google.ai.generativelanguage.RetrieverServiceClient

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

google.ai.generativelanguage.RetrieverServiceClient(
    *,
    credentials: Optional[ga_credentials.Credentials] = None,
    transport: Optional[Union[str, RetrieverServiceTransport]] = None,
    client_options: Optional[Union[client_options_lib.ClientOptions, dict]] = None,
    client_info: gapic_v1.client_info.ClientInfo = DEFAULT_CLIENT_INFO
) -> None

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 Union[str, RetrieverServiceTransport]

The transport to use. 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. It won't take effect if a transport instance is provided. (1) The api_endpoint property can be used to override the default endpoint provided by the client. GOOGLE_API_USE_MTLS_ENDPOINT environment variable can also be used to override the endpoint: "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). However, the api_endpoint property takes precedence if provided. (2) If GOOGLE_API_USE_CLIENT_CERTIFICATE environment variable is "true", then the client_cert_source property can be used to provide client certificate for mutual TLS 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.

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.

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

transport Returns the transport used by the client instance.

Methods

batch_create_chunks

View source

batch_create_chunks(
    request: Optional[Union[google.ai.generativelanguage.BatchCreateChunksRequest, dict]] = None,
    *,
    retry: OptionalRetry = gapic_v1.method.DEFAULT,
    timeout: Union[float, object] = gapic_v1.method.DEFAULT,
    metadata: Sequence[Tuple[str, str]] = ()
) -> google.ai.generativelanguage.BatchCreateChunksResponse

Batch create Chunk\ s.

# 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:
#   <a href="https://googleapis.dev/python/google-api-core/latest/client_options.html">https://googleapis.dev/python/google-api-core/latest/client_options.html</a>
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)

Args
request Union[google.ai.generativelanguage.BatchCreateChunksRequest, dict]

The request object. Request to batch create Chunk\ s.

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
google.ai.generativelanguage.BatchCreateChunksResponse Response from BatchCreateChunks containing a list of created Chunks.

batch_delete_chunks

View source

batch_delete_chunks(
    request: Optional[Union[google.ai.generativelanguage.BatchDeleteChunksRequest, dict]] = None,
    *,
    retry: OptionalRetry = gapic_v1.method.DEFAULT,
    timeout: Union[float, object] = gapic_v1.method.DEFAULT,
    metadata: Sequence[Tuple[str, str]] = ()
) -> None

Batch delete Chunk\ s.

# 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:
#   <a href="https://googleapis.dev/python/google-api-core/latest/client_options.html">https://googleapis.dev/python/google-api-core/latest/client_options.html</a>
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)

Args
request Union[google.ai.generativelanguage.BatchDeleteChunksRequest, dict]

The request object. Request to batch delete Chunk\ s.

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.

batch_update_chunks

View source

batch_update_chunks(
    request: Optional[Union[google.ai.generativelanguage.BatchUpdateChunksRequest, dict]] = None,
    *,
    retry: OptionalRetry = gapic_v1.method.DEFAULT,
    timeout: Union[float, object] = gapic_v1.method.DEFAULT,
    metadata: Sequence[Tuple[str, str]] = ()
) -> google.ai.generativelanguage.BatchUpdateChunksResponse

Batch update Chunk\ s.

# 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:
#   <a href="https://googleapis.dev/python/google-api-core/latest/client_options.html">https://googleapis.dev/python/google-api-core/latest/client_options.html</a>
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)

Args
request Union[google.ai.generativelanguage.BatchUpdateChunksRequest, dict]

The request object. Request to batch update Chunk\ s.

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
google.ai.generativelanguage.BatchUpdateChunksResponse Response from BatchUpdateChunks containing a list of updated Chunks.

create_chunk

View source

create_chunk(
    request: Optional[Union[google.ai.generativelanguage.CreateChunkRequest, dict]] = None,
    *,
    parent: Optional[str] = None,
    chunk: Optional[google.ai.generativelanguage.Chunk] = None,
    retry: OptionalRetry = gapic_v1.method.DEFAULT,
    timeout: Union[float, object] = gapic_v1.method.DEFAULT,
    metadata: Sequence[Tuple[str, str]] = ()
) -> google.ai.generativelanguage.Chunk

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:
#   <a href="https://googleapis.dev/python/google-api-core/latest/client_options.html">https://googleapis.dev/python/google-api-core/latest/client_options.html</a>
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)

Args
request Union[google.ai.generativelanguage.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.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
google.ai.generativelanguage.Chunk 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.

create_corpus

View source

create_corpus(
    request: Optional[Union[google.ai.generativelanguage.CreateCorpusRequest, dict]] = None,
    *,
    corpus: Optional[google.ai.generativelanguage.Corpus] = None,
    retry: OptionalRetry = gapic_v1.method.DEFAULT,
    timeout: Union[float, object] = gapic_v1.method.DEFAULT,
    metadata: Sequence[Tuple[str, str]] = ()
) -> google.ai.generativelanguage.Corpus

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:
#   <a href="https://googleapis.dev/python/google-api-core/latest/client_options.html">https://googleapis.dev/python/google-api-core/latest/client_options.html</a>
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)

Args
request Union[google.ai.generativelanguage.CreateCorpusRequest, dict]

The request object. Request to create a Corpus.

corpus google.ai.generativelanguage.Corpus

Required. The Corpus to create. This corresponds to the corpus 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
google.ai.generativelanguage.Corpus A Corpus is a collection of Documents. A project can create up to 5 corpora.

create_document

View source

create_document(
    request: Optional[Union[google.ai.generativelanguage.CreateDocumentRequest, dict]] = None,
    *,
    parent: Optional[str] = None,
    document: Optional[google.ai.generativelanguage.Document] = None,
    retry: OptionalRetry = gapic_v1.method.DEFAULT,
    timeout: Union[float, object] = gapic_v1.method.DEFAULT,
    metadata: Sequence[Tuple[str, str]] = ()
) -> google.ai.generativelanguage.Document

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:
#   <a href="https://googleapis.dev/python/google-api-core/latest/client_options.html">https://googleapis.dev/python/google-api-core/latest/client_options.html</a>
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)

Args
request Union[google.ai.generativelanguage.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.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
google.ai.generativelanguage.Document A Document is a collection of Chunks. A Corpus can have a maximum of 10,000 Documents.

delete_chunk

View source

delete_chunk(
    request: Optional[Union[google.ai.generativelanguage.DeleteChunkRequest, dict]] = None,
    *,
    name: Optional[str] = None,
    retry: OptionalRetry = gapic_v1.method.DEFAULT,
    timeout: Union[float, object] = gapic_v1.method.DEFAULT,
    metadata: Sequence[Tuple[str, str]] = ()
) -> None

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:
#   <a href="https://googleapis.dev/python/google-api-core/latest/client_options.html">https://googleapis.dev/python/google-api-core/latest/client_options.html</a>
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)

Args
request Union[google.ai.generativelanguage.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

View source

delete_corpus(
    request: Optional[Union[google.ai.generativelanguage.DeleteCorpusRequest, dict]] = None,
    *,
    name: Optional[str] = None,
    retry: OptionalRetry = gapic_v1.method.DEFAULT,
    timeout: Union[float, object] = gapic_v1.method.DEFAULT,
    metadata: Sequence[Tuple[str, str]] = ()
) -> None

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:
#   <a href="https://googleapis.dev/python/google-api-core/latest/client_options.html">https://googleapis.dev/python/google-api-core/latest/client_options.html</a>
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)

Args
request Union[google.ai.generativelanguage.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

View source

delete_document(
    request: Optional[Union[google.ai.generativelanguage.DeleteDocumentRequest, dict]] = None,
    *,
    name: Optional[str] = None,
    retry: OptionalRetry = gapic_v1.method.DEFAULT,
    timeout: Union[float, object] = gapic_v1.method.DEFAULT,
    metadata: Sequence[Tuple[str, str]] = ()
) -> None

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:
#   <a href="https://googleapis.dev/python/google-api-core/latest/client_options.html">https://googleapis.dev/python/google-api-core/latest/client_options.html</a>
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)

Args
request Union[google.ai.generativelanguage.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.

from_service_account_file

View source

@classmethod
from_service_account_file(
    filename: str, *args, **kwargs
)

Creates an instance of this client using the provided credentials file.

Args
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
RetrieverServiceClient The constructed client.

from_service_account_info

View source

@classmethod
from_service_account_info(
    info: dict, *args, **kwargs
)

Creates an instance of this client using the provided credentials info.

Args
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
RetrieverServiceClient The constructed client.

from_service_account_json

View source

@classmethod
from_service_account_json(
    filename: str, *args, **kwargs
)

Creates an instance of this client using the provided credentials file.

Args
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
RetrieverServiceClient The constructed client.

get_chunk

View source

get_chunk(
    request: Optional[Union[google.ai.generativelanguage.GetChunkRequest, dict]] = None,
    *,
    name: Optional[str] = None,
    retry: OptionalRetry = gapic_v1.method.DEFAULT,
    timeout: Union[float, object] = gapic_v1.method.DEFAULT,
    metadata: Sequence[Tuple[str, str]] = ()
) -> google.ai.generativelanguage.Chunk

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:
#   <a href="https://googleapis.dev/python/google-api-core/latest/client_options.html">https://googleapis.dev/python/google-api-core/latest/client_options.html</a>
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)

Args
request Union[google.ai.generativelanguage.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
google.ai.generativelanguage.Chunk 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.

get_corpus

View source

get_corpus(
    request: Optional[Union[google.ai.generativelanguage.GetCorpusRequest, dict]] = None,
    *,
    name: Optional[str] = None,
    retry: OptionalRetry = gapic_v1.method.DEFAULT,
    timeout: Union[float, object] = gapic_v1.method.DEFAULT,
    metadata: Sequence[Tuple[str, str]] = ()
) -> google.ai.generativelanguage.Corpus

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:
#   <a href="https://googleapis.dev/python/google-api-core/latest/client_options.html">https://googleapis.dev/python/google-api-core/latest/client_options.html</a>
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)

Args
request Union[google.ai.generativelanguage.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
google.ai.generativelanguage.Corpus A Corpus is a collection of Documents. A project can create up to 5 corpora.

get_document

View source

get_document(
    request: Optional[Union[google.ai.generativelanguage.GetDocumentRequest, dict]] = None,
    *,
    name: Optional[str] = None,
    retry: OptionalRetry = gapic_v1.method.DEFAULT,
    timeout: Union[float, object] = gapic_v1.method.DEFAULT,
    metadata: Sequence[Tuple[str, str]] = ()
) -> google.ai.generativelanguage.Document

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:
#   <a href="https://googleapis.dev/python/google-api-core/latest/client_options.html">https://googleapis.dev/python/google-api-core/latest/client_options.html</a>
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)

Args
request Union[google.ai.generativelanguage.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
google.ai.generativelanguage.Document A Document is a collection of Chunks. A Corpus can have a maximum of 10,000 Documents.

get_mtls_endpoint_and_cert_source

View source

@classmethod
get_mtls_endpoint_and_cert_source(
    client_options: Optional[client_options_lib.ClientOptions] = None
)

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

Args
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
Tuple[str, Callable[[], Tuple[bytes, bytes]]]: returns the API endpoint and the client cert source to use.

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

list_chunks

View source

list_chunks(
    request: Optional[Union[google.ai.generativelanguage.ListChunksRequest, dict]] = None,
    *,
    parent: Optional[str] = None,
    retry: OptionalRetry = gapic_v1.method.DEFAULT,
    timeout: Union[float, object] = gapic_v1.method.DEFAULT,
    metadata: Sequence[Tuple[str, str]] = ()
) -> pagers.ListChunksPager

Lists all Chunk\ s 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:
#   <a href="https://googleapis.dev/python/google-api-core/latest/client_options.html">https://googleapis.dev/python/google-api-core/latest/client_options.html</a>
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)

Args
request Union[google.ai.generativelanguage.ListChunksRequest, dict]

The request object. Request for listing Chunk\ s.

parent str

Required. The name of the Document containing Chunk\ s. 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
google.ai.generativelanguage_v1beta.services.retriever_service.pagers.ListChunksPager 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.

list_corpora

View source

list_corpora(
    request: Optional[Union[google.ai.generativelanguage.ListCorporaRequest, dict]] = None,
    *,
    retry: OptionalRetry = gapic_v1.method.DEFAULT,
    timeout: Union[float, object] = gapic_v1.method.DEFAULT,
    metadata: Sequence[Tuple[str, str]] = ()
) -> pagers.ListCorporaPager

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:
#   <a href="https://googleapis.dev/python/google-api-core/latest/client_options.html">https://googleapis.dev/python/google-api-core/latest/client_options.html</a>
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)

Args
request Union[google.ai.generativelanguage.ListCorporaRequest, dict]

The request object. Request for listing Corpora.

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

list_documents

View source

list_documents(
    request: Optional[Union[google.ai.generativelanguage.ListDocumentsRequest, dict]] = None,
    *,
    parent: Optional[str] = None,
    retry: OptionalRetry = gapic_v1.method.DEFAULT,
    timeout: Union[float, object] = gapic_v1.method.DEFAULT,
    metadata: Sequence[Tuple[str, str]] = ()
) -> pagers.ListDocumentsPager

Lists all Document\ s 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:
#   <a href="https://googleapis.dev/python/google-api-core/latest/client_options.html">https://googleapis.dev/python/google-api-core/latest/client_options.html</a>
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)

Args
request Union[google.ai.generativelanguage.ListDocumentsRequest, dict]

The request object. Request for listing Document\ s.

parent str

Required. The name of the Corpus containing Document\ s. 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
google.ai.generativelanguage_v1beta.services.retriever_service.pagers.ListDocumentsPager 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.

query_corpus

View source

query_corpus(
    request: Optional[Union[google.ai.generativelanguage.QueryCorpusRequest, dict]] = None,
    *,
    retry: OptionalRetry = gapic_v1.method.DEFAULT,
    timeout: Union[float, object] = gapic_v1.method.DEFAULT,
    metadata: Sequence[Tuple[str, str]] = ()
) -> google.ai.generativelanguage.QueryCorpusResponse

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:
#   <a href="https://googleapis.dev/python/google-api-core/latest/client_options.html">https://googleapis.dev/python/google-api-core/latest/client_options.html</a>
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)

Args
request Union[google.ai.generativelanguage.QueryCorpusRequest, dict]

The request object. Request for querying a Corpus.

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
google.ai.generativelanguage.QueryCorpusResponse Response from QueryCorpus containing a list of relevant chunks.

query_document

View source

query_document(
    request: Optional[Union[google.ai.generativelanguage.QueryDocumentRequest, dict]] = None,
    *,
    retry: OptionalRetry = gapic_v1.method.DEFAULT,
    timeout: Union[float, object] = gapic_v1.method.DEFAULT,
    metadata: Sequence[Tuple[str, str]] = ()
) -> google.ai.generativelanguage.QueryDocumentResponse

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:
#   <a href="https://googleapis.dev/python/google-api-core/latest/client_options.html">https://googleapis.dev/python/google-api-core/latest/client_options.html</a>
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)

Args
request Union[google.ai.generativelanguage.QueryDocumentRequest, dict]

The request object. Request for querying a Document.

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
google.ai.generativelanguage.QueryDocumentResponse Response from QueryDocument containing a list of relevant chunks.

update_chunk

View source

update_chunk(
    request: Optional[Union[google.ai.generativelanguage.UpdateChunkRequest, dict]] = None,
    *,
    chunk: Optional[google.ai.generativelanguage.Chunk] = None,
    update_mask: Optional[field_mask_pb2.FieldMask] = None,
    retry: OptionalRetry = gapic_v1.method.DEFAULT,
    timeout: Union[float, object] = gapic_v1.method.DEFAULT,
    metadata: Sequence[Tuple[str, str]] = ()
) -> google.ai.generativelanguage.Chunk

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:
#   <a href="https://googleapis.dev/python/google-api-core/latest/client_options.html">https://googleapis.dev/python/google-api-core/latest/client_options.html</a>
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)

Args
request Union[google.ai.generativelanguage.UpdateChunkRequest, dict]

The request object. Request to update a Chunk.

chunk google.ai.generativelanguage.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.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
google.ai.generativelanguage.Chunk 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.

update_corpus

View source

update_corpus(
    request: Optional[Union[google.ai.generativelanguage.UpdateCorpusRequest, dict]] = None,
    *,
    corpus: Optional[google.ai.generativelanguage.Corpus] = None,
    update_mask: Optional[field_mask_pb2.FieldMask] = None,
    retry: OptionalRetry = gapic_v1.method.DEFAULT,
    timeout: Union[float, object] = gapic_v1.method.DEFAULT,
    metadata: Sequence[Tuple[str, str]] = ()
) -> google.ai.generativelanguage.Corpus

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:
#   <a href="https://googleapis.dev/python/google-api-core/latest/client_options.html">https://googleapis.dev/python/google-api-core/latest/client_options.html</a>
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)

Args
request Union[google.ai.generativelanguage.UpdateCorpusRequest, dict]

The request object. Request to update a Corpus.

corpus google.ai.generativelanguage.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.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
google.ai.generativelanguage.Corpus A Corpus is a collection of Documents. A project can create up to 5 corpora.

update_document

View source

update_document(
    request: Optional[Union[google.ai.generativelanguage.UpdateDocumentRequest, dict]] = None,
    *,
    document: Optional[google.ai.generativelanguage.Document] = None,
    update_mask: Optional[field_mask_pb2.FieldMask] = None,
    retry: OptionalRetry = gapic_v1.method.DEFAULT,
    timeout: Union[float, object] = gapic_v1.method.DEFAULT,
    metadata: Sequence[Tuple[str, str]] = ()
) -> google.ai.generativelanguage.Document

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:
#   <a href="https://googleapis.dev/python/google-api-core/latest/client_options.html">https://googleapis.dev/python/google-api-core/latest/client_options.html</a>
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)

Args
request Union[google.ai.generativelanguage.UpdateDocumentRequest, dict]

The request object. Request to update a Document.

document google.ai.generativelanguage.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.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
google.ai.generativelanguage.Document A Document is a collection of Chunks. A Corpus can have a maximum of 10,000 Documents.

__enter__

View source

__enter__() -> 'RetrieverServiceClient'

__exit__

View source

__exit__(
    type, value, traceback
)

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!

DEFAULT_ENDPOINT 'generativelanguage.googleapis.com'
DEFAULT_MTLS_ENDPOINT 'generativelanguage.mtls.googleapis.com'