def test_resource_caching_if_already_restored(
tmp_path_factory: TempPathFactory):
initial_storage_dir = tmp_path_factory.mktemp("initial_model_storage")
model_storage = LocalModelStorage(initial_storage_dir)
resource = Resource("my resource")
# Fill model storage
test_filename = "file.txt"
test_content = "test_resource_caching"
with model_storage.write_to(resource) as temporary_directory:
file = temporary_directory / test_filename
file.write_text(test_content)
cache_dir = tmp_path_factory.mktemp("cache_dir")
# Cache resource
resource.to_cache(cache_dir, model_storage)
new_storage_dir = tmp_path_factory.mktemp("new dir")
rasa.utils.common.copy_directory(initial_storage_dir, new_storage_dir)
reinstantiated_resource = Resource.from_cache(
resource.name,
cache_dir,
LocalModelStorage(new_storage_dir),
resource.output_fingerprint,
)
assert reinstantiated_resource == resource
def test_resource_caching_if_already_restored_with_different_state(
tmp_path_factory: TempPathFactory, ):
initial_storage_dir = tmp_path_factory.mktemp("initial_model_storage")
model_storage = LocalModelStorage(initial_storage_dir)
resource = Resource("my resource")
# Fill model storage
test_filename = "file.txt"
test_content = "test_resource_caching"
with model_storage.write_to(resource) as temporary_directory:
file = temporary_directory / test_filename
file.write_text(test_content)
cache_dir = tmp_path_factory.mktemp("cache_dir")
# Cache resource
resource.to_cache(cache_dir, model_storage)
# Pretend there is an additional file which is not in the restored storage.
# This makes the directories and causes the `from_cache` part to fail
# different
(temporary_directory / "another_file").touch()
new_storage_dir = tmp_path_factory.mktemp("new dir")
rasa.utils.common.copy_directory(initial_storage_dir, new_storage_dir)
with pytest.raises(ValueError):
Resource.from_cache(
resource.name,
cache_dir,
LocalModelStorage(new_storage_dir),
resource.output_fingerprint,
)
def test_resource_caching(tmp_path_factory: TempPathFactory):
model_storage = LocalModelStorage(
tmp_path_factory.mktemp("initial_model_storage"))
resource = Resource("my resource")
# Fill model storage
test_filename = "file.txt"
test_content = "test_resource_caching"
with model_storage.write_to(resource) as temporary_directory:
file = temporary_directory / test_filename
file.write_text(test_content)
cache_dir = tmp_path_factory.mktemp("cache_dir")
# Cache resource
resource.to_cache(cache_dir, model_storage)
# Reload resource from cache and inspect
new_model_storage = LocalModelStorage(
tmp_path_factory.mktemp("new_model_storage"))
reinstantiated_resource = Resource.from_cache(resource.name, cache_dir,
new_model_storage,
resource.output_fingerprint)
assert reinstantiated_resource == resource
assert reinstantiated_resource.fingerprint() == resource.fingerprint()
# Read written resource data from model storage to see whether all expected
# contents are there
with new_model_storage.read_from(resource) as temporary_directory:
assert (temporary_directory /
test_filename).read_text() == test_content
def test_create_model_package(
tmp_path_factory: TempPathFactory,
domain: Domain,
):
train_model_storage = LocalModelStorage(
tmp_path_factory.mktemp("train model storage"))
train_schema = GraphSchema({
"train":
SchemaNode(
needs={},
uses=PersistableTestComponent,
fn="train",
constructor_name="create",
config={
"some_config": 123455,
"some more config": [{
"nested": "hi"
}]
},
),
"load":
SchemaNode(
needs={"resource": "train"},
uses=PersistableTestComponent,
fn="run_inference",
constructor_name="load",
config={},
is_target=True,
),
})
predict_schema = GraphSchema({
"run":
SchemaNode(
needs={},
uses=PersistableTestComponent,
fn="run",
constructor_name="load",
config={
"some_config": 123455,
"some more config": [{
"nested": "hi"
}]
},
),
})
# Fill model Storage
with train_model_storage.write_to(Resource("resource1")) as directory:
file = directory / "file.txt"
file.write_text("test")
# Package model
persisted_model_dir = tmp_path_factory.mktemp("persisted models")
archive_path = persisted_model_dir / "my-model.tar.gz"
trained_at = datetime.utcnow()
with freezegun.freeze_time(trained_at):
train_model_storage.create_model_package(archive_path, train_schema,
predict_schema, domain)
# Unpack and inspect packaged model
load_model_storage_dir = tmp_path_factory.mktemp("load model storage")
(
load_model_storage,
packaged_metadata,
) = LocalModelStorage.from_model_archive(load_model_storage_dir,
archive_path)
assert packaged_metadata.train_schema == train_schema
assert packaged_metadata.predict_schema == predict_schema
assert packaged_metadata.domain.as_dict() == domain.as_dict()
assert packaged_metadata.rasa_open_source_version == rasa.__version__
assert packaged_metadata.trained_at == trained_at
assert packaged_metadata.model_id
persisted_resources = load_model_storage_dir.glob("*")
assert list(persisted_resources) == [
Path(load_model_storage_dir, "resource1")
]