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.

Types for Google Ai Generativelanguage v1beta API¶

class google.ai.generativelanguage_v1beta.types.AttributionSourceId(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Identifier for the source contributing to this attribution.

This message has oneof fields (mutually exclusive fields). For each oneof, at most one member field can be set at the same time. Setting any member of the oneof automatically clears all other members.

grounding_passage¶

Identifier for an inline passage.

This field is a member of oneof source.

Type: google.ai.generativelanguage_v1beta.types.AttributionSourceId.GroundingPassageId

semantic_retriever_chunk¶

Identifier for a Chunk fetched via Semantic Retriever.

This field is a member of oneof source.

Type: google.ai.generativelanguage_v1beta.types.AttributionSourceId.SemanticRetrieverChunk

class GroundingPassageId(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Identifier for a part within a GroundingPassage.

passage_id¶

Output only. ID of the passage matching the GenerateAnswerRequest’s GroundingPassage.id.

Type: str

part_index¶

Output only. Index of the part within the GenerateAnswerRequest’s GroundingPassage.content.

Type: int

class SemanticRetrieverChunk(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Identifier for a Chunk retrieved via Semantic Retriever specified in the GenerateAnswerRequest using SemanticRetrieverConfig.

source¶

Output only. Name of the source matching the request’s SemanticRetrieverConfig.source. Example: corpora/123 or corpora/123/documents/abc

Type: str

chunk¶

Output only. Name of the Chunk containing the attributed text. Example: corpora/123/documents/abc/chunks/xyz

Type: str

class google.ai.generativelanguage_v1beta.types.AudioTranscriptionConfig(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

The audio transcription configuration.

class google.ai.generativelanguage_v1beta.types.BatchCreateChunksRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Request to batch create Chunks.

parent¶

Optional. The name of the Document where this batch of Chunks will be created. The parent field in every CreateChunkRequest must match this value. Example: corpora/my-corpus-123/documents/the-doc-abc

Type: str

requests¶

Required. The request messages specifying the Chunks to create. A maximum of 100 Chunks can be created in a batch.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.CreateChunkRequest]

class google.ai.generativelanguage_v1beta.types.BatchCreateChunksResponse(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Response from BatchCreateChunks containing a list of created Chunks.

chunks¶

Chunks created.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.Chunk]

class google.ai.generativelanguage_v1beta.types.BatchDeleteChunksRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Request to batch delete Chunks.

parent¶

Optional. The name of the Document containing the Chunks to delete. The parent field in every DeleteChunkRequest must match this value. Example: corpora/my-corpus-123/documents/the-doc-abc

Type: str

requests¶

Required. The request messages specifying the Chunks to delete.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.DeleteChunkRequest]

class google.ai.generativelanguage_v1beta.types.BatchEmbedContentsRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Batch request to get embeddings from the model for a list of prompts.

model¶

Required. The model’s resource name. This serves as an ID for the Model to use.

This name should match a model name returned by the ListModels method.

Format: models/{model}

Type: str

requests¶

Required. Embed requests for the batch. The model in each of these requests must match the model specified BatchEmbedContentsRequest.model.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.EmbedContentRequest]

class google.ai.generativelanguage_v1beta.types.BatchEmbedContentsResponse(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

The response to a BatchEmbedContentsRequest.

embeddings¶

Output only. The embeddings for each request, in the same order as provided in the batch request.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.ContentEmbedding]

class google.ai.generativelanguage_v1beta.types.BatchEmbedTextRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Batch request to get a text embedding from the model.

model¶

Required. The name of the Model to use for generating the embedding. Examples: models/embedding-gecko-001

Type: str

texts¶

Optional. The free-form input texts that the model will turn into an embedding. The current limit is 100 texts, over which an error will be thrown.

Type: MutableSequence[str]

requests¶

Optional. Embed requests for the batch. Only one of texts or requests can be set.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.EmbedTextRequest]

class google.ai.generativelanguage_v1beta.types.BatchEmbedTextResponse(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

The response to a EmbedTextRequest.

embeddings¶

Output only. The embeddings generated from the input text.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.Embedding]

class google.ai.generativelanguage_v1beta.types.BatchUpdateChunksRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Request to batch update Chunks.

parent¶

Optional. The name of the Document containing the Chunks to update. The parent field in every UpdateChunkRequest must match this value. Example: corpora/my-corpus-123/documents/the-doc-abc

Type: str

requests¶

Required. The request messages specifying the Chunks to update. A maximum of 100 Chunks can be updated in a batch.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.UpdateChunkRequest]

class google.ai.generativelanguage_v1beta.types.BatchUpdateChunksResponse(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Response from BatchUpdateChunks containing a list of updated Chunks.

chunks¶

Chunks updated.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.Chunk]

class google.ai.generativelanguage_v1beta.types.BidiGenerateContentClientContent(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Incremental update of the current conversation delivered from the client. All of the content here is unconditionally appended to the conversation history and used as part of the prompt to the model to generate content.

A message here will interrupt any current model generation.

turns¶

Optional. The content appended to the current conversation with the model. For single-turn queries, this is a single instance. For multi-turn queries, this is a repeated field that contains conversation history and the latest request.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.Content]

turn_complete¶

Optional. If true, indicates that the server content generation should start with the currently accumulated prompt. Otherwise, the server awaits additional messages before starting generation.

Type: bool

class google.ai.generativelanguage_v1beta.types.BidiGenerateContentClientMessage(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Messages sent by the client in the BidiGenerateContent call.

This message has oneof fields (mutually exclusive fields). For each oneof, at most one member field can be set at the same time. Setting any member of the oneof automatically clears all other members.

setup¶

Optional. Session configuration sent only in the first client message.

This field is a member of oneof message_type.

Type: google.ai.generativelanguage_v1beta.types.BidiGenerateContentSetup

client_content¶

Optional. Incremental update of the current conversation delivered from the client.

This field is a member of oneof message_type.

Type: google.ai.generativelanguage_v1beta.types.BidiGenerateContentClientContent

realtime_input¶

Optional. User input that is sent in real time.

This field is a member of oneof message_type.

Type: google.ai.generativelanguage_v1beta.types.BidiGenerateContentRealtimeInput

tool_response¶

Optional. Response to a ToolCallMessage received from the server.

This field is a member of oneof message_type.

Type: google.ai.generativelanguage_v1beta.types.BidiGenerateContentToolResponse

class google.ai.generativelanguage_v1beta.types.BidiGenerateContentRealtimeInput(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

User input that is sent in real time.

The different modalities (audio, video and text) are handled as concurrent streams. The ordering across these streams is not guaranteed.

This is different from [BidiGenerateContentClientContent][google.ai.generativelanguage.v1beta.BidiGenerateContentClientContent] in a few ways:

Can be sent continuously without interruption to model generation.
If there is a need to mix data interleaved across the [BidiGenerateContentClientContent][google.ai.generativelanguage.v1beta.BidiGenerateContentClientContent] and the [BidiGenerateContentRealtimeInput][google.ai.generativelanguage.v1beta.BidiGenerateContentRealtimeInput], the server attempts to optimize for best response, but there are no guarantees.
End of turn is not explicitly specified, but is rather derived from user activity (for example, end of speech).
Even before the end of turn, the data is processed incrementally to optimize for a fast start of the response from the model.

media_chunks¶

Optional. Inlined bytes data for media input. Multiple media_chunks are not supported, all but the first will be ignored.

DEPRECATED: Use one of audio, video, or text instead.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.Blob]

audio¶

Optional. These form the realtime audio input stream.

Type: google.ai.generativelanguage_v1beta.types.Blob

audio_stream_end¶

Optional. Indicates that the audio stream has ended, e.g. because the microphone was turned off.

This should only be sent when automatic activity detection is enabled (which is the default).

The client can reopen the stream by sending an audio message.

This field is a member of oneof _audio_stream_end.

Type: bool

video¶

Optional. These form the realtime video input stream.

Type: google.ai.generativelanguage_v1beta.types.Blob

text¶

Optional. These form the realtime text input stream.

This field is a member of oneof _text.

Type: str

activity_start¶

Optional. Marks the start of user activity. This can only be sent if automatic (i.e. server-side) activity detection is disabled.

Type: google.ai.generativelanguage_v1beta.types.BidiGenerateContentRealtimeInput.ActivityStart

activity_end¶

Optional. Marks the end of user activity. This can only be sent if automatic (i.e. server-side) activity detection is disabled.

Type: google.ai.generativelanguage_v1beta.types.BidiGenerateContentRealtimeInput.ActivityEnd

class ActivityEnd(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Marks the end of user activity.

class ActivityStart(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Marks the start of user activity.

class google.ai.generativelanguage_v1beta.types.BidiGenerateContentServerContent(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Incremental server update generated by the model in response to client messages.

Content is generated as quickly as possible, and not in real time. Clients may choose to buffer and play it out in real time.

model_turn¶

Output only. The content that the model has generated as part of the current conversation with the user.

This field is a member of oneof _model_turn.

Type: google.ai.generativelanguage_v1beta.types.Content

generation_complete¶

Output only. If true, indicates that the model is done generating.

When model is interrupted while generating there will be no ‘generation_complete’ message in interrupted turn, it will go through ‘interrupted > turn_complete’.

When model assumes realtime playback there will be delay between generation_complete and turn_complete that is caused by model waiting for playback to finish.

Type: bool

turn_complete¶

Output only. If true, indicates that the model has completed its turn. Generation will only start in response to additional client messages.

Type: bool

interrupted¶

Output only. If true, indicates that a client message has interrupted current model generation. If the client is playing out the content in real time, this is a good signal to stop and empty the current playback queue.

Type: bool

grounding_metadata¶

Output only. Grounding metadata for the generated content.

Type: google.ai.generativelanguage_v1beta.types.GroundingMetadata

input_transcription¶

Output only. Input audio transcription. The transcription is sent independently of the other server messages and there is no guaranteed ordering.

Type: google.ai.generativelanguage_v1beta.types.BidiGenerateContentTranscription

output_transcription¶

Output only. Output audio transcription. These transcriptions are part of the Generation output of the server. The last output transcription of this turn is sent before either generation_complete or interrupted, which in turn are followed by turn_complete. There is no guaranteed exact ordering between transcriptions and other model_turn output but the server tries to send the transcripts close to the corresponding audio output.

Type: google.ai.generativelanguage_v1beta.types.BidiGenerateContentTranscription

url_context_metadata¶

Type: google.ai.generativelanguage_v1beta.types.UrlContextMetadata

waiting_for_input¶

Output only. If true, indicates that the model is not generating content because it is waiting for more input from the user, e.g. because it expects the user to continue talking.

Type: bool

class google.ai.generativelanguage_v1beta.types.BidiGenerateContentServerMessage(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Response message for the BidiGenerateContent call.

This message has oneof fields (mutually exclusive fields). For each oneof, at most one member field can be set at the same time. Setting any member of the oneof automatically clears all other members.

setup_complete¶

Output only. Sent in response to a BidiGenerateContentSetup message from the client when setup is complete.

This field is a member of oneof message_type.

Type: google.ai.generativelanguage_v1beta.types.BidiGenerateContentSetupComplete

server_content¶

Output only. Content generated by the model in response to client messages.

This field is a member of oneof message_type.

Type: google.ai.generativelanguage_v1beta.types.BidiGenerateContentServerContent

tool_call¶

Output only. Request for the client to execute the function_calls and return the responses with the matching ids.

This field is a member of oneof message_type.

Type: google.ai.generativelanguage_v1beta.types.BidiGenerateContentToolCall

tool_call_cancellation¶

Output only. Notification for the client that a previously issued ToolCallMessage with the specified ids should be cancelled.

This field is a member of oneof message_type.

Type: google.ai.generativelanguage_v1beta.types.BidiGenerateContentToolCallCancellation

go_away¶

Output only. A notice that the server will soon disconnect.

This field is a member of oneof message_type.

Type: google.ai.generativelanguage_v1beta.types.GoAway

session_resumption_update¶

Output only. Update of the session resumption state.

This field is a member of oneof message_type.

Type: google.ai.generativelanguage_v1beta.types.SessionResumptionUpdate

usage_metadata¶

Output only. Usage metadata about the response(s).

Type: google.ai.generativelanguage_v1beta.types.UsageMetadata

class google.ai.generativelanguage_v1beta.types.BidiGenerateContentSetup(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Message to be sent in the first (and only in the first) BidiGenerateContentClientMessage. Contains configuration that will apply for the duration of the streaming RPC.

Clients should wait for a BidiGenerateContentSetupComplete message before sending any additional messages.

model¶

Required. The model’s resource name. This serves as an ID for the Model to use.

Format: models/{model}

Type: str

generation_config¶

Optional. Generation config.

The following fields are not supported:

response_logprobs
response_mime_type
logprobs
response_schema
response_json_schema
stop_sequence
routing_config
audio_timestamp

Type: google.ai.generativelanguage_v1beta.types.GenerationConfig

system_instruction¶

Optional. The user provided system instructions for the model. Note: Only text should be used in parts and content in each part will be in a separate paragraph.

Type: google.ai.generativelanguage_v1beta.types.Content

tools¶

Optional. A list of Tools the model may use to generate the next response.

A Tool is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.Tool]

realtime_input_config¶

Optional. Configures the handling of realtime input.

Type: google.ai.generativelanguage_v1beta.types.RealtimeInputConfig

session_resumption¶

Optional. Configures session resumption mechanism.

If included, the server will send SessionResumptionUpdate messages.

Type: google.ai.generativelanguage_v1beta.types.SessionResumptionConfig

context_window_compression¶

Optional. Configures a context window compression mechanism. If included, the server will automatically reduce the size of the context when it exceeds the configured length.

Type: google.ai.generativelanguage_v1beta.types.ContextWindowCompressionConfig

input_audio_transcription¶

Optional. If set, enables transcription of voice input. The transcription aligns with the input audio language, if configured.

Type: google.ai.generativelanguage_v1beta.types.AudioTranscriptionConfig

output_audio_transcription¶

Optional. If set, enables transcription of the model’s audio output. The transcription aligns with the language code specified for the output audio, if configured.

Type: google.ai.generativelanguage_v1beta.types.AudioTranscriptionConfig

class google.ai.generativelanguage_v1beta.types.BidiGenerateContentSetupComplete(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Sent in response to a BidiGenerateContentSetup message from the client.

class google.ai.generativelanguage_v1beta.types.BidiGenerateContentToolCall(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Request for the client to execute the function_calls and return the responses with the matching ids.

function_calls¶

Output only. The function call to be executed.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.FunctionCall]

class google.ai.generativelanguage_v1beta.types.BidiGenerateContentToolCallCancellation(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Notification for the client that a previously issued ToolCallMessage with the specified ids should not have been executed and should be cancelled. If there were side-effects to those tool calls, clients may attempt to undo the tool calls. This message occurs only in cases where the clients interrupt server turns.

ids¶

Output only. The ids of the tool calls to be cancelled.

Type: MutableSequence[str]

class google.ai.generativelanguage_v1beta.types.BidiGenerateContentToolResponse(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Client generated response to a ToolCall received from the server. Individual FunctionResponse objects are matched to the respective FunctionCall objects by the id field.

Note that in the unary and server-streaming GenerateContent APIs function calling happens by exchanging the Content parts, while in the bidi GenerateContent APIs function calling happens over these dedicated set of messages.

function_responses¶

Optional. The response to the function calls.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.FunctionResponse]

class google.ai.generativelanguage_v1beta.types.BidiGenerateContentTranscription(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Transcription of audio (input or output).

text¶

Transcription text.

Type: str

class google.ai.generativelanguage_v1beta.types.Blob(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Raw media bytes.

Text should not be sent as raw bytes, use the ‘text’ field.

mime_type¶

The IANA standard MIME type of the source data. Examples:

image/png
image/jpeg If an unsupported MIME type is provided, an error will be returned. For a complete list of supported types, see Supported file formats.

Type: str

data¶

Raw bytes for media formats.

Type: bytes

class google.ai.generativelanguage_v1beta.types.CachedContent(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Content that has been preprocessed and can be used in subsequent request to GenerativeService.

Cached content can be only used with model it was created for.

This message has oneof fields (mutually exclusive fields). For each oneof, at most one member field can be set at the same time. Setting any member of the oneof automatically clears all other members.

expire_time¶

Timestamp in UTC of when this resource is considered expired. This is always provided on output, regardless of what was sent on input.

This field is a member of oneof expiration.

Type: google.protobuf.timestamp_pb2.Timestamp

ttl¶

Input only. New TTL for this resource, input only.

This field is a member of oneof expiration.

Type: google.protobuf.duration_pb2.Duration

name¶

Output only. Identifier. The resource name referring to the cached content. Format: cachedContents/{id}

This field is a member of oneof _name.

Type: str

display_name¶

Optional. Immutable. The user-generated meaningful display name of the cached content. Maximum 128 Unicode characters.

This field is a member of oneof _display_name.

Type: str

model¶

Required. Immutable. The name of the Model to use for cached content Format: models/{model}

This field is a member of oneof _model.

Type: str

system_instruction¶

Optional. Input only. Immutable. Developer set system instruction. Currently text only.

This field is a member of oneof _system_instruction.

Type: google.ai.generativelanguage_v1beta.types.Content

contents¶

Optional. Input only. Immutable. The content to cache.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.Content]

tools¶

Optional. Input only. Immutable. A list of Tools the model may use to generate the next response

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.Tool]

tool_config¶

Optional. Input only. Immutable. Tool config. This config is shared for all tools.

This field is a member of oneof _tool_config.

Type: google.ai.generativelanguage_v1beta.types.ToolConfig

create_time¶

Output only. Creation time of the cache entry.

Type: google.protobuf.timestamp_pb2.Timestamp

update_time¶

Output only. When the cache entry was last updated in UTC time.

Type: google.protobuf.timestamp_pb2.Timestamp

usage_metadata¶

Output only. Metadata on the usage of the cached content.

Type: google.ai.generativelanguage_v1beta.types.CachedContent.UsageMetadata

class UsageMetadata(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Metadata on the usage of the cached content.

total_token_count¶

Total number of tokens that the cached content consumes.

Type: int

class google.ai.generativelanguage_v1beta.types.Candidate(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

A response candidate generated from the model.

index¶

Output only. Index of the candidate in the list of response candidates.

This field is a member of oneof _index.

Type: int

content¶

Output only. Generated content returned from the model.

Type: google.ai.generativelanguage_v1beta.types.Content

finish_reason¶

Optional. Output only. The reason why the model stopped generating tokens. If empty, the model has not stopped generating tokens.

Type: google.ai.generativelanguage_v1beta.types.Candidate.FinishReason

finish_message¶

Optional. Output only. Details the reason why the model stopped generating tokens. This is populated only when finish_reason is set.

This field is a member of oneof _finish_message.

Type: str

safety_ratings¶

List of ratings for the safety of a response candidate. There is at most one rating per category.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.SafetyRating]

citation_metadata¶

Output only. Citation information for model-generated candidate.

This field may be populated with recitation information for any text included in the content. These are passages that are “recited” from copyrighted material in the foundational LLM’s training data.

Type: google.ai.generativelanguage_v1beta.types.CitationMetadata

token_count¶

Output only. Token count for this candidate.

Type: int

grounding_attributions¶

Output only. Attribution information for sources that contributed to a grounded answer.

This field is populated for GenerateAnswer calls.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.GroundingAttribution]

grounding_metadata¶

Output only. Grounding metadata for the candidate.

This field is populated for GenerateContent calls.

Type: google.ai.generativelanguage_v1beta.types.GroundingMetadata

avg_logprobs¶

Output only. Average log probability score of the candidate.

Type: float

logprobs_result¶

Output only. Log-likelihood scores for the response tokens and top tokens

Type: google.ai.generativelanguage_v1beta.types.LogprobsResult

url_context_metadata¶

Output only. Metadata related to url context retrieval tool.

Type: google.ai.generativelanguage_v1beta.types.UrlContextMetadata

class FinishReason(value)[source]¶

Bases: proto.enums.Enum

Defines the reason why the model stopped generating tokens.

Values:

FINISH_REASON_UNSPECIFIED (0):: Default value. This value is unused.
STOP (1):: Natural stop point of the model or provided stop sequence.
MAX_TOKENS (2):: The maximum number of tokens as specified in the request was reached.
SAFETY (3):: The response candidate content was flagged for safety reasons.
RECITATION (4):: The response candidate content was flagged for recitation reasons.
LANGUAGE (6):: The response candidate content was flagged for using an unsupported language.
OTHER (5):: Unknown reason.
BLOCKLIST (7):: Token generation stopped because the content contains forbidden terms.
PROHIBITED_CONTENT (8):: Token generation stopped for potentially containing prohibited content.
SPII (9):: Token generation stopped because the content potentially contains Sensitive Personally Identifiable Information (SPII).
MALFORMED_FUNCTION_CALL (10):: The function call generated by the model is invalid.
IMAGE_SAFETY (11):: Token generation stopped because generated images contain safety violations.
IMAGE_PROHIBITED_CONTENT (14):: Image generation stopped because generated images has other prohibited content.
IMAGE_OTHER (15):: Image generation stopped because of other miscellaneous issue.
NO_IMAGE (16):: The model was expected to generate an image, but none was generated.
IMAGE_RECITATION (17):: Image generation stopped due to recitation.
UNEXPECTED_TOOL_CALL (12):: Model generated a tool call but no tools were enabled in the request.
TOO_MANY_TOOL_CALLS (13):: Model called too many tools consecutively, thus the system exited execution.

class google.ai.generativelanguage_v1beta.types.Chunk(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

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.

name¶

Immutable. Identifier. The Chunk resource name. The ID (name excluding the “corpora//documents//chunks/” prefix) can contain up to 40 characters that are lowercase alphanumeric or dashes (-). The ID cannot start or end with a dash. If the name is empty on create, a random 12-character unique ID will be generated. Example: corpora/{corpus_id}/documents/{document_id}/chunks/123a456b789c

Type: str

data¶

Required. The content for the Chunk, such as the text string. The maximum number of tokens per chunk is 2043.

Type: google.ai.generativelanguage_v1beta.types.ChunkData

custom_metadata¶

Optional. User provided custom metadata stored as key-value pairs. The maximum number of CustomMetadata per chunk is 20.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.CustomMetadata]

create_time¶

Output only. The Timestamp of when the Chunk was created.

Type: google.protobuf.timestamp_pb2.Timestamp

update_time¶

Output only. The Timestamp of when the Chunk was last updated.

Type: google.protobuf.timestamp_pb2.Timestamp

state¶

Output only. Current state of the Chunk.

Type: google.ai.generativelanguage_v1beta.types.Chunk.State

class State(value)[source]¶

Bases: proto.enums.Enum

States for the lifecycle of a Chunk.

Values:

STATE_UNSPECIFIED (0):: The default value. This value is used if the state is omitted.
STATE_PENDING_PROCESSING (1):: Chunk is being processed (embedding and vector storage).
STATE_ACTIVE (2):: Chunk is processed and available for querying.
STATE_FAILED (10):: Chunk failed processing.

class google.ai.generativelanguage_v1beta.types.ChunkData(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Extracted data that represents the Chunk content.

string_value¶

The Chunk content as a string. The maximum number of tokens per chunk is 2043.

This field is a member of oneof data.

Type: str

class google.ai.generativelanguage_v1beta.types.CitationMetadata(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

A collection of source attributions for a piece of content.

citation_sources¶

Citations to sources for a specific response.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.CitationSource]

class google.ai.generativelanguage_v1beta.types.CitationSource(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

A citation to a source for a portion of a specific response.

start_index¶

Optional. Start of segment of the response that is attributed to this source.

Index indicates the start of the segment, measured in bytes.

This field is a member of oneof _start_index.

Type: int

end_index¶

Optional. End of the attributed segment, exclusive.

This field is a member of oneof _end_index.

Type: int

uri¶

Optional. URI that is attributed as a source for a portion of the text.

This field is a member of oneof _uri.

Type: str

license_¶

Optional. License for the GitHub project that is attributed as a source for segment.

License info is required for code citations.

This field is a member of oneof _license.

Type: str

class google.ai.generativelanguage_v1beta.types.CodeExecution(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Tool that executes code generated by the model, and automatically returns the result to the model.

See also ExecutableCode and CodeExecutionResult which are only generated when using this tool.

class google.ai.generativelanguage_v1beta.types.CodeExecutionResult(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Result of executing the ExecutableCode.

Only generated when using the CodeExecution, and always follows a part containing the ExecutableCode.

outcome¶

Required. Outcome of the code execution.

Type: google.ai.generativelanguage_v1beta.types.CodeExecutionResult.Outcome

output¶

Optional. Contains stdout when code execution is successful, stderr or other description otherwise.

Type: str

class Outcome(value)[source]¶

Bases: proto.enums.Enum

Enumeration of possible outcomes of the code execution.

Values:

OUTCOME_UNSPECIFIED (0):: Unspecified status. This value should not be used.
OUTCOME_OK (1):: Code execution completed successfully.
OUTCOME_FAILED (2):: Code execution finished but with a failure. stderr should contain the reason.
OUTCOME_DEADLINE_EXCEEDED (3):: Code execution ran for too long, and was cancelled. There may or may not be a partial output present.

class google.ai.generativelanguage_v1beta.types.Condition(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Filter condition applicable to a single key.

This message has oneof fields (mutually exclusive fields). For each oneof, at most one member field can be set at the same time. Setting any member of the oneof automatically clears all other members.

string_value¶

The string value to filter the metadata on.

This field is a member of oneof value.

Type: str

numeric_value¶

The numeric value to filter the metadata on.

This field is a member of oneof value.

Type: float

operation¶

Required. Operator applied to the given key-value pair to trigger the condition.

Type: google.ai.generativelanguage_v1beta.types.Condition.Operator

class Operator(value)[source]¶

Bases: proto.enums.Enum

Defines the valid operators that can be applied to a key-value pair.

Values:

OPERATOR_UNSPECIFIED (0):: The default value. This value is unused.
LESS (1):: Supported by numeric.
LESS_EQUAL (2):: Supported by numeric.
EQUAL (3):: Supported by numeric & string.
GREATER_EQUAL (4):: Supported by numeric.
GREATER (5):: Supported by numeric.
NOT_EQUAL (6):: Supported by numeric & string.
INCLUDES (7):: Supported by string only when CustomMetadata value type for the given key has a string_list_value.
EXCLUDES (8):: Supported by string only when CustomMetadata value type for the given key has a string_list_value.

class google.ai.generativelanguage_v1beta.types.Content(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

The base structured datatype containing multi-part content of a message.

A Content includes a role field designating the producer of the Content and a parts field containing multi-part data that contains the content of the message turn.

parts¶

Ordered Parts that constitute a single message. Parts may have different MIME types.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.Part]

role¶

Optional. The producer of the content. Must be either ‘user’ or ‘model’. Useful to set for multi-turn conversations, otherwise can be left blank or unset.

Type: str

class google.ai.generativelanguage_v1beta.types.ContentEmbedding(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

A list of floats representing an embedding.

values¶

The embedding values.

Type: MutableSequence[float]

class google.ai.generativelanguage_v1beta.types.ContentFilter(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Content filtering metadata associated with processing a single request. ContentFilter contains a reason and an optional supporting string. The reason may be unspecified.

reason¶

The reason content was blocked during request processing.

Type: google.ai.generativelanguage_v1beta.types.ContentFilter.BlockedReason

message¶

A string that describes the filtering behavior in more detail.

This field is a member of oneof _message.

Type: str

class BlockedReason(value)[source]¶

Bases: proto.enums.Enum

A list of reasons why content may have been blocked.

Values:

BLOCKED_REASON_UNSPECIFIED (0):: A blocked reason was not specified.
SAFETY (1):: Content was blocked by safety settings.
OTHER (2):: Content was blocked, but the reason is uncategorized.

class google.ai.generativelanguage_v1beta.types.ContextWindowCompressionConfig(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Enables context window compression — a mechanism for managing the model’s context window so that it does not exceed a given length.

sliding_window¶

A sliding-window mechanism.

This field is a member of oneof compression_mechanism.

Type: google.ai.generativelanguage_v1beta.types.ContextWindowCompressionConfig.SlidingWindow

trigger_tokens¶

The number of tokens (before running a turn) required to trigger a context window compression.

This can be used to balance quality against latency as shorter context windows may result in faster model responses. However, any compression operation will cause a temporary latency increase, so they should not be triggered frequently.

If not set, the default is 80% of the model’s context window limit. This leaves 20% for the next user request/model response.

This field is a member of oneof _trigger_tokens.

Type: int

class SlidingWindow(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

The SlidingWindow method operates by discarding content at the beginning of the context window. The resulting context will always begin at the start of a USER role turn. System instructions and any BidiGenerateContentSetup.prefix_turns will always remain at the beginning of the result.

target_tokens¶

The target number of tokens to keep. The default value is trigger_tokens/2.

Discarding parts of the context window causes a temporary latency increase so this value should be calibrated to avoid frequent compression operations.

This field is a member of oneof _target_tokens.

Type: int

class google.ai.generativelanguage_v1beta.types.Corpus(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

A Corpus is a collection of Documents. A project can create up to 5 corpora.

name¶

Immutable. Identifier. The Corpus resource name. The ID (name excluding the “corpora/” prefix) can contain up to 40 characters that are lowercase alphanumeric or dashes (-). The ID cannot start or end with a dash. If the name is empty on create, a unique name will be derived from display_name along with a 12 character random suffix. Example: corpora/my-awesome-corpora-123a456b789c

Type: str

display_name¶

Optional. The human-readable display name for the Corpus. The display name must be no more than 512 characters in length, including spaces. Example: “Docs on Semantic Retriever”.

Type: str

create_time¶

Output only. The Timestamp of when the Corpus was created.

Type: google.protobuf.timestamp_pb2.Timestamp

update_time¶

Output only. The Timestamp of when the Corpus was last updated.

Type: google.protobuf.timestamp_pb2.Timestamp

class google.ai.generativelanguage_v1beta.types.CountMessageTokensRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Counts the number of tokens in the prompt sent to a model.

Models may tokenize text differently, so each model may return a different token_count.

model¶

Required. The model’s resource name. This serves as an ID for the Model to use.

This name should match a model name returned by the ListModels method.

Format: models/{model}

Type: str

prompt¶

Required. The prompt, whose token count is to be returned.

Type: google.ai.generativelanguage_v1beta.types.MessagePrompt

class google.ai.generativelanguage_v1beta.types.CountMessageTokensResponse(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

A response from CountMessageTokens.

It returns the model’s token_count for the prompt.

token_count¶

The number of tokens that the model tokenizes the prompt into.

Always non-negative.

Type: int

class google.ai.generativelanguage_v1beta.types.CountTextTokensRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Counts the number of tokens in the prompt sent to a model.

Models may tokenize text differently, so each model may return a different token_count.

model¶

Required. The model’s resource name. This serves as an ID for the Model to use.

This name should match a model name returned by the ListModels method.

Format: models/{model}

Type: str

prompt¶

Required. The free-form input text given to the model as a prompt.

Type: google.ai.generativelanguage_v1beta.types.TextPrompt

class google.ai.generativelanguage_v1beta.types.CountTextTokensResponse(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

A response from CountTextTokens.

It returns the model’s token_count for the prompt.

token_count¶

The number of tokens that the model tokenizes the prompt into.

Always non-negative.

Type: int

class google.ai.generativelanguage_v1beta.types.CountTokensRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Counts the number of tokens in the prompt sent to a model.

Models may tokenize text differently, so each model may return a different token_count.

model¶

Required. The model’s resource name. This serves as an ID for the Model to use.

This name should match a model name returned by the ListModels method.

Format: models/{model}

Type: str

contents¶

Optional. The input given to the model as a prompt. This field is ignored when generate_content_request is set.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.Content]

generate_content_request¶

Optional. The overall input given to the Model. This includes the prompt as well as other model steering information like system instructions, and/or function declarations for function calling. Models/Contents and generate_content_requests are mutually exclusive. You can either send Model + Contents or a generate_content_request, but never both.

Type: google.ai.generativelanguage_v1beta.types.GenerateContentRequest

class google.ai.generativelanguage_v1beta.types.CountTokensResponse(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

A response from CountTokens.

It returns the model’s token_count for the prompt.

total_tokens¶

The number of tokens that the Model tokenizes the prompt into. Always non-negative.

Type: int

cached_content_token_count¶

Number of tokens in the cached part of the prompt (the cached content).

Type: int

prompt_tokens_details¶

Output only. List of modalities that were processed in the request input.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.ModalityTokenCount]

cache_tokens_details¶

Output only. List of modalities that were processed in the cached content.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.ModalityTokenCount]

class google.ai.generativelanguage_v1beta.types.CreateCachedContentRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Request to create CachedContent.

cached_content¶

Required. The cached content to create.

Type: google.ai.generativelanguage_v1beta.types.CachedContent

class google.ai.generativelanguage_v1beta.types.CreateChunkRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Request to create a Chunk.

parent¶

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

Type: str

chunk¶

Required. The Chunk to create.

Type: google.ai.generativelanguage_v1beta.types.Chunk

class google.ai.generativelanguage_v1beta.types.CreateCorpusRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Request to create a Corpus.

corpus¶

Required. The Corpus to create.

Type: google.ai.generativelanguage_v1beta.types.Corpus

class google.ai.generativelanguage_v1beta.types.CreateDocumentRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Request to create a Document.

parent¶

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

Type: str

document¶

Required. The Document to create.

Type: google.ai.generativelanguage_v1beta.types.Document

class google.ai.generativelanguage_v1beta.types.CreateFileRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Request for CreateFile.

file¶

Optional. Metadata for the file to create.

Type: google.ai.generativelanguage_v1beta.types.File

class google.ai.generativelanguage_v1beta.types.CreateFileResponse(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Response for CreateFile.

file¶

Metadata for the created file.

Type: google.ai.generativelanguage_v1beta.types.File

class google.ai.generativelanguage_v1beta.types.CreatePermissionRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Request to create a Permission.

parent¶

Required. The parent resource of the Permission. Formats: tunedModels/{tuned_model} corpora/{corpus}

Type: str

permission¶

Required. The permission to create.

Type: google.ai.generativelanguage_v1beta.types.Permission

class google.ai.generativelanguage_v1beta.types.CreateTunedModelMetadata(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Metadata about the state and progress of creating a tuned model returned from the long-running operation

tuned_model¶

Name of the tuned model associated with the tuning operation.

Type: str

total_steps¶

The total number of tuning steps.

Type: int

completed_steps¶

The number of steps completed.

Type: int

completed_percent¶

The completed percentage for the tuning operation.

Type: float

snapshots¶

Metrics collected during tuning.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.TuningSnapshot]

class google.ai.generativelanguage_v1beta.types.CreateTunedModelRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Request to create a TunedModel.

tuned_model_id¶

Optional. The unique id for the tuned model if specified. This value should be up to 40 characters, the first character must be a letter, the last could be a letter or a number. The id must match the regular expression: [a-z]([a-z0-9-]{0,38}[a-z0-9])?.

This field is a member of oneof _tuned_model_id.

Type: str

tuned_model¶

Required. The tuned model to create.

Type: google.ai.generativelanguage_v1beta.types.TunedModel

class google.ai.generativelanguage_v1beta.types.CustomMetadata(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

User provided metadata stored as key-value pairs.

This message has oneof fields (mutually exclusive fields). For each oneof, at most one member field can be set at the same time. Setting any member of the oneof automatically clears all other members.

string_value¶

The string value of the metadata to store.

This field is a member of oneof value.

Type: str

string_list_value¶

The StringList value of the metadata to store.

This field is a member of oneof value.

Type: google.ai.generativelanguage_v1beta.types.StringList

numeric_value¶

The numeric value of the metadata to store.

This field is a member of oneof value.

Type: float

key¶

Required. The key of the metadata to store.

Type: str

class google.ai.generativelanguage_v1beta.types.Dataset(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Dataset for training or validation.

examples¶

Optional. Inline examples with simple input/output text.

This field is a member of oneof dataset.

Type: google.ai.generativelanguage_v1beta.types.TuningExamples

class google.ai.generativelanguage_v1beta.types.DeleteCachedContentRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Request to delete CachedContent.

name¶

Required. The resource name referring to the content cache entry Format: cachedContents/{id}

Type: str

class google.ai.generativelanguage_v1beta.types.DeleteChunkRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Request to delete a Chunk.

name¶

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

Type: str

class google.ai.generativelanguage_v1beta.types.DeleteCorpusRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Request to delete a Corpus.

name¶

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

Type: str

force¶

Optional. If set to true, any Documents and objects related to this Corpus will also be deleted.

If false (the default), a FAILED_PRECONDITION error will be returned if Corpus contains any Documents.

Type: bool

class google.ai.generativelanguage_v1beta.types.DeleteDocumentRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Request to delete a Document.

name¶

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

Type: str

force¶

Optional. If set to true, any Chunks and objects related to this Document will also be deleted.

If false (the default), a FAILED_PRECONDITION error will be returned if Document contains any Chunks.

Type: bool

class google.ai.generativelanguage_v1beta.types.DeleteFileRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Request for DeleteFile.

name¶

Required. The name of the File to delete. Example: files/abc-123

Type: str

class google.ai.generativelanguage_v1beta.types.DeletePermissionRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Request to delete the Permission.

name¶

Required. The resource name of the permission. Formats: tunedModels/{tuned_model}/permissions/{permission} corpora/{corpus}/permissions/{permission}

Type: str

class google.ai.generativelanguage_v1beta.types.DeleteTunedModelRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Request to delete a TunedModel.

name¶

Required. The resource name of the model. Format: tunedModels/my-model-id

Type: str

class google.ai.generativelanguage_v1beta.types.Document(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

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

name¶

Immutable. Identifier. The Document resource name. The ID (name excluding the “corpora/*/documents/” prefix) can contain up to 40 characters that are lowercase alphanumeric or dashes (-). The ID cannot start or end with a dash. If the name is empty on create, a unique name will be derived from display_name along with a 12 character random suffix. Example: corpora/{corpus_id}/documents/my-awesome-doc-123a456b789c

Type: str

display_name¶

Optional. The human-readable display name for the Document. The display name must be no more than 512 characters in length, including spaces. Example: “Semantic Retriever Documentation”.

Type: str

custom_metadata¶

Optional. User provided custom metadata stored as key-value pairs used for querying. A Document can have a maximum of 20 CustomMetadata.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.CustomMetadata]

update_time¶

Output only. The Timestamp of when the Document was last updated.

Type: google.protobuf.timestamp_pb2.Timestamp

create_time¶

Output only. The Timestamp of when the Document was created.

Type: google.protobuf.timestamp_pb2.Timestamp

class google.ai.generativelanguage_v1beta.types.DownloadFileRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Request for DownloadFile.

name¶

Required. The name of the File to download. Example: files/abc-123

Type: str

class google.ai.generativelanguage_v1beta.types.DownloadFileResponse(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Response for DownloadFile.

class google.ai.generativelanguage_v1beta.types.DynamicRetrievalConfig(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Describes the options to customize dynamic retrieval.

mode¶

The mode of the predictor to be used in dynamic retrieval.

Type: google.ai.generativelanguage_v1beta.types.DynamicRetrievalConfig.Mode

dynamic_threshold¶

The threshold to be used in dynamic retrieval. If not set, a system default value is used.

This field is a member of oneof _dynamic_threshold.

Type: float

class Mode(value)[source]¶

Bases: proto.enums.Enum

The mode of the predictor to be used in dynamic retrieval.

Values:

MODE_UNSPECIFIED (0):: Always trigger retrieval.
MODE_DYNAMIC (1):: Run retrieval only when system decides it is necessary.

class google.ai.generativelanguage_v1beta.types.EmbedContentRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Request containing the Content for the model to embed.

model¶

Required. The model’s resource name. This serves as an ID for the Model to use.

This name should match a model name returned by the ListModels method.

Format: models/{model}

Type: str

content¶

Required. The content to embed. Only the parts.text fields will be counted.

Type: google.ai.generativelanguage_v1beta.types.Content

task_type¶

Optional. Optional task type for which the embeddings will be used. Not supported on earlier models (models/embedding-001).

This field is a member of oneof _task_type.

Type: google.ai.generativelanguage_v1beta.types.TaskType

title¶

Optional. An optional title for the text. Only applicable when TaskType is RETRIEVAL_DOCUMENT.

Note: Specifying a title for RETRIEVAL_DOCUMENT provides better quality embeddings for retrieval.

This field is a member of oneof _title.

Type: str

output_dimensionality¶

Optional. Optional reduced dimension for the output embedding. If set, excessive values in the output embedding are truncated from the end. Supported by newer models since 2024 only. You cannot set this value if using the earlier model (models/embedding-001).

This field is a member of oneof _output_dimensionality.

Type: int

class google.ai.generativelanguage_v1beta.types.EmbedContentResponse(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

The response to an EmbedContentRequest.

embedding¶

Output only. The embedding generated from the input content.

Type: google.ai.generativelanguage_v1beta.types.ContentEmbedding

class google.ai.generativelanguage_v1beta.types.EmbedTextRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Request to get a text embedding from the model.

model¶

Required. The model name to use with the format model=models/{model}.

Type: str

text¶

Optional. The free-form input text that the model will turn into an embedding.

Type: str

class google.ai.generativelanguage_v1beta.types.EmbedTextResponse(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

The response to a EmbedTextRequest.

embedding¶

Output only. The embedding generated from the input text.

This field is a member of oneof _embedding.

Type: google.ai.generativelanguage_v1beta.types.Embedding

class google.ai.generativelanguage_v1beta.types.Embedding(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

A list of floats representing the embedding.

value¶

The embedding values.

Type: MutableSequence[float]

class google.ai.generativelanguage_v1beta.types.Example(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

An input/output example used to instruct the Model.

It demonstrates how the model should respond or format its response.

input¶

Required. An example of an input Message from the user.

Type: google.ai.generativelanguage_v1beta.types.Message

output¶

Required. An example of what the model should output given the input.

Type: google.ai.generativelanguage_v1beta.types.Message

class google.ai.generativelanguage_v1beta.types.ExecutableCode(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Code generated by the model that is meant to be executed, and the result returned to the model.

Only generated when using the CodeExecution tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated.

language¶

Required. Programming language of the code.

Type: google.ai.generativelanguage_v1beta.types.ExecutableCode.Language

code¶

Required. The code to be executed.

Type: str

class Language(value)[source]¶

Bases: proto.enums.Enum

Supported programming languages for the generated code.

Values:

LANGUAGE_UNSPECIFIED (0):: Unspecified language. This value should not be used.
PYTHON (1):: Python >= 3.10, with numpy and simpy available.

class google.ai.generativelanguage_v1beta.types.File(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

A file uploaded to the API. Next ID: 15

video_metadata¶

Output only. Metadata for a video.

This field is a member of oneof metadata.

Type: google.ai.generativelanguage_v1beta.types.VideoFileMetadata

name¶

Immutable. Identifier. The File resource name. The ID (name excluding the “files/” prefix) can contain up to 40 characters that are lowercase alphanumeric or dashes (-). The ID cannot start or end with a dash. If the name is empty on create, a unique name will be generated. Example: files/123-456

Type: str

display_name¶

Optional. The human-readable display name for the File. The display name must be no more than 512 characters in length, including spaces. Example: “Welcome Image”.

Type: str

mime_type¶

Output only. MIME type of the file.

Type: str

size_bytes¶

Output only. Size of the file in bytes.

Type: int

create_time¶

Output only. The timestamp of when the File was created.

Type: google.protobuf.timestamp_pb2.Timestamp

update_time¶

Output only. The timestamp of when the File was last updated.

Type: google.protobuf.timestamp_pb2.Timestamp

expiration_time¶

Output only. The timestamp of when the File will be deleted. Only set if the File is scheduled to expire.

Type: google.protobuf.timestamp_pb2.Timestamp

sha256_hash¶

Output only. SHA-256 hash of the uploaded bytes.

Type: bytes

uri¶

Output only. The uri of the File.

Type: str

download_uri¶

Output only. The download uri of the File.

Type: str

state¶

Output only. Processing state of the File.

Type: google.ai.generativelanguage_v1beta.types.File.State

source¶

Source of the File.

Type: google.ai.generativelanguage_v1beta.types.File.Source

error¶

Output only. Error status if File processing failed.

Type: google.rpc.status_pb2.Status

class Source(value)[source]¶

Bases: proto.enums.Enum

Values:

SOURCE_UNSPECIFIED (0):: Used if source is not specified.
UPLOADED (1):: Indicates the file is uploaded by the user.
GENERATED (2):: Indicates the file is generated by Google.
REGISTERED (3):: Indicates the file is a registered, i.e. a Google Cloud Storage file.

class State(value)[source]¶

Bases: proto.enums.Enum

States for the lifecycle of a File.

Values:

STATE_UNSPECIFIED (0):: The default value. This value is used if the state is omitted.
PROCESSING (1):: File is being processed and cannot be used for inference yet.
ACTIVE (2):: File is processed and available for inference.
FAILED (10):: File failed processing.

class google.ai.generativelanguage_v1beta.types.FileData(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

URI based data.

mime_type¶

Optional. The IANA standard MIME type of the source data.

Type: str

file_uri¶

Required. URI.

Type: str

class google.ai.generativelanguage_v1beta.types.FunctionCall(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name with the arguments and their values.

id¶

Optional. The unique id of the function call. If populated, the client to execute the function_call and return the response with the matching id.

Type: str

name¶

Required. The name of the function to call. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

Type: str

args¶

Optional. The function parameters and values in JSON object format.

This field is a member of oneof _args.

Type: google.protobuf.struct_pb2.Struct

class google.ai.generativelanguage_v1beta.types.FunctionCallingConfig(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Configuration for specifying function calling behavior.

mode¶

Optional. Specifies the mode in which function calling should execute. If unspecified, the default value will be set to AUTO.

Type: google.ai.generativelanguage_v1beta.types.FunctionCallingConfig.Mode

allowed_function_names¶

Optional. A set of function names that, when provided, limits the functions the model will call.

This should only be set when the Mode is ANY or VALIDATED. Function names should match [FunctionDeclaration.name]. When set, model will predict a function call from only allowed function names.

Type: MutableSequence[str]

class Mode(value)[source]¶

Bases: proto.enums.Enum

Defines the execution behavior for function calling by defining the execution mode.

Values:

MODE_UNSPECIFIED (0):: Unspecified function calling mode. This value should not be used.
AUTO (1):: Default model behavior, model decides to predict either a function call or a natural language response.
ANY (2):: Model is constrained to always predicting a function call only. If “allowed_function_names” are set, the predicted function call will be limited to any one of “allowed_function_names”, else the predicted function call will be any one of the provided “function_declarations”.
NONE (3):: Model will not predict any function call. Model behavior is same as when not passing any function declarations.
VALIDATED (4):: Model decides to predict either a function call or a natural language response, but will validate function calls with constrained decoding. If “allowed_function_names” are set, the predicted function call will be limited to any one of “allowed_function_names”, else the predicted function call will be any one of the provided “function_declarations”.

class google.ai.generativelanguage_v1beta.types.FunctionDeclaration(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Structured representation of a function declaration as defined by the OpenAPI 3.03 specification. Included in this declaration are the function name and parameters. This FunctionDeclaration is a representation of a block of code that can be used as a Tool by the model and executed by the client.

name¶

Required. The name of the function. Must be a-z, A-Z, 0-9, or contain underscores, colons, dots, and dashes, with a maximum length of 64.

Type: str

description¶

Required. A brief description of the function.

Type: str

parameters¶

Optional. Describes the parameters to this function. Reflects the Open API 3.03 Parameter Object string Key: the name of the parameter. Parameter names are case sensitive. Schema Value: the Schema defining the type used for the parameter.

This field is a member of oneof _parameters.

Type: google.ai.generativelanguage_v1beta.types.Schema

parameters_json_schema¶

Optional. Describes the parameters to the function in JSON Schema format. The schema must describe an object where the properties are the parameters to the function. For example:

{
  "type": "object",
  "properties": {
    "name": { "type": "string" },
    "age": { "type": "integer" }
  },
  "additionalProperties": false,
  "required": ["name", "age"],
  "propertyOrdering": ["name", "age"]
}

This field is mutually exclusive with parameters.

This field is a member of oneof _parameters_json_schema.

Type: google.protobuf.struct_pb2.Value

response¶

Optional. Describes the output from this function in JSON Schema format. Reflects the Open API 3.03 Response Object. The Schema defines the type used for the response value of the function.

This field is a member of oneof _response.

Type: google.ai.generativelanguage_v1beta.types.Schema

response_json_schema¶

Optional. Describes the output from this function in JSON Schema format. The value specified by the schema is the response value of the function.

This field is mutually exclusive with response.

This field is a member of oneof _response_json_schema.

Type: google.protobuf.struct_pb2.Value

behavior¶

Optional. Specifies the function Behavior. Currently only supported by the BidiGenerateContent method.

Type: google.ai.generativelanguage_v1beta.types.FunctionDeclaration.Behavior

class Behavior(value)[source]¶

Bases: proto.enums.Enum

Defines the function behavior. Defaults to BLOCKING.

Values:

UNSPECIFIED (0):: This value is unused.
BLOCKING (1):: If set, the system will wait to receive the function response before continuing the conversation.
NON_BLOCKING (2):: If set, the system will not wait to receive the function response. Instead, it will attempt to handle function responses as they become available while maintaining the conversation between the user and the model.

class google.ai.generativelanguage_v1beta.types.FunctionResponse(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of aFunctionCall made based on model prediction.

id¶

Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call id.

Type: str

name¶

Required. The name of the function to call. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

Type: str

response¶

Required. The function response in JSON object format. Callers can use any keys of their choice that fit the function’s syntax to return the function output, e.g. “output”, “result”, etc. In particular, if the function call failed to execute, the response can have an “error” key to return error details to the model.

Type: google.protobuf.struct_pb2.Struct

parts¶

Optional. Ordered Parts that constitute a function response. Parts may have different IANA MIME types.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.FunctionResponsePart]

will_continue¶

Optional. Signals that function call continues, and more responses will be returned, turning the function call into a generator. Is only applicable to NON_BLOCKING function calls, is ignored otherwise. If set to false, future responses will not be considered. It is allowed to return empty response with will_continue=False to signal that the function call is finished. This may still trigger the model generation. To avoid triggering the generation and finish the function call, additionally set scheduling to SILENT.

Type: bool

scheduling¶

Optional. Specifies how the response should be scheduled in the conversation. Only applicable to NON_BLOCKING function calls, is ignored otherwise. Defaults to WHEN_IDLE.

This field is a member of oneof _scheduling.

Type: google.ai.generativelanguage_v1beta.types.FunctionResponse.Scheduling

class Scheduling(value)[source]¶

Bases: proto.enums.Enum

Specifies how the response should be scheduled in the conversation.

Values:

SCHEDULING_UNSPECIFIED (0):: This value is unused.
SILENT (1):: Only add the result to the conversation context, do not interrupt or trigger generation.
WHEN_IDLE (2):: Add the result to the conversation context, and prompt to generate output without interrupting ongoing generation.
INTERRUPT (3):: Add the result to the conversation context, interrupt ongoing generation and prompt to generate output.

class google.ai.generativelanguage_v1beta.types.FunctionResponseBlob(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Raw media bytes for function response.

Text should not be sent as raw bytes, use the ‘FunctionResponse.response’ field.

mime_type¶

The IANA standard MIME type of the source data. Examples:

image/png
image/jpeg If an unsupported MIME type is provided, an error will be returned. For a complete list of supported types, see Supported file formats.

Type: str

data¶

Raw bytes for media formats.

Type: bytes

class google.ai.generativelanguage_v1beta.types.FunctionResponsePart(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

A datatype containing media that is part of a FunctionResponse message.

A FunctionResponsePart consists of data which has an associated datatype. A FunctionResponsePart can only contain one of the accepted types in FunctionResponsePart.data.

A FunctionResponsePart must have a fixed IANA MIME type identifying the type and subtype of the media if the inline_data field is filled with raw bytes.

inline_data¶

Inline media bytes.

This field is a member of oneof data.

Type: google.ai.generativelanguage_v1beta.types.FunctionResponseBlob

class google.ai.generativelanguage_v1beta.types.GenerateAnswerRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Request to generate a grounded answer from the Model.

This message has oneof fields (mutually exclusive fields). For each oneof, at most one member field can be set at the same time. Setting any member of the oneof automatically clears all other members.

inline_passages¶

Passages provided inline with the request.

This field is a member of oneof grounding_source.

Type: google.ai.generativelanguage_v1beta.types.GroundingPassages

semantic_retriever¶

Content retrieved from resources created via the Semantic Retriever API.

This field is a member of oneof grounding_source.

Type: google.ai.generativelanguage_v1beta.types.SemanticRetrieverConfig

model¶

Required. The name of the Model to use for generating the grounded response.

Format: model=models/{model}.

Type: str

contents¶

Required. The content of the current conversation with the Model. For single-turn queries, this is a single question to answer. For multi-turn queries, this is a repeated field that contains conversation history and the last Content in the list containing the question.

Note: GenerateAnswer only supports queries in English.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.Content]

answer_style¶

Required. Style in which answers should be returned.

Type: google.ai.generativelanguage_v1beta.types.GenerateAnswerRequest.AnswerStyle

safety_settings¶

Optional. A list of unique SafetySetting instances for blocking unsafe content.

This will be enforced on the GenerateAnswerRequest.contents and GenerateAnswerResponse.candidate. There should not be more than one setting for each SafetyCategory type. The API will block any contents and responses that fail to meet the thresholds set by these settings. This list overrides the default settings for each SafetyCategory specified in the safety_settings. If there is no SafetySetting for a given SafetyCategory provided in the list, the API will use the default safety setting for that category. Harm categories HARM_CATEGORY_HATE_SPEECH, HARM_CATEGORY_SEXUALLY_EXPLICIT, HARM_CATEGORY_DANGEROUS_CONTENT, HARM_CATEGORY_HARASSMENT are supported. Refer to the guide for detailed information on available safety settings. Also refer to the Safety guidance to learn how to incorporate safety considerations in your AI applications.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.SafetySetting]

temperature¶

Optional. Controls the randomness of the output.

Values can range from [0.0,1.0], inclusive. A value closer to 1.0 will produce responses that are more varied and creative, while a value closer to 0.0 will typically result in more straightforward responses from the model. A low temperature (~0.2) is usually recommended for Attributed-Question-Answering use cases.

This field is a member of oneof _temperature.

Type: float

class AnswerStyle(value)[source]¶

Bases: proto.enums.Enum

Style for grounded answers.

Values:

ANSWER_STYLE_UNSPECIFIED (0):: Unspecified answer style.
ABSTRACTIVE (1):: Succinct but abstract style.
EXTRACTIVE (2):: Very brief and extractive style.
VERBOSE (3):: Verbose style including extra details. The response may be formatted as a sentence, paragraph, multiple paragraphs, or bullet points, etc.

class google.ai.generativelanguage_v1beta.types.GenerateAnswerResponse(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Response from the model for a grounded answer.

answer¶

Candidate answer from the model.

Note: The model always attempts to provide a grounded answer, even when the answer is unlikely to be answerable from the given passages. In that case, a low-quality or ungrounded answer may be provided, along with a low answerable_probability.

Type: google.ai.generativelanguage_v1beta.types.Candidate

answerable_probability¶

Output only. The model’s estimate of the probability that its answer is correct and grounded in the input passages.

A low answerable_probability indicates that the answer might not be grounded in the sources.

When answerable_probability is low, you may want to:

Display a message to the effect of “We couldn’t answer that question” to the user.
Fall back to a general-purpose LLM that answers the question from world knowledge. The threshold and nature of such fallbacks will depend on individual use cases. 0.5 is a good starting threshold.

This field is a member of oneof _answerable_probability.

Type: float

input_feedback¶

Output only. Feedback related to the input data used to answer the question, as opposed to the model-generated response to the question.

The input data can be one or more of the following:

Question specified by the last entry in GenerateAnswerRequest.content
Conversation history specified by the other entries in GenerateAnswerRequest.content
Grounding sources (GenerateAnswerRequest.semantic_retriever or GenerateAnswerRequest.inline_passages)

This field is a member of oneof _input_feedback.

Type: google.ai.generativelanguage_v1beta.types.GenerateAnswerResponse.InputFeedback

class InputFeedback(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Feedback related to the input data used to answer the question, as opposed to the model-generated response to the question.

block_reason¶

Optional. If set, the input was blocked and no candidates are returned. Rephrase the input.

This field is a member of oneof _block_reason.

Type: google.ai.generativelanguage_v1beta.types.GenerateAnswerResponse.InputFeedback.BlockReason

safety_ratings¶

Ratings for safety of the input. There is at most one rating per category.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.SafetyRating]

class BlockReason(value)[source]¶

Bases: proto.enums.Enum

Specifies what was the reason why input was blocked.

Values:

BLOCK_REASON_UNSPECIFIED (0):: Default value. This value is unused.
SAFETY (1):: Input was blocked due to safety reasons. Inspect safety_ratings to understand which safety category blocked it.
OTHER (2):: Input was blocked due to other reasons.

class google.ai.generativelanguage_v1beta.types.GenerateContentRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Request to generate a completion from the model. NEXT ID: 18

model¶

Required. The name of the Model to use for generating the completion.

Format: models/{model}.

Type: str

system_instruction¶

Optional. Developer set system instruction(s). Currently, text only.

This field is a member of oneof _system_instruction.

Type: google.ai.generativelanguage_v1beta.types.Content

contents¶

Required. The content of the current conversation with the model.

For single-turn queries, this is a single instance. For multi-turn queries like chat, this is a repeated field that contains the conversation history and the latest request.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.Content]

tools¶

Optional. A list of Tools the Model may use to generate the next response.

A Tool is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the Model. Supported Tools are Function and code_execution. Refer to the Function calling and the Code execution guides to learn more.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.Tool]

tool_config¶

Optional. Tool configuration for any Tool specified in the request. Refer to the Function calling guide for a usage example.

Type: google.ai.generativelanguage_v1beta.types.ToolConfig

safety_settings¶

Optional. A list of unique SafetySetting instances for blocking unsafe content.

This will be enforced on the GenerateContentRequest.contents and GenerateContentResponse.candidates. There should not be more than one setting for each SafetyCategory type. The API will block any contents and responses that fail to meet the thresholds set by these settings. This list overrides the default settings for each SafetyCategory specified in the safety_settings. If there is no SafetySetting for a given SafetyCategory provided in the list, the API will use the default safety setting for that category. Harm categories HARM_CATEGORY_HATE_SPEECH, HARM_CATEGORY_SEXUALLY_EXPLICIT, HARM_CATEGORY_DANGEROUS_CONTENT, HARM_CATEGORY_HARASSMENT, HARM_CATEGORY_CIVIC_INTEGRITY are supported. Refer to the guide for detailed information on available safety settings. Also refer to the Safety guidance to learn how to incorporate safety considerations in your AI applications.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.SafetySetting]

generation_config¶

Optional. Configuration options for model generation and outputs.

This field is a member of oneof _generation_config.

Type: google.ai.generativelanguage_v1beta.types.GenerationConfig

cached_content¶

Optional. The name of the content cached to use as context to serve the prediction. Format: cachedContents/{cachedContent}

This field is a member of oneof _cached_content.

Type: str

class google.ai.generativelanguage_v1beta.types.GenerateContentResponse(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Response from the model supporting multiple candidate responses.

Safety ratings and content filtering are reported for both prompt in GenerateContentResponse.prompt_feedback and for each candidate in finish_reason and in safety_ratings. The API:

Returns either all requested candidates or none of them
Returns no candidates at all only if there was something wrong with the prompt (check prompt_feedback)
Reports feedback on each candidate in finish_reason and safety_ratings.

candidates¶

Candidate responses from the model.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.Candidate]

prompt_feedback¶

Returns the prompt’s feedback related to the content filters.

Type: google.ai.generativelanguage_v1beta.types.GenerateContentResponse.PromptFeedback

usage_metadata¶

Output only. Metadata on the generation requests’ token usage.

Type: google.ai.generativelanguage_v1beta.types.GenerateContentResponse.UsageMetadata

model_version¶

Output only. The model version used to generate the response.

Type: str

response_id¶

Output only. response_id is used to identify each response.

Type: str

class PromptFeedback(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

A set of the feedback metadata the prompt specified in GenerateContentRequest.content.

block_reason¶

Optional. If set, the prompt was blocked and no candidates are returned. Rephrase the prompt.

Type: google.ai.generativelanguage_v1beta.types.GenerateContentResponse.PromptFeedback.BlockReason

safety_ratings¶

Ratings for safety of the prompt. There is at most one rating per category.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.SafetyRating]

class BlockReason(value)[source]¶

Bases: proto.enums.Enum

Specifies the reason why the prompt was blocked.

Values:

BLOCK_REASON_UNSPECIFIED (0):: Default value. This value is unused.
SAFETY (1):: Prompt was blocked due to safety reasons. Inspect safety_ratings to understand which safety category blocked it.
OTHER (2):: Prompt was blocked due to unknown reasons.
BLOCKLIST (3):: Prompt was blocked due to the terms which are included from the terminology blocklist.
PROHIBITED_CONTENT (4):: Prompt was blocked due to prohibited content.
IMAGE_SAFETY (5):: Candidates blocked due to unsafe image generation content.

class UsageMetadata(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Metadata on the generation request’s token usage.

prompt_token_count¶

Number of tokens in the prompt. When cached_content is set, this is still the total effective prompt size meaning this includes the number of tokens in the cached content.

Type: int

cached_content_token_count¶

Number of tokens in the cached part of the prompt (the cached content)

Type: int

candidates_token_count¶

Total number of tokens across all the generated response candidates.

Type: int

tool_use_prompt_token_count¶

Output only. Number of tokens present in tool-use prompt(s).

Type: int

thoughts_token_count¶

Output only. Number of tokens of thoughts for thinking models.

Type: int

total_token_count¶

Total token count for the generation request (prompt + response candidates).

Type: int

prompt_tokens_details¶

Output only. List of modalities that were processed in the request input.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.ModalityTokenCount]

cache_tokens_details¶

Output only. List of modalities of the cached content in the request input.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.ModalityTokenCount]

candidates_tokens_details¶

Output only. List of modalities that were returned in the response.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.ModalityTokenCount]

tool_use_prompt_tokens_details¶

Output only. List of modalities that were processed for tool-use request inputs.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.ModalityTokenCount]

class google.ai.generativelanguage_v1beta.types.GenerateMessageRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Request to generate a message response from the model.

model¶

Required. The name of the model to use.

Format: name=models/{model}.

Type: str

prompt¶

Required. The structured textual input given to the model as a prompt. Given a prompt, the model will return what it predicts is the next message in the discussion.

Type: google.ai.generativelanguage_v1beta.types.MessagePrompt

temperature¶

Optional. Controls the randomness of the output.

Values can range over [0.0,1.0], inclusive. A value closer to 1.0 will produce responses that are more varied, while a value closer to 0.0 will typically result in less surprising responses from the model.

This field is a member of oneof _temperature.

Type: float

candidate_count¶

Optional. The number of generated response messages to return.

This value must be between [1, 8], inclusive. If unset, this will default to 1.

This field is a member of oneof _candidate_count.

Type: int

top_p¶

Optional. The maximum cumulative probability of tokens to consider when sampling.

The model uses combined Top-k and nucleus sampling.

Nucleus sampling considers the smallest set of tokens whose probability sum is at least top_p.

This field is a member of oneof _top_p.

Type: float

top_k¶

Optional. The maximum number of tokens to consider when sampling.

The model uses combined Top-k and nucleus sampling.

Top-k sampling considers the set of top_k most probable tokens.

This field is a member of oneof _top_k.

Type: int

class google.ai.generativelanguage_v1beta.types.GenerateMessageResponse(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

The response from the model.

This includes candidate messages and conversation history in the form of chronologically-ordered messages.

candidates¶

Candidate response messages from the model.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.Message]

messages¶

The conversation history used by the model.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.Message]

filters¶

A set of content filtering metadata for the prompt and response text.

This indicates which SafetyCategory(s) blocked a candidate from this response, the lowest HarmProbability that triggered a block, and the HarmThreshold setting for that category.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.ContentFilter]

class google.ai.generativelanguage_v1beta.types.GenerateTextRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Request to generate a text completion response from the model.

model¶

Required. The name of the Model or TunedModel to use for generating the completion. Examples: models/text-bison-001 tunedModels/sentence-translator-u3b7m

Type: str

prompt¶

Required. The free-form input text given to the model as a prompt. Given a prompt, the model will generate a TextCompletion response it predicts as the completion of the input text.

Type: google.ai.generativelanguage_v1beta.types.TextPrompt

temperature¶

Optional. Controls the randomness of the output. Note: The default value varies by model, see the Model.temperature attribute of the Model returned the getModel function.

Values can range from [0.0,1.0], inclusive. A value closer to 1.0 will produce responses that are more varied and creative, while a value closer to 0.0 will typically result in more straightforward responses from the model.

This field is a member of oneof _temperature.

Type: float

candidate_count¶

Optional. Number of generated responses to return.

This value must be between [1, 8], inclusive. If unset, this will default to 1.

This field is a member of oneof _candidate_count.

Type: int

max_output_tokens¶

Optional. The maximum number of tokens to include in a candidate.

If unset, this will default to output_token_limit specified in the Model specification.

This field is a member of oneof _max_output_tokens.

Type: int

top_p¶

Optional. The maximum cumulative probability of tokens to consider when sampling.

The model uses combined Top-k and nucleus sampling.

Tokens are sorted based on their assigned probabilities so that only the most likely tokens are considered. Top-k sampling directly limits the maximum number of tokens to consider, while Nucleus sampling limits number of tokens based on the cumulative probability.

Note: The default value varies by model, see the Model.top_p attribute of the Model returned the getModel function.

This field is a member of oneof _top_p.

Type: float

top_k¶

Optional. The maximum number of tokens to consider when sampling.

The model uses combined Top-k and nucleus sampling.

Top-k sampling considers the set of top_k most probable tokens. Defaults to 40.

Note: The default value varies by model, see the Model.top_k attribute of the Model returned the getModel function.

This field is a member of oneof _top_k.

Type: int

safety_settings¶

Optional. A list of unique SafetySetting instances for blocking unsafe content.

that will be enforced on the GenerateTextRequest.prompt and GenerateTextResponse.candidates. There should not be more than one setting for each SafetyCategory type. The API will block any prompts and responses that fail to meet the thresholds set by these settings. This list overrides the default settings for each SafetyCategory specified in the safety_settings. If there is no SafetySetting for a given SafetyCategory provided in the list, the API will use the default safety setting for that category. Harm categories HARM_CATEGORY_DEROGATORY, HARM_CATEGORY_TOXICITY, HARM_CATEGORY_VIOLENCE, HARM_CATEGORY_SEXUAL, HARM_CATEGORY_MEDICAL, HARM_CATEGORY_DANGEROUS are supported in text service.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.SafetySetting]

stop_sequences¶

The set of character sequences (up to 5) that will stop output generation. If specified, the API will stop at the first appearance of a stop sequence. The stop sequence will not be included as part of the response.

Type: MutableSequence[str]

class google.ai.generativelanguage_v1beta.types.GenerateTextResponse(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

The response from the model, including candidate completions.

candidates¶

Candidate responses from the model.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.TextCompletion]

filters¶

A set of content filtering metadata for the prompt and response text.

This indicates which SafetyCategory(s) blocked a candidate from this response, the lowest HarmProbability that triggered a block, and the HarmThreshold setting for that category. This indicates the smallest change to the SafetySettings that would be necessary to unblock at least 1 response.

The blocking is configured by the SafetySettings in the request (or the default SafetySettings of the API).

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.ContentFilter]

safety_feedback¶

Returns any safety feedback related to content filtering.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.SafetyFeedback]

class google.ai.generativelanguage_v1beta.types.GenerationConfig(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Configuration options for model generation and outputs. Not all parameters are configurable for every model. Next ID: 29

candidate_count¶

Optional. Number of generated responses to return. If unset, this will default to 1. Please note that this doesn’t work for previous generation models (Gemini 1.0 family)

This field is a member of oneof _candidate_count.

Type: int

stop_sequences¶

Optional. The set of character sequences (up to 5) that will stop output generation. If specified, the API will stop at the first appearance of a stop_sequence. The stop sequence will not be included as part of the response.

Type: MutableSequence[str]

max_output_tokens¶

Optional. The maximum number of tokens to include in a response candidate.

Note: The default value varies by model, see the Model.output_token_limit attribute of the Model returned from the getModel function.

This field is a member of oneof _max_output_tokens.

Type: int

temperature¶

Optional. Controls the randomness of the output.

Note: The default value varies by model, see the Model.temperature attribute of the Model returned from the getModel function.

Values can range from [0.0, 2.0].

This field is a member of oneof _temperature.

Type: float

top_p¶

Optional. The maximum cumulative probability of tokens to consider when sampling.

The model uses combined Top-k and Top-p (nucleus) sampling.

Tokens are sorted based on their assigned probabilities so that only the most likely tokens are considered. Top-k sampling directly limits the maximum number of tokens to consider, while Nucleus sampling limits the number of tokens based on the cumulative probability.

Note: The default value varies by Model and is specified by theModel.top_p attribute returned from the getModel function. An empty top_k attribute indicates that the model doesn’t apply top-k sampling and doesn’t allow setting top_k on requests.

This field is a member of oneof _top_p.

Type: float

top_k¶

Optional. The maximum number of tokens to consider when sampling.

Gemini models use Top-p (nucleus) sampling or a combination of Top-k and nucleus sampling. Top-k sampling considers the set of top_k most probable tokens. Models running with nucleus sampling don’t allow top_k setting.

Note: The default value varies by Model and is specified by theModel.top_p attribute returned from the getModel function. An empty top_k attribute indicates that the model doesn’t apply top-k sampling and doesn’t allow setting top_k on requests.

This field is a member of oneof _top_k.

Type: int

seed¶

Optional. Seed used in decoding. If not set, the request uses a randomly generated seed.

This field is a member of oneof _seed.

Type: int

response_mime_type¶

Optional. MIME type of the generated candidate text. Supported MIME types are: text/plain: (default) Text output. application/json: JSON response in the response candidates. text/x.enum: ENUM as a string response in the response candidates. Refer to the docs for a list of all supported text MIME types.

Type: str

response_schema¶

Optional. Output schema of the generated candidate text. Schemas must be a subset of the OpenAPI schema and can be objects, primitives or arrays.

If set, a compatible response_mime_type must also be set. Compatible MIME types: application/json: Schema for JSON response. Refer to the JSON text generation guide for more details.

Type: google.ai.generativelanguage_v1beta.types.Schema

response_json_schema¶

Optional. Output schema of the generated response. This is an alternative to response_schema that accepts JSON Schema.

If set, response_schema must be omitted, but response_mime_type is required.

While the full JSON Schema may be sent, not all features are supported. Specifically, only the following properties are supported:

$id
$defs
$ref
$anchor
type
format
title
description
enum (for strings and numbers)
items
prefixItems
minItems
maxItems
minimum
maximum
anyOf
oneOf (interpreted the same as anyOf)
properties
additionalProperties
required

The non-standard propertyOrdering property may also be set.

Cyclic references are unrolled to a limited degree and, as such, may only be used within non-required properties. (Nullable properties are not sufficient.) If $ref is set on a sub-schema, no other properties, except for than those starting as a $, may be set.

Type: google.protobuf.struct_pb2.Value

response_json_schema_ordered¶

Optional. An internal detail. Use responseJsonSchema rather than this field.

Type: google.protobuf.struct_pb2.Value

presence_penalty¶

Optional. Presence penalty applied to the next token’s logprobs if the token has already been seen in the response.

This penalty is binary on/off and not dependant on the number of times the token is used (after the first). Use [frequency_penalty][google.ai.generativelanguage.v1beta.GenerationConfig.frequency_penalty] for a penalty that increases with each use.

A positive penalty will discourage the use of tokens that have already been used in the response, increasing the vocabulary.

A negative penalty will encourage the use of tokens that have already been used in the response, decreasing the vocabulary.

This field is a member of oneof _presence_penalty.

Type: float

frequency_penalty¶

Optional. Frequency penalty applied to the next token’s logprobs, multiplied by the number of times each token has been seen in the respponse so far.

A positive penalty will discourage the use of tokens that have already been used, proportional to the number of times the token has been used: The more a token is used, the more difficult it is for the model to use that token again increasing the vocabulary of responses.

Caution: A negative penalty will encourage the model to reuse tokens proportional to the number of times the token has been used. Small negative values will reduce the vocabulary of a response. Larger negative values will cause the model to start repeating a common token until it hits the [max_output_tokens][google.ai.generativelanguage.v1beta.GenerationConfig.max_output_tokens] limit.

This field is a member of oneof _frequency_penalty.

Type: float

response_logprobs¶

Optional. If true, export the logprobs results in response.

This field is a member of oneof _response_logprobs.

Type: bool

logprobs¶

Optional. Only valid if [response_logprobs=True][google.ai.generativelanguage.v1beta.GenerationConfig.response_logprobs]. This sets the number of top logprobs to return at each decoding step in the [Candidate.logprobs_result][google.ai.generativelanguage.v1beta.Candidate.logprobs_result]. The number must be in the range of [0, 20].

This field is a member of oneof _logprobs.

Type: int

enable_enhanced_civic_answers¶

Optional. Enables enhanced civic answers. It may not be available for all models.

This field is a member of oneof _enable_enhanced_civic_answers.

Type: bool

response_modalities¶

Optional. The requested modalities of the response. Represents the set of modalities that the model can return, and should be expected in the response. This is an exact match to the modalities of the response.

A model may have multiple combinations of supported modalities. If the requested modalities do not match any of the supported combinations, an error will be returned.

An empty list is equivalent to requesting only text.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.GenerationConfig.Modality]

speech_config¶

Optional. The speech generation config.

This field is a member of oneof _speech_config.

Type: google.ai.generativelanguage_v1beta.types.SpeechConfig

thinking_config¶

Optional. Config for thinking features. An error will be returned if this field is set for models that don’t support thinking.

This field is a member of oneof _thinking_config.

Type: google.ai.generativelanguage_v1beta.types.ThinkingConfig

image_config¶

Optional. Config for image generation. An error will be returned if this field is set for models that don’t support these config options.

This field is a member of oneof _image_config.

Type: google.ai.generativelanguage_v1beta.types.ImageConfig

media_resolution¶

Optional. If specified, the media resolution specified will be used.

This field is a member of oneof _media_resolution.

Type: google.ai.generativelanguage_v1beta.types.GenerationConfig.MediaResolution

class MediaResolution(value)[source]¶

Bases: proto.enums.Enum

Media resolution for the input media.

Values:

MEDIA_RESOLUTION_UNSPECIFIED (0):: Media resolution has not been set.
MEDIA_RESOLUTION_LOW (1):: Media resolution set to low (64 tokens).
MEDIA_RESOLUTION_MEDIUM (2):: Media resolution set to medium (256 tokens).
MEDIA_RESOLUTION_HIGH (3):: Media resolution set to high (zoomed reframing with 256 tokens).

class Modality(value)[source]¶

Bases: proto.enums.Enum

Supported modalities of the response.

Values:

MODALITY_UNSPECIFIED (0):: Default value.
TEXT (1):: Indicates the model should return text.
IMAGE (2):: Indicates the model should return images.
AUDIO (3):: Indicates the model should return audio.

class google.ai.generativelanguage_v1beta.types.GetCachedContentRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Request to read CachedContent.

name¶

Required. The resource name referring to the content cache entry. Format: cachedContents/{id}

Type: str

class google.ai.generativelanguage_v1beta.types.GetChunkRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Request for getting information about a specific Chunk.

name¶

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

Type: str

class google.ai.generativelanguage_v1beta.types.GetCorpusRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Request for getting information about a specific Corpus.

name¶

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

Type: str

class google.ai.generativelanguage_v1beta.types.GetDocumentRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Request for getting information about a specific Document.

name¶

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

Type: str

class google.ai.generativelanguage_v1beta.types.GetFileRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Request for GetFile.

name¶

Required. The name of the File to get. Example: files/abc-123

Type: str

class google.ai.generativelanguage_v1beta.types.GetModelRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Request for getting information about a specific Model.

name¶

Required. The resource name of the model.

This name should match a model name returned by the ListModels method.

Format: models/{model}

Type: str

class google.ai.generativelanguage_v1beta.types.GetPermissionRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Request for getting information about a specific Permission.

name¶

Required. The resource name of the permission.

Formats: tunedModels/{tuned_model}/permissions/{permission} corpora/{corpus}/permissions/{permission}

Type: str

class google.ai.generativelanguage_v1beta.types.GetTunedModelRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Request for getting information about a specific Model.

name¶

Required. The resource name of the model.

Format: tunedModels/my-model-id

Type: str

class google.ai.generativelanguage_v1beta.types.GoAway(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

A notice that the server will soon disconnect.

time_left¶

The remaining time before the connection will be terminated as ABORTED. This duration will never be less than a model-specific minimum, which will be specified together with the rate limits for the model.

Type: google.protobuf.duration_pb2.Duration

class google.ai.generativelanguage_v1beta.types.GoogleSearchRetrieval(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Tool to retrieve public web data for grounding, powered by Google.

dynamic_retrieval_config¶

Specifies the dynamic retrieval configuration for the given source.

Type: google.ai.generativelanguage_v1beta.types.DynamicRetrievalConfig

class google.ai.generativelanguage_v1beta.types.GroundingAttribution(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Attribution for a source that contributed to an answer.

source_id¶

Output only. Identifier for the source contributing to this attribution.

Type: google.ai.generativelanguage_v1beta.types.AttributionSourceId

content¶

Grounding source content that makes up this attribution.

Type: google.ai.generativelanguage_v1beta.types.Content

class google.ai.generativelanguage_v1beta.types.GroundingChunk(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Grounding chunk.

web¶

Grounding chunk from the web.

This field is a member of oneof chunk_type.

Type: google.ai.generativelanguage_v1beta.types.GroundingChunk.Web

class Web(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Chunk from the web.

uri¶

URI reference of the chunk.

This field is a member of oneof _uri.

Type: str

title¶

Title of the chunk.

This field is a member of oneof _title.

Type: str

class google.ai.generativelanguage_v1beta.types.GroundingMetadata(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Metadata returned to client when grounding is enabled.

search_entry_point¶

Optional. Google search entry for the following-up web searches.

This field is a member of oneof _search_entry_point.

Type: google.ai.generativelanguage_v1beta.types.SearchEntryPoint

grounding_chunks¶

List of supporting references retrieved from specified grounding source.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.GroundingChunk]

grounding_supports¶

List of grounding support.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.GroundingSupport]

retrieval_metadata¶

Metadata related to retrieval in the grounding flow.

This field is a member of oneof _retrieval_metadata.

Type: google.ai.generativelanguage_v1beta.types.RetrievalMetadata

web_search_queries¶

Web search queries for the following-up web search.

Type: MutableSequence[str]

class google.ai.generativelanguage_v1beta.types.GroundingPassage(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Passage included inline with a grounding configuration.

id¶

Identifier for the passage for attributing this passage in grounded answers.

Type: str

content¶

Content of the passage.

Type: google.ai.generativelanguage_v1beta.types.Content

class google.ai.generativelanguage_v1beta.types.GroundingPassages(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

A repeated list of passages.

passages¶

List of passages.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.GroundingPassage]

class google.ai.generativelanguage_v1beta.types.GroundingSupport(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Grounding support.

segment¶

Segment of the content this support belongs to.

This field is a member of oneof _segment.

Type: google.ai.generativelanguage_v1beta.types.Segment

grounding_chunk_indices¶

A list of indices (into ‘grounding_chunk’) specifying the citations associated with the claim. For instance [1,3,4] means that grounding_chunk[1], grounding_chunk[3], grounding_chunk[4] are the retrieved content attributed to the claim.

Type: MutableSequence[int]

confidence_scores¶

Confidence score of the support references. Ranges from 0 to 1. 1 is the most confident. This list must have the same size as the grounding_chunk_indices.

Type: MutableSequence[float]

class google.ai.generativelanguage_v1beta.types.HarmCategory(value)[source]¶

Bases: proto.enums.Enum

The category of a rating.

These categories cover various kinds of harms that developers may wish to adjust.

Values:

HARM_CATEGORY_UNSPECIFIED (0):: Category is unspecified.
HARM_CATEGORY_DEROGATORY (1):: PaLM - Negative or harmful comments targeting identity and/or protected attribute.
HARM_CATEGORY_TOXICITY (2):: PaLM - Content that is rude, disrespectful, or profane.
HARM_CATEGORY_VIOLENCE (3):: PaLM - Describes scenarios depicting violence against an individual or group, or general descriptions of gore.
HARM_CATEGORY_SEXUAL (4):: PaLM - Contains references to sexual acts or other lewd content.
HARM_CATEGORY_MEDICAL (5):: PaLM - Promotes unchecked medical advice.
HARM_CATEGORY_DANGEROUS (6):: PaLM - Dangerous content that promotes, facilitates, or encourages harmful acts.
HARM_CATEGORY_HARASSMENT (7):: Gemini - Harassment content.
HARM_CATEGORY_HATE_SPEECH (8):: Gemini - Hate speech and content.
HARM_CATEGORY_SEXUALLY_EXPLICIT (9):: Gemini - Sexually explicit content.
HARM_CATEGORY_DANGEROUS_CONTENT (10):: Gemini - Dangerous content.
HARM_CATEGORY_CIVIC_INTEGRITY (11):: Gemini - Content that may be used to harm civic integrity. DEPRECATED: use enable_enhanced_civic_answers instead.

class google.ai.generativelanguage_v1beta.types.Hyperparameters(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Hyperparameters controlling the tuning process. Read more at https://ai.google.dev/docs/model_tuning_guidance

This message has oneof fields (mutually exclusive fields). For each oneof, at most one member field can be set at the same time. Setting any member of the oneof automatically clears all other members.

learning_rate¶

Optional. Immutable. The learning rate hyperparameter for tuning. If not set, a default of 0.001 or 0.0002 will be calculated based on the number of training examples.

This field is a member of oneof learning_rate_option.

Type: float

learning_rate_multiplier¶

Optional. Immutable. The learning rate multiplier is used to calculate a final learning_rate based on the default (recommended) value. Actual learning rate := learning_rate_multiplier * default learning rate Default learning rate is dependent on base model and dataset size. If not set, a default of 1.0 will be used.

This field is a member of oneof learning_rate_option.

Type: float

epoch_count¶

Immutable. The number of training epochs. An epoch is one pass through the training data. If not set, a default of 5 will be used.

This field is a member of oneof _epoch_count.

Type: int

batch_size¶

Immutable. The batch size hyperparameter for tuning. If not set, a default of 4 or 16 will be used based on the number of training examples.

This field is a member of oneof _batch_size.

Type: int

class google.ai.generativelanguage_v1beta.types.ImageConfig(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Config for image generation features.

aspect_ratio¶

Optional. The aspect ratio of the image to generate. Supported aspect ratios: 1:1, 2:3, 3:2, 3:4, 4:3, 9:16, 16:9, 21:9.

If not specified, the model will choose a default aspect ratio based on any reference images provided.

This field is a member of oneof _aspect_ratio.

Type: str

class google.ai.generativelanguage_v1beta.types.ListCachedContentsRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Request to list CachedContents.

page_size¶

Optional. The maximum number of cached contents to return. The service may return fewer than this value. If unspecified, some default (under maximum) number of items will be returned. The maximum value is 1000; values above 1000 will be coerced to 1000.

Type: int

page_token¶

Optional. A page token, received from a previous ListCachedContents call. Provide this to retrieve the subsequent page.

When paginating, all other parameters provided to ListCachedContents must match the call that provided the page token.

Type: str

class google.ai.generativelanguage_v1beta.types.ListCachedContentsResponse(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Response with CachedContents list.

cached_contents¶

List of cached contents.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.CachedContent]

next_page_token¶

A token, which can be sent as page_token to retrieve the next page. If this field is omitted, there are no subsequent pages.

Type: str

class google.ai.generativelanguage_v1beta.types.ListChunksRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Request for listing Chunks.

parent¶

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

Type: str

page_size¶

Optional. The maximum number of Chunks to return (per page). The service may return fewer Chunks.

If unspecified, at most 10 Chunks will be returned. The maximum size limit is 100 Chunks per page.

Type: int

page_token¶

Optional. A page token, received from a previous ListChunks call.

Provide the next_page_token returned in the response as an argument to the next request to retrieve the next page.

When paginating, all other parameters provided to ListChunks must match the call that provided the page token.

Type: str

class google.ai.generativelanguage_v1beta.types.ListChunksResponse(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Response from ListChunks containing a paginated list of Chunks. The Chunks are sorted by ascending chunk.create_time.

chunks¶

The returned Chunks.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.Chunk]

next_page_token¶

A token, which can be sent as page_token to retrieve the next page. If this field is omitted, there are no more pages.

Type: str

class google.ai.generativelanguage_v1beta.types.ListCorporaRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Request for listing Corpora.

page_size¶

Optional. The maximum number of Corpora to return (per page). The service may return fewer Corpora.

If unspecified, at most 10 Corpora will be returned. The maximum size limit is 20 Corpora per page.

Type: int

page_token¶

Optional. A page token, received from a previous ListCorpora call.

Provide the next_page_token returned in the response as an argument to the next request to retrieve the next page.

When paginating, all other parameters provided to ListCorpora must match the call that provided the page token.

Type: str

class google.ai.generativelanguage_v1beta.types.ListCorporaResponse(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Response from ListCorpora containing a paginated list of Corpora. The results are sorted by ascending corpus.create_time.

corpora¶

The returned corpora.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.Corpus]

next_page_token¶

A token, which can be sent as page_token to retrieve the next page. If this field is omitted, there are no more pages.

Type: str

class google.ai.generativelanguage_v1beta.types.ListDocumentsRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Request for listing Documents.

parent¶

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

Type: str

page_size¶

Optional. The maximum number of Documents to return (per page). The service may return fewer Documents.

If unspecified, at most 10 Documents will be returned. The maximum size limit is 20 Documents per page.

Type: int

page_token¶

Optional. A page token, received from a previous ListDocuments call.

Provide the next_page_token returned in the response as an argument to the next request to retrieve the next page.

When paginating, all other parameters provided to ListDocuments must match the call that provided the page token.

Type: str

class google.ai.generativelanguage_v1beta.types.ListDocumentsResponse(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Response from ListDocuments containing a paginated list of Documents. The Documents are sorted by ascending document.create_time.

documents¶

The returned Documents.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.Document]

next_page_token¶

A token, which can be sent as page_token to retrieve the next page. If this field is omitted, there are no more pages.

Type: str

class google.ai.generativelanguage_v1beta.types.ListFilesRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Request for ListFiles.

page_size¶

Optional. Maximum number of Files to return per page. If unspecified, defaults to 10. Maximum page_size is 100.

Type: int

page_token¶

Optional. A page token from a previous ListFiles call.

Type: str

class google.ai.generativelanguage_v1beta.types.ListFilesResponse(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Response for ListFiles.

files¶

The list of Files.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.File]

next_page_token¶

A token that can be sent as a page_token into a subsequent ListFiles call.

Type: str

class google.ai.generativelanguage_v1beta.types.ListModelsRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Request for listing all Models.

page_size¶

The maximum number of Models to return (per page).

If unspecified, 50 models will be returned per page. This method returns at most 1000 models per page, even if you pass a larger page_size.

Type: int

page_token¶

A page token, received from a previous ListModels call.

Provide the page_token returned by one request as an argument to the next request to retrieve the next page.

When paginating, all other parameters provided to ListModels must match the call that provided the page token.

Type: str

class google.ai.generativelanguage_v1beta.types.ListModelsResponse(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Response from ListModel containing a paginated list of Models.

models¶

The returned Models.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.Model]

next_page_token¶

A token, which can be sent as page_token to retrieve the next page.

If this field is omitted, there are no more pages.

Type: str

class google.ai.generativelanguage_v1beta.types.ListPermissionsRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Request for listing permissions.

parent¶

Required. The parent resource of the permissions. Formats: tunedModels/{tuned_model} corpora/{corpus}

Type: str

page_size¶

Optional. The maximum number of Permissions to return (per page). The service may return fewer permissions.

If unspecified, at most 10 permissions will be returned. This method returns at most 1000 permissions per page, even if you pass larger page_size.

Type: int

page_token¶

Optional. A page token, received from a previous ListPermissions call.

Provide the page_token returned by one request as an argument to the next request to retrieve the next page.

When paginating, all other parameters provided to ListPermissions must match the call that provided the page token.

Type: str

class google.ai.generativelanguage_v1beta.types.ListPermissionsResponse(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Response from ListPermissions containing a paginated list of permissions.

permissions¶

Returned permissions.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.Permission]

next_page_token¶

A token, which can be sent as page_token to retrieve the next page.

If this field is omitted, there are no more pages.

Type: str

class google.ai.generativelanguage_v1beta.types.ListTunedModelsRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Request for listing TunedModels.

page_size¶

Optional. The maximum number of TunedModels to return (per page). The service may return fewer tuned models.

If unspecified, at most 10 tuned models will be returned. This method returns at most 1000 models per page, even if you pass a larger page_size.

Type: int

page_token¶

Optional. A page token, received from a previous ListTunedModels call.

Provide the page_token returned by one request as an argument to the next request to retrieve the next page.

When paginating, all other parameters provided to ListTunedModels must match the call that provided the page token.

Type: str

filter¶

Optional. A filter is a full text search over the tuned model’s description and display name. By default, results will not include tuned models shared with everyone.

Additional operators:

owner:me

writers:me

readers:me

readers:everyone

Examples

“owner:me” returns all tuned models to which

caller has owner role “readers:me” returns all tuned models to which caller has reader role “readers:everyone” returns all tuned models that are shared with everyone

Type: str

class google.ai.generativelanguage_v1beta.types.ListTunedModelsResponse(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Response from ListTunedModels containing a paginated list of Models.

tuned_models¶

The returned Models.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.TunedModel]

next_page_token¶

A token, which can be sent as page_token to retrieve the next page.

If this field is omitted, there are no more pages.

Type: str

class google.ai.generativelanguage_v1beta.types.LogprobsResult(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Logprobs Result

log_probability_sum¶

Sum of log probabilities for all tokens.

This field is a member of oneof _log_probability_sum.

Type: float

top_candidates¶

Length = total number of decoding steps.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.LogprobsResult.TopCandidates]

chosen_candidates¶

Length = total number of decoding steps. The chosen candidates may or may not be in top_candidates.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.LogprobsResult.Candidate]

class Candidate(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Candidate for the logprobs token and score.

token¶

The candidate’s token string value.

This field is a member of oneof _token.

Type: str

token_id¶

The candidate’s token id value.

This field is a member of oneof _token_id.

Type: int

log_probability¶

The candidate’s log probability.

This field is a member of oneof _log_probability.

Type: float

class TopCandidates(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Candidates with top log probabilities at each decoding step.

candidates¶

Sorted by log probability in descending order.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.LogprobsResult.Candidate]

class google.ai.generativelanguage_v1beta.types.Media(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

A proto encapsulate various type of media.

video¶

Video as the only one for now. This is mimicking Vertex proto.

This field is a member of oneof type.

Type: google.ai.generativelanguage_v1beta.types.Video

class google.ai.generativelanguage_v1beta.types.Message(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

The base unit of structured text.

A Message includes an author and the content of the Message.

The author is used to tag messages when they are fed to the model as text.

author¶

Optional. The author of this Message.

This serves as a key for tagging the content of this Message when it is fed to the model as text.

The author can be any alphanumeric string.

Type: str

content¶

Required. The text content of the structured Message.

Type: str

citation_metadata¶

Output only. Citation information for model-generated content in this Message.

If this Message was generated as output from the model, this field may be populated with attribution information for any text included in the content. This field is used only on output.

This field is a member of oneof _citation_metadata.

Type: google.ai.generativelanguage_v1beta.types.CitationMetadata

class google.ai.generativelanguage_v1beta.types.MessagePrompt(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

All of the structured input text passed to the model as a prompt.

A MessagePrompt contains a structured set of fields that provide context for the conversation, examples of user input/model output message pairs that prime the model to respond in different ways, and the conversation history or list of messages representing the alternating turns of the conversation between the user and the model.

context¶

Optional. Text that should be provided to the model first to ground the response.

If not empty, this context will be given to the model first before the examples and messages. When using a context be sure to provide it with every request to maintain continuity.

This field can be a description of your prompt to the model to help provide context and guide the responses. Examples: “Translate the phrase from English to French.” or “Given a statement, classify the sentiment as happy, sad or neutral.”

Anything included in this field will take precedence over message history if the total input size exceeds the model’s input_token_limit and the input request is truncated.

Type: str

examples¶

Optional. Examples of what the model should generate.

This includes both user input and the response that the model should emulate.

These examples are treated identically to conversation messages except that they take precedence over the history in messages: If the total input size exceeds the model’s input_token_limit the input will be truncated. Items will be dropped from messages before examples.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.Example]

messages¶

Required. A snapshot of the recent conversation history sorted chronologically.

Turns alternate between two authors.

If the total input size exceeds the model’s input_token_limit the input will be truncated: The oldest items will be dropped from messages.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.Message]

class google.ai.generativelanguage_v1beta.types.MetadataFilter(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

User provided filter to limit retrieval based on Chunk or Document level metadata values. Example (genre = drama OR genre = action): key = “document.custom_metadata.genre” conditions = [{string_value = “drama”, operation = EQUAL}, {string_value = “action”, operation = EQUAL}]

key¶

Required. The key of the metadata to filter on.

Type: str

conditions¶

Required. The Conditions for the given key that will trigger this filter. Multiple Conditions are joined by logical ORs.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.Condition]

class google.ai.generativelanguage_v1beta.types.Modality(value)[source]¶

Bases: proto.enums.Enum

Content Part modality

Values:

MODALITY_UNSPECIFIED (0):: Unspecified modality.
TEXT (1):: Plain text.
IMAGE (2):: Image.
VIDEO (3):: Video.
AUDIO (4):: Audio.
DOCUMENT (5):: Document, e.g. PDF.

class google.ai.generativelanguage_v1beta.types.ModalityTokenCount(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Represents token counting info for a single modality.

modality¶

The modality associated with this token count.

Type: google.ai.generativelanguage_v1beta.types.Modality

token_count¶

Number of tokens.

Type: int

class google.ai.generativelanguage_v1beta.types.Model(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Information about a Generative Language Model.

name¶

Required. The resource name of the Model. Refer to Model variants for all allowed values.

Format: models/{model} with a {model} naming convention of:

“{base_model_id}-{version}”

Examples:

models/gemini-1.5-flash-001

Type: str

base_model_id¶

Required. The name of the base model, pass this to the generation request.

Examples:

gemini-1.5-flash

Type: str

version¶

Required. The version number of the model.

This represents the major version (1.0 or 1.5)

Type: str

display_name¶

The human-readable name of the model. E.g. “Gemini 1.5 Flash”. The name can be up to 128 characters long and can consist of any UTF-8 characters.

Type: str

description¶

A short description of the model.

Type: str

input_token_limit¶

Maximum number of input tokens allowed for this model.

Type: int

output_token_limit¶

Maximum number of output tokens available for this model.

Type: int

supported_generation_methods¶

The model’s supported generation methods.

The corresponding API method names are defined as Pascal case strings, such as generateMessage and generateContent.

Type: MutableSequence[str]

temperature¶

Controls the randomness of the output.

Values can range over [0.0,max_temperature], inclusive. A higher value will produce responses that are more varied, while a value closer to 0.0 will typically result in less surprising responses from the model. This value specifies default to be used by the backend while making the call to the model.

This field is a member of oneof _temperature.

Type: float

max_temperature¶

The maximum temperature this model can use.

This field is a member of oneof _max_temperature.

Type: float

top_p¶

For Nucleus sampling.

Nucleus sampling considers the smallest set of tokens whose probability sum is at least top_p. This value specifies default to be used by the backend while making the call to the model.

This field is a member of oneof _top_p.

Type: float

top_k¶

For Top-k sampling.

Top-k sampling considers the set of top_k most probable tokens. This value specifies default to be used by the backend while making the call to the model. If empty, indicates the model doesn’t use top-k sampling, and top_k isn’t allowed as a generation parameter.

This field is a member of oneof _top_k.

Type: int

thinking¶

Whether the model supports thinking.

Type: bool

class google.ai.generativelanguage_v1beta.types.MultiSpeakerVoiceConfig(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

The configuration for the multi-speaker setup.

speaker_voice_configs¶

Required. All the enabled speaker voices.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.SpeakerVoiceConfig]

class google.ai.generativelanguage_v1beta.types.Part(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

A datatype containing media that is part of a multi-part Content message.

A Part consists of data which has an associated datatype. A Part can only contain one of the accepted types in Part.data.

A Part must have a fixed IANA MIME type identifying the type and subtype of the media if the inline_data field is filled with raw bytes.

This message has oneof fields (mutually exclusive fields). For each oneof, at most one member field can be set at the same time. Setting any member of the oneof automatically clears all other members.

text¶

Inline text.

This field is a member of oneof data.

Type: str

inline_data¶

Inline media bytes.

This field is a member of oneof data.

Type: google.ai.generativelanguage_v1beta.types.Blob

function_call¶

A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name with the arguments and their values.

This field is a member of oneof data.

Type: google.ai.generativelanguage_v1beta.types.FunctionCall

function_response¶

The result output of a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model.

This field is a member of oneof data.

Type: google.ai.generativelanguage_v1beta.types.FunctionResponse

file_data¶

URI based data.

This field is a member of oneof data.

Type: google.ai.generativelanguage_v1beta.types.FileData

executable_code¶

Code generated by the model that is meant to be executed.

This field is a member of oneof data.

Type: google.ai.generativelanguage_v1beta.types.ExecutableCode

code_execution_result¶

Result of executing the ExecutableCode.

This field is a member of oneof data.

Type: google.ai.generativelanguage_v1beta.types.CodeExecutionResult

video_metadata¶

Optional. Video metadata. The metadata should only be specified while the video data is presented in inline_data or file_data.

This field is a member of oneof metadata.

Type: google.ai.generativelanguage_v1beta.types.VideoMetadata

thought¶

Optional. Indicates if the part is thought from the model.

Type: bool

thought_signature¶

Optional. An opaque signature for the thought so it can be reused in subsequent requests.

Type: bytes

part_metadata¶

Custom metadata associated with the Part. Agents using genai.Part as content representation may need to keep track of the additional information. For example it can be name of a file/source from which the Part originates or a way to multiplex multiple Part streams.

Type: google.protobuf.struct_pb2.Struct

class google.ai.generativelanguage_v1beta.types.Permission(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Permission resource grants user, group or the rest of the world access to the PaLM API resource (e.g. a tuned model, corpus).

A role is a collection of permitted operations that allows users to perform specific actions on PaLM API resources. To make them available to users, groups, or service accounts, you assign roles. When you assign a role, you grant permissions that the role contains.

There are three concentric roles. Each role is a superset of the previous role’s permitted operations:

reader can use the resource (e.g. tuned model, corpus) for inference
writer has reader’s permissions and additionally can edit and share
owner has writer’s permissions and additionally can delete

name¶

Output only. Identifier. The permission name. A unique name will be generated on create. Examples: tunedModels/{tuned_model}/permissions/{permission} corpora/{corpus}/permissions/{permission} Output only.

Type: str

grantee_type¶

Optional. Immutable. The type of the grantee.

This field is a member of oneof _grantee_type.

Type: google.ai.generativelanguage_v1beta.types.Permission.GranteeType

email_address¶

Optional. Immutable. The email address of the user of group which this permission refers. Field is not set when permission’s grantee type is EVERYONE.

This field is a member of oneof _email_address.

Type: str

role¶

Required. The role granted by this permission.

This field is a member of oneof _role.

Type: google.ai.generativelanguage_v1beta.types.Permission.Role

class GranteeType(value)[source]¶

Bases: proto.enums.Enum

Defines types of the grantee of this permission.

Values:

GRANTEE_TYPE_UNSPECIFIED (0):: The default value. This value is unused.
USER (1):: Represents a user. When set, you must provide email_address for the user.
GROUP (2):: Represents a group. When set, you must provide email_address for the group.
EVERYONE (3):: Represents access to everyone. No extra information is required.

class Role(value)[source]¶

Bases: proto.enums.Enum

Defines the role granted by this permission.

Values:

ROLE_UNSPECIFIED (0):: The default value. This value is unused.
OWNER (1):: Owner can use, update, share and delete the resource.
WRITER (2):: Writer can use, update and share the resource.
READER (3):: Reader can use the resource.

class google.ai.generativelanguage_v1beta.types.PrebuiltVoiceConfig(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

The configuration for the prebuilt speaker to use.

voice_name¶

The name of the preset voice to use.

This field is a member of oneof _voice_name.

Type: str

class google.ai.generativelanguage_v1beta.types.PredictLongRunningGeneratedVideoResponse(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Veo response.

generated_samples¶

The generated samples.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.Media]

rai_media_filtered_count¶

Returns if any videos were filtered due to RAI policies.

Type: int

rai_media_filtered_reasons¶

Returns rai failure reasons if any.

Type: MutableSequence[str]

class google.ai.generativelanguage_v1beta.types.PredictLongRunningMetadata(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Metadata for PredictLongRunning long running operations.

class google.ai.generativelanguage_v1beta.types.PredictLongRunningRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Request message for [PredictionService.PredictLongRunning].

model¶

Required. The name of the model for prediction. Format: name=models/{model}.

Type: str

instances¶

Required. The instances that are the input to the prediction call.

Type: MutableSequence[google.protobuf.struct_pb2.Value]

parameters¶

Optional. The parameters that govern the prediction call.

Type: google.protobuf.struct_pb2.Value

class google.ai.generativelanguage_v1beta.types.PredictLongRunningResponse(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Response message for [PredictionService.PredictLongRunning]

generate_video_response¶

The response of the video generation prediction.

This field is a member of oneof response.

Type: google.ai.generativelanguage_v1beta.types.PredictLongRunningGeneratedVideoResponse

class google.ai.generativelanguage_v1beta.types.PredictRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Request message for [PredictionService.Predict][google.ai.generativelanguage.v1beta.PredictionService.Predict].

model¶

Required. The name of the model for prediction. Format: name=models/{model}.

Type: str

instances¶

Required. The instances that are the input to the prediction call.

Type: MutableSequence[google.protobuf.struct_pb2.Value]

parameters¶

Optional. The parameters that govern the prediction call.

Type: google.protobuf.struct_pb2.Value

class google.ai.generativelanguage_v1beta.types.PredictResponse(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Response message for [PredictionService.Predict].

predictions¶

The outputs of the prediction call.

Type: MutableSequence[google.protobuf.struct_pb2.Value]

class google.ai.generativelanguage_v1beta.types.QueryCorpusRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Request for querying a Corpus.

name¶

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

Type: str

query¶

Required. Query string to perform semantic search.

Type: str

metadata_filters¶

Optional. Filter for Chunk and Document metadata. Each MetadataFilter object should correspond to a unique key. Multiple MetadataFilter objects are joined by logical “AND”s.

Example query at document level: (year >= 2020 OR year < 2010) AND (genre = drama OR genre = action)

MetadataFilter object list: metadata_filters = [ {key = “document.custom_metadata.year” conditions = [{int_value = 2020, operation = GREATER_EQUAL}, {int_value = 2010, operation = LESS}]}, {key = “document.custom_metadata.year” conditions = [{int_value = 2020, operation = GREATER_EQUAL}, {int_value = 2010, operation = LESS}]}, {key = “document.custom_metadata.genre” conditions = [{string_value = “drama”, operation = EQUAL}, {string_value = “action”, operation = EQUAL}]}]

Example query at chunk level for a numeric range of values: (year > 2015 AND year <= 2020)

MetadataFilter object list: metadata_filters = [ {key = “chunk.custom_metadata.year” conditions = [{int_value = 2015, operation = GREATER}]}, {key = “chunk.custom_metadata.year” conditions = [{int_value = 2020, operation = LESS_EQUAL}]}]

Note: “AND”s for the same key are only supported for numeric values. String values only support “OR”s for the same key.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.MetadataFilter]

results_count¶

Optional. The maximum number of Chunks to return. The service may return fewer Chunks.

If unspecified, at most 10 Chunks will be returned. The maximum specified result count is 100.

Type: int

class google.ai.generativelanguage_v1beta.types.QueryCorpusResponse(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Response from QueryCorpus containing a list of relevant chunks.

relevant_chunks¶

The relevant chunks.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.RelevantChunk]

class google.ai.generativelanguage_v1beta.types.QueryDocumentRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Request for querying a Document.

name¶

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

Type: str

query¶

Required. Query string to perform semantic search.

Type: str

results_count¶

Optional. The maximum number of Chunks to return. The service may return fewer Chunks.

If unspecified, at most 10 Chunks will be returned. The maximum specified result count is 100.

Type: int

metadata_filters¶

Optional. Filter for Chunk metadata. Each MetadataFilter object should correspond to a unique key. Multiple MetadataFilter objects are joined by logical “AND”s.

Note: Document-level filtering is not supported for this request because a Document name is already specified.

Example query: (year >= 2020 OR year < 2010) AND (genre = drama OR genre = action)

MetadataFilter object list: metadata_filters = [ {key = “chunk.custom_metadata.year” conditions = [{int_value = 2020, operation = GREATER_EQUAL}, {int_value = 2010, operation = LESS}}, {key = “chunk.custom_metadata.genre” conditions = [{string_value = “drama”, operation = EQUAL}, {string_value = “action”, operation = EQUAL}}]

Example query for a numeric range of values: (year > 2015 AND year <= 2020)

MetadataFilter object list: metadata_filters = [ {key = “chunk.custom_metadata.year” conditions = [{int_value = 2015, operation = GREATER}]}, {key = “chunk.custom_metadata.year” conditions = [{int_value = 2020, operation = LESS_EQUAL}]}]

Note: “AND”s for the same key are only supported for numeric values. String values only support “OR”s for the same key.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.MetadataFilter]

class google.ai.generativelanguage_v1beta.types.QueryDocumentResponse(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Response from QueryDocument containing a list of relevant chunks.

relevant_chunks¶

The returned relevant chunks.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.RelevantChunk]

class google.ai.generativelanguage_v1beta.types.RealtimeInputConfig(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Configures the realtime input behavior in BidiGenerateContent.

automatic_activity_detection¶

Optional. If not set, automatic activity detection is enabled by default. If automatic voice detection is disabled, the client must send activity signals.

Type: google.ai.generativelanguage_v1beta.types.RealtimeInputConfig.AutomaticActivityDetection

activity_handling¶

Optional. Defines what effect activity has.

This field is a member of oneof _activity_handling.

Type: google.ai.generativelanguage_v1beta.types.RealtimeInputConfig.ActivityHandling

turn_coverage¶

Optional. Defines which input is included in the user’s turn.

This field is a member of oneof _turn_coverage.

Type: google.ai.generativelanguage_v1beta.types.RealtimeInputConfig.TurnCoverage

class ActivityHandling(value)[source]¶

Bases: proto.enums.Enum

The different ways of handling user activity.

Values:

ACTIVITY_HANDLING_UNSPECIFIED (0):: If unspecified, the default behavior is START_OF_ACTIVITY_INTERRUPTS.
START_OF_ACTIVITY_INTERRUPTS (1):: If true, start of activity will interrupt the model’s response (also called “barge in”). The model’s current response will be cut-off in the moment of the interruption. This is the default behavior.
NO_INTERRUPTION (2):: The model’s response will not be interrupted.

class AutomaticActivityDetection(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Configures automatic detection of activity.

disabled¶

Optional. If enabled (the default), detected voice and text input count as activity. If disabled, the client must send activity signals.

This field is a member of oneof _disabled.

Type: bool

start_of_speech_sensitivity¶

Optional. Determines how likely speech is to be detected.

This field is a member of oneof _start_of_speech_sensitivity.

Type: google.ai.generativelanguage_v1beta.types.RealtimeInputConfig.AutomaticActivityDetection.StartSensitivity

prefix_padding_ms¶

Optional. The required duration of detected speech before start-of-speech is committed. The lower this value, the more sensitive the start-of-speech detection is and shorter speech can be recognized. However, this also increases the probability of false positives.

This field is a member of oneof _prefix_padding_ms.

Type: int

end_of_speech_sensitivity¶

Optional. Determines how likely detected speech is ended.

This field is a member of oneof _end_of_speech_sensitivity.

Type: google.ai.generativelanguage_v1beta.types.RealtimeInputConfig.AutomaticActivityDetection.EndSensitivity

silence_duration_ms¶

Optional. The required duration of detected non-speech (e.g. silence) before end-of-speech is committed. The larger this value, the longer speech gaps can be without interrupting the user’s activity but this will increase the model’s latency.

This field is a member of oneof _silence_duration_ms.

Type: int

class EndSensitivity(value)[source]¶

Bases: proto.enums.Enum

Determines how end of speech is detected.

Values:

END_SENSITIVITY_UNSPECIFIED (0):: The default is END_SENSITIVITY_HIGH.
END_SENSITIVITY_HIGH (1):: Automatic detection ends speech more often.
END_SENSITIVITY_LOW (2):: Automatic detection ends speech less often.

class StartSensitivity(value)[source]¶

Bases: proto.enums.Enum

Determines how start of speech is detected.

Values:

START_SENSITIVITY_UNSPECIFIED (0):: The default is START_SENSITIVITY_HIGH.
START_SENSITIVITY_HIGH (1):: Automatic detection will detect the start of speech more often.
START_SENSITIVITY_LOW (2):: Automatic detection will detect the start of speech less often.

class TurnCoverage(value)[source]¶

Bases: proto.enums.Enum

Options about which input is included in the user’s turn.

Values:

TURN_COVERAGE_UNSPECIFIED (0):: If unspecified, the default behavior is TURN_INCLUDES_ONLY_ACTIVITY.
TURN_INCLUDES_ONLY_ACTIVITY (1):: The users turn only includes activity since the last turn, excluding inactivity (e.g. silence on the audio stream). This is the default behavior.
TURN_INCLUDES_ALL_INPUT (2):: The users turn includes all realtime input since the last turn, including inactivity (e.g. silence on the audio stream).

class google.ai.generativelanguage_v1beta.types.RelevantChunk(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

The information for a chunk relevant to a query.

chunk_relevance_score¶

Chunk relevance to the query.

Type: float

chunk¶

Chunk associated with the query.

Type: google.ai.generativelanguage_v1beta.types.Chunk

document¶

Document associated with the chunk.

Type: google.ai.generativelanguage_v1beta.types.Document

class google.ai.generativelanguage_v1beta.types.RetrievalMetadata(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Metadata related to retrieval in the grounding flow.

google_search_dynamic_retrieval_score¶

Optional. Score indicating how likely information from google search could help answer the prompt. The score is in the range [0, 1], where 0 is the least likely and 1 is the most likely. This score is only populated when google search grounding and dynamic retrieval is enabled. It will be compared to the threshold to determine whether to trigger google search.

Type: float

class google.ai.generativelanguage_v1beta.types.SafetyFeedback(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Safety feedback for an entire request.

This field is populated if content in the input and/or response is blocked due to safety settings. SafetyFeedback may not exist for every HarmCategory. Each SafetyFeedback will return the safety settings used by the request as well as the lowest HarmProbability that should be allowed in order to return a result.

rating¶

Safety rating evaluated from content.

Type: google.ai.generativelanguage_v1beta.types.SafetyRating

setting¶

Safety settings applied to the request.

Type: google.ai.generativelanguage_v1beta.types.SafetySetting

class google.ai.generativelanguage_v1beta.types.SafetyRating(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Safety rating for a piece of content.

The safety rating contains the category of harm and the harm probability level in that category for a piece of content. Content is classified for safety across a number of harm categories and the probability of the harm classification is included here.

category¶

Required. The category for this rating.

Type: google.ai.generativelanguage_v1beta.types.HarmCategory

probability¶

Required. The probability of harm for this content.

Type: google.ai.generativelanguage_v1beta.types.SafetyRating.HarmProbability

blocked¶

Was this content blocked because of this rating?

Type: bool

class HarmProbability(value)[source]¶

Bases: proto.enums.Enum

The probability that a piece of content is harmful.

The classification system gives the probability of the content being unsafe. This does not indicate the severity of harm for a piece of content.

Values:

HARM_PROBABILITY_UNSPECIFIED (0):: Probability is unspecified.
NEGLIGIBLE (1):: Content has a negligible chance of being unsafe.
LOW (2):: Content has a low chance of being unsafe.
MEDIUM (3):: Content has a medium chance of being unsafe.
HIGH (4):: Content has a high chance of being unsafe.

class google.ai.generativelanguage_v1beta.types.SafetySetting(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Safety setting, affecting the safety-blocking behavior.

Passing a safety setting for a category changes the allowed probability that content is blocked.

category¶

Required. The category for this setting.

Type: google.ai.generativelanguage_v1beta.types.HarmCategory

threshold¶

Required. Controls the probability threshold at which harm is blocked.

Type: google.ai.generativelanguage_v1beta.types.SafetySetting.HarmBlockThreshold

class HarmBlockThreshold(value)[source]¶

Bases: proto.enums.Enum

Block at and beyond a specified harm probability.

Values:

HARM_BLOCK_THRESHOLD_UNSPECIFIED (0):: Threshold is unspecified.
BLOCK_LOW_AND_ABOVE (1):: Content with NEGLIGIBLE will be allowed.
BLOCK_MEDIUM_AND_ABOVE (2):: Content with NEGLIGIBLE and LOW will be allowed.
BLOCK_ONLY_HIGH (3):: Content with NEGLIGIBLE, LOW, and MEDIUM will be allowed.
BLOCK_NONE (4):: All content will be allowed.
OFF (5):: Turn off the safety filter.

class google.ai.generativelanguage_v1beta.types.Schema(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

The Schema object allows the definition of input and output data types. These types can be objects, but also primitives and arrays. Represents a select subset of an OpenAPI 3.0 schema object.

type_¶

Required. Data type.

Type: google.ai.generativelanguage_v1beta.types.Type

format_¶

Optional. The format of the data. Any value is allowed, but most do not trigger any special functionality.

Type: str

title¶

Optional. The title of the schema.

Type: str

description¶

Optional. A brief description of the parameter. This could contain examples of use. Parameter description may be formatted as Markdown.

Type: str

nullable¶

Optional. Indicates if the value may be null.

Type: bool

enum¶

Optional. Possible values of the element of Type.STRING with enum format. For example we can define an Enum Direction as : {type:STRING, format:enum, enum:[“EAST”, NORTH”, “SOUTH”, “WEST”]}

Type: MutableSequence[str]

items¶

Optional. Schema of the elements of Type.ARRAY.

This field is a member of oneof _items.

Type: google.ai.generativelanguage_v1beta.types.Schema

max_items¶

Optional. Maximum number of the elements for Type.ARRAY.

Type: int

min_items¶

Optional. Minimum number of the elements for Type.ARRAY.

Type: int

properties¶

Optional. Properties of Type.OBJECT.

Type: MutableMapping[str, google.ai.generativelanguage_v1beta.types.Schema]

required¶

Optional. Required properties of Type.OBJECT.

Type: MutableSequence[str]

min_properties¶

Optional. Minimum number of the properties for Type.OBJECT.

Type: int

max_properties¶

Optional. Maximum number of the properties for Type.OBJECT.

Type: int

minimum¶

Optional. SCHEMA FIELDS FOR TYPE INTEGER and NUMBER Minimum value of the Type.INTEGER and Type.NUMBER

This field is a member of oneof _minimum.

Type: float

maximum¶

Optional. Maximum value of the Type.INTEGER and Type.NUMBER

This field is a member of oneof _maximum.

Type: float

min_length¶

Optional. SCHEMA FIELDS FOR TYPE STRING Minimum length of the Type.STRING

Type: int

max_length¶

Optional. Maximum length of the Type.STRING

Type: int

pattern¶

Optional. Pattern of the Type.STRING to restrict a string to a regular expression.

Type: str

example¶

Optional. Example of the object. Will only populated when the object is the root.

Type: google.protobuf.struct_pb2.Value

any_of¶

Optional. The value should be validated against any (one or more) of the subschemas in the list.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.Schema]

property_ordering¶

Optional. The order of the properties. Not a standard field in open api spec. Used to determine the order of the properties in the response.

Type: MutableSequence[str]

default¶

Optional. Default value of the field. Per JSON Schema, this field is intended for documentation generators and doesn’t affect validation. Thus it’s included here and ignored so that developers who send schemas with a default field don’t get unknown-field errors.

Type: google.protobuf.struct_pb2.Value

class PropertiesEntry(mapping=None, *, ignore_unknown_fields=False, **kwargs)¶: Bases: proto.message.Message

class google.ai.generativelanguage_v1beta.types.SearchEntryPoint(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Google search entry point.

rendered_content¶

Optional. Web content snippet that can be embedded in a web page or an app webview.

Type: str

sdk_blob¶

Optional. Base64 encoded JSON representing array of <search term, search url> tuple.

Type: bytes

class google.ai.generativelanguage_v1beta.types.Segment(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Segment of the content.

part_index¶

Output only. The index of a Part object within its parent Content object.

Type: int

start_index¶

Output only. Start index in the given Part, measured in bytes. Offset from the start of the Part, inclusive, starting at zero.

Type: int

end_index¶

Output only. End index in the given Part, measured in bytes. Offset from the start of the Part, exclusive, starting at zero.

Type: int

text¶

Output only. The text corresponding to the segment from the response.

Type: str

class google.ai.generativelanguage_v1beta.types.SemanticRetrieverConfig(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Configuration for retrieving grounding content from a Corpus or Document created using the Semantic Retriever API.

source¶

Required. Name of the resource for retrieval. Example: corpora/123 or corpora/123/documents/abc.

Type: str

query¶

Required. Query to use for matching Chunks in the given resource by similarity.

Type: google.ai.generativelanguage_v1beta.types.Content

metadata_filters¶

Optional. Filters for selecting Documents and/or Chunks from the resource.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.MetadataFilter]

max_chunks_count¶

Optional. Maximum number of relevant Chunks to retrieve.

This field is a member of oneof _max_chunks_count.

Type: int

minimum_relevance_score¶

Optional. Minimum relevance score for retrieved relevant Chunks.

This field is a member of oneof _minimum_relevance_score.

Type: float

class google.ai.generativelanguage_v1beta.types.SessionResumptionConfig(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Session resumption configuration.

This message is included in the session configuration as BidiGenerateContentSetup.session_resumption. If configured, the server will send SessionResumptionUpdate messages.

handle¶

The handle of a previous session. If not present then a new session is created.

Session handles come from SessionResumptionUpdate.token values in previous connections.

This field is a member of oneof _handle.

Type: str

class google.ai.generativelanguage_v1beta.types.SessionResumptionUpdate(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Update of the session resumption state.

Only sent if BidiGenerateContentSetup.session_resumption was set.

new_handle¶

New handle that represents a state that can be resumed. Empty if resumable=false.

Type: str

resumable¶

True if the current session can be resumed at this point.

Resumption is not possible at some points in the session. For example, when the model is executing function calls or generating. Resuming the session (using a previous session token) in such a state will result in some data loss. In these cases, new_handle will be empty and resumable will be false.

Type: bool

class google.ai.generativelanguage_v1beta.types.SpeakerVoiceConfig(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

The configuration for a single speaker in a multi speaker setup.

speaker¶

Required. The name of the speaker to use. Should be the same as in the prompt.

Type: str

voice_config¶

Required. The configuration for the voice to use.

Type: google.ai.generativelanguage_v1beta.types.VoiceConfig

class google.ai.generativelanguage_v1beta.types.SpeechConfig(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

The speech generation config.

voice_config¶

The configuration in case of single-voice output.

Type: google.ai.generativelanguage_v1beta.types.VoiceConfig

multi_speaker_voice_config¶

Optional. The configuration for the multi-speaker setup. It is mutually exclusive with the voice_config field.

Type: google.ai.generativelanguage_v1beta.types.MultiSpeakerVoiceConfig

language_code¶

Optional. Language code (in BCP 47 format, e.g. “en-US”) for speech synthesis.

Valid values are: de-DE, en-AU, en-GB, en-IN, en-US, es-US, fr-FR, hi-IN, pt-BR, ar-XA, es-ES, fr-CA, id-ID, it-IT, ja-JP, tr-TR, vi-VN, bn-IN, gu-IN, kn-IN, ml-IN, mr-IN, ta-IN, te-IN, nl-NL, ko-KR, cmn-CN, pl-PL, ru-RU, and th-TH.

Type: str

class google.ai.generativelanguage_v1beta.types.StringList(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

User provided string values assigned to a single metadata key.

values¶

The string values of the metadata to store.

Type: MutableSequence[str]

class google.ai.generativelanguage_v1beta.types.TaskType(value)[source]¶

Bases: proto.enums.Enum

Type of task for which the embedding will be used.

Values:

TASK_TYPE_UNSPECIFIED (0):: Unset value, which will default to one of the other enum values.
RETRIEVAL_QUERY (1):: Specifies the given text is a query in a search/retrieval setting.
RETRIEVAL_DOCUMENT (2):: Specifies the given text is a document from the corpus being searched.
SEMANTIC_SIMILARITY (3):: Specifies the given text will be used for STS.
CLASSIFICATION (4):: Specifies that the given text will be classified.
CLUSTERING (5):: Specifies that the embeddings will be used for clustering.
QUESTION_ANSWERING (6):: Specifies that the given text will be used for question answering.
FACT_VERIFICATION (7):: Specifies that the given text will be used for fact verification.
CODE_RETRIEVAL_QUERY (8):: Specifies that the given text will be used for code retrieval.

class google.ai.generativelanguage_v1beta.types.TextCompletion(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Output text returned from a model.

output¶

Output only. The generated text returned from the model.

Type: str

safety_ratings¶

Ratings for the safety of a response.

There is at most one rating per category.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.SafetyRating]

citation_metadata¶

Output only. Citation information for model-generated output in this TextCompletion.

This field may be populated with attribution information for any text included in the output.

This field is a member of oneof _citation_metadata.

Type: google.ai.generativelanguage_v1beta.types.CitationMetadata

class google.ai.generativelanguage_v1beta.types.TextPrompt(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Text given to the model as a prompt.

The Model will use this TextPrompt to Generate a text completion.

text¶

Required. The prompt text.

Type: str

class google.ai.generativelanguage_v1beta.types.ThinkingConfig(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Config for thinking features.

include_thoughts¶

Indicates whether to include thoughts in the response. If true, thoughts are returned only when available.

This field is a member of oneof _include_thoughts.

Type: bool

thinking_budget¶

The number of thoughts tokens that the model should generate.

This field is a member of oneof _thinking_budget.

Type: int

class google.ai.generativelanguage_v1beta.types.Tool(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Tool details that the model may use to generate response.

A Tool is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model.

Next ID: 12

function_declarations¶

Optional. A list of FunctionDeclarations available to the model that can be used for function calling.

The model or system does not execute the function. Instead the defined function may be returned as a [FunctionCall][google.ai.generativelanguage.v1beta.Part.function_call] with arguments to the client side for execution. The model may decide to call a subset of these functions by populating [FunctionCall][google.ai.generativelanguage.v1beta.Part.function_call] in the response. The next conversation turn may contain a [FunctionResponse][google.ai.generativelanguage.v1beta.Part.function_response] with the [Content.role][google.ai.generativelanguage.v1beta.Content.role] “function” generation context for the next model turn.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.FunctionDeclaration]

google_search_retrieval¶

Optional. Retrieval tool that is powered by Google search.

Type: google.ai.generativelanguage_v1beta.types.GoogleSearchRetrieval

code_execution¶

Optional. Enables the model to execute code as part of generation.

Type: google.ai.generativelanguage_v1beta.types.CodeExecution

google_search¶

Optional. GoogleSearch tool type. Tool to support Google Search in Model. Powered by Google.

Type: google.ai.generativelanguage_v1beta.types.Tool.GoogleSearch

computer_use¶

Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations.

Type: google.ai.generativelanguage_v1beta.types.Tool.ComputerUse

url_context¶

Optional. Tool to support URL context retrieval.

Type: google.ai.generativelanguage_v1beta.types.UrlContext

class ComputerUse(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Computer Use tool type.

environment¶

Required. The environment being operated.

Type: google.ai.generativelanguage_v1beta.types.Tool.ComputerUse.Environment

excluded_predefined_functions¶

Optional. By default, predefined functions are included in the final model call. Some of them can be explicitly excluded from being automatically included. This can serve two purposes:

Using a more restricted / different action
space.
Improving the definitions / instructions of
predefined functions.

Type: MutableSequence[str]

class Environment(value)[source]¶

Bases: proto.enums.Enum

Represents the environment being operated, such as a web browser.

Values:

ENVIRONMENT_UNSPECIFIED (0):: Defaults to browser.
ENVIRONMENT_BROWSER (1):: Operates in a web browser.

class GoogleSearch(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

GoogleSearch tool type. Tool to support Google Search in Model. Powered by Google.

time_range_filter¶

Optional. Filter search results to a specific time range. If customers set a start time, they must set an end time (and vice versa).

Type: google.type.interval_pb2.Interval

class google.ai.generativelanguage_v1beta.types.ToolConfig(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

The Tool configuration containing parameters for specifying Tool use in the request.

function_calling_config¶

Optional. Function calling config.

Type: google.ai.generativelanguage_v1beta.types.FunctionCallingConfig

class google.ai.generativelanguage_v1beta.types.TransferOwnershipRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Request to transfer the ownership of the tuned model.

name¶

Required. The resource name of the tuned model to transfer ownership.

Format: tunedModels/my-model-id

Type: str

email_address¶

Required. The email address of the user to whom the tuned model is being transferred to.

Type: str

class google.ai.generativelanguage_v1beta.types.TransferOwnershipResponse(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Response from TransferOwnership.

class google.ai.generativelanguage_v1beta.types.TunedModel(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

A fine-tuned model created using ModelService.CreateTunedModel.

This message has oneof fields (mutually exclusive fields). For each oneof, at most one member field can be set at the same time. Setting any member of the oneof automatically clears all other members.

tuned_model_source¶

Optional. TunedModel to use as the starting point for training the new model.

This field is a member of oneof source_model.

Type: google.ai.generativelanguage_v1beta.types.TunedModelSource

base_model¶

Immutable. The name of the Model to tune. Example: models/gemini-1.5-flash-001

This field is a member of oneof source_model.

Type: str

name¶

Output only. The tuned model name. A unique name will be generated on create. Example: tunedModels/az2mb0bpw6i If display_name is set on create, the id portion of the name will be set by concatenating the words of the display_name with hyphens and adding a random portion for uniqueness.

Example:

display_name = Sentence Translator
name = tunedModels/sentence-translator-u3b7m

Type: str

display_name¶

Optional. The name to display for this model in user interfaces. The display name must be up to 40 characters including spaces.

Type: str

description¶

Optional. A short description of this model.

Type: str

temperature¶

Optional. Controls the randomness of the output.

Values can range over [0.0,1.0], inclusive. A value closer to 1.0 will produce responses that are more varied, while a value closer to 0.0 will typically result in less surprising responses from the model.

This value specifies default to be the one used by the base model while creating the model.

This field is a member of oneof _temperature.

Type: float

top_p¶

Optional. For Nucleus sampling.

Nucleus sampling considers the smallest set of tokens whose probability sum is at least top_p.

This value specifies default to be the one used by the base model while creating the model.

This field is a member of oneof _top_p.

Type: float

top_k¶

Optional. For Top-k sampling.

Top-k sampling considers the set of top_k most probable tokens. This value specifies default to be used by the backend while making the call to the model.

This value specifies default to be the one used by the base model while creating the model.

This field is a member of oneof _top_k.

Type: int

state¶

Output only. The state of the tuned model.

Type: google.ai.generativelanguage_v1beta.types.TunedModel.State

create_time¶

Output only. The timestamp when this model was created.

Type: google.protobuf.timestamp_pb2.Timestamp

update_time¶

Output only. The timestamp when this model was updated.

Type: google.protobuf.timestamp_pb2.Timestamp

tuning_task¶

Required. The tuning task that creates the tuned model.

Type: google.ai.generativelanguage_v1beta.types.TuningTask

reader_project_numbers¶

Optional. List of project numbers that have read access to the tuned model.

Type: MutableSequence[int]

class State(value)[source]¶

Bases: proto.enums.Enum

The state of the tuned model.

Values:

STATE_UNSPECIFIED (0):: The default value. This value is unused.
CREATING (1):: The model is being created.
ACTIVE (2):: The model is ready to be used.
FAILED (3):: The model failed to be created.

class google.ai.generativelanguage_v1beta.types.TunedModelSource(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Tuned model as a source for training a new model.

tuned_model¶

Immutable. The name of the TunedModel to use as the starting point for training the new model. Example: tunedModels/my-tuned-model

Type: str

base_model¶

Output only. The name of the base Model this TunedModel was tuned from. Example: models/gemini-1.5-flash-001

Type: str

class google.ai.generativelanguage_v1beta.types.TuningExample(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

A single example for tuning.

text_input¶

Optional. Text model input.

This field is a member of oneof model_input.

Type: str

output¶

Required. The expected model output.

Type: str

class google.ai.generativelanguage_v1beta.types.TuningExamples(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

A set of tuning examples. Can be training or validation data.

examples¶

The examples. Example input can be for text or discuss, but all examples in a set must be of the same type.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.TuningExample]

class google.ai.generativelanguage_v1beta.types.TuningSnapshot(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Record for a single tuning step.

step¶

Output only. The tuning step.

Type: int

epoch¶

Output only. The epoch this step was part of.

Type: int

mean_loss¶

Output only. The mean loss of the training examples for this step.

Type: float

compute_time¶

Output only. The timestamp when this metric was computed.

Type: google.protobuf.timestamp_pb2.Timestamp

class google.ai.generativelanguage_v1beta.types.TuningTask(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Tuning tasks that create tuned models.

start_time¶

Output only. The timestamp when tuning this model started.

Type: google.protobuf.timestamp_pb2.Timestamp

complete_time¶

Output only. The timestamp when tuning this model completed.

Type: google.protobuf.timestamp_pb2.Timestamp

snapshots¶

Output only. Metrics collected during tuning.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.TuningSnapshot]

training_data¶

Required. Input only. Immutable. The model training data.

Type: google.ai.generativelanguage_v1beta.types.Dataset

hyperparameters¶

Immutable. Hyperparameters controlling the tuning process. If not provided, default values will be used.

Type: google.ai.generativelanguage_v1beta.types.Hyperparameters

class google.ai.generativelanguage_v1beta.types.Type(value)[source]¶

Bases: proto.enums.Enum

Type contains the list of OpenAPI data types as defined by https://spec.openapis.org/oas/v3.0.3#data-types

Values:

TYPE_UNSPECIFIED (0):: Not specified, should not be used.
STRING (1):: String type.
NUMBER (2):: Number type.
INTEGER (3):: Integer type.
BOOLEAN (4):: Boolean type.
ARRAY (5):: Array type.
OBJECT (6):: Object type.
NULL (7):: Null type.

class google.ai.generativelanguage_v1beta.types.UpdateCachedContentRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Request to update CachedContent.

cached_content¶

Required. The content cache entry to update

Type: google.ai.generativelanguage_v1beta.types.CachedContent

update_mask¶

The list of fields to update.

Type: google.protobuf.field_mask_pb2.FieldMask

class google.ai.generativelanguage_v1beta.types.UpdateChunkRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Request to update a Chunk.

chunk¶

Required. The Chunk to update.

Type: google.ai.generativelanguage_v1beta.types.Chunk

update_mask¶

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

Type: google.protobuf.field_mask_pb2.FieldMask

class google.ai.generativelanguage_v1beta.types.UpdateCorpusRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Request to update a Corpus.

corpus¶

Required. The Corpus to update.

Type: google.ai.generativelanguage_v1beta.types.Corpus

update_mask¶

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

Type: google.protobuf.field_mask_pb2.FieldMask

class google.ai.generativelanguage_v1beta.types.UpdateDocumentRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Request to update a Document.

document¶

Required. The Document to update.

Type: google.ai.generativelanguage_v1beta.types.Document

update_mask¶

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

Type: google.protobuf.field_mask_pb2.FieldMask

class google.ai.generativelanguage_v1beta.types.UpdatePermissionRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Request to update the Permission.

permission¶

Required. The permission to update.

The permission’s name field is used to identify the permission to update.

Type: google.ai.generativelanguage_v1beta.types.Permission

update_mask¶

Required. The list of fields to update. Accepted ones:

role (Permission.role field)

Type: google.protobuf.field_mask_pb2.FieldMask

class google.ai.generativelanguage_v1beta.types.UpdateTunedModelRequest(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Request to update a TunedModel.

tuned_model¶

Required. The tuned model to update.

Type: google.ai.generativelanguage_v1beta.types.TunedModel

update_mask¶

Optional. The list of fields to update.

Type: google.protobuf.field_mask_pb2.FieldMask

class google.ai.generativelanguage_v1beta.types.UrlContext(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Tool to support URL context retrieval.

class google.ai.generativelanguage_v1beta.types.UrlContextMetadata(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Metadata related to url context retrieval tool.

url_metadata¶

List of url context.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.UrlMetadata]

class google.ai.generativelanguage_v1beta.types.UrlMetadata(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Context of the a single url retrieval.

retrieved_url¶

Retrieved url by the tool.

Type: str

url_retrieval_status¶

Status of the url retrieval.

Type: google.ai.generativelanguage_v1beta.types.UrlMetadata.UrlRetrievalStatus

class UrlRetrievalStatus(value)[source]¶

Bases: proto.enums.Enum

Status of the url retrieval.

Values:

URL_RETRIEVAL_STATUS_UNSPECIFIED (0):: Default value. This value is unused.
URL_RETRIEVAL_STATUS_SUCCESS (1):: Url retrieval is successful.
URL_RETRIEVAL_STATUS_ERROR (2):: Url retrieval is failed due to error.
URL_RETRIEVAL_STATUS_PAYWALL (3):: Url retrieval is failed because the content is behind paywall.
URL_RETRIEVAL_STATUS_UNSAFE (4):: Url retrieval is failed because the content is unsafe.

class google.ai.generativelanguage_v1beta.types.UsageMetadata(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Usage metadata about response(s).

prompt_token_count¶

Output only. Number of tokens in the prompt. When cached_content is set, this is still the total effective prompt size meaning this includes the number of tokens in the cached content.

Type: int

cached_content_token_count¶

Number of tokens in the cached part of the prompt (the cached content)

Type: int

response_token_count¶

Output only. Total number of tokens across all the generated response candidates.

Type: int

tool_use_prompt_token_count¶

Output only. Number of tokens present in tool-use prompt(s).

Type: int

thoughts_token_count¶

Output only. Number of tokens of thoughts for thinking models.

Type: int

total_token_count¶

Output only. Total token count for the generation request (prompt + response candidates).

Type: int

prompt_tokens_details¶

Output only. List of modalities that were processed in the request input.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.ModalityTokenCount]

cache_tokens_details¶

Output only. List of modalities of the cached content in the request input.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.ModalityTokenCount]

response_tokens_details¶

Output only. List of modalities that were returned in the response.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.ModalityTokenCount]

tool_use_prompt_tokens_details¶

Output only. List of modalities that were processed for tool-use request inputs.

Type: MutableSequence[google.ai.generativelanguage_v1beta.types.ModalityTokenCount]

class google.ai.generativelanguage_v1beta.types.Video(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Representation of a video.

This message has oneof fields (mutually exclusive fields). For each oneof, at most one member field can be set at the same time. Setting any member of the oneof automatically clears all other members.

video¶

Raw bytes.

This field is a member of oneof content.

Type: bytes

uri¶

Path to another storage.

This field is a member of oneof content.

Type: str

class google.ai.generativelanguage_v1beta.types.VideoFileMetadata(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Metadata for a video File.

video_duration¶

Duration of the video.

Type: google.protobuf.duration_pb2.Duration

class google.ai.generativelanguage_v1beta.types.VideoMetadata(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

Metadata describes the input video content.

start_offset¶

Optional. The start offset of the video.

Type: google.protobuf.duration_pb2.Duration

end_offset¶

Optional. The end offset of the video.

Type: google.protobuf.duration_pb2.Duration

fps¶

Optional. The frame rate of the video sent to the model. If not specified, the default value will be 1.0. The fps range is (0.0, 24.0].

Type: float

class google.ai.generativelanguage_v1beta.types.VoiceConfig(mapping=None, *, ignore_unknown_fields=False, **kwargs)[source]¶

Bases: proto.message.Message

The configuration for the voice to use.

prebuilt_voice_config¶

The configuration for the prebuilt voice to use.

This field is a member of oneof voice_config.

Type: google.ai.generativelanguage_v1beta.types.PrebuiltVoiceConfig

Types for Google Ai Generativelanguage v1beta API¶

google-ai-generativelanguage

Navigation

Related Topics