retrieve and print your result
status = client.call(JobStatus(id=job.id, wait=True))
wf_result = client.call(RetrieveStorageObject(status.result))
print(wf_result)
else:
print("You don't have any workflows for this dataset")
# Create an Indico API client
my_config = IndicoConfig(host="app.indico.io",
api_token_path="./path/to/indico_api_token.txt")
client = IndicoClient(config=my_config)
workflow_id = 5
"""
Example 1
Create a new submission
Generate a submission result as soon as the submission is done processing
Then mark the submission has having been retrieved
"""
submission_ids = client.call(
WorkflowSubmission(workflow_id=workflow_id, files=["./path_to_doc.pdf"]))
submission_id = submission_ids[0]
result_url = client.call(SubmissionResult(submission_id, wait=True))
result = client.call(RetrieveStorageObject(result_url.result))
print(result)
client.call(UpdateSubmission(submission_id, retrieved=True))
"""
Example 2
List all submissions that are COMPLETE or FAILED
Generate submission results for these
Delay gathering the results until required
"""
sub_filter = or_(SubmissionFilter(status="COMPLETE"),
SubmissionFilter(status="FAILED"))