As of January 1, 2020 this library no longer supports Python 2 on the latest released version. Library versions released prior to that date will continue to be available. For more information please visit Python 2 support on Google Cloud.

RetrieverService

class google.ai.generativelanguage_v1beta.services.retriever_service.RetrieverServiceAsyncClient(*, credentials: typing.Optional[google.auth.credentials.Credentials] = None, transport: typing.Optional[typing.Union[str, google.ai.generativelanguage_v1beta.services.retriever_service.transports.base.RetrieverServiceTransport, typing.Callable[[...], google.ai.generativelanguage_v1beta.services.retriever_service.transports.base.RetrieverServiceTransport]]] = 'grpc_asyncio', client_options: typing.Optional[google.api_core.client_options.ClientOptions] = None, client_info: google.api_core.gapic_v1.client_info.ClientInfo = <google.api_core.gapic_v1.client_info.ClientInfo object>)[source]

An API for semantic search over a corpus of user uploaded content.

Instantiates the retriever service async client.

Parameters
  • credentials (Optional[google.auth.credentials.Credentials]) – The authorization credentials to attach to requests. These credentials identify the application to the service; if none are specified, the client will attempt to ascertain the credentials from the environment.

  • transport (Optional[Union[str,RetrieverServiceTransport,Callable[..., RetrieverServiceTransport]]]) – The transport to use, or a Callable that constructs and returns a new transport to use. If a Callable is given, it will be called with the same set of initialization arguments as used in the RetrieverServiceTransport constructor. If set to None, a transport is chosen automatically.

  • client_options (Optional[Union[google.api_core.client_options.ClientOptions, dict]]) –

    Custom options for the client.

    1. The api_endpoint property can be used to override the default endpoint provided by the client when transport is not explicitly provided. Only if this property is not set and transport was not explicitly provided, the endpoint is determined by the GOOGLE_API_USE_MTLS_ENDPOINT environment variable, which have one of the following values: “always” (always use the default mTLS endpoint), “never” (always use the default regular endpoint) and “auto” (auto-switch to the default mTLS endpoint if client certificate is present; this is the default value).

    2. If the GOOGLE_API_USE_CLIENT_CERTIFICATE environment variable is “true”, then the client_cert_source property can be used to provide a client certificate for mTLS transport. If not provided, the default SSL client certificate will be used if present. If GOOGLE_API_USE_CLIENT_CERTIFICATE is “false” or not set, no client certificate will be used.

    3. The universe_domain property can be used to override the default “googleapis.com” universe. Note that api_endpoint property still takes precedence; and universe_domain is currently not supported for mTLS.

  • client_info (google.api_core.gapic_v1.client_info.ClientInfo) – The client info used to send a user-agent string along with API requests. If None, then default info will be used. Generally, you only need to set this if you’re developing your own client library.

Raises

google.auth.exceptions.MutualTlsChannelError – If mutual TLS transport creation failed for any reason.

property api_endpoint

Return the API endpoint used by the client instance.

Returns

The API endpoint used by the client instance.

Return type

str

async batch_create_chunks(request: Optional[Union[google.ai.generativelanguage_v1beta.types.retriever_service.BatchCreateChunksRequest, dict]] = None, *, retry: Optional[Union[google.api_core.retry.retry_unary_async.AsyncRetry, google.api_core.gapic_v1.method._MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) google.ai.generativelanguage_v1beta.types.retriever_service.BatchCreateChunksResponse[source]

Batch create Chunks.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.ai import generativelanguage_v1beta

async def sample_batch_create_chunks():
    # Create a client
    client = generativelanguage_v1beta.RetrieverServiceAsyncClient()

    # Initialize request argument(s)
    requests = generativelanguage_v1beta.CreateChunkRequest()
    requests.parent = "parent_value"
    requests.chunk.data.string_value = "string_value_value"

    request = generativelanguage_v1beta.BatchCreateChunksRequest(
        requests=requests,
    )

    # Make the request
    response = await client.batch_create_chunks(request=request)

    # Handle the response
    print(response)
Parameters
  • request (Optional[Union[google.ai.generativelanguage_v1beta.types.BatchCreateChunksRequest, dict]]) – The request object. Request to batch create Chunks.

  • retry (google.api_core.retry_async.AsyncRetry) – Designation of what errors, if any, should be retried.

  • timeout (float) – The timeout for this request.

  • metadata (Sequence[Tuple[str, str]]) – Strings which should be sent along with the request as metadata.

Returns

Response from BatchCreateChunks containing a list of created Chunks.

Return type

google.ai.generativelanguage_v1beta.types.BatchCreateChunksResponse

async batch_delete_chunks(request: Optional[Union[google.ai.generativelanguage_v1beta.types.retriever_service.BatchDeleteChunksRequest, dict]] = None, *, retry: Optional[Union[google.api_core.retry.retry_unary_async.AsyncRetry, google.api_core.gapic_v1.method._MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) None[source]

Batch delete Chunks.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.ai import generativelanguage_v1beta

async def sample_batch_delete_chunks():
    # Create a client
    client = generativelanguage_v1beta.RetrieverServiceAsyncClient()

    # Initialize request argument(s)
    requests = generativelanguage_v1beta.DeleteChunkRequest()
    requests.name = "name_value"

    request = generativelanguage_v1beta.BatchDeleteChunksRequest(
        requests=requests,
    )

    # Make the request
    await client.batch_delete_chunks(request=request)
Parameters
  • request (Optional[Union[google.ai.generativelanguage_v1beta.types.BatchDeleteChunksRequest, dict]]) – The request object. Request to batch delete Chunks.

  • retry (google.api_core.retry_async.AsyncRetry) – Designation of what errors, if any, should be retried.

  • timeout (float) – The timeout for this request.

  • metadata (Sequence[Tuple[str, str]]) – Strings which should be sent along with the request as metadata.

async batch_update_chunks(request: Optional[Union[google.ai.generativelanguage_v1beta.types.retriever_service.BatchUpdateChunksRequest, dict]] = None, *, retry: Optional[Union[google.api_core.retry.retry_unary_async.AsyncRetry, google.api_core.gapic_v1.method._MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) google.ai.generativelanguage_v1beta.types.retriever_service.BatchUpdateChunksResponse[source]

Batch update Chunks.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.ai import generativelanguage_v1beta

async def sample_batch_update_chunks():
    # Create a client
    client = generativelanguage_v1beta.RetrieverServiceAsyncClient()

    # Initialize request argument(s)
    requests = generativelanguage_v1beta.UpdateChunkRequest()
    requests.chunk.data.string_value = "string_value_value"

    request = generativelanguage_v1beta.BatchUpdateChunksRequest(
        requests=requests,
    )

    # Make the request
    response = await client.batch_update_chunks(request=request)

    # Handle the response
    print(response)
Parameters
  • request (Optional[Union[google.ai.generativelanguage_v1beta.types.BatchUpdateChunksRequest, dict]]) – The request object. Request to batch update Chunks.

  • retry (google.api_core.retry_async.AsyncRetry) – Designation of what errors, if any, should be retried.

  • timeout (float) – The timeout for this request.

  • metadata (Sequence[Tuple[str, str]]) – Strings which should be sent along with the request as metadata.

Returns

Response from BatchUpdateChunks containing a list of updated Chunks.

Return type

google.ai.generativelanguage_v1beta.types.BatchUpdateChunksResponse

static chunk_path(corpus: str, document: str, chunk: str) str

Returns a fully-qualified chunk string.

static common_billing_account_path(billing_account: str) str

Returns a fully-qualified billing_account string.

static common_folder_path(folder: str) str

Returns a fully-qualified folder string.

static common_location_path(project: str, location: str) str

Returns a fully-qualified location string.

static common_organization_path(organization: str) str

Returns a fully-qualified organization string.

static common_project_path(project: str) str

Returns a fully-qualified project string.

static corpus_path(corpus: str) str

Returns a fully-qualified corpus string.

async create_chunk(request: Optional[Union[google.ai.generativelanguage_v1beta.types.retriever_service.CreateChunkRequest, dict]] = None, *, parent: Optional[str] = None, chunk: Optional[google.ai.generativelanguage_v1beta.types.retriever.Chunk] = None, retry: Optional[Union[google.api_core.retry.retry_unary_async.AsyncRetry, google.api_core.gapic_v1.method._MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) google.ai.generativelanguage_v1beta.types.retriever.Chunk[source]

Creates a Chunk.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.ai import generativelanguage_v1beta

async def sample_create_chunk():
    # Create a client
    client = generativelanguage_v1beta.RetrieverServiceAsyncClient()

    # Initialize request argument(s)
    chunk = generativelanguage_v1beta.Chunk()
    chunk.data.string_value = "string_value_value"

    request = generativelanguage_v1beta.CreateChunkRequest(
        parent="parent_value",
        chunk=chunk,
    )

    # Make the request
    response = await client.create_chunk(request=request)

    # Handle the response
    print(response)
Parameters
  • request (Optional[Union[google.ai.generativelanguage_v1beta.types.CreateChunkRequest, dict]]) – The request object. Request to create a Chunk.

  • parent (str) –

    Required. The name of the Document where this Chunk will be created. Example: corpora/my-corpus-123/documents/the-doc-abc

    This corresponds to the parent field on the request instance; if request is provided, this should not be set.

  • chunk (google.ai.generativelanguage_v1beta.types.Chunk) – Required. The Chunk to create. This corresponds to the chunk field on the request instance; if request is provided, this should not be set.

  • retry (google.api_core.retry_async.AsyncRetry) – Designation of what errors, if any, should be retried.

  • timeout (float) – The timeout for this request.

  • metadata (Sequence[Tuple[str, str]]) – Strings which should be sent along with the request as metadata.

Returns

A Chunk is a subpart of a Document that is treated as an independent unit

for the purposes of vector representation and storage. A Corpus can have a maximum of 1 million Chunks.

Return type

google.ai.generativelanguage_v1beta.types.Chunk

async create_corpus(request: Optional[Union[google.ai.generativelanguage_v1beta.types.retriever_service.CreateCorpusRequest, dict]] = None, *, corpus: Optional[google.ai.generativelanguage_v1beta.types.retriever.Corpus] = None, retry: Optional[Union[google.api_core.retry.retry_unary_async.AsyncRetry, google.api_core.gapic_v1.method._MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) google.ai.generativelanguage_v1beta.types.retriever.Corpus[source]

Creates an empty Corpus.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.ai import generativelanguage_v1beta

async def sample_create_corpus():
    # Create a client
    client = generativelanguage_v1beta.RetrieverServiceAsyncClient()

    # Initialize request argument(s)
    request = generativelanguage_v1beta.CreateCorpusRequest(
    )

    # Make the request
    response = await client.create_corpus(request=request)

    # Handle the response
    print(response)
Parameters
Returns

A Corpus is a collection of Documents.

A project can create up to 5 corpora.

Return type

google.ai.generativelanguage_v1beta.types.Corpus

async create_document(request: Optional[Union[google.ai.generativelanguage_v1beta.types.retriever_service.CreateDocumentRequest, dict]] = None, *, parent: Optional[str] = None, document: Optional[google.ai.generativelanguage_v1beta.types.retriever.Document] = None, retry: Optional[Union[google.api_core.retry.retry_unary_async.AsyncRetry, google.api_core.gapic_v1.method._MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) google.ai.generativelanguage_v1beta.types.retriever.Document[source]

Creates an empty Document.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.ai import generativelanguage_v1beta

async def sample_create_document():
    # Create a client
    client = generativelanguage_v1beta.RetrieverServiceAsyncClient()

    # Initialize request argument(s)
    request = generativelanguage_v1beta.CreateDocumentRequest(
        parent="parent_value",
    )

    # Make the request
    response = await client.create_document(request=request)

    # Handle the response
    print(response)
Parameters
  • request (Optional[Union[google.ai.generativelanguage_v1beta.types.CreateDocumentRequest, dict]]) – The request object. Request to create a Document.

  • parent (str) –

    Required. The name of the Corpus where this Document will be created. Example: corpora/my-corpus-123

    This corresponds to the parent field on the request instance; if request is provided, this should not be set.

  • document (google.ai.generativelanguage_v1beta.types.Document) – Required. The Document to create. This corresponds to the document field on the request instance; if request is provided, this should not be set.

  • retry (google.api_core.retry_async.AsyncRetry) – Designation of what errors, if any, should be retried.

  • timeout (float) – The timeout for this request.

  • metadata (Sequence[Tuple[str, str]]) – Strings which should be sent along with the request as metadata.

Returns

A Document is a collection of Chunks.

A Corpus can have a maximum of 10,000 Documents.

Return type

google.ai.generativelanguage_v1beta.types.Document

async delete_chunk(request: Optional[Union[google.ai.generativelanguage_v1beta.types.retriever_service.DeleteChunkRequest, dict]] = None, *, name: Optional[str] = None, retry: Optional[Union[google.api_core.retry.retry_unary_async.AsyncRetry, google.api_core.gapic_v1.method._MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) None[source]

Deletes a Chunk.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.ai import generativelanguage_v1beta

async def sample_delete_chunk():
    # Create a client
    client = generativelanguage_v1beta.RetrieverServiceAsyncClient()

    # Initialize request argument(s)
    request = generativelanguage_v1beta.DeleteChunkRequest(
        name="name_value",
    )

    # Make the request
    await client.delete_chunk(request=request)
Parameters
  • request (Optional[Union[google.ai.generativelanguage_v1beta.types.DeleteChunkRequest, dict]]) – The request object. Request to delete a Chunk.

  • name (str) –

    Required. The resource name of the Chunk to delete. Example: corpora/my-corpus-123/documents/the-doc-abc/chunks/some-chunk

    This corresponds to the name field on the request instance; if request is provided, this should not be set.

  • retry (google.api_core.retry_async.AsyncRetry) – Designation of what errors, if any, should be retried.

  • timeout (float) – The timeout for this request.

  • metadata (Sequence[Tuple[str, str]]) – Strings which should be sent along with the request as metadata.

async delete_corpus(request: Optional[Union[google.ai.generativelanguage_v1beta.types.retriever_service.DeleteCorpusRequest, dict]] = None, *, name: Optional[str] = None, retry: Optional[Union[google.api_core.retry.retry_unary_async.AsyncRetry, google.api_core.gapic_v1.method._MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) None[source]

Deletes a Corpus.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.ai import generativelanguage_v1beta

async def sample_delete_corpus():
    # Create a client
    client = generativelanguage_v1beta.RetrieverServiceAsyncClient()

    # Initialize request argument(s)
    request = generativelanguage_v1beta.DeleteCorpusRequest(
        name="name_value",
    )

    # Make the request
    await client.delete_corpus(request=request)
Parameters
  • request (Optional[Union[google.ai.generativelanguage_v1beta.types.DeleteCorpusRequest, dict]]) – The request object. Request to delete a Corpus.

  • name (str) –

    Required. The resource name of the Corpus. Example: corpora/my-corpus-123

    This corresponds to the name field on the request instance; if request is provided, this should not be set.

  • retry (google.api_core.retry_async.AsyncRetry) – Designation of what errors, if any, should be retried.

  • timeout (float) – The timeout for this request.

  • metadata (Sequence[Tuple[str, str]]) – Strings which should be sent along with the request as metadata.

async delete_document(request: Optional[Union[google.ai.generativelanguage_v1beta.types.retriever_service.DeleteDocumentRequest, dict]] = None, *, name: Optional[str] = None, retry: Optional[Union[google.api_core.retry.retry_unary_async.AsyncRetry, google.api_core.gapic_v1.method._MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) None[source]

Deletes a Document.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.ai import generativelanguage_v1beta

async def sample_delete_document():
    # Create a client
    client = generativelanguage_v1beta.RetrieverServiceAsyncClient()

    # Initialize request argument(s)
    request = generativelanguage_v1beta.DeleteDocumentRequest(
        name="name_value",
    )

    # Make the request
    await client.delete_document(request=request)
Parameters
  • request (Optional[Union[google.ai.generativelanguage_v1beta.types.DeleteDocumentRequest, dict]]) – The request object. Request to delete a Document.

  • name (str) –

    Required. The resource name of the Document to delete. Example: corpora/my-corpus-123/documents/the-doc-abc

    This corresponds to the name field on the request instance; if request is provided, this should not be set.

  • retry (google.api_core.retry_async.AsyncRetry) – Designation of what errors, if any, should be retried.

  • timeout (float) – The timeout for this request.

  • metadata (Sequence[Tuple[str, str]]) – Strings which should be sent along with the request as metadata.

static document_path(corpus: str, document: str) str

Returns a fully-qualified document string.

classmethod from_service_account_file(filename: str, *args, **kwargs)[source]
Creates an instance of this client using the provided credentials

file.

Parameters
  • filename (str) – The path to the service account private key json file.

  • args – Additional arguments to pass to the constructor.

  • kwargs – Additional arguments to pass to the constructor.

Returns

The constructed client.

Return type

RetrieverServiceAsyncClient

classmethod from_service_account_info(info: dict, *args, **kwargs)[source]
Creates an instance of this client using the provided credentials

info.

Parameters
  • info (dict) – The service account private key info.

  • args – Additional arguments to pass to the constructor.

  • kwargs – Additional arguments to pass to the constructor.

Returns

The constructed client.

Return type

RetrieverServiceAsyncClient

classmethod from_service_account_json(filename: str, *args, **kwargs)
Creates an instance of this client using the provided credentials

file.

Parameters
  • filename (str) – The path to the service account private key json file.

  • args – Additional arguments to pass to the constructor.

  • kwargs – Additional arguments to pass to the constructor.

Returns

The constructed client.

Return type

RetrieverServiceAsyncClient

async get_chunk(request: Optional[Union[google.ai.generativelanguage_v1beta.types.retriever_service.GetChunkRequest, dict]] = None, *, name: Optional[str] = None, retry: Optional[Union[google.api_core.retry.retry_unary_async.AsyncRetry, google.api_core.gapic_v1.method._MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) google.ai.generativelanguage_v1beta.types.retriever.Chunk[source]

Gets information about a specific Chunk.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.ai import generativelanguage_v1beta

async def sample_get_chunk():
    # Create a client
    client = generativelanguage_v1beta.RetrieverServiceAsyncClient()

    # Initialize request argument(s)
    request = generativelanguage_v1beta.GetChunkRequest(
        name="name_value",
    )

    # Make the request
    response = await client.get_chunk(request=request)

    # Handle the response
    print(response)
Parameters
  • request (Optional[Union[google.ai.generativelanguage_v1beta.types.GetChunkRequest, dict]]) – The request object. Request for getting information about a specific Chunk.

  • name (str) –

    Required. The name of the Chunk to retrieve. Example: corpora/my-corpus-123/documents/the-doc-abc/chunks/some-chunk

    This corresponds to the name field on the request instance; if request is provided, this should not be set.

  • retry (google.api_core.retry_async.AsyncRetry) – Designation of what errors, if any, should be retried.

  • timeout (float) – The timeout for this request.

  • metadata (Sequence[Tuple[str, str]]) – Strings which should be sent along with the request as metadata.

Returns

A Chunk is a subpart of a Document that is treated as an independent unit

for the purposes of vector representation and storage. A Corpus can have a maximum of 1 million Chunks.

Return type

google.ai.generativelanguage_v1beta.types.Chunk

async get_corpus(request: Optional[Union[google.ai.generativelanguage_v1beta.types.retriever_service.GetCorpusRequest, dict]] = None, *, name: Optional[str] = None, retry: Optional[Union[google.api_core.retry.retry_unary_async.AsyncRetry, google.api_core.gapic_v1.method._MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) google.ai.generativelanguage_v1beta.types.retriever.Corpus[source]

Gets information about a specific Corpus.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.ai import generativelanguage_v1beta

async def sample_get_corpus():
    # Create a client
    client = generativelanguage_v1beta.RetrieverServiceAsyncClient()

    # Initialize request argument(s)
    request = generativelanguage_v1beta.GetCorpusRequest(
        name="name_value",
    )

    # Make the request
    response = await client.get_corpus(request=request)

    # Handle the response
    print(response)
Parameters
  • request (Optional[Union[google.ai.generativelanguage_v1beta.types.GetCorpusRequest, dict]]) – The request object. Request for getting information about a specific Corpus.

  • name (str) –

    Required. The name of the Corpus. Example: corpora/my-corpus-123

    This corresponds to the name field on the request instance; if request is provided, this should not be set.

  • retry (google.api_core.retry_async.AsyncRetry) – Designation of what errors, if any, should be retried.

  • timeout (float) – The timeout for this request.

  • metadata (Sequence[Tuple[str, str]]) – Strings which should be sent along with the request as metadata.

Returns

A Corpus is a collection of Documents.

A project can create up to 5 corpora.

Return type

google.ai.generativelanguage_v1beta.types.Corpus

async get_document(request: Optional[Union[google.ai.generativelanguage_v1beta.types.retriever_service.GetDocumentRequest, dict]] = None, *, name: Optional[str] = None, retry: Optional[Union[google.api_core.retry.retry_unary_async.AsyncRetry, google.api_core.gapic_v1.method._MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) google.ai.generativelanguage_v1beta.types.retriever.Document[source]

Gets information about a specific Document.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.ai import generativelanguage_v1beta

async def sample_get_document():
    # Create a client
    client = generativelanguage_v1beta.RetrieverServiceAsyncClient()

    # Initialize request argument(s)
    request = generativelanguage_v1beta.GetDocumentRequest(
        name="name_value",
    )

    # Make the request
    response = await client.get_document(request=request)

    # Handle the response
    print(response)
Parameters
  • request (Optional[Union[google.ai.generativelanguage_v1beta.types.GetDocumentRequest, dict]]) – The request object. Request for getting information about a specific Document.

  • name (str) –

    Required. The name of the Document to retrieve. Example: corpora/my-corpus-123/documents/the-doc-abc

    This corresponds to the name field on the request instance; if request is provided, this should not be set.

  • retry (google.api_core.retry_async.AsyncRetry) – Designation of what errors, if any, should be retried.

  • timeout (float) – The timeout for this request.

  • metadata (Sequence[Tuple[str, str]]) – Strings which should be sent along with the request as metadata.

Returns

A Document is a collection of Chunks.

A Corpus can have a maximum of 10,000 Documents.

Return type

google.ai.generativelanguage_v1beta.types.Document

classmethod get_mtls_endpoint_and_cert_source(client_options: Optional[google.api_core.client_options.ClientOptions] = None)[source]

Return the API endpoint and client cert source for mutual TLS.

The client cert source is determined in the following order: (1) if GOOGLE_API_USE_CLIENT_CERTIFICATE environment variable is not “true”, the client cert source is None. (2) if client_options.client_cert_source is provided, use the provided one; if the default client cert source exists, use the default one; otherwise the client cert source is None.

The API endpoint is determined in the following order: (1) if client_options.api_endpoint if provided, use the provided one. (2) if GOOGLE_API_USE_CLIENT_CERTIFICATE environment variable is “always”, use the default mTLS endpoint; if the environment variable is “never”, use the default API endpoint; otherwise if client cert source exists, use the default mTLS endpoint, otherwise use the default API endpoint.

More details can be found at https://google.aip.dev/auth/4114.

Parameters

client_options (google.api_core.client_options.ClientOptions) – Custom options for the client. Only the api_endpoint and client_cert_source properties may be used in this method.

Returns

returns the API endpoint and the

client cert source to use.

Return type

Tuple[str, Callable[[], Tuple[bytes, bytes]]]

Raises

google.auth.exceptions.MutualTLSChannelError – If any errors happen.

classmethod get_transport_class(label: Optional[str] = None) Type[google.ai.generativelanguage_v1beta.services.retriever_service.transports.base.RetrieverServiceTransport]

Returns an appropriate transport class.

Parameters

label – The name of the desired transport. If none is provided, then the first transport in the registry is used.

Returns

The transport class to use.

async list_chunks(request: Optional[Union[google.ai.generativelanguage_v1beta.types.retriever_service.ListChunksRequest, dict]] = None, *, parent: Optional[str] = None, retry: Optional[Union[google.api_core.retry.retry_unary_async.AsyncRetry, google.api_core.gapic_v1.method._MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) google.ai.generativelanguage_v1beta.services.retriever_service.pagers.ListChunksAsyncPager[source]

Lists all Chunks in a Document.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.ai import generativelanguage_v1beta

async def sample_list_chunks():
    # Create a client
    client = generativelanguage_v1beta.RetrieverServiceAsyncClient()

    # Initialize request argument(s)
    request = generativelanguage_v1beta.ListChunksRequest(
        parent="parent_value",
    )

    # Make the request
    page_result = client.list_chunks(request=request)

    # Handle the response
    async for response in page_result:
        print(response)
Parameters
  • request (Optional[Union[google.ai.generativelanguage_v1beta.types.ListChunksRequest, dict]]) – The request object. Request for listing Chunks.

  • parent (str) –

    Required. The name of the Document containing Chunks. Example: corpora/my-corpus-123/documents/the-doc-abc

    This corresponds to the parent field on the request instance; if request is provided, this should not be set.

  • retry (google.api_core.retry_async.AsyncRetry) – Designation of what errors, if any, should be retried.

  • timeout (float) – The timeout for this request.

  • metadata (Sequence[Tuple[str, str]]) – Strings which should be sent along with the request as metadata.

Returns

Response from ListChunks containing a paginated list of Chunks.

The Chunks are sorted by ascending chunk.create_time.

Iterating over this object will yield results and resolve additional pages automatically.

Return type

google.ai.generativelanguage_v1beta.services.retriever_service.pagers.ListChunksAsyncPager

async list_corpora(request: Optional[Union[google.ai.generativelanguage_v1beta.types.retriever_service.ListCorporaRequest, dict]] = None, *, retry: Optional[Union[google.api_core.retry.retry_unary_async.AsyncRetry, google.api_core.gapic_v1.method._MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) google.ai.generativelanguage_v1beta.services.retriever_service.pagers.ListCorporaAsyncPager[source]

Lists all Corpora owned by the user.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.ai import generativelanguage_v1beta

async def sample_list_corpora():
    # Create a client
    client = generativelanguage_v1beta.RetrieverServiceAsyncClient()

    # Initialize request argument(s)
    request = generativelanguage_v1beta.ListCorporaRequest(
    )

    # Make the request
    page_result = client.list_corpora(request=request)

    # Handle the response
    async for response in page_result:
        print(response)
Parameters
  • request (Optional[Union[google.ai.generativelanguage_v1beta.types.ListCorporaRequest, dict]]) – The request object. Request for listing Corpora.

  • retry (google.api_core.retry_async.AsyncRetry) – Designation of what errors, if any, should be retried.

  • timeout (float) – The timeout for this request.

  • metadata (Sequence[Tuple[str, str]]) – Strings which should be sent along with the request as metadata.

Returns

Response from ListCorpora containing a paginated list of Corpora.

The results are sorted by ascending corpus.create_time.

Iterating over this object will yield results and resolve additional pages automatically.

Return type

google.ai.generativelanguage_v1beta.services.retriever_service.pagers.ListCorporaAsyncPager

async list_documents(request: Optional[Union[google.ai.generativelanguage_v1beta.types.retriever_service.ListDocumentsRequest, dict]] = None, *, parent: Optional[str] = None, retry: Optional[Union[google.api_core.retry.retry_unary_async.AsyncRetry, google.api_core.gapic_v1.method._MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) google.ai.generativelanguage_v1beta.services.retriever_service.pagers.ListDocumentsAsyncPager[source]

Lists all Documents in a Corpus.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.ai import generativelanguage_v1beta

async def sample_list_documents():
    # Create a client
    client = generativelanguage_v1beta.RetrieverServiceAsyncClient()

    # Initialize request argument(s)
    request = generativelanguage_v1beta.ListDocumentsRequest(
        parent="parent_value",
    )

    # Make the request
    page_result = client.list_documents(request=request)

    # Handle the response
    async for response in page_result:
        print(response)
Parameters
  • request (Optional[Union[google.ai.generativelanguage_v1beta.types.ListDocumentsRequest, dict]]) – The request object. Request for listing Documents.

  • parent (str) –

    Required. The name of the Corpus containing Documents. Example: corpora/my-corpus-123

    This corresponds to the parent field on the request instance; if request is provided, this should not be set.

  • retry (google.api_core.retry_async.AsyncRetry) – Designation of what errors, if any, should be retried.

  • timeout (float) – The timeout for this request.

  • metadata (Sequence[Tuple[str, str]]) – Strings which should be sent along with the request as metadata.

Returns

Response from ListDocuments containing a paginated list of Documents.

The Documents are sorted by ascending document.create_time.

Iterating over this object will yield results and resolve additional pages automatically.

Return type

google.ai.generativelanguage_v1beta.services.retriever_service.pagers.ListDocumentsAsyncPager

static parse_chunk_path(path: str) Dict[str, str]

Parses a chunk path into its component segments.

static parse_common_billing_account_path(path: str) Dict[str, str]

Parse a billing_account path into its component segments.

static parse_common_folder_path(path: str) Dict[str, str]

Parse a folder path into its component segments.

static parse_common_location_path(path: str) Dict[str, str]

Parse a location path into its component segments.

static parse_common_organization_path(path: str) Dict[str, str]

Parse a organization path into its component segments.

static parse_common_project_path(path: str) Dict[str, str]

Parse a project path into its component segments.

static parse_corpus_path(path: str) Dict[str, str]

Parses a corpus path into its component segments.

static parse_document_path(path: str) Dict[str, str]

Parses a document path into its component segments.

async query_corpus(request: Optional[Union[google.ai.generativelanguage_v1beta.types.retriever_service.QueryCorpusRequest, dict]] = None, *, retry: Optional[Union[google.api_core.retry.retry_unary_async.AsyncRetry, google.api_core.gapic_v1.method._MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) google.ai.generativelanguage_v1beta.types.retriever_service.QueryCorpusResponse[source]

Performs semantic search over a Corpus.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.ai import generativelanguage_v1beta

async def sample_query_corpus():
    # Create a client
    client = generativelanguage_v1beta.RetrieverServiceAsyncClient()

    # Initialize request argument(s)
    request = generativelanguage_v1beta.QueryCorpusRequest(
        name="name_value",
        query="query_value",
    )

    # Make the request
    response = await client.query_corpus(request=request)

    # Handle the response
    print(response)
Parameters
  • request (Optional[Union[google.ai.generativelanguage_v1beta.types.QueryCorpusRequest, dict]]) – The request object. Request for querying a Corpus.

  • retry (google.api_core.retry_async.AsyncRetry) – Designation of what errors, if any, should be retried.

  • timeout (float) – The timeout for this request.

  • metadata (Sequence[Tuple[str, str]]) – Strings which should be sent along with the request as metadata.

Returns

Response from QueryCorpus containing a list of relevant chunks.

Return type

google.ai.generativelanguage_v1beta.types.QueryCorpusResponse

async query_document(request: Optional[Union[google.ai.generativelanguage_v1beta.types.retriever_service.QueryDocumentRequest, dict]] = None, *, retry: Optional[Union[google.api_core.retry.retry_unary_async.AsyncRetry, google.api_core.gapic_v1.method._MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) google.ai.generativelanguage_v1beta.types.retriever_service.QueryDocumentResponse[source]

Performs semantic search over a Document.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.ai import generativelanguage_v1beta

async def sample_query_document():
    # Create a client
    client = generativelanguage_v1beta.RetrieverServiceAsyncClient()

    # Initialize request argument(s)
    request = generativelanguage_v1beta.QueryDocumentRequest(
        name="name_value",
        query="query_value",
    )

    # Make the request
    response = await client.query_document(request=request)

    # Handle the response
    print(response)
Parameters
  • request (Optional[Union[google.ai.generativelanguage_v1beta.types.QueryDocumentRequest, dict]]) – The request object. Request for querying a Document.

  • retry (google.api_core.retry_async.AsyncRetry) – Designation of what errors, if any, should be retried.

  • timeout (float) – The timeout for this request.

  • metadata (Sequence[Tuple[str, str]]) – Strings which should be sent along with the request as metadata.

Returns

Response from QueryDocument containing a list of relevant chunks.

Return type

google.ai.generativelanguage_v1beta.types.QueryDocumentResponse

property transport: google.ai.generativelanguage_v1beta.services.retriever_service.transports.base.RetrieverServiceTransport

Returns the transport used by the client instance.

Returns

The transport used by the client instance.

Return type

RetrieverServiceTransport

property universe_domain: str

Return the universe domain used by the client instance.

Returns

The universe domain used

by the client instance.

Return type

str

async update_chunk(request: Optional[Union[google.ai.generativelanguage_v1beta.types.retriever_service.UpdateChunkRequest, dict]] = None, *, chunk: Optional[google.ai.generativelanguage_v1beta.types.retriever.Chunk] = None, update_mask: Optional[google.protobuf.field_mask_pb2.FieldMask] = None, retry: Optional[Union[google.api_core.retry.retry_unary_async.AsyncRetry, google.api_core.gapic_v1.method._MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) google.ai.generativelanguage_v1beta.types.retriever.Chunk[source]

Updates a Chunk.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.ai import generativelanguage_v1beta

async def sample_update_chunk():
    # Create a client
    client = generativelanguage_v1beta.RetrieverServiceAsyncClient()

    # Initialize request argument(s)
    chunk = generativelanguage_v1beta.Chunk()
    chunk.data.string_value = "string_value_value"

    request = generativelanguage_v1beta.UpdateChunkRequest(
        chunk=chunk,
    )

    # Make the request
    response = await client.update_chunk(request=request)

    # Handle the response
    print(response)
Parameters
  • request (Optional[Union[google.ai.generativelanguage_v1beta.types.UpdateChunkRequest, dict]]) – The request object. Request to update a Chunk.

  • chunk (google.ai.generativelanguage_v1beta.types.Chunk) – Required. The Chunk to update. This corresponds to the chunk field on the request instance; if request is provided, this should not be set.

  • update_mask (google.protobuf.field_mask_pb2.FieldMask) –

    Required. The list of fields to update. Currently, this only supports updating custom_metadata and data.

    This corresponds to the update_mask field on the request instance; if request is provided, this should not be set.

  • retry (google.api_core.retry_async.AsyncRetry) – Designation of what errors, if any, should be retried.

  • timeout (float) – The timeout for this request.

  • metadata (Sequence[Tuple[str, str]]) – Strings which should be sent along with the request as metadata.

Returns

A Chunk is a subpart of a Document that is treated as an independent unit

for the purposes of vector representation and storage. A Corpus can have a maximum of 1 million Chunks.

Return type

google.ai.generativelanguage_v1beta.types.Chunk

async update_corpus(request: Optional[Union[google.ai.generativelanguage_v1beta.types.retriever_service.UpdateCorpusRequest, dict]] = None, *, corpus: Optional[google.ai.generativelanguage_v1beta.types.retriever.Corpus] = None, update_mask: Optional[google.protobuf.field_mask_pb2.FieldMask] = None, retry: Optional[Union[google.api_core.retry.retry_unary_async.AsyncRetry, google.api_core.gapic_v1.method._MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) google.ai.generativelanguage_v1beta.types.retriever.Corpus[source]

Updates a Corpus.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.ai import generativelanguage_v1beta

async def sample_update_corpus():
    # Create a client
    client = generativelanguage_v1beta.RetrieverServiceAsyncClient()

    # Initialize request argument(s)
    request = generativelanguage_v1beta.UpdateCorpusRequest(
    )

    # Make the request
    response = await client.update_corpus(request=request)

    # Handle the response
    print(response)
Parameters
  • request (Optional[Union[google.ai.generativelanguage_v1beta.types.UpdateCorpusRequest, dict]]) – The request object. Request to update a Corpus.

  • corpus (google.ai.generativelanguage_v1beta.types.Corpus) – Required. The Corpus to update. This corresponds to the corpus field on the request instance; if request is provided, this should not be set.

  • update_mask (google.protobuf.field_mask_pb2.FieldMask) –

    Required. The list of fields to update. Currently, this only supports updating display_name.

    This corresponds to the update_mask field on the request instance; if request is provided, this should not be set.

  • retry (google.api_core.retry_async.AsyncRetry) – Designation of what errors, if any, should be retried.

  • timeout (float) – The timeout for this request.

  • metadata (Sequence[Tuple[str, str]]) – Strings which should be sent along with the request as metadata.

Returns

A Corpus is a collection of Documents.

A project can create up to 5 corpora.

Return type

google.ai.generativelanguage_v1beta.types.Corpus

async update_document(request: Optional[Union[google.ai.generativelanguage_v1beta.types.retriever_service.UpdateDocumentRequest, dict]] = None, *, document: Optional[google.ai.generativelanguage_v1beta.types.retriever.Document] = None, update_mask: Optional[google.protobuf.field_mask_pb2.FieldMask] = None, retry: Optional[Union[google.api_core.retry.retry_unary_async.AsyncRetry, google.api_core.gapic_v1.method._MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) google.ai.generativelanguage_v1beta.types.retriever.Document[source]

Updates a Document.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.ai import generativelanguage_v1beta

async def sample_update_document():
    # Create a client
    client = generativelanguage_v1beta.RetrieverServiceAsyncClient()

    # Initialize request argument(s)
    request = generativelanguage_v1beta.UpdateDocumentRequest(
    )

    # Make the request
    response = await client.update_document(request=request)

    # Handle the response
    print(response)
Parameters
  • request (Optional[Union[google.ai.generativelanguage_v1beta.types.UpdateDocumentRequest, dict]]) – The request object. Request to update a Document.

  • document (google.ai.generativelanguage_v1beta.types.Document) – Required. The Document to update. This corresponds to the document field on the request instance; if request is provided, this should not be set.

  • update_mask (google.protobuf.field_mask_pb2.FieldMask) –

    Required. The list of fields to update. Currently, this only supports updating display_name and custom_metadata.

    This corresponds to the update_mask field on the request instance; if request is provided, this should not be set.

  • retry (google.api_core.retry_async.AsyncRetry) – Designation of what errors, if any, should be retried.

  • timeout (float) – The timeout for this request.

  • metadata (Sequence[Tuple[str, str]]) – Strings which should be sent along with the request as metadata.

Returns

A Document is a collection of Chunks.

A Corpus can have a maximum of 10,000 Documents.

Return type

google.ai.generativelanguage_v1beta.types.Document

class google.ai.generativelanguage_v1beta.services.retriever_service.RetrieverServiceClient(*, credentials: typing.Optional[google.auth.credentials.Credentials] = None, transport: typing.Optional[typing.Union[str, google.ai.generativelanguage_v1beta.services.retriever_service.transports.base.RetrieverServiceTransport, typing.Callable[[...], google.ai.generativelanguage_v1beta.services.retriever_service.transports.base.RetrieverServiceTransport]]] = None, client_options: typing.Optional[typing.Union[google.api_core.client_options.ClientOptions, dict]] = None, client_info: google.api_core.gapic_v1.client_info.ClientInfo = <google.api_core.gapic_v1.client_info.ClientInfo object>)[source]

An API for semantic search over a corpus of user uploaded content.

Instantiates the retriever service client.

Parameters
  • credentials (Optional[google.auth.credentials.Credentials]) – The authorization credentials to attach to requests. These credentials identify the application to the service; if none are specified, the client will attempt to ascertain the credentials from the environment.

  • transport (Optional[Union[str,RetrieverServiceTransport,Callable[..., RetrieverServiceTransport]]]) – The transport to use, or a Callable that constructs and returns a new transport. If a Callable is given, it will be called with the same set of initialization arguments as used in the RetrieverServiceTransport constructor. If set to None, a transport is chosen automatically.

  • client_options (Optional[Union[google.api_core.client_options.ClientOptions, dict]]) –

    Custom options for the client.

    1. The api_endpoint property can be used to override the default endpoint provided by the client when transport is not explicitly provided. Only if this property is not set and transport was not explicitly provided, the endpoint is determined by the GOOGLE_API_USE_MTLS_ENDPOINT environment variable, which have one of the following values: “always” (always use the default mTLS endpoint), “never” (always use the default regular endpoint) and “auto” (auto-switch to the default mTLS endpoint if client certificate is present; this is the default value).

    2. If the GOOGLE_API_USE_CLIENT_CERTIFICATE environment variable is “true”, then the client_cert_source property can be used to provide a client certificate for mTLS transport. If not provided, the default SSL client certificate will be used if present. If GOOGLE_API_USE_CLIENT_CERTIFICATE is “false” or not set, no client certificate will be used.

    3. The universe_domain property can be used to override the default “googleapis.com” universe. Note that the api_endpoint property still takes precedence; and universe_domain is currently not supported for mTLS.

  • client_info (google.api_core.gapic_v1.client_info.ClientInfo) – The client info used to send a user-agent string along with API requests. If None, then default info will be used. Generally, you only need to set this if you’re developing your own client library.

Raises

google.auth.exceptions.MutualTLSChannelError – If mutual TLS transport creation failed for any reason.

__exit__(type, value, traceback)[source]

Releases underlying transport’s resources.

Warning

ONLY use as a context manager if the transport is NOT shared with other clients! Exiting the with block will CLOSE the transport and may cause errors in other clients!

property api_endpoint

Return the API endpoint used by the client instance.

Returns

The API endpoint used by the client instance.

Return type

str

batch_create_chunks(request: Optional[Union[google.ai.generativelanguage_v1beta.types.retriever_service.BatchCreateChunksRequest, dict]] = None, *, retry: Optional[Union[google.api_core.retry.retry_unary.Retry, google.api_core.gapic_v1.method._MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) google.ai.generativelanguage_v1beta.types.retriever_service.BatchCreateChunksResponse[source]

Batch create Chunks.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.ai import generativelanguage_v1beta

def sample_batch_create_chunks():
    # Create a client
    client = generativelanguage_v1beta.RetrieverServiceClient()

    # Initialize request argument(s)
    requests = generativelanguage_v1beta.CreateChunkRequest()
    requests.parent = "parent_value"
    requests.chunk.data.string_value = "string_value_value"

    request = generativelanguage_v1beta.BatchCreateChunksRequest(
        requests=requests,
    )

    # Make the request
    response = client.batch_create_chunks(request=request)

    # Handle the response
    print(response)
Parameters
Returns

Response from BatchCreateChunks containing a list of created Chunks.

Return type

google.ai.generativelanguage_v1beta.types.BatchCreateChunksResponse

batch_delete_chunks(request: Optional[Union[google.ai.generativelanguage_v1beta.types.retriever_service.BatchDeleteChunksRequest, dict]] = None, *, retry: Optional[Union[google.api_core.retry.retry_unary.Retry, google.api_core.gapic_v1.method._MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) None[source]

Batch delete Chunks.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.ai import generativelanguage_v1beta

def sample_batch_delete_chunks():
    # Create a client
    client = generativelanguage_v1beta.RetrieverServiceClient()

    # Initialize request argument(s)
    requests = generativelanguage_v1beta.DeleteChunkRequest()
    requests.name = "name_value"

    request = generativelanguage_v1beta.BatchDeleteChunksRequest(
        requests=requests,
    )

    # Make the request
    client.batch_delete_chunks(request=request)
Parameters
batch_update_chunks(request: Optional[Union[google.ai.generativelanguage_v1beta.types.retriever_service.BatchUpdateChunksRequest, dict]] = None, *, retry: Optional[Union[google.api_core.retry.retry_unary.Retry, google.api_core.gapic_v1.method._MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) google.ai.generativelanguage_v1beta.types.retriever_service.BatchUpdateChunksResponse[source]

Batch update Chunks.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.ai import generativelanguage_v1beta

def sample_batch_update_chunks():
    # Create a client
    client = generativelanguage_v1beta.RetrieverServiceClient()

    # Initialize request argument(s)
    requests = generativelanguage_v1beta.UpdateChunkRequest()
    requests.chunk.data.string_value = "string_value_value"

    request = generativelanguage_v1beta.BatchUpdateChunksRequest(
        requests=requests,
    )

    # Make the request
    response = client.batch_update_chunks(request=request)

    # Handle the response
    print(response)
Parameters
Returns

Response from BatchUpdateChunks containing a list of updated Chunks.

Return type

google.ai.generativelanguage_v1beta.types.BatchUpdateChunksResponse

static chunk_path(corpus: str, document: str, chunk: str) str[source]

Returns a fully-qualified chunk string.

static common_billing_account_path(billing_account: str) str[source]

Returns a fully-qualified billing_account string.

static common_folder_path(folder: str) str[source]

Returns a fully-qualified folder string.

static common_location_path(project: str, location: str) str[source]

Returns a fully-qualified location string.

static common_organization_path(organization: str) str[source]

Returns a fully-qualified organization string.

static common_project_path(project: str) str[source]

Returns a fully-qualified project string.

static corpus_path(corpus: str) str[source]

Returns a fully-qualified corpus string.

create_chunk(request: Optional[Union[google.ai.generativelanguage_v1beta.types.retriever_service.CreateChunkRequest, dict]] = None, *, parent: Optional[str] = None, chunk: Optional[google.ai.generativelanguage_v1beta.types.retriever.Chunk] = None, retry: Optional[Union[google.api_core.retry.retry_unary.Retry, google.api_core.gapic_v1.method._MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) google.ai.generativelanguage_v1beta.types.retriever.Chunk[source]

Creates a Chunk.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.ai import generativelanguage_v1beta

def sample_create_chunk():
    # Create a client
    client = generativelanguage_v1beta.RetrieverServiceClient()

    # Initialize request argument(s)
    chunk = generativelanguage_v1beta.Chunk()
    chunk.data.string_value = "string_value_value"

    request = generativelanguage_v1beta.CreateChunkRequest(
        parent="parent_value",
        chunk=chunk,
    )

    # Make the request
    response = client.create_chunk(request=request)

    # Handle the response
    print(response)
Parameters
  • request (Union[google.ai.generativelanguage_v1beta.types.CreateChunkRequest, dict]) – The request object. Request to create a Chunk.

  • parent (str) –

    Required. The name of the Document where this Chunk will be created. Example: corpora/my-corpus-123/documents/the-doc-abc

    This corresponds to the parent field on the request instance; if request is provided, this should not be set.

  • chunk (google.ai.generativelanguage_v1beta.types.Chunk) – Required. The Chunk to create. This corresponds to the chunk field on the request instance; if request is provided, this should not be set.

  • retry (google.api_core.retry.Retry) – Designation of what errors, if any, should be retried.

  • timeout (float) – The timeout for this request.

  • metadata (Sequence[Tuple[str, str]]) – Strings which should be sent along with the request as metadata.

Returns

A Chunk is a subpart of a Document that is treated as an independent unit

for the purposes of vector representation and storage. A Corpus can have a maximum of 1 million Chunks.

Return type

google.ai.generativelanguage_v1beta.types.Chunk

create_corpus(request: Optional[Union[google.ai.generativelanguage_v1beta.types.retriever_service.CreateCorpusRequest, dict]] = None, *, corpus: Optional[google.ai.generativelanguage_v1beta.types.retriever.Corpus] = None, retry: Optional[Union[google.api_core.retry.retry_unary.Retry, google.api_core.gapic_v1.method._MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) google.ai.generativelanguage_v1beta.types.retriever.Corpus[source]

Creates an empty Corpus.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.ai import generativelanguage_v1beta

def sample_create_corpus():
    # Create a client
    client = generativelanguage_v1beta.RetrieverServiceClient()

    # Initialize request argument(s)
    request = generativelanguage_v1beta.CreateCorpusRequest(
    )

    # Make the request
    response = client.create_corpus(request=request)

    # Handle the response
    print(response)
Parameters
Returns

A Corpus is a collection of Documents.

A project can create up to 5 corpora.

Return type

google.ai.generativelanguage_v1beta.types.Corpus

create_document(request: Optional[Union[google.ai.generativelanguage_v1beta.types.retriever_service.CreateDocumentRequest, dict]] = None, *, parent: Optional[str] = None, document: Optional[google.ai.generativelanguage_v1beta.types.retriever.Document] = None, retry: Optional[Union[google.api_core.retry.retry_unary.Retry, google.api_core.gapic_v1.method._MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) google.ai.generativelanguage_v1beta.types.retriever.Document[source]

Creates an empty Document.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.ai import generativelanguage_v1beta

def sample_create_document():
    # Create a client
    client = generativelanguage_v1beta.RetrieverServiceClient()

    # Initialize request argument(s)
    request = generativelanguage_v1beta.CreateDocumentRequest(
        parent="parent_value",
    )

    # Make the request
    response = client.create_document(request=request)

    # Handle the response
    print(response)
Parameters
  • request (Union[google.ai.generativelanguage_v1beta.types.CreateDocumentRequest, dict]) – The request object. Request to create a Document.

  • parent (str) –

    Required. The name of the Corpus where this Document will be created. Example: corpora/my-corpus-123

    This corresponds to the parent field on the request instance; if request is provided, this should not be set.

  • document (google.ai.generativelanguage_v1beta.types.Document) – Required. The Document to create. This corresponds to the document field on the request instance; if request is provided, this should not be set.

  • retry (google.api_core.retry.Retry) – Designation of what errors, if any, should be retried.

  • timeout (float) – The timeout for this request.

  • metadata (Sequence[Tuple[str, str]]) – Strings which should be sent along with the request as metadata.

Returns

A Document is a collection of Chunks.

A Corpus can have a maximum of 10,000 Documents.

Return type

google.ai.generativelanguage_v1beta.types.Document

delete_chunk(request: Optional[Union[google.ai.generativelanguage_v1beta.types.retriever_service.DeleteChunkRequest, dict]] = None, *, name: Optional[str] = None, retry: Optional[Union[google.api_core.retry.retry_unary.Retry, google.api_core.gapic_v1.method._MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) None[source]

Deletes a Chunk.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.ai import generativelanguage_v1beta

def sample_delete_chunk():
    # Create a client
    client = generativelanguage_v1beta.RetrieverServiceClient()

    # Initialize request argument(s)
    request = generativelanguage_v1beta.DeleteChunkRequest(
        name="name_value",
    )

    # Make the request
    client.delete_chunk(request=request)
Parameters
  • request (Union[google.ai.generativelanguage_v1beta.types.DeleteChunkRequest, dict]) – The request object. Request to delete a Chunk.

  • name (str) –

    Required. The resource name of the Chunk to delete. Example: corpora/my-corpus-123/documents/the-doc-abc/chunks/some-chunk

    This corresponds to the name field on the request instance; if request is provided, this should not be set.

  • retry (google.api_core.retry.Retry) – Designation of what errors, if any, should be retried.

  • timeout (float) – The timeout for this request.

  • metadata (Sequence[Tuple[str, str]]) – Strings which should be sent along with the request as metadata.

delete_corpus(request: Optional[Union[google.ai.generativelanguage_v1beta.types.retriever_service.DeleteCorpusRequest, dict]] = None, *, name: Optional[str] = None, retry: Optional[Union[google.api_core.retry.retry_unary.Retry, google.api_core.gapic_v1.method._MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) None[source]

Deletes a Corpus.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.ai import generativelanguage_v1beta

def sample_delete_corpus():
    # Create a client
    client = generativelanguage_v1beta.RetrieverServiceClient()

    # Initialize request argument(s)
    request = generativelanguage_v1beta.DeleteCorpusRequest(
        name="name_value",
    )

    # Make the request
    client.delete_corpus(request=request)
Parameters
  • request (Union[google.ai.generativelanguage_v1beta.types.DeleteCorpusRequest, dict]) – The request object. Request to delete a Corpus.

  • name (str) –

    Required. The resource name of the Corpus. Example: corpora/my-corpus-123

    This corresponds to the name field on the request instance; if request is provided, this should not be set.

  • retry (google.api_core.retry.Retry) – Designation of what errors, if any, should be retried.

  • timeout (float) – The timeout for this request.

  • metadata (Sequence[Tuple[str, str]]) – Strings which should be sent along with the request as metadata.

delete_document(request: Optional[Union[google.ai.generativelanguage_v1beta.types.retriever_service.DeleteDocumentRequest, dict]] = None, *, name: Optional[str] = None, retry: Optional[Union[google.api_core.retry.retry_unary.Retry, google.api_core.gapic_v1.method._MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) None[source]

Deletes a Document.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.ai import generativelanguage_v1beta

def sample_delete_document():
    # Create a client
    client = generativelanguage_v1beta.RetrieverServiceClient()

    # Initialize request argument(s)
    request = generativelanguage_v1beta.DeleteDocumentRequest(
        name="name_value",
    )

    # Make the request
    client.delete_document(request=request)
Parameters
  • request (Union[google.ai.generativelanguage_v1beta.types.DeleteDocumentRequest, dict]) – The request object. Request to delete a Document.

  • name (str) –

    Required. The resource name of the Document to delete. Example: corpora/my-corpus-123/documents/the-doc-abc

    This corresponds to the name field on the request instance; if request is provided, this should not be set.

  • retry (google.api_core.retry.Retry) – Designation of what errors, if any, should be retried.

  • timeout (float) – The timeout for this request.

  • metadata (Sequence[Tuple[str, str]]) – Strings which should be sent along with the request as metadata.

static document_path(corpus: str, document: str) str[source]

Returns a fully-qualified document string.

classmethod from_service_account_file(filename: str, *args, **kwargs)[source]
Creates an instance of this client using the provided credentials

file.

Parameters
  • filename (str) – The path to the service account private key json file.

  • args – Additional arguments to pass to the constructor.

  • kwargs – Additional arguments to pass to the constructor.

Returns

The constructed client.

Return type

RetrieverServiceClient

classmethod from_service_account_info(info: dict, *args, **kwargs)[source]
Creates an instance of this client using the provided credentials

info.

Parameters
  • info (dict) – The service account private key info.

  • args – Additional arguments to pass to the constructor.

  • kwargs – Additional arguments to pass to the constructor.

Returns

The constructed client.

Return type

RetrieverServiceClient

classmethod from_service_account_json(filename: str, *args, **kwargs)
Creates an instance of this client using the provided credentials

file.

Parameters
  • filename (str) – The path to the service account private key json file.

  • args – Additional arguments to pass to the constructor.

  • kwargs – Additional arguments to pass to the constructor.

Returns

The constructed client.

Return type

RetrieverServiceClient

get_chunk(request: Optional[Union[google.ai.generativelanguage_v1beta.types.retriever_service.GetChunkRequest, dict]] = None, *, name: Optional[str] = None, retry: Optional[Union[google.api_core.retry.retry_unary.Retry, google.api_core.gapic_v1.method._MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) google.ai.generativelanguage_v1beta.types.retriever.Chunk[source]

Gets information about a specific Chunk.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.ai import generativelanguage_v1beta

def sample_get_chunk():
    # Create a client
    client = generativelanguage_v1beta.RetrieverServiceClient()

    # Initialize request argument(s)
    request = generativelanguage_v1beta.GetChunkRequest(
        name="name_value",
    )

    # Make the request
    response = client.get_chunk(request=request)

    # Handle the response
    print(response)
Parameters
  • request (Union[google.ai.generativelanguage_v1beta.types.GetChunkRequest, dict]) – The request object. Request for getting information about a specific Chunk.

  • name (str) –

    Required. The name of the Chunk to retrieve. Example: corpora/my-corpus-123/documents/the-doc-abc/chunks/some-chunk

    This corresponds to the name field on the request instance; if request is provided, this should not be set.

  • retry (google.api_core.retry.Retry) – Designation of what errors, if any, should be retried.

  • timeout (float) – The timeout for this request.

  • metadata (Sequence[Tuple[str, str]]) – Strings which should be sent along with the request as metadata.

Returns

A Chunk is a subpart of a Document that is treated as an independent unit

for the purposes of vector representation and storage. A Corpus can have a maximum of 1 million Chunks.

Return type

google.ai.generativelanguage_v1beta.types.Chunk

get_corpus(request: Optional[Union[google.ai.generativelanguage_v1beta.types.retriever_service.GetCorpusRequest, dict]] = None, *, name: Optional[str] = None, retry: Optional[Union[google.api_core.retry.retry_unary.Retry, google.api_core.gapic_v1.method._MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) google.ai.generativelanguage_v1beta.types.retriever.Corpus[source]

Gets information about a specific Corpus.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.ai import generativelanguage_v1beta

def sample_get_corpus():
    # Create a client
    client = generativelanguage_v1beta.RetrieverServiceClient()

    # Initialize request argument(s)
    request = generativelanguage_v1beta.GetCorpusRequest(
        name="name_value",
    )

    # Make the request
    response = client.get_corpus(request=request)

    # Handle the response
    print(response)
Parameters
  • request (Union[google.ai.generativelanguage_v1beta.types.GetCorpusRequest, dict]) – The request object. Request for getting information about a specific Corpus.

  • name (str) –

    Required. The name of the Corpus. Example: corpora/my-corpus-123

    This corresponds to the name field on the request instance; if request is provided, this should not be set.

  • retry (google.api_core.retry.Retry) – Designation of what errors, if any, should be retried.

  • timeout (float) – The timeout for this request.

  • metadata (Sequence[Tuple[str, str]]) – Strings which should be sent along with the request as metadata.

Returns

A Corpus is a collection of Documents.

A project can create up to 5 corpora.

Return type

google.ai.generativelanguage_v1beta.types.Corpus

get_document(request: Optional[Union[google.ai.generativelanguage_v1beta.types.retriever_service.GetDocumentRequest, dict]] = None, *, name: Optional[str] = None, retry: Optional[Union[google.api_core.retry.retry_unary.Retry, google.api_core.gapic_v1.method._MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) google.ai.generativelanguage_v1beta.types.retriever.Document[source]

Gets information about a specific Document.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.ai import generativelanguage_v1beta

def sample_get_document():
    # Create a client
    client = generativelanguage_v1beta.RetrieverServiceClient()

    # Initialize request argument(s)
    request = generativelanguage_v1beta.GetDocumentRequest(
        name="name_value",
    )

    # Make the request
    response = client.get_document(request=request)

    # Handle the response
    print(response)
Parameters
  • request (Union[google.ai.generativelanguage_v1beta.types.GetDocumentRequest, dict]) – The request object. Request for getting information about a specific Document.

  • name (str) –

    Required. The name of the Document to retrieve. Example: corpora/my-corpus-123/documents/the-doc-abc

    This corresponds to the name field on the request instance; if request is provided, this should not be set.

  • retry (google.api_core.retry.Retry) – Designation of what errors, if any, should be retried.

  • timeout (float) – The timeout for this request.

  • metadata (Sequence[Tuple[str, str]]) – Strings which should be sent along with the request as metadata.

Returns

A Document is a collection of Chunks.

A Corpus can have a maximum of 10,000 Documents.

Return type

google.ai.generativelanguage_v1beta.types.Document

classmethod get_mtls_endpoint_and_cert_source(client_options: Optional[google.api_core.client_options.ClientOptions] = None)[source]

Deprecated. Return the API endpoint and client cert source for mutual TLS.

The client cert source is determined in the following order: (1) if GOOGLE_API_USE_CLIENT_CERTIFICATE environment variable is not “true”, the client cert source is None. (2) if client_options.client_cert_source is provided, use the provided one; if the default client cert source exists, use the default one; otherwise the client cert source is None.

The API endpoint is determined in the following order: (1) if client_options.api_endpoint if provided, use the provided one. (2) if GOOGLE_API_USE_CLIENT_CERTIFICATE environment variable is “always”, use the default mTLS endpoint; if the environment variable is “never”, use the default API endpoint; otherwise if client cert source exists, use the default mTLS endpoint, otherwise use the default API endpoint.

More details can be found at https://google.aip.dev/auth/4114.

Parameters

client_options (google.api_core.client_options.ClientOptions) – Custom options for the client. Only the api_endpoint and client_cert_source properties may be used in this method.

Returns

returns the API endpoint and the

client cert source to use.

Return type

Tuple[str, Callable[[], Tuple[bytes, bytes]]]

Raises

google.auth.exceptions.MutualTLSChannelError – If any errors happen.

list_chunks(request: Optional[Union[google.ai.generativelanguage_v1beta.types.retriever_service.ListChunksRequest, dict]] = None, *, parent: Optional[str] = None, retry: Optional[Union[google.api_core.retry.retry_unary.Retry, google.api_core.gapic_v1.method._MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) google.ai.generativelanguage_v1beta.services.retriever_service.pagers.ListChunksPager[source]

Lists all Chunks in a Document.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.ai import generativelanguage_v1beta

def sample_list_chunks():
    # Create a client
    client = generativelanguage_v1beta.RetrieverServiceClient()

    # Initialize request argument(s)
    request = generativelanguage_v1beta.ListChunksRequest(
        parent="parent_value",
    )

    # Make the request
    page_result = client.list_chunks(request=request)

    # Handle the response
    for response in page_result:
        print(response)
Parameters
  • request (Union[google.ai.generativelanguage_v1beta.types.ListChunksRequest, dict]) – The request object. Request for listing Chunks.

  • parent (str) –

    Required. The name of the Document containing Chunks. Example: corpora/my-corpus-123/documents/the-doc-abc

    This corresponds to the parent field on the request instance; if request is provided, this should not be set.

  • retry (google.api_core.retry.Retry) – Designation of what errors, if any, should be retried.

  • timeout (float) – The timeout for this request.

  • metadata (Sequence[Tuple[str, str]]) – Strings which should be sent along with the request as metadata.

Returns

Response from ListChunks containing a paginated list of Chunks.

The Chunks are sorted by ascending chunk.create_time.

Iterating over this object will yield results and resolve additional pages automatically.

Return type

google.ai.generativelanguage_v1beta.services.retriever_service.pagers.ListChunksPager

list_corpora(request: Optional[Union[google.ai.generativelanguage_v1beta.types.retriever_service.ListCorporaRequest, dict]] = None, *, retry: Optional[Union[google.api_core.retry.retry_unary.Retry, google.api_core.gapic_v1.method._MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) google.ai.generativelanguage_v1beta.services.retriever_service.pagers.ListCorporaPager[source]

Lists all Corpora owned by the user.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.ai import generativelanguage_v1beta

def sample_list_corpora():
    # Create a client
    client = generativelanguage_v1beta.RetrieverServiceClient()

    # Initialize request argument(s)
    request = generativelanguage_v1beta.ListCorporaRequest(
    )

    # Make the request
    page_result = client.list_corpora(request=request)

    # Handle the response
    for response in page_result:
        print(response)
Parameters
Returns

Response from ListCorpora containing a paginated list of Corpora.

The results are sorted by ascending corpus.create_time.

Iterating over this object will yield results and resolve additional pages automatically.

Return type

google.ai.generativelanguage_v1beta.services.retriever_service.pagers.ListCorporaPager

list_documents(request: Optional[Union[google.ai.generativelanguage_v1beta.types.retriever_service.ListDocumentsRequest, dict]] = None, *, parent: Optional[str] = None, retry: Optional[Union[google.api_core.retry.retry_unary.Retry, google.api_core.gapic_v1.method._MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) google.ai.generativelanguage_v1beta.services.retriever_service.pagers.ListDocumentsPager[source]

Lists all Documents in a Corpus.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.ai import generativelanguage_v1beta

def sample_list_documents():
    # Create a client
    client = generativelanguage_v1beta.RetrieverServiceClient()

    # Initialize request argument(s)
    request = generativelanguage_v1beta.ListDocumentsRequest(
        parent="parent_value",
    )

    # Make the request
    page_result = client.list_documents(request=request)

    # Handle the response
    for response in page_result:
        print(response)
Parameters
  • request (Union[google.ai.generativelanguage_v1beta.types.ListDocumentsRequest, dict]) – The request object. Request for listing Documents.

  • parent (str) –

    Required. The name of the Corpus containing Documents. Example: corpora/my-corpus-123

    This corresponds to the parent field on the request instance; if request is provided, this should not be set.

  • retry (google.api_core.retry.Retry) – Designation of what errors, if any, should be retried.

  • timeout (float) – The timeout for this request.

  • metadata (Sequence[Tuple[str, str]]) – Strings which should be sent along with the request as metadata.

Returns

Response from ListDocuments containing a paginated list of Documents.

The Documents are sorted by ascending document.create_time.

Iterating over this object will yield results and resolve additional pages automatically.

Return type

google.ai.generativelanguage_v1beta.services.retriever_service.pagers.ListDocumentsPager

static parse_chunk_path(path: str) Dict[str, str][source]

Parses a chunk path into its component segments.

static parse_common_billing_account_path(path: str) Dict[str, str][source]

Parse a billing_account path into its component segments.

static parse_common_folder_path(path: str) Dict[str, str][source]

Parse a folder path into its component segments.

static parse_common_location_path(path: str) Dict[str, str][source]

Parse a location path into its component segments.

static parse_common_organization_path(path: str) Dict[str, str][source]

Parse a organization path into its component segments.

static parse_common_project_path(path: str) Dict[str, str][source]

Parse a project path into its component segments.

static parse_corpus_path(path: str) Dict[str, str][source]

Parses a corpus path into its component segments.

static parse_document_path(path: str) Dict[str, str][source]

Parses a document path into its component segments.

query_corpus(request: Optional[Union[google.ai.generativelanguage_v1beta.types.retriever_service.QueryCorpusRequest, dict]] = None, *, retry: Optional[Union[google.api_core.retry.retry_unary.Retry, google.api_core.gapic_v1.method._MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) google.ai.generativelanguage_v1beta.types.retriever_service.QueryCorpusResponse[source]

Performs semantic search over a Corpus.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.ai import generativelanguage_v1beta

def sample_query_corpus():
    # Create a client
    client = generativelanguage_v1beta.RetrieverServiceClient()

    # Initialize request argument(s)
    request = generativelanguage_v1beta.QueryCorpusRequest(
        name="name_value",
        query="query_value",
    )

    # Make the request
    response = client.query_corpus(request=request)

    # Handle the response
    print(response)
Parameters
Returns

Response from QueryCorpus containing a list of relevant chunks.

Return type

google.ai.generativelanguage_v1beta.types.QueryCorpusResponse

query_document(request: Optional[Union[google.ai.generativelanguage_v1beta.types.retriever_service.QueryDocumentRequest, dict]] = None, *, retry: Optional[Union[google.api_core.retry.retry_unary.Retry, google.api_core.gapic_v1.method._MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) google.ai.generativelanguage_v1beta.types.retriever_service.QueryDocumentResponse[source]

Performs semantic search over a Document.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.ai import generativelanguage_v1beta

def sample_query_document():
    # Create a client
    client = generativelanguage_v1beta.RetrieverServiceClient()

    # Initialize request argument(s)
    request = generativelanguage_v1beta.QueryDocumentRequest(
        name="name_value",
        query="query_value",
    )

    # Make the request
    response = client.query_document(request=request)

    # Handle the response
    print(response)
Parameters
Returns

Response from QueryDocument containing a list of relevant chunks.

Return type

google.ai.generativelanguage_v1beta.types.QueryDocumentResponse

property transport: google.ai.generativelanguage_v1beta.services.retriever_service.transports.base.RetrieverServiceTransport

Returns the transport used by the client instance.

Returns

The transport used by the client

instance.

Return type

RetrieverServiceTransport

property universe_domain: str

Return the universe domain used by the client instance.

Returns

The universe domain used by the client instance.

Return type

str

update_chunk(request: Optional[Union[google.ai.generativelanguage_v1beta.types.retriever_service.UpdateChunkRequest, dict]] = None, *, chunk: Optional[google.ai.generativelanguage_v1beta.types.retriever.Chunk] = None, update_mask: Optional[google.protobuf.field_mask_pb2.FieldMask] = None, retry: Optional[Union[google.api_core.retry.retry_unary.Retry, google.api_core.gapic_v1.method._MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) google.ai.generativelanguage_v1beta.types.retriever.Chunk[source]

Updates a Chunk.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.ai import generativelanguage_v1beta

def sample_update_chunk():
    # Create a client
    client = generativelanguage_v1beta.RetrieverServiceClient()

    # Initialize request argument(s)
    chunk = generativelanguage_v1beta.Chunk()
    chunk.data.string_value = "string_value_value"

    request = generativelanguage_v1beta.UpdateChunkRequest(
        chunk=chunk,
    )

    # Make the request
    response = client.update_chunk(request=request)

    # Handle the response
    print(response)
Parameters
Returns

A Chunk is a subpart of a Document that is treated as an independent unit

for the purposes of vector representation and storage. A Corpus can have a maximum of 1 million Chunks.

Return type

google.ai.generativelanguage_v1beta.types.Chunk

update_corpus(request: Optional[Union[google.ai.generativelanguage_v1beta.types.retriever_service.UpdateCorpusRequest, dict]] = None, *, corpus: Optional[google.ai.generativelanguage_v1beta.types.retriever.Corpus] = None, update_mask: Optional[google.protobuf.field_mask_pb2.FieldMask] = None, retry: Optional[Union[google.api_core.retry.retry_unary.Retry, google.api_core.gapic_v1.method._MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) google.ai.generativelanguage_v1beta.types.retriever.Corpus[source]

Updates a Corpus.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.ai import generativelanguage_v1beta

def sample_update_corpus():
    # Create a client
    client = generativelanguage_v1beta.RetrieverServiceClient()

    # Initialize request argument(s)
    request = generativelanguage_v1beta.UpdateCorpusRequest(
    )

    # Make the request
    response = client.update_corpus(request=request)

    # Handle the response
    print(response)
Parameters
Returns

A Corpus is a collection of Documents.

A project can create up to 5 corpora.

Return type

google.ai.generativelanguage_v1beta.types.Corpus

update_document(request: Optional[Union[google.ai.generativelanguage_v1beta.types.retriever_service.UpdateDocumentRequest, dict]] = None, *, document: Optional[google.ai.generativelanguage_v1beta.types.retriever.Document] = None, update_mask: Optional[google.protobuf.field_mask_pb2.FieldMask] = None, retry: Optional[Union[google.api_core.retry.retry_unary.Retry, google.api_core.gapic_v1.method._MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ()) google.ai.generativelanguage_v1beta.types.retriever.Document[source]

Updates a Document.

# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
#   client as shown in:
#   https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.ai import generativelanguage_v1beta

def sample_update_document():
    # Create a client
    client = generativelanguage_v1beta.RetrieverServiceClient()

    # Initialize request argument(s)
    request = generativelanguage_v1beta.UpdateDocumentRequest(
    )

    # Make the request
    response = client.update_document(request=request)

    # Handle the response
    print(response)
Parameters
Returns

A Document is a collection of Chunks.

A Corpus can have a maximum of 10,000 Documents.

Return type

google.ai.generativelanguage_v1beta.types.Document

class google.ai.generativelanguage_v1beta.services.retriever_service.pagers.ListChunksAsyncPager(method: Callable[[...], Awaitable[google.ai.generativelanguage_v1beta.types.retriever_service.ListChunksResponse]], request: google.ai.generativelanguage_v1beta.types.retriever_service.ListChunksRequest, response: google.ai.generativelanguage_v1beta.types.retriever_service.ListChunksResponse, *, retry: Optional[Union[google.api_core.retry.retry_unary_async.AsyncRetry, google.api_core.gapic_v1.method._MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ())[source]

A pager for iterating through list_chunks requests.

This class thinly wraps an initial google.ai.generativelanguage_v1beta.types.ListChunksResponse object, and provides an __aiter__ method to iterate through its chunks field.

If there are more pages, the __aiter__ method will make additional ListChunks requests and continue to iterate through the chunks field on the corresponding responses.

All the usual google.ai.generativelanguage_v1beta.types.ListChunksResponse attributes are available on the pager. If multiple requests are made, only the most recent response is retained, and thus used for attribute lookup.

Instantiates the pager.

Parameters
class google.ai.generativelanguage_v1beta.services.retriever_service.pagers.ListChunksPager(method: Callable[[...], google.ai.generativelanguage_v1beta.types.retriever_service.ListChunksResponse], request: google.ai.generativelanguage_v1beta.types.retriever_service.ListChunksRequest, response: google.ai.generativelanguage_v1beta.types.retriever_service.ListChunksResponse, *, retry: Optional[Union[google.api_core.retry.retry_unary.Retry, google.api_core.gapic_v1.method._MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ())[source]

A pager for iterating through list_chunks requests.

This class thinly wraps an initial google.ai.generativelanguage_v1beta.types.ListChunksResponse object, and provides an __iter__ method to iterate through its chunks field.

If there are more pages, the __iter__ method will make additional ListChunks requests and continue to iterate through the chunks field on the corresponding responses.

All the usual google.ai.generativelanguage_v1beta.types.ListChunksResponse attributes are available on the pager. If multiple requests are made, only the most recent response is retained, and thus used for attribute lookup.

Instantiate the pager.

Parameters
class google.ai.generativelanguage_v1beta.services.retriever_service.pagers.ListCorporaAsyncPager(method: Callable[[...], Awaitable[google.ai.generativelanguage_v1beta.types.retriever_service.ListCorporaResponse]], request: google.ai.generativelanguage_v1beta.types.retriever_service.ListCorporaRequest, response: google.ai.generativelanguage_v1beta.types.retriever_service.ListCorporaResponse, *, retry: Optional[Union[google.api_core.retry.retry_unary_async.AsyncRetry, google.api_core.gapic_v1.method._MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ())[source]

A pager for iterating through list_corpora requests.

This class thinly wraps an initial google.ai.generativelanguage_v1beta.types.ListCorporaResponse object, and provides an __aiter__ method to iterate through its corpora field.

If there are more pages, the __aiter__ method will make additional ListCorpora requests and continue to iterate through the corpora field on the corresponding responses.

All the usual google.ai.generativelanguage_v1beta.types.ListCorporaResponse attributes are available on the pager. If multiple requests are made, only the most recent response is retained, and thus used for attribute lookup.

Instantiates the pager.

Parameters
class google.ai.generativelanguage_v1beta.services.retriever_service.pagers.ListCorporaPager(method: Callable[[...], google.ai.generativelanguage_v1beta.types.retriever_service.ListCorporaResponse], request: google.ai.generativelanguage_v1beta.types.retriever_service.ListCorporaRequest, response: google.ai.generativelanguage_v1beta.types.retriever_service.ListCorporaResponse, *, retry: Optional[Union[google.api_core.retry.retry_unary.Retry, google.api_core.gapic_v1.method._MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ())[source]

A pager for iterating through list_corpora requests.

This class thinly wraps an initial google.ai.generativelanguage_v1beta.types.ListCorporaResponse object, and provides an __iter__ method to iterate through its corpora field.

If there are more pages, the __iter__ method will make additional ListCorpora requests and continue to iterate through the corpora field on the corresponding responses.

All the usual google.ai.generativelanguage_v1beta.types.ListCorporaResponse attributes are available on the pager. If multiple requests are made, only the most recent response is retained, and thus used for attribute lookup.

Instantiate the pager.

Parameters
class google.ai.generativelanguage_v1beta.services.retriever_service.pagers.ListDocumentsAsyncPager(method: Callable[[...], Awaitable[google.ai.generativelanguage_v1beta.types.retriever_service.ListDocumentsResponse]], request: google.ai.generativelanguage_v1beta.types.retriever_service.ListDocumentsRequest, response: google.ai.generativelanguage_v1beta.types.retriever_service.ListDocumentsResponse, *, retry: Optional[Union[google.api_core.retry.retry_unary_async.AsyncRetry, google.api_core.gapic_v1.method._MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ())[source]

A pager for iterating through list_documents requests.

This class thinly wraps an initial google.ai.generativelanguage_v1beta.types.ListDocumentsResponse object, and provides an __aiter__ method to iterate through its documents field.

If there are more pages, the __aiter__ method will make additional ListDocuments requests and continue to iterate through the documents field on the corresponding responses.

All the usual google.ai.generativelanguage_v1beta.types.ListDocumentsResponse attributes are available on the pager. If multiple requests are made, only the most recent response is retained, and thus used for attribute lookup.

Instantiates the pager.

Parameters
class google.ai.generativelanguage_v1beta.services.retriever_service.pagers.ListDocumentsPager(method: Callable[[...], google.ai.generativelanguage_v1beta.types.retriever_service.ListDocumentsResponse], request: google.ai.generativelanguage_v1beta.types.retriever_service.ListDocumentsRequest, response: google.ai.generativelanguage_v1beta.types.retriever_service.ListDocumentsResponse, *, retry: Optional[Union[google.api_core.retry.retry_unary.Retry, google.api_core.gapic_v1.method._MethodDefault]] = _MethodDefault._DEFAULT_VALUE, timeout: Union[float, object] = _MethodDefault._DEFAULT_VALUE, metadata: Sequence[Tuple[str, str]] = ())[source]

A pager for iterating through list_documents requests.

This class thinly wraps an initial google.ai.generativelanguage_v1beta.types.ListDocumentsResponse object, and provides an __iter__ method to iterate through its documents field.

If there are more pages, the __iter__ method will make additional ListDocuments requests and continue to iterate through the documents field on the corresponding responses.

All the usual google.ai.generativelanguage_v1beta.types.ListDocumentsResponse attributes are available on the pager. If multiple requests are made, only the most recent response is retained, and thus used for attribute lookup.

Instantiate the pager.

Parameters