unstructured-ingest 0.3.10__py3-none-any.whl → 0.3.12__py3-none-any.whl

test/integration/connectors/{databricks_tests → databricks}/test_volumes_native.py

@@ -1,10 +1,10 @@
 import json
 import os
-import tempfile
 import uuid
 from contextlib import contextmanager
 from dataclasses import dataclass
 from pathlib import Path
+from unittest import mock
 
 import pytest
 from databricks.sdk import WorkspaceClient
@@ -31,11 +31,15 @@ from unstructured_ingest.v2.processes.connectors.databricks.volumes_native impor
 
 
 @dataclass
-class EnvData:
+class BaseEnvData:
     host: str
+    catalog: str
+
+
+@dataclass
+class BasicAuthEnvData(BaseEnvData):
     client_id: str
     client_secret: str
-    catalog: str
 
     def get_connection_config(self) -> DatabricksNativeVolumesConnectionConfig:
         return DatabricksNativeVolumesConnectionConfig(
@@ -47,8 +51,21 @@ class EnvData:
         )
 
 
-def get_env_data() -> EnvData:
-    return EnvData(
+@dataclass
+class PATEnvData(BaseEnvData):
+    token: str
+
+    def get_connection_config(self) -> DatabricksNativeVolumesConnectionConfig:
+        return DatabricksNativeVolumesConnectionConfig(
+            host=self.host,
+            access_config=DatabricksNativeVolumesAccessConfig(
+                token=self.token,
+            ),
+        )
+
+
+def get_basic_auth_env_data() -> BasicAuthEnvData:
+    return BasicAuthEnvData(
         host=os.environ["DATABRICKS_HOST"],
         client_id=os.environ["DATABRICKS_CLIENT_ID"],
         client_secret=os.environ["DATABRICKS_CLIENT_SECRET"],
@@ -56,23 +73,30 @@ def get_env_data() -> EnvData:
     )
 
 
+def get_pat_env_data() -> PATEnvData:
+    return PATEnvData(
+        host=os.environ["DATABRICKS_HOST"],
+        catalog=os.environ["DATABRICKS_CATALOG"],
+        token=os.environ["DATABRICKS_PAT"],
+    )
+
+
 @pytest.mark.asyncio
 @pytest.mark.tags(CONNECTOR_TYPE, SOURCE_TAG)
 @requires_env(
     "DATABRICKS_HOST", "DATABRICKS_CLIENT_ID", "DATABRICKS_CLIENT_SECRET", "DATABRICKS_CATALOG"
 )
-async def test_volumes_native_source():
-    env_data = get_env_data()
-    indexer_config = DatabricksNativeVolumesIndexerConfig(
-        recursive=True,
-        volume="test-platform",
-        volume_path="databricks-volumes-test-input",
-        catalog=env_data.catalog,
-    )
-    connection_config = env_data.get_connection_config()
-    with tempfile.TemporaryDirectory() as tempdir:
-        tempdir_path = Path(tempdir)
-        download_config = DatabricksNativeVolumesDownloaderConfig(download_dir=tempdir_path)
+async def test_volumes_native_source(tmp_path: Path):
+    env_data = get_basic_auth_env_data()
+    with mock.patch.dict(os.environ, clear=True):
+        indexer_config = DatabricksNativeVolumesIndexerConfig(
+            recursive=True,
+            volume="test-platform",
+            volume_path="databricks-volumes-test-input",
+            catalog=env_data.catalog,
+        )
+        connection_config = env_data.get_connection_config()
+        download_config = DatabricksNativeVolumesDownloaderConfig(download_dir=tmp_path)
         indexer = DatabricksNativeVolumesIndexer(
             connection_config=connection_config, index_config=indexer_config
         )
@@ -89,12 +113,44 @@ async def test_volumes_native_source():
         )
 
 
+@pytest.mark.asyncio
+@pytest.mark.tags(CONNECTOR_TYPE, SOURCE_TAG)
+@requires_env("DATABRICKS_HOST", "DATABRICKS_PAT", "DATABRICKS_CATALOG")
+async def test_volumes_native_source_pat(tmp_path: Path):
+    env_data = get_pat_env_data()
+    with mock.patch.dict(os.environ, clear=True):
+        indexer_config = DatabricksNativeVolumesIndexerConfig(
+            recursive=True,
+            volume="test-platform",
+            volume_path="databricks-volumes-test-input",
+            catalog=env_data.catalog,
+        )
+        connection_config = env_data.get_connection_config()
+        download_config = DatabricksNativeVolumesDownloaderConfig(download_dir=tmp_path)
+        indexer = DatabricksNativeVolumesIndexer(
+            connection_config=connection_config, index_config=indexer_config
+        )
+        downloader = DatabricksNativeVolumesDownloader(
+            connection_config=connection_config, download_config=download_config
+        )
+        await source_connector_validation(
+            indexer=indexer,
+            downloader=downloader,
+            configs=SourceValidationConfigs(
+                test_id="databricks_volumes_native_pat",
+                expected_num_files=1,
+            ),
+        )
+
+
 def _get_volume_path(catalog: str, volume: str, volume_path: str):
     return f"/Volumes/{catalog}/default/{volume}/{volume_path}"
 
 
 @contextmanager
-def databricks_destination_context(env_data: EnvData, volume: str, volume_path) -> WorkspaceClient:
+def databricks_destination_context(
+    env_data: BasicAuthEnvData, volume: str, volume_path
+) -> WorkspaceClient:
     client = WorkspaceClient(
         host=env_data.host, client_id=env_data.client_id, client_secret=env_data.client_secret
     )
@@ -137,7 +193,7 @@ def validate_upload(client: WorkspaceClient, catalog: str, volume: str, volume_p
     "DATABRICKS_HOST", "DATABRICKS_CLIENT_ID", "DATABRICKS_CLIENT_SECRET", "DATABRICKS_CATALOG"
 )
 async def test_volumes_native_destination(upload_file: Path):
-    env_data = get_env_data()
+    env_data = get_basic_auth_env_data()
     volume_path = f"databricks-volumes-test-output-{uuid.uuid4()}"
     file_data = FileData(
         source_identifiers=SourceIdentifiers(fullpath=upload_file.name, filename=upload_file.name),

test/integration/connectors/sql/test_postgres.py

@@ -15,7 +15,7 @@ from test.integration.connectors.utils.validation.source import (
     SourceValidationConfigs,
     source_connector_validation,
 )
-from unstructured_ingest.v2.interfaces import FileData
+from unstructured_ingest.v2.interfaces import FileData, SourceIdentifiers
 from unstructured_ingest.v2.processes.connectors.sql.postgres import (
     CONNECTOR_TYPE,
     PostgresAccessConfig,
@@ -119,7 +119,11 @@ def validate_destination(
 async def test_postgres_destination(upload_file: Path, temp_dir: Path):
     # the postgres destination connector doesn't leverage the file data but is required as an input,
     # mocking it with arbitrary values to meet the base requirements:
-    mock_file_data = FileData(identifier="mock file data", connector_type=CONNECTOR_TYPE)
+    mock_file_data = FileData(
+        identifier="mock file data",
+        connector_type=CONNECTOR_TYPE,
+        source_identifiers=SourceIdentifiers(filename=upload_file.name, fullpath=upload_file.name),
+    )
     with docker_compose_context(
         docker_compose_path=env_setup_path / "sql" / "postgres" / "destination"
     ):

test/integration/connectors/sql/test_singlestore.py

@@ -15,7 +15,7 @@ from test.integration.connectors.utils.validation.source import (
     SourceValidationConfigs,
     source_connector_validation,
 )
-from unstructured_ingest.v2.interfaces import FileData
+from unstructured_ingest.v2.interfaces import FileData, SourceIdentifiers
 from unstructured_ingest.v2.processes.connectors.sql.singlestore import (
     CONNECTOR_TYPE,
     SingleStoreAccessConfig,
@@ -103,7 +103,11 @@ def validate_destination(
 @pytest.mark.asyncio
 @pytest.mark.tags(CONNECTOR_TYPE, DESTINATION_TAG, "sql")
 async def test_singlestore_destination(upload_file: Path, temp_dir: Path):
-    mock_file_data = FileData(identifier="mock file data", connector_type=CONNECTOR_TYPE)
+    mock_file_data = FileData(
+        identifier="mock file data",
+        connector_type=CONNECTOR_TYPE,
+        source_identifiers=SourceIdentifiers(filename=upload_file.name, fullpath=upload_file.name),
+    )
     with docker_compose_context(
         docker_compose_path=env_setup_path / "sql" / "singlestore" / "destination"
     ):

test/integration/connectors/sql/test_snowflake.py

@@ -17,7 +17,7 @@ from test.integration.connectors.utils.validation.source import (
     source_connector_validation,
 )
 from test.integration.utils import requires_env
-from unstructured_ingest.v2.interfaces import FileData
+from unstructured_ingest.v2.interfaces import FileData, SourceIdentifiers
 from unstructured_ingest.v2.processes.connectors.sql.snowflake import (
     CONNECTOR_TYPE,
     SnowflakeAccessConfig,
@@ -170,7 +170,11 @@ async def test_snowflake_destination(
 ):
     # the postgres destination connector doesn't leverage the file data but is required as an input,
     # mocking it with arbitrary values to meet the base requirements:
-    mock_file_data = FileData(identifier="mock file data", connector_type=CONNECTOR_TYPE)
+    mock_file_data = FileData(
+        identifier="mock file data",
+        connector_type=CONNECTOR_TYPE,
+        source_identifiers=SourceIdentifiers(filename=upload_file.name, fullpath=upload_file.name),
+    )
     init_db_destination()
     stager = SnowflakeUploadStager()
     staged_path = stager.run(

test/integration/connectors/sql/test_sqlite.py

@@ -15,7 +15,7 @@ from test.integration.connectors.utils.validation.source import (
     SourceValidationConfigs,
     source_connector_validation,
 )
-from unstructured_ingest.v2.interfaces import FileData
+from unstructured_ingest.v2.interfaces import FileData, SourceIdentifiers
 from unstructured_ingest.v2.processes.connectors.sql.sqlite import (
     CONNECTOR_TYPE,
     SQLiteConnectionConfig,
@@ -116,7 +116,11 @@ async def test_sqlite_destination(
 ):
     # the sqlite destination connector doesn't leverage the file data but is required as an input,
     # mocking it with arbitrary values to meet the base requirements:
-    mock_file_data = FileData(identifier="mock file data", connector_type=CONNECTOR_TYPE)
+    mock_file_data = FileData(
+        identifier="mock file data",
+        connector_type=CONNECTOR_TYPE,
+        source_identifiers=SourceIdentifiers(filename=upload_file.name, fullpath=upload_file.name),
+    )
     stager = SQLiteUploadStager()
     staged_path = stager.run(
         elements_filepath=upload_file,

test/integration/connectors/test_milvus.py

@@ -174,6 +174,19 @@ def test_precheck_fails_on_nonexistent_collection(collection: str):
         uploader.precheck()
 
 
+@pytest.mark.tags(CONNECTOR_TYPE, DESTINATION_TAG)
+def test_precheck_fails_on_nonexisting_db(collection: str):
+    uploader = MilvusUploader(
+        connection_config=MilvusConnectionConfig(uri=DB_URI),
+        upload_config=MilvusUploaderConfig(db_name="nonexisting_db", collection_name=collection),
+    )
+    with pytest.raises(
+        DestinationConnectionError,
+        match="database not found",
+    ):
+        uploader.precheck()
+
+
 @pytest.mark.parametrize("upload_file_str", ["upload_file_ndjson", "upload_file"])
 def test_milvus_stager(
     request: TopRequest,

test/integration/connectors/test_onedrive.py

@@ -20,6 +20,9 @@ from unstructured_ingest.v2.processes.connectors.onedrive import (
 
 
 @pytest.fixture
+@pytest.mark.xfail(
+    reason="Issues with test setup on the provider side."
+)  # TODO: remove line when issues are addressed
 def onedrive_test_folder() -> str:
     """
     Pytest fixture that creates a test folder in OneDrive and deletes it after test run.
@@ -66,6 +69,9 @@ def get_connection_config():
 
 @pytest.mark.tags(CONNECTOR_TYPE, DESTINATION_TAG)
 @requires_env("MS_CLIENT_CRED", "MS_CLIENT_ID", "MS_TENANT_ID", "MS_USER_PNAME")
+@pytest.mark.xfail(
+    reason="Issues with test setup on the provider side."
+)  # TODO: remove line when issues are addressed
 def test_onedrive_destination(upload_file: Path, onedrive_test_folder: str):
     """
     Integration test for the OneDrive destination connector.

test/integration/connectors/test_redis.py

@@ -0,0 +1,119 @@
+import asyncio
+import json
+import os
+from pathlib import Path
+from typing import Optional
+
+import numpy as np
+import pytest
+from redis import exceptions as redis_exceptions
+from redis.asyncio import Redis, from_url
+
+from test.integration.connectors.utils.constants import DESTINATION_TAG
+from test.integration.utils import requires_env
+from unstructured_ingest.v2.interfaces.file_data import FileData, SourceIdentifiers
+from unstructured_ingest.v2.processes.connectors.redisdb import (
+    CONNECTOR_TYPE as REDIS_CONNECTOR_TYPE,
+)
+from unstructured_ingest.v2.processes.connectors.redisdb import (
+    RedisAccessConfig,
+    RedisConnectionConfig,
+    RedisUploader,
+    RedisUploaderConfig,
+)
+
+
+async def delete_record(client: Redis, element_id: str) -> None:
+    await client.delete(element_id)
+
+
+async def validate_upload(client: Redis, first_element: dict):
+    element_id = first_element["element_id"]
+    expected_text = first_element["text"]
+    expected_embeddings = first_element["embeddings"]
+    async with client.pipeline(transaction=True) as pipe:
+        try:
+            response = await pipe.json().get(element_id, "$").execute()
+            response = response[0][0]
+        except redis_exceptions.ResponseError:
+            response = await pipe.get(element_id).execute()
+            response = json.loads(response[0])
+
+    embedding_similarity = np.linalg.norm(
+        np.array(response["embeddings"]) - np.array(expected_embeddings)
+    )
+
+    assert response is not None
+    assert response["element_id"] == element_id
+    assert response["text"] == expected_text
+    assert embedding_similarity < 1e-10
+
+
+async def redis_destination_test(
+    upload_file: Path,
+    tmp_path: Path,
+    connection_kwargs: dict,
+    uri: Optional[str] = None,
+    password: Optional[str] = None,
+):
+    uploader = RedisUploader(
+        connection_config=RedisConnectionConfig(
+            **connection_kwargs, access_config=RedisAccessConfig(uri=uri, password=password)
+        ),
+        upload_config=RedisUploaderConfig(batch_size=10),
+    )
+
+    file_data = FileData(
+        source_identifiers=SourceIdentifiers(fullpath=upload_file.name, filename=upload_file.name),
+        connector_type=REDIS_CONNECTOR_TYPE,
+        identifier="mock-file-data",
+    )
+    with upload_file.open() as upload_fp:
+        elements = json.load(upload_fp)
+    first_element = elements[0]
+
+    try:
+        if uploader.is_async():
+            await uploader.run_data_async(data=elements, file_data=file_data)
+
+        if uri:
+            async with from_url(uri) as client:
+                await validate_upload(client=client, first_element=first_element)
+        else:
+            async with Redis(**connection_kwargs, password=password) as client:
+                await validate_upload(client=client, first_element=first_element)
+    except Exception as e:
+        raise e
+    finally:
+        if uri:
+            async with from_url(uri) as client:
+                tasks = [delete_record(client, element["element_id"]) for element in elements]
+                await asyncio.gather(*tasks)
+        else:
+            async with Redis(**connection_kwargs, password=password) as client:
+                tasks = [delete_record(client, element["element_id"]) for element in elements]
+                await asyncio.gather(*tasks)
+
+
+@pytest.mark.asyncio
+@pytest.mark.tags(REDIS_CONNECTOR_TYPE, DESTINATION_TAG)
+@requires_env("AZURE_REDIS_INGEST_TEST_PASSWORD")
+async def test_redis_destination_azure_with_password(upload_file: Path, tmp_path: Path):
+    connection_kwargs = {
+        "host": "utic-dashboard-dev.redis.cache.windows.net",
+        "port": 6380,
+        "db": 0,
+        "ssl": True,
+    }
+    redis_pw = os.environ["AZURE_REDIS_INGEST_TEST_PASSWORD"]
+    await redis_destination_test(upload_file, tmp_path, connection_kwargs, password=redis_pw)
+
+
+@pytest.mark.asyncio
+@pytest.mark.tags(REDIS_CONNECTOR_TYPE, DESTINATION_TAG, "redis")
+@requires_env("AZURE_REDIS_INGEST_TEST_PASSWORD")
+async def test_redis_destination_azure_with_uri(upload_file: Path, tmp_path: Path):
+    connection_kwargs = {}
+    redis_pw = os.environ["AZURE_REDIS_INGEST_TEST_PASSWORD"]
+    uri = f"rediss://:{redis_pw}@utic-dashboard-dev.redis.cache.windows.net:6380/0"
+    await redis_destination_test(upload_file, tmp_path, connection_kwargs, uri=uri)

test/integration/connectors/test_vectara.py

@@ -0,0 +1,270 @@
+import json
+import os
+import time
+from pathlib import Path
+from typing import Generator
+from uuid import uuid4
+
+import pytest
+import requests
+
+from test.integration.connectors.utils.constants import DESTINATION_TAG
+from test.integration.utils import requires_env
+from unstructured_ingest.v2.interfaces.file_data import FileData, SourceIdentifiers
+from unstructured_ingest.v2.logger import logger
+from unstructured_ingest.v2.processes.connectors.vectara import (
+    CONNECTOR_TYPE as VECTARA_CONNECTOR_TYPE,
+)
+from unstructured_ingest.v2.processes.connectors.vectara import (
+    VectaraAccessConfig,
+    VectaraConnectionConfig,
+    VectaraUploader,
+    VectaraUploaderConfig,
+    VectaraUploadStager,
+    VectaraUploadStagerConfig,
+)
+
+
+def validate_upload(response: dict, expected_data: dict):
+    element_id = expected_data["element_id"]
+    expected_text = expected_data["text"]
+    filename = expected_data["metadata"]["filename"]
+    filetype = expected_data["metadata"]["filetype"]
+    page_number = expected_data["metadata"]["page_number"]
+
+    response = response["search_results"][0]
+
+    assert response is not None
+    assert response["text"] == expected_text
+    assert response["part_metadata"]["element_id"] == element_id
+    assert response["part_metadata"]["filename"] == filename
+    assert response["part_metadata"]["filetype"] == filetype
+    assert response["part_metadata"]["page_number"] == page_number
+
+
+@requires_env("VECTARA_OAUTH_CLIENT_ID", "VECTARA_OAUTH_SECRET", "VECTARA_CUSTOMER_ID")
+def _get_jwt_token():
+    """Connect to the server and get a JWT token."""
+    customer_id = os.environ["VECTARA_CUSTOMER_ID"]
+    token_endpoint = (
+        f"https://vectara-prod-{customer_id}.auth.us-west-2.amazoncognito.com/oauth2/token"
+    )
+    headers = {
+        "Content-Type": "application/x-www-form-urlencoded",
+    }
+    data = {
+        "grant_type": "client_credentials",
+        "client_id": os.environ["VECTARA_OAUTH_CLIENT_ID"],
+        "client_secret": os.environ["VECTARA_OAUTH_SECRET"],
+    }
+
+    response = requests.post(token_endpoint, headers=headers, data=data)
+    response.raise_for_status()
+    response_json = response.json()
+
+    return response_json.get("access_token")
+
+
+def query_data(corpus_key: str, element_id: str) -> dict:
+
+    url = f"https://api.vectara.io/v2/corpora/{corpus_key}/query"
+
+    # the query below requires the corpus to have filter attributes for element_id
+
+    data = json.dumps(
+        {
+            "query": "string",
+            "search": {
+                "metadata_filter": f"part.element_id = '{element_id}'",
+                "lexical_interpolation": 1,
+                "limit": 10,
+            },
+        }
+    )
+
+    jwt_token = _get_jwt_token()
+    headers = {
+        "Content-Type": "application/json",
+        "Accept": "application/json",
+        "Authorization": f"Bearer {jwt_token}",
+        "X-source": "unstructured",
+    }
+
+    response = requests.post(url, headers=headers, data=data)
+    response.raise_for_status()
+    response_json = response.json()
+
+    return response_json
+
+
+def create_corpora(corpus_key: str, corpus_name: str) -> None:
+    url = "https://api.vectara.io/v2/corpora"
+    data = json.dumps({"key": corpus_key, "name": corpus_name, "description": "integration test"})
+    jwt_token = _get_jwt_token()
+    headers = {
+        "Content-Type": "application/json",
+        "Accept": "application/json",
+        "Authorization": f"Bearer {jwt_token}",
+        "X-source": "unstructured",
+    }
+
+    response = requests.post(url, headers=headers, data=data)
+    response.raise_for_status()
+
+
+def replace_filter_attributes(corpus_key: str) -> None:
+    url = f"https://api.vectara.io/v2/corpora/{corpus_key}/replace_filter_attributes"
+    data = json.dumps(
+        {
+            "filter_attributes": [
+                {"name": "element_id", "level": "part", "indexed": True, "type": "text"}
+            ]
+        }
+    )
+    jwt_token = _get_jwt_token()
+    headers = {
+        "Content-Type": "application/json",
+        "Accept": "application/json",
+        "Authorization": f"Bearer {jwt_token}",
+        "X-source": "unstructured",
+    }
+
+    response = requests.post(url, headers=headers, data=data)
+    response.raise_for_status()
+
+
+def delete_corpora(corpus_key: str) -> None:
+    url = f"https://api.vectara.io/v2/corpora/{corpus_key}"
+
+    jwt_token = _get_jwt_token()
+    headers = {
+        "Content-Type": "application/json",
+        "Accept": "application/json",
+        "Authorization": f"Bearer {jwt_token}",
+        "X-source": "unstructured",
+    }
+
+    response = requests.delete(url, headers=headers)
+    response.raise_for_status()
+
+
+def list_corpora() -> list:
+    url = "https://api.vectara.io/v2/corpora?limit=100"
+    jwt_token = _get_jwt_token()
+    headers = {
+        "Content-Type": "application/json",
+        "Accept": "application/json",
+        "Authorization": f"Bearer {jwt_token}",
+        "X-source": "unstructured",
+    }
+    response = requests.get(url, headers=headers)
+    response.raise_for_status()
+    response_json = response.json()
+    if response_json.get("corpora"):
+        return [item["key"] for item in response_json.get("corpora")]
+    else:
+        return []
+
+
+def wait_for_ready(corpus_key: str, timeout=60, interval=2) -> None:
+    def is_ready_status():
+        corpora_list = list_corpora()
+        return corpus_key in corpora_list
+
+    start = time.time()
+    is_ready = is_ready_status()
+    while not is_ready and time.time() - start < timeout:
+        time.sleep(interval)
+        is_ready = is_ready_status()
+    if not is_ready:
+        raise TimeoutError("time out waiting for corpus to be ready")
+
+
+def wait_for_delete(corpus_key: str, timeout=60, interval=2) -> None:
+    start = time.time()
+    while time.time() - start < timeout:
+        corpora_list = list_corpora()
+        if corpus_key not in corpora_list:
+            return
+        time.sleep(interval)
+
+    raise TimeoutError("time out waiting for corpus to delete")
+
+
+@pytest.fixture
+def corpora_util() -> Generator[str, None, None]:
+    random_id = str(uuid4()).split("-")[0]
+    corpus_key = f"ingest-test-{random_id}"
+    corpus_name = "ingest-test"
+    logger.info(f"Creating corpus with key: {corpus_key}")
+    try:
+        create_corpora(corpus_key, corpus_name)
+        replace_filter_attributes(corpus_key)
+        wait_for_ready(corpus_key=corpus_key)
+        yield corpus_key
+    except Exception as e:
+        logger.error(f"failed to create corpus {corpus_key}: {e}")
+    finally:
+        logger.info(f"deleting corpus: {corpus_key}")
+        delete_corpora(corpus_key)
+        wait_for_delete(corpus_key=corpus_key)
+
+
+@pytest.mark.asyncio
+@pytest.mark.tags(VECTARA_CONNECTOR_TYPE, DESTINATION_TAG, "vectara")
+@requires_env("VECTARA_OAUTH_CLIENT_ID", "VECTARA_OAUTH_SECRET", "VECTARA_CUSTOMER_ID")
+async def test_vectara_destination(
+    upload_file: Path, tmp_path: Path, corpora_util: str, retries=30, interval=10
+):
+    corpus_key = corpora_util
+    connection_kwargs = {
+        "customer_id": os.environ["VECTARA_CUSTOMER_ID"],
+        "corpus_key": corpus_key,
+    }
+
+    oauth_client_id = os.environ["VECTARA_OAUTH_CLIENT_ID"]
+    oauth_secret = os.environ["VECTARA_OAUTH_SECRET"]
+
+    file_data = FileData(
+        source_identifiers=SourceIdentifiers(fullpath=upload_file.name, filename=upload_file.name),
+        connector_type=VECTARA_CONNECTOR_TYPE,
+        identifier="mock-file-data",
+    )
+
+    stager_config = VectaraUploadStagerConfig(batch_size=10)
+    stager = VectaraUploadStager(upload_stager_config=stager_config)
+    new_upload_file = stager.run(
+        elements_filepath=upload_file,
+        output_dir=tmp_path,
+        output_filename=upload_file.name,
+        file_data=file_data,
+    )
+
+    uploader = VectaraUploader(
+        connection_config=VectaraConnectionConfig(
+            **connection_kwargs,
+            access_config=VectaraAccessConfig(
+                oauth_client_id=oauth_client_id, oauth_secret=oauth_secret
+            ),
+        ),
+        upload_config=VectaraUploaderConfig(),
+    )
+
+    with new_upload_file.open() as new_upload_fp:
+        elements_stager = json.load(new_upload_fp)
+
+    if uploader.is_async():
+        await uploader.run_data_async(data=elements_stager, file_data=file_data)
+
+    with upload_file.open() as upload_fp:
+        elements = json.load(upload_fp)
+    first_element = elements[0]
+
+    for i in range(retries):
+        response = query_data(corpus_key, first_element["element_id"])
+        if not response["search_results"]:
+            time.sleep(interval)
+        else:
+            break
+
+    validate_upload(response=response, expected_data=first_element)