Azure Search Python SDK

main.py

# azure-search-documents==11.3.0
# faker=15.3.3

import os
from azure.core.credentials import AzureKeyCredential
from azure.search.documents import SearchClient
from azure.search.documents.indexes import SearchIndexClient
from azure.search.documents.indexes.models import (
    CorsOptions,
    ComplexField,
    SearchIndex,
    ScoringProfile,
    SearchFieldDataType,
    SimpleField,
    SearchableField
)


endpoint = os.environ["AZURE_SEARCH_ENDPOINT"]
key = os.environ["AZURE_SEARCH_API_KEY"]

# index name - for organizing the search fields, indices and the documents.
index_name = "profiles"

# Python client for managing index in Azure Search
search_index_client = SearchIndexClient(endpoint, AzureKeyCredential(key))

# Python client for performing search
search_client = SearchClient(endpoint, index_name, AzureKeyCredential(key))

# Search Fields
fields = [
    SimpleField(name="username",
                type=SearchFieldDataType.String, key=True),
    SearchableField(name="name", type=SearchFieldDataType.String),
    SearchableField(name="mail", type=SearchFieldDataType.String),
    ComplexField(name="address", fields=[
        SearchableField(name="address1", type=SearchFieldDataType.String),
        SearchableField(name="address2", type=SearchFieldDataType.String),
    ])
]

# Search index object
index = SearchIndex(
    name=index_name,
    fields=fields,
    scoring_profiles=[],
    cors_options=CorsOptions(allowed_origins=["*"], max_age_in_seconds=60))


def add_documents(count: int) -> list[str]:
    """Add documents to the search index

    Args:
        count (int): number of document to add. Essentially, using Faker to
        generate the number of profiles.

    Returns:
        list[str]: list of user names.
    """
    import faker
    faker_inst = faker.Faker()

    def create_profile(profile):
        del profile["sex"]
        del profile["birthdate"]
        addresses = profile["address"].split("\n")
        profile["address"] = {
            "address1": addresses[0],
            "address2": addresses[1],
        }
        return profile

    profiles = [create_profile(faker_inst.simple_profile())
                for _ in range(count)]

    search_client.upload_documents(documents=profiles)
    return [p["name"] for p in profiles]


if __name__ == "__main__":
    # 0. remove index if it exists
    # search_index_client.delete_index(index)

    # 1. create index and data
    search_index_client.create_index(index)
    names = add_documents(100)
    print(names)  # for search reference

    # 2. search
    # enter a search text, can use the names as reference
    # results = list(search_client.search("some text")) 
    # print(results)