def search(
workspace: Path,
data_dir: Path,
flow: Flow,
threshold: Optional[float],
top_k: int,
num_queries: int,
):
if not workspace.exists():
raise FileNotFoundError(
f'The directory {workspace} does not exist. Please index first via `python app.py index`'
)
with flow:
create_query_audios(num_queries, data_dir)
responses = flow.post(
'/search',
inputs=create_docs(os.path.join(data_dir, 'query', '*.mp3')),
return_results=True,
)
result_html, accuracy = report_results(responses, threshold, top_k)
write_html(str(workspace / 'demo.html'), result_html, accuracy, top_k)
def hello_world(args):
"""
Runs Jina's Hello World.
Usage:
Use it via CLI :command:`jina hello-world`.
Description:
It downloads Fashion-MNIST dataset and :term:`Indexer<indexes>` 50,000 images.
The index is stored into 4 *shards*. It randomly samples 128 unseen images as :term:`Queries<Searching>`
Results are shown in a webpage.
More options can be found in :command:`jina hello-world --help`
:param args: Argparse object
"""
Path(args.workdir).mkdir(parents=True, exist_ok=True)
targets = {
'index-labels': {
'url': args.index_labels_url,
'filename': os.path.join(args.workdir, 'index-labels'),
},
'query-labels': {
'url': args.query_labels_url,
'filename': os.path.join(args.workdir, 'query-labels'),
},
'index': {
'url': args.index_data_url,
'filename': os.path.join(args.workdir, 'index-original'),
},
'query': {
'url': args.query_data_url,
'filename': os.path.join(args.workdir, 'query-original'),
},
}
# download the data
download_data(targets, args.download_proxy)
# reduce the network load by using `fp16`, or even `uint8`
os.environ['JINA_ARRAY_QUANT'] = 'fp16'
os.environ['HW_WORKDIR'] = args.workdir
# now comes the real work
# load index flow from a YAML file
f = Flow().add(uses=MyEncoder,
parallel=2).add(uses=MyIndexer).add(uses=MyEvaluator)
# run it!
with f:
f.index(
index_generator(num_docs=targets['index']['data'].shape[0],
target=targets),
request_size=args.request_size,
)
# wait for couple of seconds
countdown(
3,
reason=colored(
'behold! im going to switch to query mode',
'cyan',
attrs=['underline', 'bold', 'reverse'],
),
)
# f.search(
# query_generator(
# num_docs=args.num_query, target=targets, with_groundtruth=True
# ),
# shuffle=True,
# on_done=print_result,
# request_size=args.request_size,
# parameters={'top_k': args.top_k},
# )
f.post(
'/eval',
query_generator(num_docs=args.num_query,
target=targets,
with_groundtruth=True),
shuffle=True,
on_done=print_result,
request_size=args.request_size,
parameters={'top_k': args.top_k},
)
# write result to html
write_html(os.path.join(args.workdir, 'demo.html'))
def hello_world(args):
"""
Runs Jina's Hello World.
Usage:
Use it via CLI :command:`jina hello fashion`.
Description:
It downloads Fashion-MNIST dataset and :term:`Indexer<indexes>` 50,000 images.
The index is stored into 4 *shards*. It randomly samples 128 unseen images as :term:`Queries<Searching>`
Results are shown in a webpage.
More options can be found in :command:`jina hello-world --help`
:param args: Argparse object
"""
Path(args.workdir).mkdir(parents=True, exist_ok=True)
targets = {
'index-labels': {
'url': args.index_labels_url,
'filename': os.path.join(args.workdir, 'index-labels'),
},
'query-labels': {
'url': args.query_labels_url,
'filename': os.path.join(args.workdir, 'query-labels'),
},
'index': {
'url': args.index_data_url,
'filename': os.path.join(args.workdir, 'index-original'),
},
'query': {
'url': args.query_data_url,
'filename': os.path.join(args.workdir, 'query-original'),
},
}
# download the data
download_data(targets, args.download_proxy)
# now comes the real work
# load index flow from a YAML file
f = (Flow().add(uses=MyEncoder, replicas=2).add(uses=MyIndexer,
workspace=args.workdir))
# run it!
with f:
f.index(
index_generator(num_docs=targets['index']['data'].shape[0],
target=targets),
show_progress=True,
)
groundtruths = get_groundtruths(targets)
evaluate_print_callback = partial(print_result, groundtruths)
evaluate_print_callback.__name__ = 'evaluate_print_callback'
f.post(
'/search',
query_generator(num_docs=args.num_query, target=targets),
shuffle=True,
on_done=evaluate_print_callback,
parameters={'top_k': args.top_k},
show_progress=True,
)
# write result to html
write_html(os.path.join(args.workdir, 'demo.html'))