upload_documents_to_discovery_collection.py 文件源码

def main():
    insurance_lib_data_dir = resource_filename('resources', 'insurance_lib_v2')
    print('Using data from {}'.format(insurance_lib_data_dir))

    # Either re-use an existing collection id by over riding the below, or leave as is to create one
    collection_id = "TestCollection-InsLibV2"

    discovery = DiscoveryProxy()

    collection_id = discovery.setup_collection(collection_id=collection_id,
                                               config_id="889a08c9-cad9-4287-a87d-2f0380363bff")
    discovery.print_collection_stats(collection_id)

    # This thing seems to misbehave when run from python notebooks due to its use of multiprocessing, so just
    # running in a script
    discovery.upload_documents(collection_id=collection_id,
                               corpus=document_corpus_as_iterable(
                                   path.join(insurance_lib_data_dir, 'document_corpus.solr.xml')))

    discovery.print_collection_stats(collection_id)