def main(task, num_docs, top_k):
workspace_path = '/tmp/jina/urbandict'
os.environ['TMP_WORKSPACE'] = get_random_ws(workspace_path)
print(f'{os.environ["TMP_WORKSPACE"]}')
data_fn = os.environ.get('WASHED_DATA_DIR', os.path.join(workspace_path, 'urbandict-word-defs.csv'))
if task == 'index':
f = Flow().load_config('flow-index.yml')
with f:
f.index_lines(filepath=data_fn, size=num_docs, batch_size=16)
elif task == 'query':
f = Flow().load_config('flow-query.yml')
with f:
while True:
text = input('word definition: ')
if not text:
break
ppr = lambda x: print_topk(x, text)
f.search_lines(lines=[text, ], output_fn=ppr, topk=top_k)
elif task == 'query_restful':
f = Flow().load_config('flow-query.yml')
f.use_rest_gateway()
with f:
f.block()
else:
raise NotImplementedError(
f'unknown task: {task}. A valid task is `index` or `query` or `query_restful`.')
def query(num_docs, top_k):
config(num_docs, mode = 'search')
f = Flow().load_config('flow-query.yml')
with f:
while True:
text = input('please type a sentence: ')
if not text:
break
ppr = lambda x: print_topk(x, text)
f.search_lines(lines=[text, ], output_fn=ppr, top_k=top_k)
def query(top_k):
f = Flow().load_config("flow-query.yml")
with f:
while True:
text = input("please type a description: ")
if not text:
break
def ppr(x):
print_topk(x, text)
f.search_lines(lines=[text, ], output_fn=ppr, top_k=top_k)
def query(num_docs, top_k):
f = Flow().load_config('flow-query.yml')
with f:
while True:
text = input('please type a sentence: ')
if not text:
break
def ppr(x):
return print_topk(x, text)
f.search_lines(lines=[text, ], output_fn=ppr, top_k=top_k)
def query(top_k):
f = Flow().load_config("flows/query.yml")
with f:
while True:
text = input("please type a sentence: ")
if not text:
break
def ppr(x):
print_topk(x, text)
f.search_lines(lines=[text, ], line_format='text', on_done=ppr, top_k=top_k)
def query(top_k):
f = Flow().load_config("flows/query.yml")
with f:
while True:
text = input("please type a sentence: ")
if not text:
break
with TimeContext(f'QPS: query with 1', logger=f.logger):
f.search_lines(lines=[
text,
], line_format='text', top_k=top_k)
def main(task, num_docs, top_k):
os.environ['TMP_WORKSPACE'] = get_random_ws(os.environ['TMP_DATA_DIR'])
data_path = os.path.join(os.environ['TMP_DATA_DIR'], 'character-lines.csv')
if task == 'index':
f = Flow().load_config('flow-index.yml')
with f:
f.index_lines(filepath=data_path, size=num_docs, batch_size=8)
elif task == 'query':
f = Flow().load_config('flow-query.yml')
with f:
while True:
text = input('please type a sentence: ')
if not text:
break
ppr = lambda x: print_topk(x, text)
f.search_lines(lines=[
text,
], output_fn=ppr, topk=top_k)
else:
raise NotImplementedError(
f'unknown task: {task}. A valid task is either `index` or `query`.'
)
def main(task, num_docs, top_k):
workspace_path = '/tmp/jina/urbandict'
os.environ['WORKDIR'] = get_random_ws(workspace_path)
data_fn = os.environ.get(
'WASHED_DATA_DIR',
os.path.join(workspace_path, 'urbandict-word-defs.csv'))
if task == 'index':
workspace = os.environ['WORKDIR']
if os.path.exists(workspace):
print(
f'\n +---------------------------------------------------------------------------------+ \
\n | 🤖🤖🤖 | \
\n | The directory {workspace} already exists. Please remove it before indexing again. | \
\n | 🤖🤖🤖 | \
\n +---------------------------------------------------------------------------------+'
)
f = Flow().load_config('flow-index.yml')
with f:
f.index_lines(filepath=data_fn, size=num_docs, batch_size=16)
elif task == 'query':
f = Flow().load_config('flow-query.yml')
with f:
while True:
text = input('word definition: ')
if not text:
break
ppr = lambda x: print_topk(x, text)
f.search_lines(lines=[
text,
], output_fn=ppr, top_k=top_k)
elif task == 'query_restful':
f = Flow().load_config('flow-query.yml')
f.use_rest_gateway()
with f:
f.block()
else:
raise NotImplementedError(
f'unknown task: {task}. A valid task is `index` or `query` or `query_restful`.'
)
