File: aiplatform_v1.projects.locations.publishers.models.html

package info (click to toggle)
python-googleapi 2.182.0-1
links: PTS
area: main
in suites: forky, sid
size: 533,852 kB
sloc: python: 11,076; javascript: 249; sh: 114; makefile: 59
file content (2308 lines) | stat: -rw-r--r-- 240,879 bytes
<html><body>
<style>

body, h1, h2, h3, div, span, p, pre, a {
  margin: 0;
  padding: 0;
  border: 0;
  font-weight: inherit;
  font-style: inherit;
  font-size: 100%;
  font-family: inherit;
  vertical-align: baseline;
}

body {
  font-size: 13px;
  padding: 1em;
}

h1 {
  font-size: 26px;
  margin-bottom: 1em;
}

h2 {
  font-size: 24px;
  margin-bottom: 1em;
}

h3 {
  font-size: 20px;
  margin-bottom: 1em;
  margin-top: 1em;
}

pre, code {
  line-height: 1.5;
  font-family: Monaco, 'DejaVu Sans Mono', 'Bitstream Vera Sans Mono', 'Lucida Console', monospace;
}

pre {
  margin-top: 0.5em;
}

h1, h2, h3, p {
  font-family: Arial, sans serif;
}

h1, h2, h3 {
  border-bottom: solid #CCC 1px;
}

.toc_element {
  margin-top: 0.5em;
}

.firstline {
  margin-left: 2 em;
}

.method  {
  margin-top: 1em;
  border: solid 1px #CCC;
  padding: 1em;
  background: #EEE;
}

.details {
  font-weight: bold;
  font-size: 14px;
}

</style>

<h1><a href="aiplatform_v1.html">Vertex AI API</a> . <a href="aiplatform_v1.projects.html">projects</a> . <a href="aiplatform_v1.projects.locations.html">locations</a> . <a href="aiplatform_v1.projects.locations.publishers.html">publishers</a> . <a href="aiplatform_v1.projects.locations.publishers.models.html">models</a></h1>
<h2>Instance Methods</h2>
<p class="toc_element">
  <code><a href="#close">close()</a></code></p>
<p class="firstline">Close httplib2 connections.</p>
<p class="toc_element">
  <code><a href="#computeTokens">computeTokens(endpoint, body=None, x__xgafv=None)</a></code></p>
<p class="firstline">Return a list of tokens based on the input text.</p>
<p class="toc_element">
  <code><a href="#countTokens">countTokens(endpoint, body=None, x__xgafv=None)</a></code></p>
<p class="firstline">Perform a token counting.</p>
<p class="toc_element">
  <code><a href="#fetchPredictOperation">fetchPredictOperation(endpoint, body=None, x__xgafv=None)</a></code></p>
<p class="firstline">Fetch an asynchronous online prediction operation.</p>
<p class="toc_element">
  <code><a href="#generateContent">generateContent(model, body=None, x__xgafv=None)</a></code></p>
<p class="firstline">Generate content with multimodal inputs.</p>
<p class="toc_element">
  <code><a href="#predict">predict(endpoint, body=None, x__xgafv=None)</a></code></p>
<p class="firstline">Perform an online prediction.</p>
<p class="toc_element">
  <code><a href="#predictLongRunning">predictLongRunning(endpoint, body=None, x__xgafv=None)</a></code></p>
<p class="firstline"></p>
<p class="toc_element">
  <code><a href="#rawPredict">rawPredict(endpoint, body=None, x__xgafv=None)</a></code></p>
<p class="firstline">Perform an online prediction with an arbitrary HTTP payload. The response includes the following HTTP headers: * `X-Vertex-AI-Endpoint-Id`: ID of the Endpoint that served this prediction. * `X-Vertex-AI-Deployed-Model-Id`: ID of the Endpoint's DeployedModel that served this prediction.</p>
<p class="toc_element">
  <code><a href="#serverStreamingPredict">serverStreamingPredict(endpoint, body=None, x__xgafv=None)</a></code></p>
<p class="firstline">Perform a server-side streaming online prediction request for Vertex LLM streaming.</p>
<p class="toc_element">
  <code><a href="#streamGenerateContent">streamGenerateContent(model, body=None, x__xgafv=None)</a></code></p>
<p class="firstline">Generate content with multimodal inputs with streaming support.</p>
<p class="toc_element">
  <code><a href="#streamRawPredict">streamRawPredict(endpoint, body=None, x__xgafv=None)</a></code></p>
<p class="firstline">Perform a streaming online prediction with an arbitrary HTTP payload.</p>
<h3>Method Details</h3>
<div class="method">
    <code class="details" id="close">close()</code>
  <pre>Close httplib2 connections.</pre>
</div>

<div class="method">
    <code class="details" id="computeTokens">computeTokens(endpoint, body=None, x__xgafv=None)</code>
  <pre>Return a list of tokens based on the input text.

Args:
  endpoint: string, Required. The name of the Endpoint requested to get lists of tokens and token ids. (required)
  body: object, The request body.
    The object takes the form of:

{ # Request message for ComputeTokens RPC call.
  &quot;contents&quot;: [ # Optional. Input content.
    { # 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.
      &quot;parts&quot;: [ # Required. Ordered `Parts` that constitute a single message. Parts may have different IANA MIME types.
        { # 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 `inline_data` or `file_data` field is filled with raw bytes.
          &quot;codeExecutionResult&quot;: { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. Result of executing the [ExecutableCode].
            &quot;outcome&quot;: &quot;A String&quot;, # Required. Outcome of the code execution.
            &quot;output&quot;: &quot;A String&quot;, # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
          },
          &quot;executableCode&quot;: { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is meant to be executed.
            &quot;code&quot;: &quot;A String&quot;, # Required. The code to be executed.
            &quot;language&quot;: &quot;A String&quot;, # Required. Programming language of the `code`.
          },
          &quot;fileData&quot;: { # URI based data. # Optional. URI based data.
            &quot;displayName&quot;: &quot;A String&quot;, # Optional. Display name of the file data. Used to provide a label or filename to distinguish file datas. This field is only returned in PromptMessage for prompt management. It is currently used in the Gemini GenerateContent calls only when server side tools (code_execution, google_search, and url_context) are enabled.
            &quot;fileUri&quot;: &quot;A String&quot;, # Required. URI.
            &quot;mimeType&quot;: &quot;A String&quot;, # Required. The IANA standard MIME type of the source data.
          },
          &quot;functionCall&quot;: { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] with the parameters and their values.
            &quot;args&quot;: { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details.
              &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
            },
            &quot;name&quot;: &quot;A String&quot;, # Required. The name of the function to call. Matches [FunctionDeclaration.name].
          },
          &quot;functionResponse&quot;: { # 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 a [FunctionCall] made based on model prediction. # Optional. 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 call. It is used as context to the model.
            &quot;name&quot;: &quot;A String&quot;, # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name].
            &quot;response&quot;: { # Required. The function response in JSON object format. Use &quot;output&quot; key to specify function output and &quot;error&quot; key to specify error details (if any). If &quot;output&quot; and &quot;error&quot; keys are not specified, then whole &quot;response&quot; is treated as function output.
              &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
            },
          },
          &quot;inlineData&quot;: { # Content blob. # Optional. Inlined bytes data.
            &quot;data&quot;: &quot;A String&quot;, # Required. Raw bytes.
            &quot;displayName&quot;: &quot;A String&quot;, # Optional. Display name of the blob. Used to provide a label or filename to distinguish blobs. This field is only returned in PromptMessage for prompt management. It is currently used in the Gemini GenerateContent calls only when server side tools (code_execution, google_search, and url_context) are enabled.
            &quot;mimeType&quot;: &quot;A String&quot;, # Required. The IANA standard MIME type of the source data.
          },
          &quot;text&quot;: &quot;A String&quot;, # Optional. Text part (can be code).
          &quot;thought&quot;: True or False, # Optional. Indicates if the part is thought from the model.
          &quot;thoughtSignature&quot;: &quot;A String&quot;, # Optional. An opaque signature for the thought so it can be reused in subsequent requests.
          &quot;videoMetadata&quot;: { # Metadata describes the input video content. # Optional. Video metadata. The metadata should only be specified while the video data is presented in inline_data or file_data.
            &quot;endOffset&quot;: &quot;A String&quot;, # Optional. The end offset of the video.
            &quot;fps&quot;: 3.14, # 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].
            &quot;startOffset&quot;: &quot;A String&quot;, # Optional. The start offset of the video.
          },
        },
      ],
      &quot;role&quot;: &quot;A String&quot;, # Optional. The producer of the content. Must be either &#x27;user&#x27; or &#x27;model&#x27;. Useful to set for multi-turn conversations, otherwise can be left blank or unset.
    },
  ],
  &quot;instances&quot;: [ # Optional. The instances that are the input to token computing API call. Schema is identical to the prediction schema of the text model, even for the non-text models, like chat models, or Codey models.
    &quot;&quot;,
  ],
  &quot;model&quot;: &quot;A String&quot;, # Optional. The name of the publisher model requested to serve the prediction. Format: projects/{project}/locations/{location}/publishers/*/models/*
}

  x__xgafv: string, V1 error format.
    Allowed values
      1 - v1 error format
      2 - v2 error format

Returns:
  An object of the form:

    { # Response message for ComputeTokens RPC call.
  &quot;tokensInfo&quot;: [ # Lists of tokens info from the input. A ComputeTokensRequest could have multiple instances with a prompt in each instance. We also need to return lists of tokens info for the request with multiple instances.
    { # Tokens info with a list of tokens and the corresponding list of token ids.
      &quot;role&quot;: &quot;A String&quot;, # Optional. Optional fields for the role from the corresponding Content.
      &quot;tokenIds&quot;: [ # A list of token ids from the input.
        &quot;A String&quot;,
      ],
      &quot;tokens&quot;: [ # A list of tokens from the input.
        &quot;A String&quot;,
      ],
    },
  ],
}</pre>
</div>

<div class="method">
    <code class="details" id="countTokens">countTokens(endpoint, body=None, x__xgafv=None)</code>
  <pre>Perform a token counting.

Args:
  endpoint: string, Required. The name of the Endpoint requested to perform token counting. Format: `projects/{project}/locations/{location}/endpoints/{endpoint}` (required)
  body: object, The request body.
    The object takes the form of:

{ # Request message for PredictionService.CountTokens.
  &quot;contents&quot;: [ # Optional. Input content.
    { # 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.
      &quot;parts&quot;: [ # Required. Ordered `Parts` that constitute a single message. Parts may have different IANA MIME types.
        { # 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 `inline_data` or `file_data` field is filled with raw bytes.
          &quot;codeExecutionResult&quot;: { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. Result of executing the [ExecutableCode].
            &quot;outcome&quot;: &quot;A String&quot;, # Required. Outcome of the code execution.
            &quot;output&quot;: &quot;A String&quot;, # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
          },
          &quot;executableCode&quot;: { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is meant to be executed.
            &quot;code&quot;: &quot;A String&quot;, # Required. The code to be executed.
            &quot;language&quot;: &quot;A String&quot;, # Required. Programming language of the `code`.
          },
          &quot;fileData&quot;: { # URI based data. # Optional. URI based data.
            &quot;displayName&quot;: &quot;A String&quot;, # Optional. Display name of the file data. Used to provide a label or filename to distinguish file datas. This field is only returned in PromptMessage for prompt management. It is currently used in the Gemini GenerateContent calls only when server side tools (code_execution, google_search, and url_context) are enabled.
            &quot;fileUri&quot;: &quot;A String&quot;, # Required. URI.
            &quot;mimeType&quot;: &quot;A String&quot;, # Required. The IANA standard MIME type of the source data.
          },
          &quot;functionCall&quot;: { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] with the parameters and their values.
            &quot;args&quot;: { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details.
              &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
            },
            &quot;name&quot;: &quot;A String&quot;, # Required. The name of the function to call. Matches [FunctionDeclaration.name].
          },
          &quot;functionResponse&quot;: { # 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 a [FunctionCall] made based on model prediction. # Optional. 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 call. It is used as context to the model.
            &quot;name&quot;: &quot;A String&quot;, # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name].
            &quot;response&quot;: { # Required. The function response in JSON object format. Use &quot;output&quot; key to specify function output and &quot;error&quot; key to specify error details (if any). If &quot;output&quot; and &quot;error&quot; keys are not specified, then whole &quot;response&quot; is treated as function output.
              &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
            },
          },
          &quot;inlineData&quot;: { # Content blob. # Optional. Inlined bytes data.
            &quot;data&quot;: &quot;A String&quot;, # Required. Raw bytes.
            &quot;displayName&quot;: &quot;A String&quot;, # Optional. Display name of the blob. Used to provide a label or filename to distinguish blobs. This field is only returned in PromptMessage for prompt management. It is currently used in the Gemini GenerateContent calls only when server side tools (code_execution, google_search, and url_context) are enabled.
            &quot;mimeType&quot;: &quot;A String&quot;, # Required. The IANA standard MIME type of the source data.
          },
          &quot;text&quot;: &quot;A String&quot;, # Optional. Text part (can be code).
          &quot;thought&quot;: True or False, # Optional. Indicates if the part is thought from the model.
          &quot;thoughtSignature&quot;: &quot;A String&quot;, # Optional. An opaque signature for the thought so it can be reused in subsequent requests.
          &quot;videoMetadata&quot;: { # Metadata describes the input video content. # Optional. Video metadata. The metadata should only be specified while the video data is presented in inline_data or file_data.
            &quot;endOffset&quot;: &quot;A String&quot;, # Optional. The end offset of the video.
            &quot;fps&quot;: 3.14, # 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].
            &quot;startOffset&quot;: &quot;A String&quot;, # Optional. The start offset of the video.
          },
        },
      ],
      &quot;role&quot;: &quot;A String&quot;, # Optional. The producer of the content. Must be either &#x27;user&#x27; or &#x27;model&#x27;. Useful to set for multi-turn conversations, otherwise can be left blank or unset.
    },
  ],
  &quot;generationConfig&quot;: { # Generation config. # Optional. Generation config that the model will use to generate the response.
    &quot;audioTimestamp&quot;: True or False, # Optional. If enabled, audio timestamp will be included in the request to the model.
    &quot;candidateCount&quot;: 42, # Optional. Number of candidates to generate.
    &quot;enableAffectiveDialog&quot;: True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly.
    &quot;frequencyPenalty&quot;: 3.14, # Optional. Frequency penalties.
    &quot;logprobs&quot;: 42, # Optional. Logit probabilities.
    &quot;maxOutputTokens&quot;: 42, # Optional. The maximum number of output tokens to generate per message.
    &quot;mediaResolution&quot;: &quot;A String&quot;, # Optional. If specified, the media resolution specified will be used.
    &quot;presencePenalty&quot;: 3.14, # Optional. Positive penalties.
    &quot;responseJsonSchema&quot;: &quot;&quot;, # Optional. Output schema of the generated response. This is an alternative to `response_schema` that accepts [JSON Schema](https://json-schema.org/). 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.
    &quot;responseLogprobs&quot;: True or False, # Optional. If true, export the logprobs results in response.
    &quot;responseMimeType&quot;: &quot;A String&quot;, # Optional. Output response mimetype of the generated candidate text. Supported mimetype: - `text/plain`: (default) Text output. - `application/json`: JSON response in the candidates. The model needs to be prompted to output the appropriate response type, otherwise the behavior is undefined. This is a preview feature.
    &quot;responseModalities&quot;: [ # Optional. The modalities of the response.
      &quot;A String&quot;,
    ],
    &quot;responseSchema&quot;: { # Schema is used to define the format of input/output data. Represents a select subset of an [OpenAPI 3.0 schema object](https://spec.openapis.org/oas/v3.0.3#schema-object). More fields may be added in the future as needed. # Optional. 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](https://spec.openapis.org/oas/v3.0.3#schema). If set, a compatible response_mime_type must also be set. Compatible mimetypes: `application/json`: Schema for JSON response.
      &quot;additionalProperties&quot;: &quot;&quot;, # Optional. Can either be a boolean or an object; controls the presence of additional properties.
      &quot;anyOf&quot;: [ # Optional. The value should be validated against any (one or more) of the subschemas in the list.
        # Object with schema name: GoogleCloudAiplatformV1Schema
      ],
      &quot;default&quot;: &quot;&quot;, # Optional. Default value of the data.
      &quot;defs&quot;: { # Optional. A map of definitions for use by `ref` Only allowed at the root of the schema.
        &quot;a_key&quot;: # Object with schema name: GoogleCloudAiplatformV1Schema
      },
      &quot;description&quot;: &quot;A String&quot;, # Optional. The description of the data.
      &quot;enum&quot;: [ # Optional. Possible values of the element of primitive type with enum format. Examples: 1. We can define direction as : {type:STRING, format:enum, enum:[&quot;EAST&quot;, NORTH&quot;, &quot;SOUTH&quot;, &quot;WEST&quot;]} 2. We can define apartment number as : {type:INTEGER, format:enum, enum:[&quot;101&quot;, &quot;201&quot;, &quot;301&quot;]}
        &quot;A String&quot;,
      ],
      &quot;example&quot;: &quot;&quot;, # Optional. Example of the object. Will only populated when the object is the root.
      &quot;format&quot;: &quot;A String&quot;, # Optional. The format of the data. Supported formats: for NUMBER type: &quot;float&quot;, &quot;double&quot; for INTEGER type: &quot;int32&quot;, &quot;int64&quot; for STRING type: &quot;email&quot;, &quot;byte&quot;, etc
      &quot;items&quot;: # Object with schema name: GoogleCloudAiplatformV1Schema # Optional. SCHEMA FIELDS FOR TYPE ARRAY Schema of the elements of Type.ARRAY.
      &quot;maxItems&quot;: &quot;A String&quot;, # Optional. Maximum number of the elements for Type.ARRAY.
      &quot;maxLength&quot;: &quot;A String&quot;, # Optional. Maximum length of the Type.STRING
      &quot;maxProperties&quot;: &quot;A String&quot;, # Optional. Maximum number of the properties for Type.OBJECT.
      &quot;maximum&quot;: 3.14, # Optional. Maximum value of the Type.INTEGER and Type.NUMBER
      &quot;minItems&quot;: &quot;A String&quot;, # Optional. Minimum number of the elements for Type.ARRAY.
      &quot;minLength&quot;: &quot;A String&quot;, # Optional. SCHEMA FIELDS FOR TYPE STRING Minimum length of the Type.STRING
      &quot;minProperties&quot;: &quot;A String&quot;, # Optional. Minimum number of the properties for Type.OBJECT.
      &quot;minimum&quot;: 3.14, # Optional. SCHEMA FIELDS FOR TYPE INTEGER and NUMBER Minimum value of the Type.INTEGER and Type.NUMBER
      &quot;nullable&quot;: True or False, # Optional. Indicates if the value may be null.
      &quot;pattern&quot;: &quot;A String&quot;, # Optional. Pattern of the Type.STRING to restrict a string to a regular expression.
      &quot;properties&quot;: { # Optional. SCHEMA FIELDS FOR TYPE OBJECT Properties of Type.OBJECT.
        &quot;a_key&quot;: # Object with schema name: GoogleCloudAiplatformV1Schema
      },
      &quot;propertyOrdering&quot;: [ # Optional. The order of the properties. Not a standard field in open api spec. Only used to support the order of the properties.
        &quot;A String&quot;,
      ],
      &quot;ref&quot;: &quot;A String&quot;, # Optional. Allows indirect references between schema nodes. The value should be a valid reference to a child of the root `defs`. For example, the following schema defines a reference to a schema node named &quot;Pet&quot;: type: object properties: pet: ref: #/defs/Pet defs: Pet: type: object properties: name: type: string The value of the &quot;pet&quot; property is a reference to the schema node named &quot;Pet&quot;. See details in https://json-schema.org/understanding-json-schema/structuring
      &quot;required&quot;: [ # Optional. Required properties of Type.OBJECT.
        &quot;A String&quot;,
      ],
      &quot;title&quot;: &quot;A String&quot;, # Optional. The title of the Schema.
      &quot;type&quot;: &quot;A String&quot;, # Optional. The type of the data.
    },
    &quot;routingConfig&quot;: { # The configuration for routing the request to a specific model. # Optional. Routing configuration.
      &quot;autoMode&quot;: { # When automated routing is specified, the routing will be determined by the pretrained routing model and customer provided model routing preference. # Automated routing.
        &quot;modelRoutingPreference&quot;: &quot;A String&quot;, # The model routing preference.
      },
      &quot;manualMode&quot;: { # When manual routing is set, the specified model will be used directly. # Manual routing.
        &quot;modelName&quot;: &quot;A String&quot;, # The model name to use. Only the public LLM models are accepted. See [Supported models](https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/inference#supported-models).
      },
    },
    &quot;seed&quot;: 42, # Optional. Seed.
    &quot;speechConfig&quot;: { # The speech generation config. # Optional. The speech generation config.
      &quot;languageCode&quot;: &quot;A String&quot;, # Optional. Language code (ISO 639. e.g. en-US) for the speech synthesization.
      &quot;voiceConfig&quot;: { # The configuration for the voice to use. # The configuration for the speaker to use.
        &quot;prebuiltVoiceConfig&quot;: { # The configuration for the prebuilt speaker to use. # The configuration for the prebuilt voice to use.
          &quot;voiceName&quot;: &quot;A String&quot;, # The name of the preset voice to use.
        },
      },
    },
    &quot;stopSequences&quot;: [ # Optional. Stop sequences.
      &quot;A String&quot;,
    ],
    &quot;temperature&quot;: 3.14, # Optional. Controls the randomness of predictions.
    &quot;thinkingConfig&quot;: { # Config for thinking features. # Optional. Config for thinking features. An error will be returned if this field is set for models that don&#x27;t support thinking.
      &quot;includeThoughts&quot;: True or False, # Optional. Indicates whether to include thoughts in the response. If true, thoughts are returned only when available.
      &quot;thinkingBudget&quot;: 42, # Optional. Indicates the thinking budget in tokens.
    },
    &quot;topK&quot;: 3.14, # Optional. If specified, top-k sampling will be used.
    &quot;topP&quot;: 3.14, # Optional. If specified, nucleus sampling will be used.
  },
  &quot;instances&quot;: [ # Optional. The instances that are the input to token counting call. Schema is identical to the prediction schema of the underlying model.
    &quot;&quot;,
  ],
  &quot;model&quot;: &quot;A String&quot;, # Optional. The name of the publisher model requested to serve the prediction. Format: `projects/{project}/locations/{location}/publishers/*/models/*`
  &quot;systemInstruction&quot;: { # 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. # 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.
    &quot;parts&quot;: [ # Required. Ordered `Parts` that constitute a single message. Parts may have different IANA MIME types.
      { # 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 `inline_data` or `file_data` field is filled with raw bytes.
        &quot;codeExecutionResult&quot;: { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. Result of executing the [ExecutableCode].
          &quot;outcome&quot;: &quot;A String&quot;, # Required. Outcome of the code execution.
          &quot;output&quot;: &quot;A String&quot;, # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
        },
        &quot;executableCode&quot;: { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is meant to be executed.
          &quot;code&quot;: &quot;A String&quot;, # Required. The code to be executed.
          &quot;language&quot;: &quot;A String&quot;, # Required. Programming language of the `code`.
        },
        &quot;fileData&quot;: { # URI based data. # Optional. URI based data.
          &quot;displayName&quot;: &quot;A String&quot;, # Optional. Display name of the file data. Used to provide a label or filename to distinguish file datas. This field is only returned in PromptMessage for prompt management. It is currently used in the Gemini GenerateContent calls only when server side tools (code_execution, google_search, and url_context) are enabled.
          &quot;fileUri&quot;: &quot;A String&quot;, # Required. URI.
          &quot;mimeType&quot;: &quot;A String&quot;, # Required. The IANA standard MIME type of the source data.
        },
        &quot;functionCall&quot;: { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] with the parameters and their values.
          &quot;args&quot;: { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details.
            &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
          },
          &quot;name&quot;: &quot;A String&quot;, # Required. The name of the function to call. Matches [FunctionDeclaration.name].
        },
        &quot;functionResponse&quot;: { # 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 a [FunctionCall] made based on model prediction. # Optional. 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 call. It is used as context to the model.
          &quot;name&quot;: &quot;A String&quot;, # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name].
          &quot;response&quot;: { # Required. The function response in JSON object format. Use &quot;output&quot; key to specify function output and &quot;error&quot; key to specify error details (if any). If &quot;output&quot; and &quot;error&quot; keys are not specified, then whole &quot;response&quot; is treated as function output.
            &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
          },
        },
        &quot;inlineData&quot;: { # Content blob. # Optional. Inlined bytes data.
          &quot;data&quot;: &quot;A String&quot;, # Required. Raw bytes.
          &quot;displayName&quot;: &quot;A String&quot;, # Optional. Display name of the blob. Used to provide a label or filename to distinguish blobs. This field is only returned in PromptMessage for prompt management. It is currently used in the Gemini GenerateContent calls only when server side tools (code_execution, google_search, and url_context) are enabled.
          &quot;mimeType&quot;: &quot;A String&quot;, # Required. The IANA standard MIME type of the source data.
        },
        &quot;text&quot;: &quot;A String&quot;, # Optional. Text part (can be code).
        &quot;thought&quot;: True or False, # Optional. Indicates if the part is thought from the model.
        &quot;thoughtSignature&quot;: &quot;A String&quot;, # Optional. An opaque signature for the thought so it can be reused in subsequent requests.
        &quot;videoMetadata&quot;: { # Metadata describes the input video content. # Optional. Video metadata. The metadata should only be specified while the video data is presented in inline_data or file_data.
          &quot;endOffset&quot;: &quot;A String&quot;, # Optional. The end offset of the video.
          &quot;fps&quot;: 3.14, # 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].
          &quot;startOffset&quot;: &quot;A String&quot;, # Optional. The start offset of the video.
        },
      },
    ],
    &quot;role&quot;: &quot;A String&quot;, # Optional. The producer of the content. Must be either &#x27;user&#x27; or &#x27;model&#x27;. Useful to set for multi-turn conversations, otherwise can be left blank or unset.
  },
  &quot;tools&quot;: [ # 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.
    { # 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. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval).
      &quot;codeExecution&quot;: { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation.
      },
      &quot;enterpriseWebSearch&quot;: { # Tool to search public web data, powered by Vertex AI Search and Sec4 compliance. # Optional. Tool to support searching public web data, powered by Vertex AI Search and Sec4 compliance.
        &quot;excludeDomains&quot;: [ # Optional. List of domains to be excluded from the search results. The default limit is 2000 domains.
          &quot;A String&quot;,
        ],
      },
      &quot;functionDeclarations&quot;: [ # Optional. Function tool type. One or more function declarations to be passed to the model along with the current user query. Model may decide to call a subset of these functions by populating FunctionCall in the response. User should provide a FunctionResponse for each function call in the next turn. Based on the function responses, Model will generate the final response back to the user. Maximum 512 function declarations can be provided.
        { # Structured representation of a function declaration as defined by the [OpenAPI 3.0 specification](https://spec.openapis.org/oas/v3.0.3). Included in this declaration are the function name, description, parameters and response type. 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.
          &quot;description&quot;: &quot;A String&quot;, # Optional. Description and purpose of the function. Model uses it to decide how and whether to call the function.
          &quot;name&quot;: &quot;A String&quot;, # Required. The name of the function to call. Must start with a letter or an underscore. Must be a-z, A-Z, 0-9, or contain underscores, dots and dashes, with a maximum length of 64.
          &quot;parameters&quot;: { # Schema is used to define the format of input/output data. Represents a select subset of an [OpenAPI 3.0 schema object](https://spec.openapis.org/oas/v3.0.3#schema-object). More fields may be added in the future as needed. # Optional. Describes the parameters to this function in JSON Schema Object format. 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. For function with no parameters, this can be left unset. Parameter names must start with a letter or an underscore and must only contain chars a-z, A-Z, 0-9, or underscores with a maximum length of 64. Example with 1 required and 1 optional parameter: type: OBJECT properties: param1: type: STRING param2: type: INTEGER required: - param1
            &quot;additionalProperties&quot;: &quot;&quot;, # Optional. Can either be a boolean or an object; controls the presence of additional properties.
            &quot;anyOf&quot;: [ # Optional. The value should be validated against any (one or more) of the subschemas in the list.
              # Object with schema name: GoogleCloudAiplatformV1Schema
            ],
            &quot;default&quot;: &quot;&quot;, # Optional. Default value of the data.
            &quot;defs&quot;: { # Optional. A map of definitions for use by `ref` Only allowed at the root of the schema.
              &quot;a_key&quot;: # Object with schema name: GoogleCloudAiplatformV1Schema
            },
            &quot;description&quot;: &quot;A String&quot;, # Optional. The description of the data.
            &quot;enum&quot;: [ # Optional. Possible values of the element of primitive type with enum format. Examples: 1. We can define direction as : {type:STRING, format:enum, enum:[&quot;EAST&quot;, NORTH&quot;, &quot;SOUTH&quot;, &quot;WEST&quot;]} 2. We can define apartment number as : {type:INTEGER, format:enum, enum:[&quot;101&quot;, &quot;201&quot;, &quot;301&quot;]}
              &quot;A String&quot;,
            ],
            &quot;example&quot;: &quot;&quot;, # Optional. Example of the object. Will only populated when the object is the root.
            &quot;format&quot;: &quot;A String&quot;, # Optional. The format of the data. Supported formats: for NUMBER type: &quot;float&quot;, &quot;double&quot; for INTEGER type: &quot;int32&quot;, &quot;int64&quot; for STRING type: &quot;email&quot;, &quot;byte&quot;, etc
            &quot;items&quot;: # Object with schema name: GoogleCloudAiplatformV1Schema # Optional. SCHEMA FIELDS FOR TYPE ARRAY Schema of the elements of Type.ARRAY.
            &quot;maxItems&quot;: &quot;A String&quot;, # Optional. Maximum number of the elements for Type.ARRAY.
            &quot;maxLength&quot;: &quot;A String&quot;, # Optional. Maximum length of the Type.STRING
            &quot;maxProperties&quot;: &quot;A String&quot;, # Optional. Maximum number of the properties for Type.OBJECT.
            &quot;maximum&quot;: 3.14, # Optional. Maximum value of the Type.INTEGER and Type.NUMBER
            &quot;minItems&quot;: &quot;A String&quot;, # Optional. Minimum number of the elements for Type.ARRAY.
            &quot;minLength&quot;: &quot;A String&quot;, # Optional. SCHEMA FIELDS FOR TYPE STRING Minimum length of the Type.STRING
            &quot;minProperties&quot;: &quot;A String&quot;, # Optional. Minimum number of the properties for Type.OBJECT.
            &quot;minimum&quot;: 3.14, # Optional. SCHEMA FIELDS FOR TYPE INTEGER and NUMBER Minimum value of the Type.INTEGER and Type.NUMBER
            &quot;nullable&quot;: True or False, # Optional. Indicates if the value may be null.
            &quot;pattern&quot;: &quot;A String&quot;, # Optional. Pattern of the Type.STRING to restrict a string to a regular expression.
            &quot;properties&quot;: { # Optional. SCHEMA FIELDS FOR TYPE OBJECT Properties of Type.OBJECT.
              &quot;a_key&quot;: # Object with schema name: GoogleCloudAiplatformV1Schema
            },
            &quot;propertyOrdering&quot;: [ # Optional. The order of the properties. Not a standard field in open api spec. Only used to support the order of the properties.
              &quot;A String&quot;,
            ],
            &quot;ref&quot;: &quot;A String&quot;, # Optional. Allows indirect references between schema nodes. The value should be a valid reference to a child of the root `defs`. For example, the following schema defines a reference to a schema node named &quot;Pet&quot;: type: object properties: pet: ref: #/defs/Pet defs: Pet: type: object properties: name: type: string The value of the &quot;pet&quot; property is a reference to the schema node named &quot;Pet&quot;. See details in https://json-schema.org/understanding-json-schema/structuring
            &quot;required&quot;: [ # Optional. Required properties of Type.OBJECT.
              &quot;A String&quot;,
            ],
            &quot;title&quot;: &quot;A String&quot;, # Optional. The title of the Schema.
            &quot;type&quot;: &quot;A String&quot;, # Optional. The type of the data.
          },
          &quot;parametersJsonSchema&quot;: &quot;&quot;, # 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: ``` { &quot;type&quot;: &quot;object&quot;, &quot;properties&quot;: { &quot;name&quot;: { &quot;type&quot;: &quot;string&quot; }, &quot;age&quot;: { &quot;type&quot;: &quot;integer&quot; } }, &quot;additionalProperties&quot;: false, &quot;required&quot;: [&quot;name&quot;, &quot;age&quot;], &quot;propertyOrdering&quot;: [&quot;name&quot;, &quot;age&quot;] } ``` This field is mutually exclusive with `parameters`.
          &quot;response&quot;: { # Schema is used to define the format of input/output data. Represents a select subset of an [OpenAPI 3.0 schema object](https://spec.openapis.org/oas/v3.0.3#schema-object). More fields may be added in the future as needed. # 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.
            &quot;additionalProperties&quot;: &quot;&quot;, # Optional. Can either be a boolean or an object; controls the presence of additional properties.
            &quot;anyOf&quot;: [ # Optional. The value should be validated against any (one or more) of the subschemas in the list.
              # Object with schema name: GoogleCloudAiplatformV1Schema
            ],
            &quot;default&quot;: &quot;&quot;, # Optional. Default value of the data.
            &quot;defs&quot;: { # Optional. A map of definitions for use by `ref` Only allowed at the root of the schema.
              &quot;a_key&quot;: # Object with schema name: GoogleCloudAiplatformV1Schema
            },
            &quot;description&quot;: &quot;A String&quot;, # Optional. The description of the data.
            &quot;enum&quot;: [ # Optional. Possible values of the element of primitive type with enum format. Examples: 1. We can define direction as : {type:STRING, format:enum, enum:[&quot;EAST&quot;, NORTH&quot;, &quot;SOUTH&quot;, &quot;WEST&quot;]} 2. We can define apartment number as : {type:INTEGER, format:enum, enum:[&quot;101&quot;, &quot;201&quot;, &quot;301&quot;]}
              &quot;A String&quot;,
            ],
            &quot;example&quot;: &quot;&quot;, # Optional. Example of the object. Will only populated when the object is the root.
            &quot;format&quot;: &quot;A String&quot;, # Optional. The format of the data. Supported formats: for NUMBER type: &quot;float&quot;, &quot;double&quot; for INTEGER type: &quot;int32&quot;, &quot;int64&quot; for STRING type: &quot;email&quot;, &quot;byte&quot;, etc
            &quot;items&quot;: # Object with schema name: GoogleCloudAiplatformV1Schema # Optional. SCHEMA FIELDS FOR TYPE ARRAY Schema of the elements of Type.ARRAY.
            &quot;maxItems&quot;: &quot;A String&quot;, # Optional. Maximum number of the elements for Type.ARRAY.
            &quot;maxLength&quot;: &quot;A String&quot;, # Optional. Maximum length of the Type.STRING
            &quot;maxProperties&quot;: &quot;A String&quot;, # Optional. Maximum number of the properties for Type.OBJECT.
            &quot;maximum&quot;: 3.14, # Optional. Maximum value of the Type.INTEGER and Type.NUMBER
            &quot;minItems&quot;: &quot;A String&quot;, # Optional. Minimum number of the elements for Type.ARRAY.
            &quot;minLength&quot;: &quot;A String&quot;, # Optional. SCHEMA FIELDS FOR TYPE STRING Minimum length of the Type.STRING
            &quot;minProperties&quot;: &quot;A String&quot;, # Optional. Minimum number of the properties for Type.OBJECT.
            &quot;minimum&quot;: 3.14, # Optional. SCHEMA FIELDS FOR TYPE INTEGER and NUMBER Minimum value of the Type.INTEGER and Type.NUMBER
            &quot;nullable&quot;: True or False, # Optional. Indicates if the value may be null.
            &quot;pattern&quot;: &quot;A String&quot;, # Optional. Pattern of the Type.STRING to restrict a string to a regular expression.
            &quot;properties&quot;: { # Optional. SCHEMA FIELDS FOR TYPE OBJECT Properties of Type.OBJECT.
              &quot;a_key&quot;: # Object with schema name: GoogleCloudAiplatformV1Schema
            },
            &quot;propertyOrdering&quot;: [ # Optional. The order of the properties. Not a standard field in open api spec. Only used to support the order of the properties.
              &quot;A String&quot;,
            ],
            &quot;ref&quot;: &quot;A String&quot;, # Optional. Allows indirect references between schema nodes. The value should be a valid reference to a child of the root `defs`. For example, the following schema defines a reference to a schema node named &quot;Pet&quot;: type: object properties: pet: ref: #/defs/Pet defs: Pet: type: object properties: name: type: string The value of the &quot;pet&quot; property is a reference to the schema node named &quot;Pet&quot;. See details in https://json-schema.org/understanding-json-schema/structuring
            &quot;required&quot;: [ # Optional. Required properties of Type.OBJECT.
              &quot;A String&quot;,
            ],
            &quot;title&quot;: &quot;A String&quot;, # Optional. The title of the Schema.
            &quot;type&quot;: &quot;A String&quot;, # Optional. The type of the data.
          },
          &quot;responseJsonSchema&quot;: &quot;&quot;, # 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`.
        },
      ],
      &quot;googleMaps&quot;: { # Tool to retrieve public maps data for grounding, powered by Google. # Optional. GoogleMaps tool type. Tool to support Google Maps in Model.
      },
      &quot;googleSearch&quot;: { # GoogleSearch tool type. Tool to support Google Search in Model. Powered by Google. # Optional. GoogleSearch tool type. Tool to support Google Search in Model. Powered by Google.
        &quot;excludeDomains&quot;: [ # Optional. List of domains to be excluded from the search results. The default limit is 2000 domains. Example: [&quot;amazon.com&quot;, &quot;facebook.com&quot;].
          &quot;A String&quot;,
        ],
      },
      &quot;googleSearchRetrieval&quot;: { # Tool to retrieve public web data for grounding, powered by Google. # Optional. GoogleSearchRetrieval tool type. Specialized retrieval tool that is powered by Google search.
        &quot;dynamicRetrievalConfig&quot;: { # Describes the options to customize dynamic retrieval. # Specifies the dynamic retrieval configuration for the given source.
          &quot;dynamicThreshold&quot;: 3.14, # Optional. The threshold to be used in dynamic retrieval. If not set, a system default value is used.
          &quot;mode&quot;: &quot;A String&quot;, # The mode of the predictor to be used in dynamic retrieval.
        },
      },
      &quot;retrieval&quot;: { # Defines a retrieval tool that model can call to access external knowledge. # Optional. Retrieval tool type. System will always execute the provided retrieval tool(s) to get external knowledge to answer the prompt. Retrieval results are presented to the model for generation.
        &quot;disableAttribution&quot;: True or False, # Optional. Deprecated. This option is no longer supported.
        &quot;externalApi&quot;: { # Retrieve from data source powered by external API for grounding. The external API is not owned by Google, but need to follow the pre-defined API spec. # Use data source powered by external API for grounding.
          &quot;apiAuth&quot;: { # The generic reusable api auth config. Deprecated. Please use AuthConfig (google/cloud/aiplatform/master/auth.proto) instead. # The authentication config to access the API. Deprecated. Please use auth_config instead.
            &quot;apiKeyConfig&quot;: { # The API secret. # The API secret.
              &quot;apiKeySecretVersion&quot;: &quot;A String&quot;, # Required. The SecretManager secret version resource name storing API key. e.g. projects/{project}/secrets/{secret}/versions/{version}
              &quot;apiKeyString&quot;: &quot;A String&quot;, # The API key string. Either this or `api_key_secret_version` must be set.
            },
          },
          &quot;apiSpec&quot;: &quot;A String&quot;, # The API spec that the external API implements.
          &quot;authConfig&quot;: { # Auth configuration to run the extension. # The authentication config to access the API.
            &quot;apiKeyConfig&quot;: { # Config for authentication with API key. # Config for API key auth.
              &quot;apiKeySecret&quot;: &quot;A String&quot;, # Optional. The name of the SecretManager secret version resource storing the API key. Format: `projects/{project}/secrets/{secrete}/versions/{version}` - If both `api_key_secret` and `api_key_string` are specified, this field takes precedence over `api_key_string`. - If specified, the `secretmanager.versions.access` permission should be granted to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) on the specified resource.
              &quot;apiKeyString&quot;: &quot;A String&quot;, # Optional. The API key to be used in the request directly.
              &quot;httpElementLocation&quot;: &quot;A String&quot;, # Optional. The location of the API key.
              &quot;name&quot;: &quot;A String&quot;, # Optional. The parameter name of the API key. E.g. If the API request is &quot;https://example.com/act?api_key=&quot;, &quot;api_key&quot; would be the parameter name.
            },
            &quot;authType&quot;: &quot;A String&quot;, # Type of auth scheme.
            &quot;googleServiceAccountConfig&quot;: { # Config for Google Service Account Authentication. # Config for Google Service Account auth.
              &quot;serviceAccount&quot;: &quot;A String&quot;, # Optional. The service account that the extension execution service runs as. - If the service account is specified, the `iam.serviceAccounts.getAccessToken` permission should be granted to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) on the specified service account. - If not specified, the Vertex AI Extension Service Agent will be used to execute the Extension.
            },
            &quot;httpBasicAuthConfig&quot;: { # Config for HTTP Basic Authentication. # Config for HTTP Basic auth.
              &quot;credentialSecret&quot;: &quot;A String&quot;, # Required. The name of the SecretManager secret version resource storing the base64 encoded credentials. Format: `projects/{project}/secrets/{secrete}/versions/{version}` - If specified, the `secretmanager.versions.access` permission should be granted to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) on the specified resource.
            },
            &quot;oauthConfig&quot;: { # Config for user oauth. # Config for user oauth.
              &quot;accessToken&quot;: &quot;A String&quot;, # Access token for extension endpoint. Only used to propagate token from [[ExecuteExtensionRequest.runtime_auth_config]] at request time.
              &quot;serviceAccount&quot;: &quot;A String&quot;, # The service account used to generate access tokens for executing the Extension. - If the service account is specified, the `iam.serviceAccounts.getAccessToken` permission should be granted to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) on the provided service account.
            },
            &quot;oidcConfig&quot;: { # Config for user OIDC auth. # Config for user OIDC auth.
              &quot;idToken&quot;: &quot;A String&quot;, # OpenID Connect formatted ID token for extension endpoint. Only used to propagate token from [[ExecuteExtensionRequest.runtime_auth_config]] at request time.
              &quot;serviceAccount&quot;: &quot;A String&quot;, # The service account used to generate an OpenID Connect (OIDC)-compatible JWT token signed by the Google OIDC Provider (accounts.google.com) for extension endpoint (https://cloud.google.com/iam/docs/create-short-lived-credentials-direct#sa-credentials-oidc). - The audience for the token will be set to the URL in the server url defined in the OpenApi spec. - If the service account is provided, the service account should grant `iam.serviceAccounts.getOpenIdToken` permission to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents).
            },
          },
          &quot;elasticSearchParams&quot;: { # The search parameters to use for the ELASTIC_SEARCH spec. # Parameters for the elastic search API.
            &quot;index&quot;: &quot;A String&quot;, # The ElasticSearch index to use.
            &quot;numHits&quot;: 42, # Optional. Number of hits (chunks) to request. When specified, it is passed to Elasticsearch as the `num_hits` param.
            &quot;searchTemplate&quot;: &quot;A String&quot;, # The ElasticSearch search template to use.
          },
          &quot;endpoint&quot;: &quot;A String&quot;, # The endpoint of the external API. The system will call the API at this endpoint to retrieve the data for grounding. Example: https://acme.com:443/search
          &quot;simpleSearchParams&quot;: { # The search parameters to use for SIMPLE_SEARCH spec. # Parameters for the simple search API.
          },
        },
        &quot;vertexAiSearch&quot;: { # Retrieve from Vertex AI Search datastore or engine for grounding. datastore and engine are mutually exclusive. See https://cloud.google.com/products/agent-builder # Set to use data source powered by Vertex AI Search.
          &quot;dataStoreSpecs&quot;: [ # Specifications that define the specific DataStores to be searched, along with configurations for those data stores. This is only considered for Engines with multiple data stores. It should only be set if engine is used.
            { # Define data stores within engine to filter on in a search call and configurations for those data stores. For more information, see https://cloud.google.com/generative-ai-app-builder/docs/reference/rpc/google.cloud.discoveryengine.v1#datastorespec
              &quot;dataStore&quot;: &quot;A String&quot;, # Full resource name of DataStore, such as Format: `projects/{project}/locations/{location}/collections/{collection}/dataStores/{dataStore}`
              &quot;filter&quot;: &quot;A String&quot;, # Optional. Filter specification to filter documents in the data store specified by data_store field. For more information on filtering, see [Filtering](https://cloud.google.com/generative-ai-app-builder/docs/filter-search-metadata)
            },
          ],
          &quot;datastore&quot;: &quot;A String&quot;, # Optional. Fully-qualified Vertex AI Search data store resource ID. Format: `projects/{project}/locations/{location}/collections/{collection}/dataStores/{dataStore}`
          &quot;engine&quot;: &quot;A String&quot;, # Optional. Fully-qualified Vertex AI Search engine resource ID. Format: `projects/{project}/locations/{location}/collections/{collection}/engines/{engine}`
          &quot;filter&quot;: &quot;A String&quot;, # Optional. Filter strings to be passed to the search API.
          &quot;maxResults&quot;: 42, # Optional. Number of search results to return per query. The default value is 10. The maximumm allowed value is 10.
        },
        &quot;vertexRagStore&quot;: { # Retrieve from Vertex RAG Store for grounding. # Set to use data source powered by Vertex RAG store. User data is uploaded via the VertexRagDataService.
          &quot;ragResources&quot;: [ # Optional. The representation of the rag source. It can be used to specify corpus only or ragfiles. Currently only support one corpus or multiple files from one corpus. In the future we may open up multiple corpora support.
            { # The definition of the Rag resource.
              &quot;ragCorpus&quot;: &quot;A String&quot;, # Optional. RagCorpora resource name. Format: `projects/{project}/locations/{location}/ragCorpora/{rag_corpus}`
              &quot;ragFileIds&quot;: [ # Optional. rag_file_id. The files should be in the same rag_corpus set in rag_corpus field.
                &quot;A String&quot;,
              ],
            },
          ],
          &quot;ragRetrievalConfig&quot;: { # Specifies the context retrieval config. # Optional. The retrieval config for the Rag query.
            &quot;filter&quot;: { # Config for filters. # Optional. Config for filters.
              &quot;metadataFilter&quot;: &quot;A String&quot;, # Optional. String for metadata filtering.
              &quot;vectorDistanceThreshold&quot;: 3.14, # Optional. Only returns contexts with vector distance smaller than the threshold.
              &quot;vectorSimilarityThreshold&quot;: 3.14, # Optional. Only returns contexts with vector similarity larger than the threshold.
            },
            &quot;ranking&quot;: { # Config for ranking and reranking. # Optional. Config for ranking and reranking.
              &quot;llmRanker&quot;: { # Config for LlmRanker. # Optional. Config for LlmRanker.
                &quot;modelName&quot;: &quot;A String&quot;, # Optional. The model name used for ranking. See [Supported models](https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/inference#supported-models).
              },
              &quot;rankService&quot;: { # Config for Rank Service. # Optional. Config for Rank Service.
                &quot;modelName&quot;: &quot;A String&quot;, # Optional. The model name of the rank service. Format: `semantic-ranker-512@latest`
              },
            },
            &quot;topK&quot;: 42, # Optional. The number of contexts to retrieve.
          },
          &quot;similarityTopK&quot;: 42, # Optional. Number of top k results to return from the selected corpora.
          &quot;vectorDistanceThreshold&quot;: 3.14, # Optional. Only return results with vector distance smaller than the threshold.
        },
      },
      &quot;urlContext&quot;: { # Tool to support URL context. # Optional. Tool to support URL context retrieval.
      },
    },
  ],
}

  x__xgafv: string, V1 error format.
    Allowed values
      1 - v1 error format
      2 - v2 error format

Returns:
  An object of the form:

    { # Response message for PredictionService.CountTokens.
  &quot;promptTokensDetails&quot;: [ # Output only. List of modalities that were processed in the request input.
    { # Represents token counting info for a single modality.
      &quot;modality&quot;: &quot;A String&quot;, # The modality associated with this token count.
      &quot;tokenCount&quot;: 42, # Number of tokens.
    },
  ],
  &quot;totalBillableCharacters&quot;: 42, # The total number of billable characters counted across all instances from the request.
  &quot;totalTokens&quot;: 42, # The total number of tokens counted across all instances from the request.
}</pre>
</div>

<div class="method">
    <code class="details" id="fetchPredictOperation">fetchPredictOperation(endpoint, body=None, x__xgafv=None)</code>
  <pre>Fetch an asynchronous online prediction operation.

Args:
  endpoint: string, Required. The name of the Endpoint requested to serve the prediction. Format: `projects/{project}/locations/{location}/endpoints/{endpoint}` or `projects/{project}/locations/{location}/publishers/{publisher}/models/{model}` (required)
  body: object, The request body.
    The object takes the form of:

{ # Request message for PredictionService.FetchPredictOperation.
  &quot;operationName&quot;: &quot;A String&quot;, # Required. The server-assigned name for the operation.
}

  x__xgafv: string, V1 error format.
    Allowed values
      1 - v1 error format
      2 - v2 error format

Returns:
  An object of the form:

    { # This resource represents a long-running operation that is the result of a network API call.
  &quot;done&quot;: True or False, # If the value is `false`, it means the operation is still in progress. If `true`, the operation is completed, and either `error` or `response` is available.
  &quot;error&quot;: { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # The error result of the operation in case of failure or cancellation.
    &quot;code&quot;: 42, # The status code, which should be an enum value of google.rpc.Code.
    &quot;details&quot;: [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
      {
        &quot;a_key&quot;: &quot;&quot;, # Properties of the object. Contains field @type with type URL.
      },
    ],
    &quot;message&quot;: &quot;A String&quot;, # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
  },
  &quot;metadata&quot;: { # Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any.
    &quot;a_key&quot;: &quot;&quot;, # Properties of the object. Contains field @type with type URL.
  },
  &quot;name&quot;: &quot;A String&quot;, # The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id}`.
  &quot;response&quot;: { # The normal, successful response of the operation. If the original method returns no data on success, such as `Delete`, the response is `google.protobuf.Empty`. If the original method is standard `Get`/`Create`/`Update`, the response should be the resource. For other methods, the response should have the type `XxxResponse`, where `Xxx` is the original method name. For example, if the original method name is `TakeSnapshot()`, the inferred response type is `TakeSnapshotResponse`.
    &quot;a_key&quot;: &quot;&quot;, # Properties of the object. Contains field @type with type URL.
  },
}</pre>
</div>

<div class="method">
    <code class="details" id="generateContent">generateContent(model, body=None, x__xgafv=None)</code>
  <pre>Generate content with multimodal inputs.

Args:
  model: string, Required. The fully qualified name of the publisher model or tuned model endpoint to use. Publisher model format: `projects/{project}/locations/{location}/publishers/*/models/*` Tuned model endpoint format: `projects/{project}/locations/{location}/endpoints/{endpoint}` (required)
  body: object, The request body.
    The object takes the form of:

{ # Request message for [PredictionService.GenerateContent].
  &quot;cachedContent&quot;: &quot;A String&quot;, # Optional. The name of the cached content used as context to serve the prediction. Note: only used in explicit caching, where users can have control over caching (e.g. what content to cache) and enjoy guaranteed cost savings. Format: `projects/{project}/locations/{location}/cachedContents/{cachedContent}`
  &quot;contents&quot;: [ # Required. The content of 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 + latest request.
    { # 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.
      &quot;parts&quot;: [ # Required. Ordered `Parts` that constitute a single message. Parts may have different IANA MIME types.
        { # 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 `inline_data` or `file_data` field is filled with raw bytes.
          &quot;codeExecutionResult&quot;: { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. Result of executing the [ExecutableCode].
            &quot;outcome&quot;: &quot;A String&quot;, # Required. Outcome of the code execution.
            &quot;output&quot;: &quot;A String&quot;, # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
          },
          &quot;executableCode&quot;: { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is meant to be executed.
            &quot;code&quot;: &quot;A String&quot;, # Required. The code to be executed.
            &quot;language&quot;: &quot;A String&quot;, # Required. Programming language of the `code`.
          },
          &quot;fileData&quot;: { # URI based data. # Optional. URI based data.
            &quot;displayName&quot;: &quot;A String&quot;, # Optional. Display name of the file data. Used to provide a label or filename to distinguish file datas. This field is only returned in PromptMessage for prompt management. It is currently used in the Gemini GenerateContent calls only when server side tools (code_execution, google_search, and url_context) are enabled.
            &quot;fileUri&quot;: &quot;A String&quot;, # Required. URI.
            &quot;mimeType&quot;: &quot;A String&quot;, # Required. The IANA standard MIME type of the source data.
          },
          &quot;functionCall&quot;: { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] with the parameters and their values.
            &quot;args&quot;: { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details.
              &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
            },
            &quot;name&quot;: &quot;A String&quot;, # Required. The name of the function to call. Matches [FunctionDeclaration.name].
          },
          &quot;functionResponse&quot;: { # 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 a [FunctionCall] made based on model prediction. # Optional. 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 call. It is used as context to the model.
            &quot;name&quot;: &quot;A String&quot;, # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name].
            &quot;response&quot;: { # Required. The function response in JSON object format. Use &quot;output&quot; key to specify function output and &quot;error&quot; key to specify error details (if any). If &quot;output&quot; and &quot;error&quot; keys are not specified, then whole &quot;response&quot; is treated as function output.
              &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
            },
          },
          &quot;inlineData&quot;: { # Content blob. # Optional. Inlined bytes data.
            &quot;data&quot;: &quot;A String&quot;, # Required. Raw bytes.
            &quot;displayName&quot;: &quot;A String&quot;, # Optional. Display name of the blob. Used to provide a label or filename to distinguish blobs. This field is only returned in PromptMessage for prompt management. It is currently used in the Gemini GenerateContent calls only when server side tools (code_execution, google_search, and url_context) are enabled.
            &quot;mimeType&quot;: &quot;A String&quot;, # Required. The IANA standard MIME type of the source data.
          },
          &quot;text&quot;: &quot;A String&quot;, # Optional. Text part (can be code).
          &quot;thought&quot;: True or False, # Optional. Indicates if the part is thought from the model.
          &quot;thoughtSignature&quot;: &quot;A String&quot;, # Optional. An opaque signature for the thought so it can be reused in subsequent requests.
          &quot;videoMetadata&quot;: { # Metadata describes the input video content. # Optional. Video metadata. The metadata should only be specified while the video data is presented in inline_data or file_data.
            &quot;endOffset&quot;: &quot;A String&quot;, # Optional. The end offset of the video.
            &quot;fps&quot;: 3.14, # 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].
            &quot;startOffset&quot;: &quot;A String&quot;, # Optional. The start offset of the video.
          },
        },
      ],
      &quot;role&quot;: &quot;A String&quot;, # Optional. The producer of the content. Must be either &#x27;user&#x27; or &#x27;model&#x27;. Useful to set for multi-turn conversations, otherwise can be left blank or unset.
    },
  ],
  &quot;generationConfig&quot;: { # Generation config. # Optional. Generation config.
    &quot;audioTimestamp&quot;: True or False, # Optional. If enabled, audio timestamp will be included in the request to the model.
    &quot;candidateCount&quot;: 42, # Optional. Number of candidates to generate.
    &quot;enableAffectiveDialog&quot;: True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly.
    &quot;frequencyPenalty&quot;: 3.14, # Optional. Frequency penalties.
    &quot;logprobs&quot;: 42, # Optional. Logit probabilities.
    &quot;maxOutputTokens&quot;: 42, # Optional. The maximum number of output tokens to generate per message.
    &quot;mediaResolution&quot;: &quot;A String&quot;, # Optional. If specified, the media resolution specified will be used.
    &quot;presencePenalty&quot;: 3.14, # Optional. Positive penalties.
    &quot;responseJsonSchema&quot;: &quot;&quot;, # Optional. Output schema of the generated response. This is an alternative to `response_schema` that accepts [JSON Schema](https://json-schema.org/). 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.
    &quot;responseLogprobs&quot;: True or False, # Optional. If true, export the logprobs results in response.
    &quot;responseMimeType&quot;: &quot;A String&quot;, # Optional. Output response mimetype of the generated candidate text. Supported mimetype: - `text/plain`: (default) Text output. - `application/json`: JSON response in the candidates. The model needs to be prompted to output the appropriate response type, otherwise the behavior is undefined. This is a preview feature.
    &quot;responseModalities&quot;: [ # Optional. The modalities of the response.
      &quot;A String&quot;,
    ],
    &quot;responseSchema&quot;: { # Schema is used to define the format of input/output data. Represents a select subset of an [OpenAPI 3.0 schema object](https://spec.openapis.org/oas/v3.0.3#schema-object). More fields may be added in the future as needed. # Optional. 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](https://spec.openapis.org/oas/v3.0.3#schema). If set, a compatible response_mime_type must also be set. Compatible mimetypes: `application/json`: Schema for JSON response.
      &quot;additionalProperties&quot;: &quot;&quot;, # Optional. Can either be a boolean or an object; controls the presence of additional properties.
      &quot;anyOf&quot;: [ # Optional. The value should be validated against any (one or more) of the subschemas in the list.
        # Object with schema name: GoogleCloudAiplatformV1Schema
      ],
      &quot;default&quot;: &quot;&quot;, # Optional. Default value of the data.
      &quot;defs&quot;: { # Optional. A map of definitions for use by `ref` Only allowed at the root of the schema.
        &quot;a_key&quot;: # Object with schema name: GoogleCloudAiplatformV1Schema
      },
      &quot;description&quot;: &quot;A String&quot;, # Optional. The description of the data.
      &quot;enum&quot;: [ # Optional. Possible values of the element of primitive type with enum format. Examples: 1. We can define direction as : {type:STRING, format:enum, enum:[&quot;EAST&quot;, NORTH&quot;, &quot;SOUTH&quot;, &quot;WEST&quot;]} 2. We can define apartment number as : {type:INTEGER, format:enum, enum:[&quot;101&quot;, &quot;201&quot;, &quot;301&quot;]}
        &quot;A String&quot;,
      ],
      &quot;example&quot;: &quot;&quot;, # Optional. Example of the object. Will only populated when the object is the root.
      &quot;format&quot;: &quot;A String&quot;, # Optional. The format of the data. Supported formats: for NUMBER type: &quot;float&quot;, &quot;double&quot; for INTEGER type: &quot;int32&quot;, &quot;int64&quot; for STRING type: &quot;email&quot;, &quot;byte&quot;, etc
      &quot;items&quot;: # Object with schema name: GoogleCloudAiplatformV1Schema # Optional. SCHEMA FIELDS FOR TYPE ARRAY Schema of the elements of Type.ARRAY.
      &quot;maxItems&quot;: &quot;A String&quot;, # Optional. Maximum number of the elements for Type.ARRAY.
      &quot;maxLength&quot;: &quot;A String&quot;, # Optional. Maximum length of the Type.STRING
      &quot;maxProperties&quot;: &quot;A String&quot;, # Optional. Maximum number of the properties for Type.OBJECT.
      &quot;maximum&quot;: 3.14, # Optional. Maximum value of the Type.INTEGER and Type.NUMBER
      &quot;minItems&quot;: &quot;A String&quot;, # Optional. Minimum number of the elements for Type.ARRAY.
      &quot;minLength&quot;: &quot;A String&quot;, # Optional. SCHEMA FIELDS FOR TYPE STRING Minimum length of the Type.STRING
      &quot;minProperties&quot;: &quot;A String&quot;, # Optional. Minimum number of the properties for Type.OBJECT.
      &quot;minimum&quot;: 3.14, # Optional. SCHEMA FIELDS FOR TYPE INTEGER and NUMBER Minimum value of the Type.INTEGER and Type.NUMBER
      &quot;nullable&quot;: True or False, # Optional. Indicates if the value may be null.
      &quot;pattern&quot;: &quot;A String&quot;, # Optional. Pattern of the Type.STRING to restrict a string to a regular expression.
      &quot;properties&quot;: { # Optional. SCHEMA FIELDS FOR TYPE OBJECT Properties of Type.OBJECT.
        &quot;a_key&quot;: # Object with schema name: GoogleCloudAiplatformV1Schema
      },
      &quot;propertyOrdering&quot;: [ # Optional. The order of the properties. Not a standard field in open api spec. Only used to support the order of the properties.
        &quot;A String&quot;,
      ],
      &quot;ref&quot;: &quot;A String&quot;, # Optional. Allows indirect references between schema nodes. The value should be a valid reference to a child of the root `defs`. For example, the following schema defines a reference to a schema node named &quot;Pet&quot;: type: object properties: pet: ref: #/defs/Pet defs: Pet: type: object properties: name: type: string The value of the &quot;pet&quot; property is a reference to the schema node named &quot;Pet&quot;. See details in https://json-schema.org/understanding-json-schema/structuring
      &quot;required&quot;: [ # Optional. Required properties of Type.OBJECT.
        &quot;A String&quot;,
      ],
      &quot;title&quot;: &quot;A String&quot;, # Optional. The title of the Schema.
      &quot;type&quot;: &quot;A String&quot;, # Optional. The type of the data.
    },
    &quot;routingConfig&quot;: { # The configuration for routing the request to a specific model. # Optional. Routing configuration.
      &quot;autoMode&quot;: { # When automated routing is specified, the routing will be determined by the pretrained routing model and customer provided model routing preference. # Automated routing.
        &quot;modelRoutingPreference&quot;: &quot;A String&quot;, # The model routing preference.
      },
      &quot;manualMode&quot;: { # When manual routing is set, the specified model will be used directly. # Manual routing.
        &quot;modelName&quot;: &quot;A String&quot;, # The model name to use. Only the public LLM models are accepted. See [Supported models](https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/inference#supported-models).
      },
    },
    &quot;seed&quot;: 42, # Optional. Seed.
    &quot;speechConfig&quot;: { # The speech generation config. # Optional. The speech generation config.
      &quot;languageCode&quot;: &quot;A String&quot;, # Optional. Language code (ISO 639. e.g. en-US) for the speech synthesization.
      &quot;voiceConfig&quot;: { # The configuration for the voice to use. # The configuration for the speaker to use.
        &quot;prebuiltVoiceConfig&quot;: { # The configuration for the prebuilt speaker to use. # The configuration for the prebuilt voice to use.
          &quot;voiceName&quot;: &quot;A String&quot;, # The name of the preset voice to use.
        },
      },
    },
    &quot;stopSequences&quot;: [ # Optional. Stop sequences.
      &quot;A String&quot;,
    ],
    &quot;temperature&quot;: 3.14, # Optional. Controls the randomness of predictions.
    &quot;thinkingConfig&quot;: { # Config for thinking features. # Optional. Config for thinking features. An error will be returned if this field is set for models that don&#x27;t support thinking.
      &quot;includeThoughts&quot;: True or False, # Optional. Indicates whether to include thoughts in the response. If true, thoughts are returned only when available.
      &quot;thinkingBudget&quot;: 42, # Optional. Indicates the thinking budget in tokens.
    },
    &quot;topK&quot;: 3.14, # Optional. If specified, top-k sampling will be used.
    &quot;topP&quot;: 3.14, # Optional. If specified, nucleus sampling will be used.
  },
  &quot;labels&quot;: { # Optional. The labels with user-defined metadata for the request. It is used for billing and reporting only. Label keys and values can be no longer than 63 characters (Unicode codepoints) and can only contain lowercase letters, numeric characters, underscores, and dashes. International characters are allowed. Label values are optional. Label keys must start with a letter.
    &quot;a_key&quot;: &quot;A String&quot;,
  },
  &quot;modelArmorConfig&quot;: { # Configuration for Model Armor integrations of prompt and responses. # Optional. Settings for prompt and response sanitization using the Model Armor service. If supplied, safety_settings must not be supplied.
    &quot;promptTemplateName&quot;: &quot;A String&quot;, # Optional. The name of the Model Armor template to use for prompt sanitization.
    &quot;responseTemplateName&quot;: &quot;A String&quot;, # Optional. The name of the Model Armor template to use for response sanitization.
  },
  &quot;safetySettings&quot;: [ # Optional. Per request settings for blocking unsafe content. Enforced on GenerateContentResponse.candidates.
    { # Safety settings.
      &quot;category&quot;: &quot;A String&quot;, # Required. Harm category.
      &quot;method&quot;: &quot;A String&quot;, # Optional. Specify if the threshold is used for probability or severity score. If not specified, the threshold is used for probability score.
      &quot;threshold&quot;: &quot;A String&quot;, # Required. The harm block threshold.
    },
  ],
  &quot;systemInstruction&quot;: { # 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. # 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.
    &quot;parts&quot;: [ # Required. Ordered `Parts` that constitute a single message. Parts may have different IANA MIME types.
      { # 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 `inline_data` or `file_data` field is filled with raw bytes.
        &quot;codeExecutionResult&quot;: { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. Result of executing the [ExecutableCode].
          &quot;outcome&quot;: &quot;A String&quot;, # Required. Outcome of the code execution.
          &quot;output&quot;: &quot;A String&quot;, # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
        },
        &quot;executableCode&quot;: { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is meant to be executed.
          &quot;code&quot;: &quot;A String&quot;, # Required. The code to be executed.
          &quot;language&quot;: &quot;A String&quot;, # Required. Programming language of the `code`.
        },
        &quot;fileData&quot;: { # URI based data. # Optional. URI based data.
          &quot;displayName&quot;: &quot;A String&quot;, # Optional. Display name of the file data. Used to provide a label or filename to distinguish file datas. This field is only returned in PromptMessage for prompt management. It is currently used in the Gemini GenerateContent calls only when server side tools (code_execution, google_search, and url_context) are enabled.
          &quot;fileUri&quot;: &quot;A String&quot;, # Required. URI.
          &quot;mimeType&quot;: &quot;A String&quot;, # Required. The IANA standard MIME type of the source data.
        },
        &quot;functionCall&quot;: { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] with the parameters and their values.
          &quot;args&quot;: { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details.
            &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
          },
          &quot;name&quot;: &quot;A String&quot;, # Required. The name of the function to call. Matches [FunctionDeclaration.name].
        },
        &quot;functionResponse&quot;: { # 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 a [FunctionCall] made based on model prediction. # Optional. 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 call. It is used as context to the model.
          &quot;name&quot;: &quot;A String&quot;, # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name].
          &quot;response&quot;: { # Required. The function response in JSON object format. Use &quot;output&quot; key to specify function output and &quot;error&quot; key to specify error details (if any). If &quot;output&quot; and &quot;error&quot; keys are not specified, then whole &quot;response&quot; is treated as function output.
            &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
          },
        },
        &quot;inlineData&quot;: { # Content blob. # Optional. Inlined bytes data.
          &quot;data&quot;: &quot;A String&quot;, # Required. Raw bytes.
          &quot;displayName&quot;: &quot;A String&quot;, # Optional. Display name of the blob. Used to provide a label or filename to distinguish blobs. This field is only returned in PromptMessage for prompt management. It is currently used in the Gemini GenerateContent calls only when server side tools (code_execution, google_search, and url_context) are enabled.
          &quot;mimeType&quot;: &quot;A String&quot;, # Required. The IANA standard MIME type of the source data.
        },
        &quot;text&quot;: &quot;A String&quot;, # Optional. Text part (can be code).
        &quot;thought&quot;: True or False, # Optional. Indicates if the part is thought from the model.
        &quot;thoughtSignature&quot;: &quot;A String&quot;, # Optional. An opaque signature for the thought so it can be reused in subsequent requests.
        &quot;videoMetadata&quot;: { # Metadata describes the input video content. # Optional. Video metadata. The metadata should only be specified while the video data is presented in inline_data or file_data.
          &quot;endOffset&quot;: &quot;A String&quot;, # Optional. The end offset of the video.
          &quot;fps&quot;: 3.14, # 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].
          &quot;startOffset&quot;: &quot;A String&quot;, # Optional. The start offset of the video.
        },
      },
    ],
    &quot;role&quot;: &quot;A String&quot;, # Optional. The producer of the content. Must be either &#x27;user&#x27; or &#x27;model&#x27;. Useful to set for multi-turn conversations, otherwise can be left blank or unset.
  },
  &quot;toolConfig&quot;: { # Tool config. This config is shared for all tools provided in the request. # Optional. Tool config. This config is shared for all tools provided in the request.
    &quot;functionCallingConfig&quot;: { # Function calling config. # Optional. Function calling config.
      &quot;allowedFunctionNames&quot;: [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match [FunctionDeclaration.name]. With mode set to ANY, model will predict a function call from the set of function names provided.
        &quot;A String&quot;,
      ],
      &quot;mode&quot;: &quot;A String&quot;, # Optional. Function calling mode.
    },
    &quot;retrievalConfig&quot;: { # Retrieval config. # Optional. Retrieval config.
      &quot;languageCode&quot;: &quot;A String&quot;, # The language code of the user.
      &quot;latLng&quot;: { # An object that represents a latitude/longitude pair. This is expressed as a pair of doubles to represent degrees latitude and degrees longitude. Unless specified otherwise, this object must conform to the WGS84 standard. Values must be within normalized ranges. # The location of the user.
        &quot;latitude&quot;: 3.14, # The latitude in degrees. It must be in the range [-90.0, +90.0].
        &quot;longitude&quot;: 3.14, # The longitude in degrees. It must be in the range [-180.0, +180.0].
      },
    },
  },
  &quot;tools&quot;: [ # 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.
    { # 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. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval).
      &quot;codeExecution&quot;: { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation.
      },
      &quot;enterpriseWebSearch&quot;: { # Tool to search public web data, powered by Vertex AI Search and Sec4 compliance. # Optional. Tool to support searching public web data, powered by Vertex AI Search and Sec4 compliance.
        &quot;excludeDomains&quot;: [ # Optional. List of domains to be excluded from the search results. The default limit is 2000 domains.
          &quot;A String&quot;,
        ],
      },
      &quot;functionDeclarations&quot;: [ # Optional. Function tool type. One or more function declarations to be passed to the model along with the current user query. Model may decide to call a subset of these functions by populating FunctionCall in the response. User should provide a FunctionResponse for each function call in the next turn. Based on the function responses, Model will generate the final response back to the user. Maximum 512 function declarations can be provided.
        { # Structured representation of a function declaration as defined by the [OpenAPI 3.0 specification](https://spec.openapis.org/oas/v3.0.3). Included in this declaration are the function name, description, parameters and response type. 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.
          &quot;description&quot;: &quot;A String&quot;, # Optional. Description and purpose of the function. Model uses it to decide how and whether to call the function.
          &quot;name&quot;: &quot;A String&quot;, # Required. The name of the function to call. Must start with a letter or an underscore. Must be a-z, A-Z, 0-9, or contain underscores, dots and dashes, with a maximum length of 64.
          &quot;parameters&quot;: { # Schema is used to define the format of input/output data. Represents a select subset of an [OpenAPI 3.0 schema object](https://spec.openapis.org/oas/v3.0.3#schema-object). More fields may be added in the future as needed. # Optional. Describes the parameters to this function in JSON Schema Object format. 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. For function with no parameters, this can be left unset. Parameter names must start with a letter or an underscore and must only contain chars a-z, A-Z, 0-9, or underscores with a maximum length of 64. Example with 1 required and 1 optional parameter: type: OBJECT properties: param1: type: STRING param2: type: INTEGER required: - param1
            &quot;additionalProperties&quot;: &quot;&quot;, # Optional. Can either be a boolean or an object; controls the presence of additional properties.
            &quot;anyOf&quot;: [ # Optional. The value should be validated against any (one or more) of the subschemas in the list.
              # Object with schema name: GoogleCloudAiplatformV1Schema
            ],
            &quot;default&quot;: &quot;&quot;, # Optional. Default value of the data.
            &quot;defs&quot;: { # Optional. A map of definitions for use by `ref` Only allowed at the root of the schema.
              &quot;a_key&quot;: # Object with schema name: GoogleCloudAiplatformV1Schema
            },
            &quot;description&quot;: &quot;A String&quot;, # Optional. The description of the data.
            &quot;enum&quot;: [ # Optional. Possible values of the element of primitive type with enum format. Examples: 1. We can define direction as : {type:STRING, format:enum, enum:[&quot;EAST&quot;, NORTH&quot;, &quot;SOUTH&quot;, &quot;WEST&quot;]} 2. We can define apartment number as : {type:INTEGER, format:enum, enum:[&quot;101&quot;, &quot;201&quot;, &quot;301&quot;]}
              &quot;A String&quot;,
            ],
            &quot;example&quot;: &quot;&quot;, # Optional. Example of the object. Will only populated when the object is the root.
            &quot;format&quot;: &quot;A String&quot;, # Optional. The format of the data. Supported formats: for NUMBER type: &quot;float&quot;, &quot;double&quot; for INTEGER type: &quot;int32&quot;, &quot;int64&quot; for STRING type: &quot;email&quot;, &quot;byte&quot;, etc
            &quot;items&quot;: # Object with schema name: GoogleCloudAiplatformV1Schema # Optional. SCHEMA FIELDS FOR TYPE ARRAY Schema of the elements of Type.ARRAY.
            &quot;maxItems&quot;: &quot;A String&quot;, # Optional. Maximum number of the elements for Type.ARRAY.
            &quot;maxLength&quot;: &quot;A String&quot;, # Optional. Maximum length of the Type.STRING
            &quot;maxProperties&quot;: &quot;A String&quot;, # Optional. Maximum number of the properties for Type.OBJECT.
            &quot;maximum&quot;: 3.14, # Optional. Maximum value of the Type.INTEGER and Type.NUMBER
            &quot;minItems&quot;: &quot;A String&quot;, # Optional. Minimum number of the elements for Type.ARRAY.
            &quot;minLength&quot;: &quot;A String&quot;, # Optional. SCHEMA FIELDS FOR TYPE STRING Minimum length of the Type.STRING
            &quot;minProperties&quot;: &quot;A String&quot;, # Optional. Minimum number of the properties for Type.OBJECT.
            &quot;minimum&quot;: 3.14, # Optional. SCHEMA FIELDS FOR TYPE INTEGER and NUMBER Minimum value of the Type.INTEGER and Type.NUMBER
            &quot;nullable&quot;: True or False, # Optional. Indicates if the value may be null.
            &quot;pattern&quot;: &quot;A String&quot;, # Optional. Pattern of the Type.STRING to restrict a string to a regular expression.
            &quot;properties&quot;: { # Optional. SCHEMA FIELDS FOR TYPE OBJECT Properties of Type.OBJECT.
              &quot;a_key&quot;: # Object with schema name: GoogleCloudAiplatformV1Schema
            },
            &quot;propertyOrdering&quot;: [ # Optional. The order of the properties. Not a standard field in open api spec. Only used to support the order of the properties.
              &quot;A String&quot;,
            ],
            &quot;ref&quot;: &quot;A String&quot;, # Optional. Allows indirect references between schema nodes. The value should be a valid reference to a child of the root `defs`. For example, the following schema defines a reference to a schema node named &quot;Pet&quot;: type: object properties: pet: ref: #/defs/Pet defs: Pet: type: object properties: name: type: string The value of the &quot;pet&quot; property is a reference to the schema node named &quot;Pet&quot;. See details in https://json-schema.org/understanding-json-schema/structuring
            &quot;required&quot;: [ # Optional. Required properties of Type.OBJECT.
              &quot;A String&quot;,
            ],
            &quot;title&quot;: &quot;A String&quot;, # Optional. The title of the Schema.
            &quot;type&quot;: &quot;A String&quot;, # Optional. The type of the data.
          },
          &quot;parametersJsonSchema&quot;: &quot;&quot;, # 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: ``` { &quot;type&quot;: &quot;object&quot;, &quot;properties&quot;: { &quot;name&quot;: { &quot;type&quot;: &quot;string&quot; }, &quot;age&quot;: { &quot;type&quot;: &quot;integer&quot; } }, &quot;additionalProperties&quot;: false, &quot;required&quot;: [&quot;name&quot;, &quot;age&quot;], &quot;propertyOrdering&quot;: [&quot;name&quot;, &quot;age&quot;] } ``` This field is mutually exclusive with `parameters`.
          &quot;response&quot;: { # Schema is used to define the format of input/output data. Represents a select subset of an [OpenAPI 3.0 schema object](https://spec.openapis.org/oas/v3.0.3#schema-object). More fields may be added in the future as needed. # 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.
            &quot;additionalProperties&quot;: &quot;&quot;, # Optional. Can either be a boolean or an object; controls the presence of additional properties.
            &quot;anyOf&quot;: [ # Optional. The value should be validated against any (one or more) of the subschemas in the list.
              # Object with schema name: GoogleCloudAiplatformV1Schema
            ],
            &quot;default&quot;: &quot;&quot;, # Optional. Default value of the data.
            &quot;defs&quot;: { # Optional. A map of definitions for use by `ref` Only allowed at the root of the schema.
              &quot;a_key&quot;: # Object with schema name: GoogleCloudAiplatformV1Schema
            },
            &quot;description&quot;: &quot;A String&quot;, # Optional. The description of the data.
            &quot;enum&quot;: [ # Optional. Possible values of the element of primitive type with enum format. Examples: 1. We can define direction as : {type:STRING, format:enum, enum:[&quot;EAST&quot;, NORTH&quot;, &quot;SOUTH&quot;, &quot;WEST&quot;]} 2. We can define apartment number as : {type:INTEGER, format:enum, enum:[&quot;101&quot;, &quot;201&quot;, &quot;301&quot;]}
              &quot;A String&quot;,
            ],
            &quot;example&quot;: &quot;&quot;, # Optional. Example of the object. Will only populated when the object is the root.
            &quot;format&quot;: &quot;A String&quot;, # Optional. The format of the data. Supported formats: for NUMBER type: &quot;float&quot;, &quot;double&quot; for INTEGER type: &quot;int32&quot;, &quot;int64&quot; for STRING type: &quot;email&quot;, &quot;byte&quot;, etc
            &quot;items&quot;: # Object with schema name: GoogleCloudAiplatformV1Schema # Optional. SCHEMA FIELDS FOR TYPE ARRAY Schema of the elements of Type.ARRAY.
            &quot;maxItems&quot;: &quot;A String&quot;, # Optional. Maximum number of the elements for Type.ARRAY.
            &quot;maxLength&quot;: &quot;A String&quot;, # Optional. Maximum length of the Type.STRING
            &quot;maxProperties&quot;: &quot;A String&quot;, # Optional. Maximum number of the properties for Type.OBJECT.
            &quot;maximum&quot;: 3.14, # Optional. Maximum value of the Type.INTEGER and Type.NUMBER
            &quot;minItems&quot;: &quot;A String&quot;, # Optional. Minimum number of the elements for Type.ARRAY.
            &quot;minLength&quot;: &quot;A String&quot;, # Optional. SCHEMA FIELDS FOR TYPE STRING Minimum length of the Type.STRING
            &quot;minProperties&quot;: &quot;A String&quot;, # Optional. Minimum number of the properties for Type.OBJECT.
            &quot;minimum&quot;: 3.14, # Optional. SCHEMA FIELDS FOR TYPE INTEGER and NUMBER Minimum value of the Type.INTEGER and Type.NUMBER
            &quot;nullable&quot;: True or False, # Optional. Indicates if the value may be null.
            &quot;pattern&quot;: &quot;A String&quot;, # Optional. Pattern of the Type.STRING to restrict a string to a regular expression.
            &quot;properties&quot;: { # Optional. SCHEMA FIELDS FOR TYPE OBJECT Properties of Type.OBJECT.
              &quot;a_key&quot;: # Object with schema name: GoogleCloudAiplatformV1Schema
            },
            &quot;propertyOrdering&quot;: [ # Optional. The order of the properties. Not a standard field in open api spec. Only used to support the order of the properties.
              &quot;A String&quot;,
            ],
            &quot;ref&quot;: &quot;A String&quot;, # Optional. Allows indirect references between schema nodes. The value should be a valid reference to a child of the root `defs`. For example, the following schema defines a reference to a schema node named &quot;Pet&quot;: type: object properties: pet: ref: #/defs/Pet defs: Pet: type: object properties: name: type: string The value of the &quot;pet&quot; property is a reference to the schema node named &quot;Pet&quot;. See details in https://json-schema.org/understanding-json-schema/structuring
            &quot;required&quot;: [ # Optional. Required properties of Type.OBJECT.
              &quot;A String&quot;,
            ],
            &quot;title&quot;: &quot;A String&quot;, # Optional. The title of the Schema.
            &quot;type&quot;: &quot;A String&quot;, # Optional. The type of the data.
          },
          &quot;responseJsonSchema&quot;: &quot;&quot;, # 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`.
        },
      ],
      &quot;googleMaps&quot;: { # Tool to retrieve public maps data for grounding, powered by Google. # Optional. GoogleMaps tool type. Tool to support Google Maps in Model.
      },
      &quot;googleSearch&quot;: { # GoogleSearch tool type. Tool to support Google Search in Model. Powered by Google. # Optional. GoogleSearch tool type. Tool to support Google Search in Model. Powered by Google.
        &quot;excludeDomains&quot;: [ # Optional. List of domains to be excluded from the search results. The default limit is 2000 domains. Example: [&quot;amazon.com&quot;, &quot;facebook.com&quot;].
          &quot;A String&quot;,
        ],
      },
      &quot;googleSearchRetrieval&quot;: { # Tool to retrieve public web data for grounding, powered by Google. # Optional. GoogleSearchRetrieval tool type. Specialized retrieval tool that is powered by Google search.
        &quot;dynamicRetrievalConfig&quot;: { # Describes the options to customize dynamic retrieval. # Specifies the dynamic retrieval configuration for the given source.
          &quot;dynamicThreshold&quot;: 3.14, # Optional. The threshold to be used in dynamic retrieval. If not set, a system default value is used.
          &quot;mode&quot;: &quot;A String&quot;, # The mode of the predictor to be used in dynamic retrieval.
        },
      },
      &quot;retrieval&quot;: { # Defines a retrieval tool that model can call to access external knowledge. # Optional. Retrieval tool type. System will always execute the provided retrieval tool(s) to get external knowledge to answer the prompt. Retrieval results are presented to the model for generation.
        &quot;disableAttribution&quot;: True or False, # Optional. Deprecated. This option is no longer supported.
        &quot;externalApi&quot;: { # Retrieve from data source powered by external API for grounding. The external API is not owned by Google, but need to follow the pre-defined API spec. # Use data source powered by external API for grounding.
          &quot;apiAuth&quot;: { # The generic reusable api auth config. Deprecated. Please use AuthConfig (google/cloud/aiplatform/master/auth.proto) instead. # The authentication config to access the API. Deprecated. Please use auth_config instead.
            &quot;apiKeyConfig&quot;: { # The API secret. # The API secret.
              &quot;apiKeySecretVersion&quot;: &quot;A String&quot;, # Required. The SecretManager secret version resource name storing API key. e.g. projects/{project}/secrets/{secret}/versions/{version}
              &quot;apiKeyString&quot;: &quot;A String&quot;, # The API key string. Either this or `api_key_secret_version` must be set.
            },
          },
          &quot;apiSpec&quot;: &quot;A String&quot;, # The API spec that the external API implements.
          &quot;authConfig&quot;: { # Auth configuration to run the extension. # The authentication config to access the API.
            &quot;apiKeyConfig&quot;: { # Config for authentication with API key. # Config for API key auth.
              &quot;apiKeySecret&quot;: &quot;A String&quot;, # Optional. The name of the SecretManager secret version resource storing the API key. Format: `projects/{project}/secrets/{secrete}/versions/{version}` - If both `api_key_secret` and `api_key_string` are specified, this field takes precedence over `api_key_string`. - If specified, the `secretmanager.versions.access` permission should be granted to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) on the specified resource.
              &quot;apiKeyString&quot;: &quot;A String&quot;, # Optional. The API key to be used in the request directly.
              &quot;httpElementLocation&quot;: &quot;A String&quot;, # Optional. The location of the API key.
              &quot;name&quot;: &quot;A String&quot;, # Optional. The parameter name of the API key. E.g. If the API request is &quot;https://example.com/act?api_key=&quot;, &quot;api_key&quot; would be the parameter name.
            },
            &quot;authType&quot;: &quot;A String&quot;, # Type of auth scheme.
            &quot;googleServiceAccountConfig&quot;: { # Config for Google Service Account Authentication. # Config for Google Service Account auth.
              &quot;serviceAccount&quot;: &quot;A String&quot;, # Optional. The service account that the extension execution service runs as. - If the service account is specified, the `iam.serviceAccounts.getAccessToken` permission should be granted to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) on the specified service account. - If not specified, the Vertex AI Extension Service Agent will be used to execute the Extension.
            },
            &quot;httpBasicAuthConfig&quot;: { # Config for HTTP Basic Authentication. # Config for HTTP Basic auth.
              &quot;credentialSecret&quot;: &quot;A String&quot;, # Required. The name of the SecretManager secret version resource storing the base64 encoded credentials. Format: `projects/{project}/secrets/{secrete}/versions/{version}` - If specified, the `secretmanager.versions.access` permission should be granted to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) on the specified resource.
            },
            &quot;oauthConfig&quot;: { # Config for user oauth. # Config for user oauth.
              &quot;accessToken&quot;: &quot;A String&quot;, # Access token for extension endpoint. Only used to propagate token from [[ExecuteExtensionRequest.runtime_auth_config]] at request time.
              &quot;serviceAccount&quot;: &quot;A String&quot;, # The service account used to generate access tokens for executing the Extension. - If the service account is specified, the `iam.serviceAccounts.getAccessToken` permission should be granted to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) on the provided service account.
            },
            &quot;oidcConfig&quot;: { # Config for user OIDC auth. # Config for user OIDC auth.
              &quot;idToken&quot;: &quot;A String&quot;, # OpenID Connect formatted ID token for extension endpoint. Only used to propagate token from [[ExecuteExtensionRequest.runtime_auth_config]] at request time.
              &quot;serviceAccount&quot;: &quot;A String&quot;, # The service account used to generate an OpenID Connect (OIDC)-compatible JWT token signed by the Google OIDC Provider (accounts.google.com) for extension endpoint (https://cloud.google.com/iam/docs/create-short-lived-credentials-direct#sa-credentials-oidc). - The audience for the token will be set to the URL in the server url defined in the OpenApi spec. - If the service account is provided, the service account should grant `iam.serviceAccounts.getOpenIdToken` permission to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents).
            },
          },
          &quot;elasticSearchParams&quot;: { # The search parameters to use for the ELASTIC_SEARCH spec. # Parameters for the elastic search API.
            &quot;index&quot;: &quot;A String&quot;, # The ElasticSearch index to use.
            &quot;numHits&quot;: 42, # Optional. Number of hits (chunks) to request. When specified, it is passed to Elasticsearch as the `num_hits` param.
            &quot;searchTemplate&quot;: &quot;A String&quot;, # The ElasticSearch search template to use.
          },
          &quot;endpoint&quot;: &quot;A String&quot;, # The endpoint of the external API. The system will call the API at this endpoint to retrieve the data for grounding. Example: https://acme.com:443/search
          &quot;simpleSearchParams&quot;: { # The search parameters to use for SIMPLE_SEARCH spec. # Parameters for the simple search API.
          },
        },
        &quot;vertexAiSearch&quot;: { # Retrieve from Vertex AI Search datastore or engine for grounding. datastore and engine are mutually exclusive. See https://cloud.google.com/products/agent-builder # Set to use data source powered by Vertex AI Search.
          &quot;dataStoreSpecs&quot;: [ # Specifications that define the specific DataStores to be searched, along with configurations for those data stores. This is only considered for Engines with multiple data stores. It should only be set if engine is used.
            { # Define data stores within engine to filter on in a search call and configurations for those data stores. For more information, see https://cloud.google.com/generative-ai-app-builder/docs/reference/rpc/google.cloud.discoveryengine.v1#datastorespec
              &quot;dataStore&quot;: &quot;A String&quot;, # Full resource name of DataStore, such as Format: `projects/{project}/locations/{location}/collections/{collection}/dataStores/{dataStore}`
              &quot;filter&quot;: &quot;A String&quot;, # Optional. Filter specification to filter documents in the data store specified by data_store field. For more information on filtering, see [Filtering](https://cloud.google.com/generative-ai-app-builder/docs/filter-search-metadata)
            },
          ],
          &quot;datastore&quot;: &quot;A String&quot;, # Optional. Fully-qualified Vertex AI Search data store resource ID. Format: `projects/{project}/locations/{location}/collections/{collection}/dataStores/{dataStore}`
          &quot;engine&quot;: &quot;A String&quot;, # Optional. Fully-qualified Vertex AI Search engine resource ID. Format: `projects/{project}/locations/{location}/collections/{collection}/engines/{engine}`
          &quot;filter&quot;: &quot;A String&quot;, # Optional. Filter strings to be passed to the search API.
          &quot;maxResults&quot;: 42, # Optional. Number of search results to return per query. The default value is 10. The maximumm allowed value is 10.
        },
        &quot;vertexRagStore&quot;: { # Retrieve from Vertex RAG Store for grounding. # Set to use data source powered by Vertex RAG store. User data is uploaded via the VertexRagDataService.
          &quot;ragResources&quot;: [ # Optional. The representation of the rag source. It can be used to specify corpus only or ragfiles. Currently only support one corpus or multiple files from one corpus. In the future we may open up multiple corpora support.
            { # The definition of the Rag resource.
              &quot;ragCorpus&quot;: &quot;A String&quot;, # Optional. RagCorpora resource name. Format: `projects/{project}/locations/{location}/ragCorpora/{rag_corpus}`
              &quot;ragFileIds&quot;: [ # Optional. rag_file_id. The files should be in the same rag_corpus set in rag_corpus field.
                &quot;A String&quot;,
              ],
            },
          ],
          &quot;ragRetrievalConfig&quot;: { # Specifies the context retrieval config. # Optional. The retrieval config for the Rag query.
            &quot;filter&quot;: { # Config for filters. # Optional. Config for filters.
              &quot;metadataFilter&quot;: &quot;A String&quot;, # Optional. String for metadata filtering.
              &quot;vectorDistanceThreshold&quot;: 3.14, # Optional. Only returns contexts with vector distance smaller than the threshold.
              &quot;vectorSimilarityThreshold&quot;: 3.14, # Optional. Only returns contexts with vector similarity larger than the threshold.
            },
            &quot;ranking&quot;: { # Config for ranking and reranking. # Optional. Config for ranking and reranking.
              &quot;llmRanker&quot;: { # Config for LlmRanker. # Optional. Config for LlmRanker.
                &quot;modelName&quot;: &quot;A String&quot;, # Optional. The model name used for ranking. See [Supported models](https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/inference#supported-models).
              },
              &quot;rankService&quot;: { # Config for Rank Service. # Optional. Config for Rank Service.
                &quot;modelName&quot;: &quot;A String&quot;, # Optional. The model name of the rank service. Format: `semantic-ranker-512@latest`
              },
            },
            &quot;topK&quot;: 42, # Optional. The number of contexts to retrieve.
          },
          &quot;similarityTopK&quot;: 42, # Optional. Number of top k results to return from the selected corpora.
          &quot;vectorDistanceThreshold&quot;: 3.14, # Optional. Only return results with vector distance smaller than the threshold.
        },
      },
      &quot;urlContext&quot;: { # Tool to support URL context. # Optional. Tool to support URL context retrieval.
      },
    },
  ],
}

  x__xgafv: string, V1 error format.
    Allowed values
      1 - v1 error format
      2 - v2 error format

Returns:
  An object of the form:

    { # Response message for [PredictionService.GenerateContent].
  &quot;candidates&quot;: [ # Output only. Generated candidates.
    { # A response candidate generated from the model.
      &quot;avgLogprobs&quot;: 3.14, # Output only. Average log probability score of the candidate.
      &quot;citationMetadata&quot;: { # A collection of source attributions for a piece of content. # Output only. Source attribution of the generated content.
        &quot;citations&quot;: [ # Output only. List of citations.
          { # Source attributions for content.
            &quot;endIndex&quot;: 42, # Output only. End index into the content.
            &quot;license&quot;: &quot;A String&quot;, # Output only. License of the attribution.
            &quot;publicationDate&quot;: { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # Output only. Publication date of the attribution.
              &quot;day&quot;: 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn&#x27;t significant.
              &quot;month&quot;: 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
              &quot;year&quot;: 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
            },
            &quot;startIndex&quot;: 42, # Output only. Start index into the content.
            &quot;title&quot;: &quot;A String&quot;, # Output only. Title of the attribution.
            &quot;uri&quot;: &quot;A String&quot;, # Output only. Url reference of the attribution.
          },
        ],
      },
      &quot;content&quot;: { # 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. # Output only. Content parts of the candidate.
        &quot;parts&quot;: [ # Required. Ordered `Parts` that constitute a single message. Parts may have different IANA MIME types.
          { # 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 `inline_data` or `file_data` field is filled with raw bytes.
            &quot;codeExecutionResult&quot;: { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. Result of executing the [ExecutableCode].
              &quot;outcome&quot;: &quot;A String&quot;, # Required. Outcome of the code execution.
              &quot;output&quot;: &quot;A String&quot;, # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
            },
            &quot;executableCode&quot;: { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is meant to be executed.
              &quot;code&quot;: &quot;A String&quot;, # Required. The code to be executed.
              &quot;language&quot;: &quot;A String&quot;, # Required. Programming language of the `code`.
            },
            &quot;fileData&quot;: { # URI based data. # Optional. URI based data.
              &quot;displayName&quot;: &quot;A String&quot;, # Optional. Display name of the file data. Used to provide a label or filename to distinguish file datas. This field is only returned in PromptMessage for prompt management. It is currently used in the Gemini GenerateContent calls only when server side tools (code_execution, google_search, and url_context) are enabled.
              &quot;fileUri&quot;: &quot;A String&quot;, # Required. URI.
              &quot;mimeType&quot;: &quot;A String&quot;, # Required. The IANA standard MIME type of the source data.
            },
            &quot;functionCall&quot;: { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] with the parameters and their values.
              &quot;args&quot;: { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details.
                &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
              },
              &quot;name&quot;: &quot;A String&quot;, # Required. The name of the function to call. Matches [FunctionDeclaration.name].
            },
            &quot;functionResponse&quot;: { # 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 a [FunctionCall] made based on model prediction. # Optional. 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 call. It is used as context to the model.
              &quot;name&quot;: &quot;A String&quot;, # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name].
              &quot;response&quot;: { # Required. The function response in JSON object format. Use &quot;output&quot; key to specify function output and &quot;error&quot; key to specify error details (if any). If &quot;output&quot; and &quot;error&quot; keys are not specified, then whole &quot;response&quot; is treated as function output.
                &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
              },
            },
            &quot;inlineData&quot;: { # Content blob. # Optional. Inlined bytes data.
              &quot;data&quot;: &quot;A String&quot;, # Required. Raw bytes.
              &quot;displayName&quot;: &quot;A String&quot;, # Optional. Display name of the blob. Used to provide a label or filename to distinguish blobs. This field is only returned in PromptMessage for prompt management. It is currently used in the Gemini GenerateContent calls only when server side tools (code_execution, google_search, and url_context) are enabled.
              &quot;mimeType&quot;: &quot;A String&quot;, # Required. The IANA standard MIME type of the source data.
            },
            &quot;text&quot;: &quot;A String&quot;, # Optional. Text part (can be code).
            &quot;thought&quot;: True or False, # Optional. Indicates if the part is thought from the model.
            &quot;thoughtSignature&quot;: &quot;A String&quot;, # Optional. An opaque signature for the thought so it can be reused in subsequent requests.
            &quot;videoMetadata&quot;: { # Metadata describes the input video content. # Optional. Video metadata. The metadata should only be specified while the video data is presented in inline_data or file_data.
              &quot;endOffset&quot;: &quot;A String&quot;, # Optional. The end offset of the video.
              &quot;fps&quot;: 3.14, # 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].
              &quot;startOffset&quot;: &quot;A String&quot;, # Optional. The start offset of the video.
            },
          },
        ],
        &quot;role&quot;: &quot;A String&quot;, # Optional. The producer of the content. Must be either &#x27;user&#x27; or &#x27;model&#x27;. Useful to set for multi-turn conversations, otherwise can be left blank or unset.
      },
      &quot;finishMessage&quot;: &quot;A String&quot;, # Output only. Describes the reason the mode stopped generating tokens in more detail. This is only filled when `finish_reason` is set.
      &quot;finishReason&quot;: &quot;A String&quot;, # Output only. The reason why the model stopped generating tokens. If empty, the model has not stopped generating the tokens.
      &quot;groundingMetadata&quot;: { # Metadata returned to client when grounding is enabled. # Output only. Metadata specifies sources used to ground generated content.
        &quot;googleMapsWidgetContextToken&quot;: &quot;A String&quot;, # Optional. Output only. Resource name of the Google Maps widget context token to be used with the PlacesContextElement widget to render contextual data. This is populated only for Google Maps grounding.
        &quot;groundingChunks&quot;: [ # List of supporting references retrieved from specified grounding source.
          { # Grounding chunk.
            &quot;maps&quot;: { # Chunk from Google Maps. # Grounding chunk from Google Maps.
              &quot;placeAnswerSources&quot;: { # Sources used to generate the place answer. # Sources used to generate the place answer. This includes review snippets and photos that were used to generate the answer, as well as uris to flag content.
                &quot;flagContentUri&quot;: &quot;A String&quot;, # A link where users can flag a problem with the generated answer.
                &quot;reviewSnippets&quot;: [ # Snippets of reviews that are used to generate the answer.
                  { # Encapsulates a review snippet.
                    &quot;authorAttribution&quot;: { # Author attribution for a photo or review. # This review&#x27;s author.
                      &quot;displayName&quot;: &quot;A String&quot;, # Name of the author of the Photo or Review.
                      &quot;photoUri&quot;: &quot;A String&quot;, # Profile photo URI of the author of the Photo or Review.
                      &quot;uri&quot;: &quot;A String&quot;, # URI of the author of the Photo or Review.
                    },
                    &quot;flagContentUri&quot;: &quot;A String&quot;, # A link where users can flag a problem with the review.
                    &quot;googleMapsUri&quot;: &quot;A String&quot;, # A link to show the review on Google Maps.
                    &quot;relativePublishTimeDescription&quot;: &quot;A String&quot;, # A string of formatted recent time, expressing the review time relative to the current time in a form appropriate for the language and country.
                    &quot;review&quot;: &quot;A String&quot;, # A reference representing this place review which may be used to look up this place review again.
                  },
                ],
              },
              &quot;placeId&quot;: &quot;A String&quot;, # This Place&#x27;s resource name, in `places/{place_id}` format. Can be used to look up the Place.
              &quot;text&quot;: &quot;A String&quot;, # Text of the chunk.
              &quot;title&quot;: &quot;A String&quot;, # Title of the chunk.
              &quot;uri&quot;: &quot;A String&quot;, # URI reference of the chunk.
            },
            &quot;retrievedContext&quot;: { # Chunk from context retrieved by the retrieval tools. # Grounding chunk from context retrieved by the retrieval tools.
              &quot;documentName&quot;: &quot;A String&quot;, # Output only. The full document name for the referenced Vertex AI Search document.
              &quot;ragChunk&quot;: { # A RagChunk includes the content of a chunk of a RagFile, and associated metadata. # Additional context for the RAG retrieval result. This is only populated when using the RAG retrieval tool.
                &quot;pageSpan&quot;: { # Represents where the chunk starts and ends in the document. # If populated, represents where the chunk starts and ends in the document.
                  &quot;firstPage&quot;: 42, # Page where chunk starts in the document. Inclusive. 1-indexed.
                  &quot;lastPage&quot;: 42, # Page where chunk ends in the document. Inclusive. 1-indexed.
                },
                &quot;text&quot;: &quot;A String&quot;, # The content of the chunk.
              },
              &quot;text&quot;: &quot;A String&quot;, # Text of the attribution.
              &quot;title&quot;: &quot;A String&quot;, # Title of the attribution.
              &quot;uri&quot;: &quot;A String&quot;, # URI reference of the attribution.
            },
            &quot;web&quot;: { # Chunk from the web. # Grounding chunk from the web.
              &quot;domain&quot;: &quot;A String&quot;, # Domain of the (original) URI.
              &quot;title&quot;: &quot;A String&quot;, # Title of the chunk.
              &quot;uri&quot;: &quot;A String&quot;, # URI reference of the chunk.
            },
          },
        ],
        &quot;groundingSupports&quot;: [ # Optional. List of grounding support.
          { # Grounding support.
            &quot;confidenceScores&quot;: [ # Confidence score of the support references. Ranges from 0 to 1. 1 is the most confident. For Gemini 2.0 and before, this list must have the same size as the grounding_chunk_indices. For Gemini 2.5 and after, this list will be empty and should be ignored.
              3.14,
            ],
            &quot;groundingChunkIndices&quot;: [ # A list of indices (into &#x27;grounding_chunk&#x27;) 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.
              42,
            ],
            &quot;segment&quot;: { # Segment of the content. # Segment of the content this support belongs to.
              &quot;endIndex&quot;: 42, # Output only. End index in the given Part, measured in bytes. Offset from the start of the Part, exclusive, starting at zero.
              &quot;partIndex&quot;: 42, # Output only. The index of a Part object within its parent Content object.
              &quot;startIndex&quot;: 42, # Output only. Start index in the given Part, measured in bytes. Offset from the start of the Part, inclusive, starting at zero.
              &quot;text&quot;: &quot;A String&quot;, # Output only. The text corresponding to the segment from the response.
            },
          },
        ],
        &quot;retrievalMetadata&quot;: { # Metadata related to retrieval in the grounding flow. # Optional. Output only. Retrieval metadata.
          &quot;googleSearchDynamicRetrievalScore&quot;: 3.14, # 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.
        },
        &quot;searchEntryPoint&quot;: { # Google search entry point. # Optional. Google search entry for the following-up web searches.
          &quot;renderedContent&quot;: &quot;A String&quot;, # Optional. Web content snippet that can be embedded in a web page or an app webview.
          &quot;sdkBlob&quot;: &quot;A String&quot;, # Optional. Base64 encoded JSON representing array of tuple.
        },
        &quot;webSearchQueries&quot;: [ # Optional. Web search queries for the following-up web search.
          &quot;A String&quot;,
        ],
      },
      &quot;index&quot;: 42, # Output only. Index of the candidate.
      &quot;logprobsResult&quot;: { # Logprobs Result # Output only. Log-likelihood scores for the response tokens and top tokens
        &quot;chosenCandidates&quot;: [ # Length = total number of decoding steps. The chosen candidates may or may not be in top_candidates.
          { # Candidate for the logprobs token and score.
            &quot;logProbability&quot;: 3.14, # The candidate&#x27;s log probability.
            &quot;token&quot;: &quot;A String&quot;, # The candidate&#x27;s token string value.
            &quot;tokenId&quot;: 42, # The candidate&#x27;s token id value.
          },
        ],
        &quot;topCandidates&quot;: [ # Length = total number of decoding steps.
          { # Candidates with top log probabilities at each decoding step.
            &quot;candidates&quot;: [ # Sorted by log probability in descending order.
              { # Candidate for the logprobs token and score.
                &quot;logProbability&quot;: 3.14, # The candidate&#x27;s log probability.
                &quot;token&quot;: &quot;A String&quot;, # The candidate&#x27;s token string value.
                &quot;tokenId&quot;: 42, # The candidate&#x27;s token id value.
              },
            ],
          },
        ],
      },
      &quot;safetyRatings&quot;: [ # Output only. List of ratings for the safety of a response candidate. There is at most one rating per category.
        { # Safety rating corresponding to the generated content.
          &quot;blocked&quot;: True or False, # Output only. Indicates whether the content was filtered out because of this rating.
          &quot;category&quot;: &quot;A String&quot;, # Output only. Harm category.
          &quot;overwrittenThreshold&quot;: &quot;A String&quot;, # Output only. The overwritten threshold for the safety category of Gemini 2.0 image out. If minors are detected in the output image, the threshold of each safety category will be overwritten if user sets a lower threshold.
          &quot;probability&quot;: &quot;A String&quot;, # Output only. Harm probability levels in the content.
          &quot;probabilityScore&quot;: 3.14, # Output only. Harm probability score.
          &quot;severity&quot;: &quot;A String&quot;, # Output only. Harm severity levels in the content.
          &quot;severityScore&quot;: 3.14, # Output only. Harm severity score.
        },
      ],
      &quot;urlContextMetadata&quot;: { # Metadata related to url context retrieval tool. # Output only. Metadata related to url context retrieval tool.
        &quot;urlMetadata&quot;: [ # Output only. List of url context.
          { # Context of the a single url retrieval.
            &quot;retrievedUrl&quot;: &quot;A String&quot;, # Retrieved url by the tool.
            &quot;urlRetrievalStatus&quot;: &quot;A String&quot;, # Status of the url retrieval.
          },
        ],
      },
    },
  ],
  &quot;createTime&quot;: &quot;A String&quot;, # Output only. Timestamp when the request is made to the server.
  &quot;modelVersion&quot;: &quot;A String&quot;, # Output only. The model version used to generate the response.
  &quot;promptFeedback&quot;: { # Content filter results for a prompt sent in the request. # Output only. Content filter results for a prompt sent in the request. Note: Sent only in the first stream chunk. Only happens when no candidates were generated due to content violations.
    &quot;blockReason&quot;: &quot;A String&quot;, # Output only. Blocked reason.
    &quot;blockReasonMessage&quot;: &quot;A String&quot;, # Output only. A readable block reason message.
    &quot;safetyRatings&quot;: [ # Output only. Safety ratings.
      { # Safety rating corresponding to the generated content.
        &quot;blocked&quot;: True or False, # Output only. Indicates whether the content was filtered out because of this rating.
        &quot;category&quot;: &quot;A String&quot;, # Output only. Harm category.
        &quot;overwrittenThreshold&quot;: &quot;A String&quot;, # Output only. The overwritten threshold for the safety category of Gemini 2.0 image out. If minors are detected in the output image, the threshold of each safety category will be overwritten if user sets a lower threshold.
        &quot;probability&quot;: &quot;A String&quot;, # Output only. Harm probability levels in the content.
        &quot;probabilityScore&quot;: 3.14, # Output only. Harm probability score.
        &quot;severity&quot;: &quot;A String&quot;, # Output only. Harm severity levels in the content.
        &quot;severityScore&quot;: 3.14, # Output only. Harm severity score.
      },
    ],
  },
  &quot;responseId&quot;: &quot;A String&quot;, # Output only. response_id is used to identify each response. It is the encoding of the event_id.
  &quot;usageMetadata&quot;: { # Usage metadata about response(s). # Usage metadata about the response(s).
    &quot;cacheTokensDetails&quot;: [ # Output only. List of modalities of the cached content in the request input.
      { # Represents token counting info for a single modality.
        &quot;modality&quot;: &quot;A String&quot;, # The modality associated with this token count.
        &quot;tokenCount&quot;: 42, # Number of tokens.
      },
    ],
    &quot;cachedContentTokenCount&quot;: 42, # Output only. Number of tokens in the cached part in the input (the cached content).
    &quot;candidatesTokenCount&quot;: 42, # Number of tokens in the response(s).
    &quot;candidatesTokensDetails&quot;: [ # Output only. List of modalities that were returned in the response.
      { # Represents token counting info for a single modality.
        &quot;modality&quot;: &quot;A String&quot;, # The modality associated with this token count.
        &quot;tokenCount&quot;: 42, # Number of tokens.
      },
    ],
    &quot;promptTokenCount&quot;: 42, # Number of tokens in the request. When `cached_content` is set, this is still the total effective prompt size meaning this includes the number of tokens in the cached content.
    &quot;promptTokensDetails&quot;: [ # Output only. List of modalities that were processed in the request input.
      { # Represents token counting info for a single modality.
        &quot;modality&quot;: &quot;A String&quot;, # The modality associated with this token count.
        &quot;tokenCount&quot;: 42, # Number of tokens.
      },
    ],
    &quot;thoughtsTokenCount&quot;: 42, # Output only. Number of tokens present in thoughts output.
    &quot;toolUsePromptTokenCount&quot;: 42, # Output only. Number of tokens present in tool-use prompt(s).
    &quot;toolUsePromptTokensDetails&quot;: [ # Output only. List of modalities that were processed for tool-use request inputs.
      { # Represents token counting info for a single modality.
        &quot;modality&quot;: &quot;A String&quot;, # The modality associated with this token count.
        &quot;tokenCount&quot;: 42, # Number of tokens.
      },
    ],
    &quot;totalTokenCount&quot;: 42, # Total token count for prompt, response candidates, and tool-use prompts (if present).
    &quot;trafficType&quot;: &quot;A String&quot;, # Output only. Traffic type. This shows whether a request consumes Pay-As-You-Go or Provisioned Throughput quota.
  },
}</pre>
</div>

<div class="method">
    <code class="details" id="predict">predict(endpoint, body=None, x__xgafv=None)</code>
  <pre>Perform an online prediction.

Args:
  endpoint: string, Required. The name of the Endpoint requested to serve the prediction. Format: `projects/{project}/locations/{location}/endpoints/{endpoint}` (required)
  body: object, The request body.
    The object takes the form of:

{ # Request message for PredictionService.Predict.
  &quot;instances&quot;: [ # Required. The instances that are the input to the prediction call. A DeployedModel may have an upper limit on the number of instances it supports per request, and when it is exceeded the prediction call errors in case of AutoML Models, or, in case of customer created Models, the behaviour is as documented by that Model. The schema of any single instance may be specified via Endpoint&#x27;s DeployedModels&#x27; Model&#x27;s PredictSchemata&#x27;s instance_schema_uri.
    &quot;&quot;,
  ],
  &quot;parameters&quot;: &quot;&quot;, # The parameters that govern the prediction. The schema of the parameters may be specified via Endpoint&#x27;s DeployedModels&#x27; Model&#x27;s PredictSchemata&#x27;s parameters_schema_uri.
}

  x__xgafv: string, V1 error format.
    Allowed values
      1 - v1 error format
      2 - v2 error format

Returns:
  An object of the form:

    { # Response message for PredictionService.Predict.
  &quot;deployedModelId&quot;: &quot;A String&quot;, # ID of the Endpoint&#x27;s DeployedModel that served this prediction.
  &quot;metadata&quot;: &quot;&quot;, # Output only. Request-level metadata returned by the model. The metadata type will be dependent upon the model implementation.
  &quot;model&quot;: &quot;A String&quot;, # Output only. The resource name of the Model which is deployed as the DeployedModel that this prediction hits.
  &quot;modelDisplayName&quot;: &quot;A String&quot;, # Output only. The display name of the Model which is deployed as the DeployedModel that this prediction hits.
  &quot;modelVersionId&quot;: &quot;A String&quot;, # Output only. The version ID of the Model which is deployed as the DeployedModel that this prediction hits.
  &quot;predictions&quot;: [ # The predictions that are the output of the predictions call. The schema of any single prediction may be specified via Endpoint&#x27;s DeployedModels&#x27; Model&#x27;s PredictSchemata&#x27;s prediction_schema_uri.
    &quot;&quot;,
  ],
}</pre>
</div>

<div class="method">
    <code class="details" id="predictLongRunning">predictLongRunning(endpoint, body=None, x__xgafv=None)</code>
  <pre>

Args:
  endpoint: string, Required. The name of the Endpoint requested to serve the prediction. Format: `projects/{project}/locations/{location}/endpoints/{endpoint}` or `projects/{project}/locations/{location}/publishers/{publisher}/models/{model}` (required)
  body: object, The request body.
    The object takes the form of:

{ # Request message for PredictionService.PredictLongRunning.
  &quot;instances&quot;: [ # Required. The instances that are the input to the prediction call. A DeployedModel may have an upper limit on the number of instances it supports per request, and when it is exceeded the prediction call errors in case of AutoML Models, or, in case of customer created Models, the behaviour is as documented by that Model. The schema of any single instance may be specified via Endpoint&#x27;s DeployedModels&#x27; Model&#x27;s PredictSchemata&#x27;s instance_schema_uri.
    &quot;&quot;,
  ],
  &quot;parameters&quot;: &quot;&quot;, # Optional. The parameters that govern the prediction. The schema of the parameters may be specified via Endpoint&#x27;s DeployedModels&#x27; Model&#x27;s PredictSchemata&#x27;s parameters_schema_uri.
}

  x__xgafv: string, V1 error format.
    Allowed values
      1 - v1 error format
      2 - v2 error format

Returns:
  An object of the form:

    { # This resource represents a long-running operation that is the result of a network API call.
  &quot;done&quot;: True or False, # If the value is `false`, it means the operation is still in progress. If `true`, the operation is completed, and either `error` or `response` is available.
  &quot;error&quot;: { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # The error result of the operation in case of failure or cancellation.
    &quot;code&quot;: 42, # The status code, which should be an enum value of google.rpc.Code.
    &quot;details&quot;: [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
      {
        &quot;a_key&quot;: &quot;&quot;, # Properties of the object. Contains field @type with type URL.
      },
    ],
    &quot;message&quot;: &quot;A String&quot;, # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
  },
  &quot;metadata&quot;: { # Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any.
    &quot;a_key&quot;: &quot;&quot;, # Properties of the object. Contains field @type with type URL.
  },
  &quot;name&quot;: &quot;A String&quot;, # The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id}`.
  &quot;response&quot;: { # The normal, successful response of the operation. If the original method returns no data on success, such as `Delete`, the response is `google.protobuf.Empty`. If the original method is standard `Get`/`Create`/`Update`, the response should be the resource. For other methods, the response should have the type `XxxResponse`, where `Xxx` is the original method name. For example, if the original method name is `TakeSnapshot()`, the inferred response type is `TakeSnapshotResponse`.
    &quot;a_key&quot;: &quot;&quot;, # Properties of the object. Contains field @type with type URL.
  },
}</pre>
</div>

<div class="method">
    <code class="details" id="rawPredict">rawPredict(endpoint, body=None, x__xgafv=None)</code>
  <pre>Perform an online prediction with an arbitrary HTTP payload. The response includes the following HTTP headers: * `X-Vertex-AI-Endpoint-Id`: ID of the Endpoint that served this prediction. * `X-Vertex-AI-Deployed-Model-Id`: ID of the Endpoint&#x27;s DeployedModel that served this prediction.

Args:
  endpoint: string, Required. The name of the Endpoint requested to serve the prediction. Format: `projects/{project}/locations/{location}/endpoints/{endpoint}` (required)
  body: object, The request body.
    The object takes the form of:

{ # Request message for PredictionService.RawPredict.
  &quot;httpBody&quot;: { # Message that represents an arbitrary HTTP body. It should only be used for payload formats that can&#x27;t be represented as JSON, such as raw binary or an HTML page. This message can be used both in streaming and non-streaming API methods in the request as well as the response. It can be used as a top-level request field, which is convenient if one wants to extract parameters from either the URL or HTTP template into the request fields and also want access to the raw HTTP body. Example: message GetResourceRequest { // A unique request id. string request_id = 1; // The raw HTTP body is bound to this field. google.api.HttpBody http_body = 2; } service ResourceService { rpc GetResource(GetResourceRequest) returns (google.api.HttpBody); rpc UpdateResource(google.api.HttpBody) returns (google.protobuf.Empty); } Example with streaming methods: service CaldavService { rpc GetCalendar(stream google.api.HttpBody) returns (stream google.api.HttpBody); rpc UpdateCalendar(stream google.api.HttpBody) returns (stream google.api.HttpBody); } Use of this type only changes how the request and response bodies are handled, all other features will continue to work unchanged. # The prediction input. Supports HTTP headers and arbitrary data payload. A DeployedModel may have an upper limit on the number of instances it supports per request. When this limit it is exceeded for an AutoML model, the RawPredict method returns an error. When this limit is exceeded for a custom-trained model, the behavior varies depending on the model. You can specify the schema for each instance in the predict_schemata.instance_schema_uri field when you create a Model. This schema applies when you deploy the `Model` as a `DeployedModel` to an Endpoint and use the `RawPredict` method.
    &quot;contentType&quot;: &quot;A String&quot;, # The HTTP Content-Type header value specifying the content type of the body.
    &quot;data&quot;: &quot;A String&quot;, # The HTTP request/response body as raw binary.
    &quot;extensions&quot;: [ # Application specific response metadata. Must be set in the first response for streaming APIs.
      {
        &quot;a_key&quot;: &quot;&quot;, # Properties of the object. Contains field @type with type URL.
      },
    ],
  },
}

  x__xgafv: string, V1 error format.
    Allowed values
      1 - v1 error format
      2 - v2 error format

Returns:
  An object of the form:

    { # Message that represents an arbitrary HTTP body. It should only be used for payload formats that can&#x27;t be represented as JSON, such as raw binary or an HTML page. This message can be used both in streaming and non-streaming API methods in the request as well as the response. It can be used as a top-level request field, which is convenient if one wants to extract parameters from either the URL or HTTP template into the request fields and also want access to the raw HTTP body. Example: message GetResourceRequest { // A unique request id. string request_id = 1; // The raw HTTP body is bound to this field. google.api.HttpBody http_body = 2; } service ResourceService { rpc GetResource(GetResourceRequest) returns (google.api.HttpBody); rpc UpdateResource(google.api.HttpBody) returns (google.protobuf.Empty); } Example with streaming methods: service CaldavService { rpc GetCalendar(stream google.api.HttpBody) returns (stream google.api.HttpBody); rpc UpdateCalendar(stream google.api.HttpBody) returns (stream google.api.HttpBody); } Use of this type only changes how the request and response bodies are handled, all other features will continue to work unchanged.
  &quot;contentType&quot;: &quot;A String&quot;, # The HTTP Content-Type header value specifying the content type of the body.
  &quot;data&quot;: &quot;A String&quot;, # The HTTP request/response body as raw binary.
  &quot;extensions&quot;: [ # Application specific response metadata. Must be set in the first response for streaming APIs.
    {
      &quot;a_key&quot;: &quot;&quot;, # Properties of the object. Contains field @type with type URL.
    },
  ],
}</pre>
</div>

<div class="method">
    <code class="details" id="serverStreamingPredict">serverStreamingPredict(endpoint, body=None, x__xgafv=None)</code>
  <pre>Perform a server-side streaming online prediction request for Vertex LLM streaming.

Args:
  endpoint: string, Required. The name of the Endpoint requested to serve the prediction. Format: `projects/{project}/locations/{location}/endpoints/{endpoint}` (required)
  body: object, The request body.
    The object takes the form of:

{ # Request message for PredictionService.StreamingPredict. The first message must contain endpoint field and optionally input. The subsequent messages must contain input.
  &quot;inputs&quot;: [ # The prediction input.
    { # A tensor value type.
      &quot;boolVal&quot;: [ # Type specific representations that make it easy to create tensor protos in all languages. Only the representation corresponding to &quot;dtype&quot; can be set. The values hold the flattened representation of the tensor in row major order. BOOL
        True or False,
      ],
      &quot;bytesVal&quot;: [ # STRING
        &quot;A String&quot;,
      ],
      &quot;doubleVal&quot;: [ # DOUBLE
        3.14,
      ],
      &quot;dtype&quot;: &quot;A String&quot;, # The data type of tensor.
      &quot;floatVal&quot;: [ # FLOAT
        3.14,
      ],
      &quot;int64Val&quot;: [ # INT64
        &quot;A String&quot;,
      ],
      &quot;intVal&quot;: [ # INT_8 INT_16 INT_32
        42,
      ],
      &quot;listVal&quot;: [ # A list of tensor values.
        # Object with schema name: GoogleCloudAiplatformV1Tensor
      ],
      &quot;shape&quot;: [ # Shape of the tensor.
        &quot;A String&quot;,
      ],
      &quot;stringVal&quot;: [ # STRING
        &quot;A String&quot;,
      ],
      &quot;structVal&quot;: { # A map of string to tensor.
        &quot;a_key&quot;: # Object with schema name: GoogleCloudAiplatformV1Tensor
      },
      &quot;tensorVal&quot;: &quot;A String&quot;, # Serialized raw tensor content.
      &quot;uint64Val&quot;: [ # UINT64
        &quot;A String&quot;,
      ],
      &quot;uintVal&quot;: [ # UINT8 UINT16 UINT32
        42,
      ],
    },
  ],
  &quot;parameters&quot;: { # A tensor value type. # The parameters that govern the prediction.
    &quot;boolVal&quot;: [ # Type specific representations that make it easy to create tensor protos in all languages. Only the representation corresponding to &quot;dtype&quot; can be set. The values hold the flattened representation of the tensor in row major order. BOOL
      True or False,
    ],
    &quot;bytesVal&quot;: [ # STRING
      &quot;A String&quot;,
    ],
    &quot;doubleVal&quot;: [ # DOUBLE
      3.14,
    ],
    &quot;dtype&quot;: &quot;A String&quot;, # The data type of tensor.
    &quot;floatVal&quot;: [ # FLOAT
      3.14,
    ],
    &quot;int64Val&quot;: [ # INT64
      &quot;A String&quot;,
    ],
    &quot;intVal&quot;: [ # INT_8 INT_16 INT_32
      42,
    ],
    &quot;listVal&quot;: [ # A list of tensor values.
      # Object with schema name: GoogleCloudAiplatformV1Tensor
    ],
    &quot;shape&quot;: [ # Shape of the tensor.
      &quot;A String&quot;,
    ],
    &quot;stringVal&quot;: [ # STRING
      &quot;A String&quot;,
    ],
    &quot;structVal&quot;: { # A map of string to tensor.
      &quot;a_key&quot;: # Object with schema name: GoogleCloudAiplatformV1Tensor
    },
    &quot;tensorVal&quot;: &quot;A String&quot;, # Serialized raw tensor content.
    &quot;uint64Val&quot;: [ # UINT64
      &quot;A String&quot;,
    ],
    &quot;uintVal&quot;: [ # UINT8 UINT16 UINT32
      42,
    ],
  },
}

  x__xgafv: string, V1 error format.
    Allowed values
      1 - v1 error format
      2 - v2 error format

Returns:
  An object of the form:

    { # Response message for PredictionService.StreamingPredict.
  &quot;outputs&quot;: [ # The prediction output.
    { # A tensor value type.
      &quot;boolVal&quot;: [ # Type specific representations that make it easy to create tensor protos in all languages. Only the representation corresponding to &quot;dtype&quot; can be set. The values hold the flattened representation of the tensor in row major order. BOOL
        True or False,
      ],
      &quot;bytesVal&quot;: [ # STRING
        &quot;A String&quot;,
      ],
      &quot;doubleVal&quot;: [ # DOUBLE
        3.14,
      ],
      &quot;dtype&quot;: &quot;A String&quot;, # The data type of tensor.
      &quot;floatVal&quot;: [ # FLOAT
        3.14,
      ],
      &quot;int64Val&quot;: [ # INT64
        &quot;A String&quot;,
      ],
      &quot;intVal&quot;: [ # INT_8 INT_16 INT_32
        42,
      ],
      &quot;listVal&quot;: [ # A list of tensor values.
        # Object with schema name: GoogleCloudAiplatformV1Tensor
      ],
      &quot;shape&quot;: [ # Shape of the tensor.
        &quot;A String&quot;,
      ],
      &quot;stringVal&quot;: [ # STRING
        &quot;A String&quot;,
      ],
      &quot;structVal&quot;: { # A map of string to tensor.
        &quot;a_key&quot;: # Object with schema name: GoogleCloudAiplatformV1Tensor
      },
      &quot;tensorVal&quot;: &quot;A String&quot;, # Serialized raw tensor content.
      &quot;uint64Val&quot;: [ # UINT64
        &quot;A String&quot;,
      ],
      &quot;uintVal&quot;: [ # UINT8 UINT16 UINT32
        42,
      ],
    },
  ],
  &quot;parameters&quot;: { # A tensor value type. # The parameters that govern the prediction.
    &quot;boolVal&quot;: [ # Type specific representations that make it easy to create tensor protos in all languages. Only the representation corresponding to &quot;dtype&quot; can be set. The values hold the flattened representation of the tensor in row major order. BOOL
      True or False,
    ],
    &quot;bytesVal&quot;: [ # STRING
      &quot;A String&quot;,
    ],
    &quot;doubleVal&quot;: [ # DOUBLE
      3.14,
    ],
    &quot;dtype&quot;: &quot;A String&quot;, # The data type of tensor.
    &quot;floatVal&quot;: [ # FLOAT
      3.14,
    ],
    &quot;int64Val&quot;: [ # INT64
      &quot;A String&quot;,
    ],
    &quot;intVal&quot;: [ # INT_8 INT_16 INT_32
      42,
    ],
    &quot;listVal&quot;: [ # A list of tensor values.
      # Object with schema name: GoogleCloudAiplatformV1Tensor
    ],
    &quot;shape&quot;: [ # Shape of the tensor.
      &quot;A String&quot;,
    ],
    &quot;stringVal&quot;: [ # STRING
      &quot;A String&quot;,
    ],
    &quot;structVal&quot;: { # A map of string to tensor.
      &quot;a_key&quot;: # Object with schema name: GoogleCloudAiplatformV1Tensor
    },
    &quot;tensorVal&quot;: &quot;A String&quot;, # Serialized raw tensor content.
    &quot;uint64Val&quot;: [ # UINT64
      &quot;A String&quot;,
    ],
    &quot;uintVal&quot;: [ # UINT8 UINT16 UINT32
      42,
    ],
  },
}</pre>
</div>

<div class="method">
    <code class="details" id="streamGenerateContent">streamGenerateContent(model, body=None, x__xgafv=None)</code>
  <pre>Generate content with multimodal inputs with streaming support.

Args:
  model: string, Required. The fully qualified name of the publisher model or tuned model endpoint to use. Publisher model format: `projects/{project}/locations/{location}/publishers/*/models/*` Tuned model endpoint format: `projects/{project}/locations/{location}/endpoints/{endpoint}` (required)
  body: object, The request body.
    The object takes the form of:

{ # Request message for [PredictionService.GenerateContent].
  &quot;cachedContent&quot;: &quot;A String&quot;, # Optional. The name of the cached content used as context to serve the prediction. Note: only used in explicit caching, where users can have control over caching (e.g. what content to cache) and enjoy guaranteed cost savings. Format: `projects/{project}/locations/{location}/cachedContents/{cachedContent}`
  &quot;contents&quot;: [ # Required. The content of 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 + latest request.
    { # 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.
      &quot;parts&quot;: [ # Required. Ordered `Parts` that constitute a single message. Parts may have different IANA MIME types.
        { # 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 `inline_data` or `file_data` field is filled with raw bytes.
          &quot;codeExecutionResult&quot;: { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. Result of executing the [ExecutableCode].
            &quot;outcome&quot;: &quot;A String&quot;, # Required. Outcome of the code execution.
            &quot;output&quot;: &quot;A String&quot;, # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
          },
          &quot;executableCode&quot;: { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is meant to be executed.
            &quot;code&quot;: &quot;A String&quot;, # Required. The code to be executed.
            &quot;language&quot;: &quot;A String&quot;, # Required. Programming language of the `code`.
          },
          &quot;fileData&quot;: { # URI based data. # Optional. URI based data.
            &quot;displayName&quot;: &quot;A String&quot;, # Optional. Display name of the file data. Used to provide a label or filename to distinguish file datas. This field is only returned in PromptMessage for prompt management. It is currently used in the Gemini GenerateContent calls only when server side tools (code_execution, google_search, and url_context) are enabled.
            &quot;fileUri&quot;: &quot;A String&quot;, # Required. URI.
            &quot;mimeType&quot;: &quot;A String&quot;, # Required. The IANA standard MIME type of the source data.
          },
          &quot;functionCall&quot;: { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] with the parameters and their values.
            &quot;args&quot;: { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details.
              &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
            },
            &quot;name&quot;: &quot;A String&quot;, # Required. The name of the function to call. Matches [FunctionDeclaration.name].
          },
          &quot;functionResponse&quot;: { # 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 a [FunctionCall] made based on model prediction. # Optional. 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 call. It is used as context to the model.
            &quot;name&quot;: &quot;A String&quot;, # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name].
            &quot;response&quot;: { # Required. The function response in JSON object format. Use &quot;output&quot; key to specify function output and &quot;error&quot; key to specify error details (if any). If &quot;output&quot; and &quot;error&quot; keys are not specified, then whole &quot;response&quot; is treated as function output.
              &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
            },
          },
          &quot;inlineData&quot;: { # Content blob. # Optional. Inlined bytes data.
            &quot;data&quot;: &quot;A String&quot;, # Required. Raw bytes.
            &quot;displayName&quot;: &quot;A String&quot;, # Optional. Display name of the blob. Used to provide a label or filename to distinguish blobs. This field is only returned in PromptMessage for prompt management. It is currently used in the Gemini GenerateContent calls only when server side tools (code_execution, google_search, and url_context) are enabled.
            &quot;mimeType&quot;: &quot;A String&quot;, # Required. The IANA standard MIME type of the source data.
          },
          &quot;text&quot;: &quot;A String&quot;, # Optional. Text part (can be code).
          &quot;thought&quot;: True or False, # Optional. Indicates if the part is thought from the model.
          &quot;thoughtSignature&quot;: &quot;A String&quot;, # Optional. An opaque signature for the thought so it can be reused in subsequent requests.
          &quot;videoMetadata&quot;: { # Metadata describes the input video content. # Optional. Video metadata. The metadata should only be specified while the video data is presented in inline_data or file_data.
            &quot;endOffset&quot;: &quot;A String&quot;, # Optional. The end offset of the video.
            &quot;fps&quot;: 3.14, # 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].
            &quot;startOffset&quot;: &quot;A String&quot;, # Optional. The start offset of the video.
          },
        },
      ],
      &quot;role&quot;: &quot;A String&quot;, # Optional. The producer of the content. Must be either &#x27;user&#x27; or &#x27;model&#x27;. Useful to set for multi-turn conversations, otherwise can be left blank or unset.
    },
  ],
  &quot;generationConfig&quot;: { # Generation config. # Optional. Generation config.
    &quot;audioTimestamp&quot;: True or False, # Optional. If enabled, audio timestamp will be included in the request to the model.
    &quot;candidateCount&quot;: 42, # Optional. Number of candidates to generate.
    &quot;enableAffectiveDialog&quot;: True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly.
    &quot;frequencyPenalty&quot;: 3.14, # Optional. Frequency penalties.
    &quot;logprobs&quot;: 42, # Optional. Logit probabilities.
    &quot;maxOutputTokens&quot;: 42, # Optional. The maximum number of output tokens to generate per message.
    &quot;mediaResolution&quot;: &quot;A String&quot;, # Optional. If specified, the media resolution specified will be used.
    &quot;presencePenalty&quot;: 3.14, # Optional. Positive penalties.
    &quot;responseJsonSchema&quot;: &quot;&quot;, # Optional. Output schema of the generated response. This is an alternative to `response_schema` that accepts [JSON Schema](https://json-schema.org/). 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.
    &quot;responseLogprobs&quot;: True or False, # Optional. If true, export the logprobs results in response.
    &quot;responseMimeType&quot;: &quot;A String&quot;, # Optional. Output response mimetype of the generated candidate text. Supported mimetype: - `text/plain`: (default) Text output. - `application/json`: JSON response in the candidates. The model needs to be prompted to output the appropriate response type, otherwise the behavior is undefined. This is a preview feature.
    &quot;responseModalities&quot;: [ # Optional. The modalities of the response.
      &quot;A String&quot;,
    ],
    &quot;responseSchema&quot;: { # Schema is used to define the format of input/output data. Represents a select subset of an [OpenAPI 3.0 schema object](https://spec.openapis.org/oas/v3.0.3#schema-object). More fields may be added in the future as needed. # Optional. 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](https://spec.openapis.org/oas/v3.0.3#schema). If set, a compatible response_mime_type must also be set. Compatible mimetypes: `application/json`: Schema for JSON response.
      &quot;additionalProperties&quot;: &quot;&quot;, # Optional. Can either be a boolean or an object; controls the presence of additional properties.
      &quot;anyOf&quot;: [ # Optional. The value should be validated against any (one or more) of the subschemas in the list.
        # Object with schema name: GoogleCloudAiplatformV1Schema
      ],
      &quot;default&quot;: &quot;&quot;, # Optional. Default value of the data.
      &quot;defs&quot;: { # Optional. A map of definitions for use by `ref` Only allowed at the root of the schema.
        &quot;a_key&quot;: # Object with schema name: GoogleCloudAiplatformV1Schema
      },
      &quot;description&quot;: &quot;A String&quot;, # Optional. The description of the data.
      &quot;enum&quot;: [ # Optional. Possible values of the element of primitive type with enum format. Examples: 1. We can define direction as : {type:STRING, format:enum, enum:[&quot;EAST&quot;, NORTH&quot;, &quot;SOUTH&quot;, &quot;WEST&quot;]} 2. We can define apartment number as : {type:INTEGER, format:enum, enum:[&quot;101&quot;, &quot;201&quot;, &quot;301&quot;]}
        &quot;A String&quot;,
      ],
      &quot;example&quot;: &quot;&quot;, # Optional. Example of the object. Will only populated when the object is the root.
      &quot;format&quot;: &quot;A String&quot;, # Optional. The format of the data. Supported formats: for NUMBER type: &quot;float&quot;, &quot;double&quot; for INTEGER type: &quot;int32&quot;, &quot;int64&quot; for STRING type: &quot;email&quot;, &quot;byte&quot;, etc
      &quot;items&quot;: # Object with schema name: GoogleCloudAiplatformV1Schema # Optional. SCHEMA FIELDS FOR TYPE ARRAY Schema of the elements of Type.ARRAY.
      &quot;maxItems&quot;: &quot;A String&quot;, # Optional. Maximum number of the elements for Type.ARRAY.
      &quot;maxLength&quot;: &quot;A String&quot;, # Optional. Maximum length of the Type.STRING
      &quot;maxProperties&quot;: &quot;A String&quot;, # Optional. Maximum number of the properties for Type.OBJECT.
      &quot;maximum&quot;: 3.14, # Optional. Maximum value of the Type.INTEGER and Type.NUMBER
      &quot;minItems&quot;: &quot;A String&quot;, # Optional. Minimum number of the elements for Type.ARRAY.
      &quot;minLength&quot;: &quot;A String&quot;, # Optional. SCHEMA FIELDS FOR TYPE STRING Minimum length of the Type.STRING
      &quot;minProperties&quot;: &quot;A String&quot;, # Optional. Minimum number of the properties for Type.OBJECT.
      &quot;minimum&quot;: 3.14, # Optional. SCHEMA FIELDS FOR TYPE INTEGER and NUMBER Minimum value of the Type.INTEGER and Type.NUMBER
      &quot;nullable&quot;: True or False, # Optional. Indicates if the value may be null.
      &quot;pattern&quot;: &quot;A String&quot;, # Optional. Pattern of the Type.STRING to restrict a string to a regular expression.
      &quot;properties&quot;: { # Optional. SCHEMA FIELDS FOR TYPE OBJECT Properties of Type.OBJECT.
        &quot;a_key&quot;: # Object with schema name: GoogleCloudAiplatformV1Schema
      },
      &quot;propertyOrdering&quot;: [ # Optional. The order of the properties. Not a standard field in open api spec. Only used to support the order of the properties.
        &quot;A String&quot;,
      ],
      &quot;ref&quot;: &quot;A String&quot;, # Optional. Allows indirect references between schema nodes. The value should be a valid reference to a child of the root `defs`. For example, the following schema defines a reference to a schema node named &quot;Pet&quot;: type: object properties: pet: ref: #/defs/Pet defs: Pet: type: object properties: name: type: string The value of the &quot;pet&quot; property is a reference to the schema node named &quot;Pet&quot;. See details in https://json-schema.org/understanding-json-schema/structuring
      &quot;required&quot;: [ # Optional. Required properties of Type.OBJECT.
        &quot;A String&quot;,
      ],
      &quot;title&quot;: &quot;A String&quot;, # Optional. The title of the Schema.
      &quot;type&quot;: &quot;A String&quot;, # Optional. The type of the data.
    },
    &quot;routingConfig&quot;: { # The configuration for routing the request to a specific model. # Optional. Routing configuration.
      &quot;autoMode&quot;: { # When automated routing is specified, the routing will be determined by the pretrained routing model and customer provided model routing preference. # Automated routing.
        &quot;modelRoutingPreference&quot;: &quot;A String&quot;, # The model routing preference.
      },
      &quot;manualMode&quot;: { # When manual routing is set, the specified model will be used directly. # Manual routing.
        &quot;modelName&quot;: &quot;A String&quot;, # The model name to use. Only the public LLM models are accepted. See [Supported models](https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/inference#supported-models).
      },
    },
    &quot;seed&quot;: 42, # Optional. Seed.
    &quot;speechConfig&quot;: { # The speech generation config. # Optional. The speech generation config.
      &quot;languageCode&quot;: &quot;A String&quot;, # Optional. Language code (ISO 639. e.g. en-US) for the speech synthesization.
      &quot;voiceConfig&quot;: { # The configuration for the voice to use. # The configuration for the speaker to use.
        &quot;prebuiltVoiceConfig&quot;: { # The configuration for the prebuilt speaker to use. # The configuration for the prebuilt voice to use.
          &quot;voiceName&quot;: &quot;A String&quot;, # The name of the preset voice to use.
        },
      },
    },
    &quot;stopSequences&quot;: [ # Optional. Stop sequences.
      &quot;A String&quot;,
    ],
    &quot;temperature&quot;: 3.14, # Optional. Controls the randomness of predictions.
    &quot;thinkingConfig&quot;: { # Config for thinking features. # Optional. Config for thinking features. An error will be returned if this field is set for models that don&#x27;t support thinking.
      &quot;includeThoughts&quot;: True or False, # Optional. Indicates whether to include thoughts in the response. If true, thoughts are returned only when available.
      &quot;thinkingBudget&quot;: 42, # Optional. Indicates the thinking budget in tokens.
    },
    &quot;topK&quot;: 3.14, # Optional. If specified, top-k sampling will be used.
    &quot;topP&quot;: 3.14, # Optional. If specified, nucleus sampling will be used.
  },
  &quot;labels&quot;: { # Optional. The labels with user-defined metadata for the request. It is used for billing and reporting only. Label keys and values can be no longer than 63 characters (Unicode codepoints) and can only contain lowercase letters, numeric characters, underscores, and dashes. International characters are allowed. Label values are optional. Label keys must start with a letter.
    &quot;a_key&quot;: &quot;A String&quot;,
  },
  &quot;modelArmorConfig&quot;: { # Configuration for Model Armor integrations of prompt and responses. # Optional. Settings for prompt and response sanitization using the Model Armor service. If supplied, safety_settings must not be supplied.
    &quot;promptTemplateName&quot;: &quot;A String&quot;, # Optional. The name of the Model Armor template to use for prompt sanitization.
    &quot;responseTemplateName&quot;: &quot;A String&quot;, # Optional. The name of the Model Armor template to use for response sanitization.
  },
  &quot;safetySettings&quot;: [ # Optional. Per request settings for blocking unsafe content. Enforced on GenerateContentResponse.candidates.
    { # Safety settings.
      &quot;category&quot;: &quot;A String&quot;, # Required. Harm category.
      &quot;method&quot;: &quot;A String&quot;, # Optional. Specify if the threshold is used for probability or severity score. If not specified, the threshold is used for probability score.
      &quot;threshold&quot;: &quot;A String&quot;, # Required. The harm block threshold.
    },
  ],
  &quot;systemInstruction&quot;: { # 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. # 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.
    &quot;parts&quot;: [ # Required. Ordered `Parts` that constitute a single message. Parts may have different IANA MIME types.
      { # 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 `inline_data` or `file_data` field is filled with raw bytes.
        &quot;codeExecutionResult&quot;: { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. Result of executing the [ExecutableCode].
          &quot;outcome&quot;: &quot;A String&quot;, # Required. Outcome of the code execution.
          &quot;output&quot;: &quot;A String&quot;, # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
        },
        &quot;executableCode&quot;: { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is meant to be executed.
          &quot;code&quot;: &quot;A String&quot;, # Required. The code to be executed.
          &quot;language&quot;: &quot;A String&quot;, # Required. Programming language of the `code`.
        },
        &quot;fileData&quot;: { # URI based data. # Optional. URI based data.
          &quot;displayName&quot;: &quot;A String&quot;, # Optional. Display name of the file data. Used to provide a label or filename to distinguish file datas. This field is only returned in PromptMessage for prompt management. It is currently used in the Gemini GenerateContent calls only when server side tools (code_execution, google_search, and url_context) are enabled.
          &quot;fileUri&quot;: &quot;A String&quot;, # Required. URI.
          &quot;mimeType&quot;: &quot;A String&quot;, # Required. The IANA standard MIME type of the source data.
        },
        &quot;functionCall&quot;: { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] with the parameters and their values.
          &quot;args&quot;: { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details.
            &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
          },
          &quot;name&quot;: &quot;A String&quot;, # Required. The name of the function to call. Matches [FunctionDeclaration.name].
        },
        &quot;functionResponse&quot;: { # 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 a [FunctionCall] made based on model prediction. # Optional. 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 call. It is used as context to the model.
          &quot;name&quot;: &quot;A String&quot;, # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name].
          &quot;response&quot;: { # Required. The function response in JSON object format. Use &quot;output&quot; key to specify function output and &quot;error&quot; key to specify error details (if any). If &quot;output&quot; and &quot;error&quot; keys are not specified, then whole &quot;response&quot; is treated as function output.
            &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
          },
        },
        &quot;inlineData&quot;: { # Content blob. # Optional. Inlined bytes data.
          &quot;data&quot;: &quot;A String&quot;, # Required. Raw bytes.
          &quot;displayName&quot;: &quot;A String&quot;, # Optional. Display name of the blob. Used to provide a label or filename to distinguish blobs. This field is only returned in PromptMessage for prompt management. It is currently used in the Gemini GenerateContent calls only when server side tools (code_execution, google_search, and url_context) are enabled.
          &quot;mimeType&quot;: &quot;A String&quot;, # Required. The IANA standard MIME type of the source data.
        },
        &quot;text&quot;: &quot;A String&quot;, # Optional. Text part (can be code).
        &quot;thought&quot;: True or False, # Optional. Indicates if the part is thought from the model.
        &quot;thoughtSignature&quot;: &quot;A String&quot;, # Optional. An opaque signature for the thought so it can be reused in subsequent requests.
        &quot;videoMetadata&quot;: { # Metadata describes the input video content. # Optional. Video metadata. The metadata should only be specified while the video data is presented in inline_data or file_data.
          &quot;endOffset&quot;: &quot;A String&quot;, # Optional. The end offset of the video.
          &quot;fps&quot;: 3.14, # 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].
          &quot;startOffset&quot;: &quot;A String&quot;, # Optional. The start offset of the video.
        },
      },
    ],
    &quot;role&quot;: &quot;A String&quot;, # Optional. The producer of the content. Must be either &#x27;user&#x27; or &#x27;model&#x27;. Useful to set for multi-turn conversations, otherwise can be left blank or unset.
  },
  &quot;toolConfig&quot;: { # Tool config. This config is shared for all tools provided in the request. # Optional. Tool config. This config is shared for all tools provided in the request.
    &quot;functionCallingConfig&quot;: { # Function calling config. # Optional. Function calling config.
      &quot;allowedFunctionNames&quot;: [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match [FunctionDeclaration.name]. With mode set to ANY, model will predict a function call from the set of function names provided.
        &quot;A String&quot;,
      ],
      &quot;mode&quot;: &quot;A String&quot;, # Optional. Function calling mode.
    },
    &quot;retrievalConfig&quot;: { # Retrieval config. # Optional. Retrieval config.
      &quot;languageCode&quot;: &quot;A String&quot;, # The language code of the user.
      &quot;latLng&quot;: { # An object that represents a latitude/longitude pair. This is expressed as a pair of doubles to represent degrees latitude and degrees longitude. Unless specified otherwise, this object must conform to the WGS84 standard. Values must be within normalized ranges. # The location of the user.
        &quot;latitude&quot;: 3.14, # The latitude in degrees. It must be in the range [-90.0, +90.0].
        &quot;longitude&quot;: 3.14, # The longitude in degrees. It must be in the range [-180.0, +180.0].
      },
    },
  },
  &quot;tools&quot;: [ # 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.
    { # 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. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval).
      &quot;codeExecution&quot;: { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation.
      },
      &quot;enterpriseWebSearch&quot;: { # Tool to search public web data, powered by Vertex AI Search and Sec4 compliance. # Optional. Tool to support searching public web data, powered by Vertex AI Search and Sec4 compliance.
        &quot;excludeDomains&quot;: [ # Optional. List of domains to be excluded from the search results. The default limit is 2000 domains.
          &quot;A String&quot;,
        ],
      },
      &quot;functionDeclarations&quot;: [ # Optional. Function tool type. One or more function declarations to be passed to the model along with the current user query. Model may decide to call a subset of these functions by populating FunctionCall in the response. User should provide a FunctionResponse for each function call in the next turn. Based on the function responses, Model will generate the final response back to the user. Maximum 512 function declarations can be provided.
        { # Structured representation of a function declaration as defined by the [OpenAPI 3.0 specification](https://spec.openapis.org/oas/v3.0.3). Included in this declaration are the function name, description, parameters and response type. 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.
          &quot;description&quot;: &quot;A String&quot;, # Optional. Description and purpose of the function. Model uses it to decide how and whether to call the function.
          &quot;name&quot;: &quot;A String&quot;, # Required. The name of the function to call. Must start with a letter or an underscore. Must be a-z, A-Z, 0-9, or contain underscores, dots and dashes, with a maximum length of 64.
          &quot;parameters&quot;: { # Schema is used to define the format of input/output data. Represents a select subset of an [OpenAPI 3.0 schema object](https://spec.openapis.org/oas/v3.0.3#schema-object). More fields may be added in the future as needed. # Optional. Describes the parameters to this function in JSON Schema Object format. 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. For function with no parameters, this can be left unset. Parameter names must start with a letter or an underscore and must only contain chars a-z, A-Z, 0-9, or underscores with a maximum length of 64. Example with 1 required and 1 optional parameter: type: OBJECT properties: param1: type: STRING param2: type: INTEGER required: - param1
            &quot;additionalProperties&quot;: &quot;&quot;, # Optional. Can either be a boolean or an object; controls the presence of additional properties.
            &quot;anyOf&quot;: [ # Optional. The value should be validated against any (one or more) of the subschemas in the list.
              # Object with schema name: GoogleCloudAiplatformV1Schema
            ],
            &quot;default&quot;: &quot;&quot;, # Optional. Default value of the data.
            &quot;defs&quot;: { # Optional. A map of definitions for use by `ref` Only allowed at the root of the schema.
              &quot;a_key&quot;: # Object with schema name: GoogleCloudAiplatformV1Schema
            },
            &quot;description&quot;: &quot;A String&quot;, # Optional. The description of the data.
            &quot;enum&quot;: [ # Optional. Possible values of the element of primitive type with enum format. Examples: 1. We can define direction as : {type:STRING, format:enum, enum:[&quot;EAST&quot;, NORTH&quot;, &quot;SOUTH&quot;, &quot;WEST&quot;]} 2. We can define apartment number as : {type:INTEGER, format:enum, enum:[&quot;101&quot;, &quot;201&quot;, &quot;301&quot;]}
              &quot;A String&quot;,
            ],
            &quot;example&quot;: &quot;&quot;, # Optional. Example of the object. Will only populated when the object is the root.
            &quot;format&quot;: &quot;A String&quot;, # Optional. The format of the data. Supported formats: for NUMBER type: &quot;float&quot;, &quot;double&quot; for INTEGER type: &quot;int32&quot;, &quot;int64&quot; for STRING type: &quot;email&quot;, &quot;byte&quot;, etc
            &quot;items&quot;: # Object with schema name: GoogleCloudAiplatformV1Schema # Optional. SCHEMA FIELDS FOR TYPE ARRAY Schema of the elements of Type.ARRAY.
            &quot;maxItems&quot;: &quot;A String&quot;, # Optional. Maximum number of the elements for Type.ARRAY.
            &quot;maxLength&quot;: &quot;A String&quot;, # Optional. Maximum length of the Type.STRING
            &quot;maxProperties&quot;: &quot;A String&quot;, # Optional. Maximum number of the properties for Type.OBJECT.
            &quot;maximum&quot;: 3.14, # Optional. Maximum value of the Type.INTEGER and Type.NUMBER
            &quot;minItems&quot;: &quot;A String&quot;, # Optional. Minimum number of the elements for Type.ARRAY.
            &quot;minLength&quot;: &quot;A String&quot;, # Optional. SCHEMA FIELDS FOR TYPE STRING Minimum length of the Type.STRING
            &quot;minProperties&quot;: &quot;A String&quot;, # Optional. Minimum number of the properties for Type.OBJECT.
            &quot;minimum&quot;: 3.14, # Optional. SCHEMA FIELDS FOR TYPE INTEGER and NUMBER Minimum value of the Type.INTEGER and Type.NUMBER
            &quot;nullable&quot;: True or False, # Optional. Indicates if the value may be null.
            &quot;pattern&quot;: &quot;A String&quot;, # Optional. Pattern of the Type.STRING to restrict a string to a regular expression.
            &quot;properties&quot;: { # Optional. SCHEMA FIELDS FOR TYPE OBJECT Properties of Type.OBJECT.
              &quot;a_key&quot;: # Object with schema name: GoogleCloudAiplatformV1Schema
            },
            &quot;propertyOrdering&quot;: [ # Optional. The order of the properties. Not a standard field in open api spec. Only used to support the order of the properties.
              &quot;A String&quot;,
            ],
            &quot;ref&quot;: &quot;A String&quot;, # Optional. Allows indirect references between schema nodes. The value should be a valid reference to a child of the root `defs`. For example, the following schema defines a reference to a schema node named &quot;Pet&quot;: type: object properties: pet: ref: #/defs/Pet defs: Pet: type: object properties: name: type: string The value of the &quot;pet&quot; property is a reference to the schema node named &quot;Pet&quot;. See details in https://json-schema.org/understanding-json-schema/structuring
            &quot;required&quot;: [ # Optional. Required properties of Type.OBJECT.
              &quot;A String&quot;,
            ],
            &quot;title&quot;: &quot;A String&quot;, # Optional. The title of the Schema.
            &quot;type&quot;: &quot;A String&quot;, # Optional. The type of the data.
          },
          &quot;parametersJsonSchema&quot;: &quot;&quot;, # 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: ``` { &quot;type&quot;: &quot;object&quot;, &quot;properties&quot;: { &quot;name&quot;: { &quot;type&quot;: &quot;string&quot; }, &quot;age&quot;: { &quot;type&quot;: &quot;integer&quot; } }, &quot;additionalProperties&quot;: false, &quot;required&quot;: [&quot;name&quot;, &quot;age&quot;], &quot;propertyOrdering&quot;: [&quot;name&quot;, &quot;age&quot;] } ``` This field is mutually exclusive with `parameters`.
          &quot;response&quot;: { # Schema is used to define the format of input/output data. Represents a select subset of an [OpenAPI 3.0 schema object](https://spec.openapis.org/oas/v3.0.3#schema-object). More fields may be added in the future as needed. # 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.
            &quot;additionalProperties&quot;: &quot;&quot;, # Optional. Can either be a boolean or an object; controls the presence of additional properties.
            &quot;anyOf&quot;: [ # Optional. The value should be validated against any (one or more) of the subschemas in the list.
              # Object with schema name: GoogleCloudAiplatformV1Schema
            ],
            &quot;default&quot;: &quot;&quot;, # Optional. Default value of the data.
            &quot;defs&quot;: { # Optional. A map of definitions for use by `ref` Only allowed at the root of the schema.
              &quot;a_key&quot;: # Object with schema name: GoogleCloudAiplatformV1Schema
            },
            &quot;description&quot;: &quot;A String&quot;, # Optional. The description of the data.
            &quot;enum&quot;: [ # Optional. Possible values of the element of primitive type with enum format. Examples: 1. We can define direction as : {type:STRING, format:enum, enum:[&quot;EAST&quot;, NORTH&quot;, &quot;SOUTH&quot;, &quot;WEST&quot;]} 2. We can define apartment number as : {type:INTEGER, format:enum, enum:[&quot;101&quot;, &quot;201&quot;, &quot;301&quot;]}
              &quot;A String&quot;,
            ],
            &quot;example&quot;: &quot;&quot;, # Optional. Example of the object. Will only populated when the object is the root.
            &quot;format&quot;: &quot;A String&quot;, # Optional. The format of the data. Supported formats: for NUMBER type: &quot;float&quot;, &quot;double&quot; for INTEGER type: &quot;int32&quot;, &quot;int64&quot; for STRING type: &quot;email&quot;, &quot;byte&quot;, etc
            &quot;items&quot;: # Object with schema name: GoogleCloudAiplatformV1Schema # Optional. SCHEMA FIELDS FOR TYPE ARRAY Schema of the elements of Type.ARRAY.
            &quot;maxItems&quot;: &quot;A String&quot;, # Optional. Maximum number of the elements for Type.ARRAY.
            &quot;maxLength&quot;: &quot;A String&quot;, # Optional. Maximum length of the Type.STRING
            &quot;maxProperties&quot;: &quot;A String&quot;, # Optional. Maximum number of the properties for Type.OBJECT.
            &quot;maximum&quot;: 3.14, # Optional. Maximum value of the Type.INTEGER and Type.NUMBER
            &quot;minItems&quot;: &quot;A String&quot;, # Optional. Minimum number of the elements for Type.ARRAY.
            &quot;minLength&quot;: &quot;A String&quot;, # Optional. SCHEMA FIELDS FOR TYPE STRING Minimum length of the Type.STRING
            &quot;minProperties&quot;: &quot;A String&quot;, # Optional. Minimum number of the properties for Type.OBJECT.
            &quot;minimum&quot;: 3.14, # Optional. SCHEMA FIELDS FOR TYPE INTEGER and NUMBER Minimum value of the Type.INTEGER and Type.NUMBER
            &quot;nullable&quot;: True or False, # Optional. Indicates if the value may be null.
            &quot;pattern&quot;: &quot;A String&quot;, # Optional. Pattern of the Type.STRING to restrict a string to a regular expression.
            &quot;properties&quot;: { # Optional. SCHEMA FIELDS FOR TYPE OBJECT Properties of Type.OBJECT.
              &quot;a_key&quot;: # Object with schema name: GoogleCloudAiplatformV1Schema
            },
            &quot;propertyOrdering&quot;: [ # Optional. The order of the properties. Not a standard field in open api spec. Only used to support the order of the properties.
              &quot;A String&quot;,
            ],
            &quot;ref&quot;: &quot;A String&quot;, # Optional. Allows indirect references between schema nodes. The value should be a valid reference to a child of the root `defs`. For example, the following schema defines a reference to a schema node named &quot;Pet&quot;: type: object properties: pet: ref: #/defs/Pet defs: Pet: type: object properties: name: type: string The value of the &quot;pet&quot; property is a reference to the schema node named &quot;Pet&quot;. See details in https://json-schema.org/understanding-json-schema/structuring
            &quot;required&quot;: [ # Optional. Required properties of Type.OBJECT.
              &quot;A String&quot;,
            ],
            &quot;title&quot;: &quot;A String&quot;, # Optional. The title of the Schema.
            &quot;type&quot;: &quot;A String&quot;, # Optional. The type of the data.
          },
          &quot;responseJsonSchema&quot;: &quot;&quot;, # 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`.
        },
      ],
      &quot;googleMaps&quot;: { # Tool to retrieve public maps data for grounding, powered by Google. # Optional. GoogleMaps tool type. Tool to support Google Maps in Model.
      },
      &quot;googleSearch&quot;: { # GoogleSearch tool type. Tool to support Google Search in Model. Powered by Google. # Optional. GoogleSearch tool type. Tool to support Google Search in Model. Powered by Google.
        &quot;excludeDomains&quot;: [ # Optional. List of domains to be excluded from the search results. The default limit is 2000 domains. Example: [&quot;amazon.com&quot;, &quot;facebook.com&quot;].
          &quot;A String&quot;,
        ],
      },
      &quot;googleSearchRetrieval&quot;: { # Tool to retrieve public web data for grounding, powered by Google. # Optional. GoogleSearchRetrieval tool type. Specialized retrieval tool that is powered by Google search.
        &quot;dynamicRetrievalConfig&quot;: { # Describes the options to customize dynamic retrieval. # Specifies the dynamic retrieval configuration for the given source.
          &quot;dynamicThreshold&quot;: 3.14, # Optional. The threshold to be used in dynamic retrieval. If not set, a system default value is used.
          &quot;mode&quot;: &quot;A String&quot;, # The mode of the predictor to be used in dynamic retrieval.
        },
      },
      &quot;retrieval&quot;: { # Defines a retrieval tool that model can call to access external knowledge. # Optional. Retrieval tool type. System will always execute the provided retrieval tool(s) to get external knowledge to answer the prompt. Retrieval results are presented to the model for generation.
        &quot;disableAttribution&quot;: True or False, # Optional. Deprecated. This option is no longer supported.
        &quot;externalApi&quot;: { # Retrieve from data source powered by external API for grounding. The external API is not owned by Google, but need to follow the pre-defined API spec. # Use data source powered by external API for grounding.
          &quot;apiAuth&quot;: { # The generic reusable api auth config. Deprecated. Please use AuthConfig (google/cloud/aiplatform/master/auth.proto) instead. # The authentication config to access the API. Deprecated. Please use auth_config instead.
            &quot;apiKeyConfig&quot;: { # The API secret. # The API secret.
              &quot;apiKeySecretVersion&quot;: &quot;A String&quot;, # Required. The SecretManager secret version resource name storing API key. e.g. projects/{project}/secrets/{secret}/versions/{version}
              &quot;apiKeyString&quot;: &quot;A String&quot;, # The API key string. Either this or `api_key_secret_version` must be set.
            },
          },
          &quot;apiSpec&quot;: &quot;A String&quot;, # The API spec that the external API implements.
          &quot;authConfig&quot;: { # Auth configuration to run the extension. # The authentication config to access the API.
            &quot;apiKeyConfig&quot;: { # Config for authentication with API key. # Config for API key auth.
              &quot;apiKeySecret&quot;: &quot;A String&quot;, # Optional. The name of the SecretManager secret version resource storing the API key. Format: `projects/{project}/secrets/{secrete}/versions/{version}` - If both `api_key_secret` and `api_key_string` are specified, this field takes precedence over `api_key_string`. - If specified, the `secretmanager.versions.access` permission should be granted to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) on the specified resource.
              &quot;apiKeyString&quot;: &quot;A String&quot;, # Optional. The API key to be used in the request directly.
              &quot;httpElementLocation&quot;: &quot;A String&quot;, # Optional. The location of the API key.
              &quot;name&quot;: &quot;A String&quot;, # Optional. The parameter name of the API key. E.g. If the API request is &quot;https://example.com/act?api_key=&quot;, &quot;api_key&quot; would be the parameter name.
            },
            &quot;authType&quot;: &quot;A String&quot;, # Type of auth scheme.
            &quot;googleServiceAccountConfig&quot;: { # Config for Google Service Account Authentication. # Config for Google Service Account auth.
              &quot;serviceAccount&quot;: &quot;A String&quot;, # Optional. The service account that the extension execution service runs as. - If the service account is specified, the `iam.serviceAccounts.getAccessToken` permission should be granted to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) on the specified service account. - If not specified, the Vertex AI Extension Service Agent will be used to execute the Extension.
            },
            &quot;httpBasicAuthConfig&quot;: { # Config for HTTP Basic Authentication. # Config for HTTP Basic auth.
              &quot;credentialSecret&quot;: &quot;A String&quot;, # Required. The name of the SecretManager secret version resource storing the base64 encoded credentials. Format: `projects/{project}/secrets/{secrete}/versions/{version}` - If specified, the `secretmanager.versions.access` permission should be granted to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) on the specified resource.
            },
            &quot;oauthConfig&quot;: { # Config for user oauth. # Config for user oauth.
              &quot;accessToken&quot;: &quot;A String&quot;, # Access token for extension endpoint. Only used to propagate token from [[ExecuteExtensionRequest.runtime_auth_config]] at request time.
              &quot;serviceAccount&quot;: &quot;A String&quot;, # The service account used to generate access tokens for executing the Extension. - If the service account is specified, the `iam.serviceAccounts.getAccessToken` permission should be granted to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) on the provided service account.
            },
            &quot;oidcConfig&quot;: { # Config for user OIDC auth. # Config for user OIDC auth.
              &quot;idToken&quot;: &quot;A String&quot;, # OpenID Connect formatted ID token for extension endpoint. Only used to propagate token from [[ExecuteExtensionRequest.runtime_auth_config]] at request time.
              &quot;serviceAccount&quot;: &quot;A String&quot;, # The service account used to generate an OpenID Connect (OIDC)-compatible JWT token signed by the Google OIDC Provider (accounts.google.com) for extension endpoint (https://cloud.google.com/iam/docs/create-short-lived-credentials-direct#sa-credentials-oidc). - The audience for the token will be set to the URL in the server url defined in the OpenApi spec. - If the service account is provided, the service account should grant `iam.serviceAccounts.getOpenIdToken` permission to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents).
            },
          },
          &quot;elasticSearchParams&quot;: { # The search parameters to use for the ELASTIC_SEARCH spec. # Parameters for the elastic search API.
            &quot;index&quot;: &quot;A String&quot;, # The ElasticSearch index to use.
            &quot;numHits&quot;: 42, # Optional. Number of hits (chunks) to request. When specified, it is passed to Elasticsearch as the `num_hits` param.
            &quot;searchTemplate&quot;: &quot;A String&quot;, # The ElasticSearch search template to use.
          },
          &quot;endpoint&quot;: &quot;A String&quot;, # The endpoint of the external API. The system will call the API at this endpoint to retrieve the data for grounding. Example: https://acme.com:443/search
          &quot;simpleSearchParams&quot;: { # The search parameters to use for SIMPLE_SEARCH spec. # Parameters for the simple search API.
          },
        },
        &quot;vertexAiSearch&quot;: { # Retrieve from Vertex AI Search datastore or engine for grounding. datastore and engine are mutually exclusive. See https://cloud.google.com/products/agent-builder # Set to use data source powered by Vertex AI Search.
          &quot;dataStoreSpecs&quot;: [ # Specifications that define the specific DataStores to be searched, along with configurations for those data stores. This is only considered for Engines with multiple data stores. It should only be set if engine is used.
            { # Define data stores within engine to filter on in a search call and configurations for those data stores. For more information, see https://cloud.google.com/generative-ai-app-builder/docs/reference/rpc/google.cloud.discoveryengine.v1#datastorespec
              &quot;dataStore&quot;: &quot;A String&quot;, # Full resource name of DataStore, such as Format: `projects/{project}/locations/{location}/collections/{collection}/dataStores/{dataStore}`
              &quot;filter&quot;: &quot;A String&quot;, # Optional. Filter specification to filter documents in the data store specified by data_store field. For more information on filtering, see [Filtering](https://cloud.google.com/generative-ai-app-builder/docs/filter-search-metadata)
            },
          ],
          &quot;datastore&quot;: &quot;A String&quot;, # Optional. Fully-qualified Vertex AI Search data store resource ID. Format: `projects/{project}/locations/{location}/collections/{collection}/dataStores/{dataStore}`
          &quot;engine&quot;: &quot;A String&quot;, # Optional. Fully-qualified Vertex AI Search engine resource ID. Format: `projects/{project}/locations/{location}/collections/{collection}/engines/{engine}`
          &quot;filter&quot;: &quot;A String&quot;, # Optional. Filter strings to be passed to the search API.
          &quot;maxResults&quot;: 42, # Optional. Number of search results to return per query. The default value is 10. The maximumm allowed value is 10.
        },
        &quot;vertexRagStore&quot;: { # Retrieve from Vertex RAG Store for grounding. # Set to use data source powered by Vertex RAG store. User data is uploaded via the VertexRagDataService.
          &quot;ragResources&quot;: [ # Optional. The representation of the rag source. It can be used to specify corpus only or ragfiles. Currently only support one corpus or multiple files from one corpus. In the future we may open up multiple corpora support.
            { # The definition of the Rag resource.
              &quot;ragCorpus&quot;: &quot;A String&quot;, # Optional. RagCorpora resource name. Format: `projects/{project}/locations/{location}/ragCorpora/{rag_corpus}`
              &quot;ragFileIds&quot;: [ # Optional. rag_file_id. The files should be in the same rag_corpus set in rag_corpus field.
                &quot;A String&quot;,
              ],
            },
          ],
          &quot;ragRetrievalConfig&quot;: { # Specifies the context retrieval config. # Optional. The retrieval config for the Rag query.
            &quot;filter&quot;: { # Config for filters. # Optional. Config for filters.
              &quot;metadataFilter&quot;: &quot;A String&quot;, # Optional. String for metadata filtering.
              &quot;vectorDistanceThreshold&quot;: 3.14, # Optional. Only returns contexts with vector distance smaller than the threshold.
              &quot;vectorSimilarityThreshold&quot;: 3.14, # Optional. Only returns contexts with vector similarity larger than the threshold.
            },
            &quot;ranking&quot;: { # Config for ranking and reranking. # Optional. Config for ranking and reranking.
              &quot;llmRanker&quot;: { # Config for LlmRanker. # Optional. Config for LlmRanker.
                &quot;modelName&quot;: &quot;A String&quot;, # Optional. The model name used for ranking. See [Supported models](https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/inference#supported-models).
              },
              &quot;rankService&quot;: { # Config for Rank Service. # Optional. Config for Rank Service.
                &quot;modelName&quot;: &quot;A String&quot;, # Optional. The model name of the rank service. Format: `semantic-ranker-512@latest`
              },
            },
            &quot;topK&quot;: 42, # Optional. The number of contexts to retrieve.
          },
          &quot;similarityTopK&quot;: 42, # Optional. Number of top k results to return from the selected corpora.
          &quot;vectorDistanceThreshold&quot;: 3.14, # Optional. Only return results with vector distance smaller than the threshold.
        },
      },
      &quot;urlContext&quot;: { # Tool to support URL context. # Optional. Tool to support URL context retrieval.
      },
    },
  ],
}

  x__xgafv: string, V1 error format.
    Allowed values
      1 - v1 error format
      2 - v2 error format

Returns:
  An object of the form:

    { # Response message for [PredictionService.GenerateContent].
  &quot;candidates&quot;: [ # Output only. Generated candidates.
    { # A response candidate generated from the model.
      &quot;avgLogprobs&quot;: 3.14, # Output only. Average log probability score of the candidate.
      &quot;citationMetadata&quot;: { # A collection of source attributions for a piece of content. # Output only. Source attribution of the generated content.
        &quot;citations&quot;: [ # Output only. List of citations.
          { # Source attributions for content.
            &quot;endIndex&quot;: 42, # Output only. End index into the content.
            &quot;license&quot;: &quot;A String&quot;, # Output only. License of the attribution.
            &quot;publicationDate&quot;: { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # Output only. Publication date of the attribution.
              &quot;day&quot;: 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn&#x27;t significant.
              &quot;month&quot;: 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
              &quot;year&quot;: 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
            },
            &quot;startIndex&quot;: 42, # Output only. Start index into the content.
            &quot;title&quot;: &quot;A String&quot;, # Output only. Title of the attribution.
            &quot;uri&quot;: &quot;A String&quot;, # Output only. Url reference of the attribution.
          },
        ],
      },
      &quot;content&quot;: { # 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. # Output only. Content parts of the candidate.
        &quot;parts&quot;: [ # Required. Ordered `Parts` that constitute a single message. Parts may have different IANA MIME types.
          { # 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 `inline_data` or `file_data` field is filled with raw bytes.
            &quot;codeExecutionResult&quot;: { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. Result of executing the [ExecutableCode].
              &quot;outcome&quot;: &quot;A String&quot;, # Required. Outcome of the code execution.
              &quot;output&quot;: &quot;A String&quot;, # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
            },
            &quot;executableCode&quot;: { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is meant to be executed.
              &quot;code&quot;: &quot;A String&quot;, # Required. The code to be executed.
              &quot;language&quot;: &quot;A String&quot;, # Required. Programming language of the `code`.
            },
            &quot;fileData&quot;: { # URI based data. # Optional. URI based data.
              &quot;displayName&quot;: &quot;A String&quot;, # Optional. Display name of the file data. Used to provide a label or filename to distinguish file datas. This field is only returned in PromptMessage for prompt management. It is currently used in the Gemini GenerateContent calls only when server side tools (code_execution, google_search, and url_context) are enabled.
              &quot;fileUri&quot;: &quot;A String&quot;, # Required. URI.
              &quot;mimeType&quot;: &quot;A String&quot;, # Required. The IANA standard MIME type of the source data.
            },
            &quot;functionCall&quot;: { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] with the parameters and their values.
              &quot;args&quot;: { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details.
                &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
              },
              &quot;name&quot;: &quot;A String&quot;, # Required. The name of the function to call. Matches [FunctionDeclaration.name].
            },
            &quot;functionResponse&quot;: { # 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 a [FunctionCall] made based on model prediction. # Optional. 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 call. It is used as context to the model.
              &quot;name&quot;: &quot;A String&quot;, # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name].
              &quot;response&quot;: { # Required. The function response in JSON object format. Use &quot;output&quot; key to specify function output and &quot;error&quot; key to specify error details (if any). If &quot;output&quot; and &quot;error&quot; keys are not specified, then whole &quot;response&quot; is treated as function output.
                &quot;a_key&quot;: &quot;&quot;, # Properties of the object.
              },
            },
            &quot;inlineData&quot;: { # Content blob. # Optional. Inlined bytes data.
              &quot;data&quot;: &quot;A String&quot;, # Required. Raw bytes.
              &quot;displayName&quot;: &quot;A String&quot;, # Optional. Display name of the blob. Used to provide a label or filename to distinguish blobs. This field is only returned in PromptMessage for prompt management. It is currently used in the Gemini GenerateContent calls only when server side tools (code_execution, google_search, and url_context) are enabled.
              &quot;mimeType&quot;: &quot;A String&quot;, # Required. The IANA standard MIME type of the source data.
            },
            &quot;text&quot;: &quot;A String&quot;, # Optional. Text part (can be code).
            &quot;thought&quot;: True or False, # Optional. Indicates if the part is thought from the model.
            &quot;thoughtSignature&quot;: &quot;A String&quot;, # Optional. An opaque signature for the thought so it can be reused in subsequent requests.
            &quot;videoMetadata&quot;: { # Metadata describes the input video content. # Optional. Video metadata. The metadata should only be specified while the video data is presented in inline_data or file_data.
              &quot;endOffset&quot;: &quot;A String&quot;, # Optional. The end offset of the video.
              &quot;fps&quot;: 3.14, # 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].
              &quot;startOffset&quot;: &quot;A String&quot;, # Optional. The start offset of the video.
            },
          },
        ],
        &quot;role&quot;: &quot;A String&quot;, # Optional. The producer of the content. Must be either &#x27;user&#x27; or &#x27;model&#x27;. Useful to set for multi-turn conversations, otherwise can be left blank or unset.
      },
      &quot;finishMessage&quot;: &quot;A String&quot;, # Output only. Describes the reason the mode stopped generating tokens in more detail. This is only filled when `finish_reason` is set.
      &quot;finishReason&quot;: &quot;A String&quot;, # Output only. The reason why the model stopped generating tokens. If empty, the model has not stopped generating the tokens.
      &quot;groundingMetadata&quot;: { # Metadata returned to client when grounding is enabled. # Output only. Metadata specifies sources used to ground generated content.
        &quot;googleMapsWidgetContextToken&quot;: &quot;A String&quot;, # Optional. Output only. Resource name of the Google Maps widget context token to be used with the PlacesContextElement widget to render contextual data. This is populated only for Google Maps grounding.
        &quot;groundingChunks&quot;: [ # List of supporting references retrieved from specified grounding source.
          { # Grounding chunk.
            &quot;maps&quot;: { # Chunk from Google Maps. # Grounding chunk from Google Maps.
              &quot;placeAnswerSources&quot;: { # Sources used to generate the place answer. # Sources used to generate the place answer. This includes review snippets and photos that were used to generate the answer, as well as uris to flag content.
                &quot;flagContentUri&quot;: &quot;A String&quot;, # A link where users can flag a problem with the generated answer.
                &quot;reviewSnippets&quot;: [ # Snippets of reviews that are used to generate the answer.
                  { # Encapsulates a review snippet.
                    &quot;authorAttribution&quot;: { # Author attribution for a photo or review. # This review&#x27;s author.
                      &quot;displayName&quot;: &quot;A String&quot;, # Name of the author of the Photo or Review.
                      &quot;photoUri&quot;: &quot;A String&quot;, # Profile photo URI of the author of the Photo or Review.
                      &quot;uri&quot;: &quot;A String&quot;, # URI of the author of the Photo or Review.
                    },
                    &quot;flagContentUri&quot;: &quot;A String&quot;, # A link where users can flag a problem with the review.
                    &quot;googleMapsUri&quot;: &quot;A String&quot;, # A link to show the review on Google Maps.
                    &quot;relativePublishTimeDescription&quot;: &quot;A String&quot;, # A string of formatted recent time, expressing the review time relative to the current time in a form appropriate for the language and country.
                    &quot;review&quot;: &quot;A String&quot;, # A reference representing this place review which may be used to look up this place review again.
                  },
                ],
              },
              &quot;placeId&quot;: &quot;A String&quot;, # This Place&#x27;s resource name, in `places/{place_id}` format. Can be used to look up the Place.
              &quot;text&quot;: &quot;A String&quot;, # Text of the chunk.
              &quot;title&quot;: &quot;A String&quot;, # Title of the chunk.
              &quot;uri&quot;: &quot;A String&quot;, # URI reference of the chunk.
            },
            &quot;retrievedContext&quot;: { # Chunk from context retrieved by the retrieval tools. # Grounding chunk from context retrieved by the retrieval tools.
              &quot;documentName&quot;: &quot;A String&quot;, # Output only. The full document name for the referenced Vertex AI Search document.
              &quot;ragChunk&quot;: { # A RagChunk includes the content of a chunk of a RagFile, and associated metadata. # Additional context for the RAG retrieval result. This is only populated when using the RAG retrieval tool.
                &quot;pageSpan&quot;: { # Represents where the chunk starts and ends in the document. # If populated, represents where the chunk starts and ends in the document.
                  &quot;firstPage&quot;: 42, # Page where chunk starts in the document. Inclusive. 1-indexed.
                  &quot;lastPage&quot;: 42, # Page where chunk ends in the document. Inclusive. 1-indexed.
                },
                &quot;text&quot;: &quot;A String&quot;, # The content of the chunk.
              },
              &quot;text&quot;: &quot;A String&quot;, # Text of the attribution.
              &quot;title&quot;: &quot;A String&quot;, # Title of the attribution.
              &quot;uri&quot;: &quot;A String&quot;, # URI reference of the attribution.
            },
            &quot;web&quot;: { # Chunk from the web. # Grounding chunk from the web.
              &quot;domain&quot;: &quot;A String&quot;, # Domain of the (original) URI.
              &quot;title&quot;: &quot;A String&quot;, # Title of the chunk.
              &quot;uri&quot;: &quot;A String&quot;, # URI reference of the chunk.
            },
          },
        ],
        &quot;groundingSupports&quot;: [ # Optional. List of grounding support.
          { # Grounding support.
            &quot;confidenceScores&quot;: [ # Confidence score of the support references. Ranges from 0 to 1. 1 is the most confident. For Gemini 2.0 and before, this list must have the same size as the grounding_chunk_indices. For Gemini 2.5 and after, this list will be empty and should be ignored.
              3.14,
            ],
            &quot;groundingChunkIndices&quot;: [ # A list of indices (into &#x27;grounding_chunk&#x27;) 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.
              42,
            ],
            &quot;segment&quot;: { # Segment of the content. # Segment of the content this support belongs to.
              &quot;endIndex&quot;: 42, # Output only. End index in the given Part, measured in bytes. Offset from the start of the Part, exclusive, starting at zero.
              &quot;partIndex&quot;: 42, # Output only. The index of a Part object within its parent Content object.
              &quot;startIndex&quot;: 42, # Output only. Start index in the given Part, measured in bytes. Offset from the start of the Part, inclusive, starting at zero.
              &quot;text&quot;: &quot;A String&quot;, # Output only. The text corresponding to the segment from the response.
            },
          },
        ],
        &quot;retrievalMetadata&quot;: { # Metadata related to retrieval in the grounding flow. # Optional. Output only. Retrieval metadata.
          &quot;googleSearchDynamicRetrievalScore&quot;: 3.14, # 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.
        },
        &quot;searchEntryPoint&quot;: { # Google search entry point. # Optional. Google search entry for the following-up web searches.
          &quot;renderedContent&quot;: &quot;A String&quot;, # Optional. Web content snippet that can be embedded in a web page or an app webview.
          &quot;sdkBlob&quot;: &quot;A String&quot;, # Optional. Base64 encoded JSON representing array of tuple.
        },
        &quot;webSearchQueries&quot;: [ # Optional. Web search queries for the following-up web search.
          &quot;A String&quot;,
        ],
      },
      &quot;index&quot;: 42, # Output only. Index of the candidate.
      &quot;logprobsResult&quot;: { # Logprobs Result # Output only. Log-likelihood scores for the response tokens and top tokens
        &quot;chosenCandidates&quot;: [ # Length = total number of decoding steps. The chosen candidates may or may not be in top_candidates.
          { # Candidate for the logprobs token and score.
            &quot;logProbability&quot;: 3.14, # The candidate&#x27;s log probability.
            &quot;token&quot;: &quot;A String&quot;, # The candidate&#x27;s token string value.
            &quot;tokenId&quot;: 42, # The candidate&#x27;s token id value.
          },
        ],
        &quot;topCandidates&quot;: [ # Length = total number of decoding steps.
          { # Candidates with top log probabilities at each decoding step.
            &quot;candidates&quot;: [ # Sorted by log probability in descending order.
              { # Candidate for the logprobs token and score.
                &quot;logProbability&quot;: 3.14, # The candidate&#x27;s log probability.
                &quot;token&quot;: &quot;A String&quot;, # The candidate&#x27;s token string value.
                &quot;tokenId&quot;: 42, # The candidate&#x27;s token id value.
              },
            ],
          },
        ],
      },
      &quot;safetyRatings&quot;: [ # Output only. List of ratings for the safety of a response candidate. There is at most one rating per category.
        { # Safety rating corresponding to the generated content.
          &quot;blocked&quot;: True or False, # Output only. Indicates whether the content was filtered out because of this rating.
          &quot;category&quot;: &quot;A String&quot;, # Output only. Harm category.
          &quot;overwrittenThreshold&quot;: &quot;A String&quot;, # Output only. The overwritten threshold for the safety category of Gemini 2.0 image out. If minors are detected in the output image, the threshold of each safety category will be overwritten if user sets a lower threshold.
          &quot;probability&quot;: &quot;A String&quot;, # Output only. Harm probability levels in the content.
          &quot;probabilityScore&quot;: 3.14, # Output only. Harm probability score.
          &quot;severity&quot;: &quot;A String&quot;, # Output only. Harm severity levels in the content.
          &quot;severityScore&quot;: 3.14, # Output only. Harm severity score.
        },
      ],
      &quot;urlContextMetadata&quot;: { # Metadata related to url context retrieval tool. # Output only. Metadata related to url context retrieval tool.
        &quot;urlMetadata&quot;: [ # Output only. List of url context.
          { # Context of the a single url retrieval.
            &quot;retrievedUrl&quot;: &quot;A String&quot;, # Retrieved url by the tool.
            &quot;urlRetrievalStatus&quot;: &quot;A String&quot;, # Status of the url retrieval.
          },
        ],
      },
    },
  ],
  &quot;createTime&quot;: &quot;A String&quot;, # Output only. Timestamp when the request is made to the server.
  &quot;modelVersion&quot;: &quot;A String&quot;, # Output only. The model version used to generate the response.
  &quot;promptFeedback&quot;: { # Content filter results for a prompt sent in the request. # Output only. Content filter results for a prompt sent in the request. Note: Sent only in the first stream chunk. Only happens when no candidates were generated due to content violations.
    &quot;blockReason&quot;: &quot;A String&quot;, # Output only. Blocked reason.
    &quot;blockReasonMessage&quot;: &quot;A String&quot;, # Output only. A readable block reason message.
    &quot;safetyRatings&quot;: [ # Output only. Safety ratings.
      { # Safety rating corresponding to the generated content.
        &quot;blocked&quot;: True or False, # Output only. Indicates whether the content was filtered out because of this rating.
        &quot;category&quot;: &quot;A String&quot;, # Output only. Harm category.
        &quot;overwrittenThreshold&quot;: &quot;A String&quot;, # Output only. The overwritten threshold for the safety category of Gemini 2.0 image out. If minors are detected in the output image, the threshold of each safety category will be overwritten if user sets a lower threshold.
        &quot;probability&quot;: &quot;A String&quot;, # Output only. Harm probability levels in the content.
        &quot;probabilityScore&quot;: 3.14, # Output only. Harm probability score.
        &quot;severity&quot;: &quot;A String&quot;, # Output only. Harm severity levels in the content.
        &quot;severityScore&quot;: 3.14, # Output only. Harm severity score.
      },
    ],
  },
  &quot;responseId&quot;: &quot;A String&quot;, # Output only. response_id is used to identify each response. It is the encoding of the event_id.
  &quot;usageMetadata&quot;: { # Usage metadata about response(s). # Usage metadata about the response(s).
    &quot;cacheTokensDetails&quot;: [ # Output only. List of modalities of the cached content in the request input.
      { # Represents token counting info for a single modality.
        &quot;modality&quot;: &quot;A String&quot;, # The modality associated with this token count.
        &quot;tokenCount&quot;: 42, # Number of tokens.
      },
    ],
    &quot;cachedContentTokenCount&quot;: 42, # Output only. Number of tokens in the cached part in the input (the cached content).
    &quot;candidatesTokenCount&quot;: 42, # Number of tokens in the response(s).
    &quot;candidatesTokensDetails&quot;: [ # Output only. List of modalities that were returned in the response.
      { # Represents token counting info for a single modality.
        &quot;modality&quot;: &quot;A String&quot;, # The modality associated with this token count.
        &quot;tokenCount&quot;: 42, # Number of tokens.
      },
    ],
    &quot;promptTokenCount&quot;: 42, # Number of tokens in the request. When `cached_content` is set, this is still the total effective prompt size meaning this includes the number of tokens in the cached content.
    &quot;promptTokensDetails&quot;: [ # Output only. List of modalities that were processed in the request input.
      { # Represents token counting info for a single modality.
        &quot;modality&quot;: &quot;A String&quot;, # The modality associated with this token count.
        &quot;tokenCount&quot;: 42, # Number of tokens.
      },
    ],
    &quot;thoughtsTokenCount&quot;: 42, # Output only. Number of tokens present in thoughts output.
    &quot;toolUsePromptTokenCount&quot;: 42, # Output only. Number of tokens present in tool-use prompt(s).
    &quot;toolUsePromptTokensDetails&quot;: [ # Output only. List of modalities that were processed for tool-use request inputs.
      { # Represents token counting info for a single modality.
        &quot;modality&quot;: &quot;A String&quot;, # The modality associated with this token count.
        &quot;tokenCount&quot;: 42, # Number of tokens.
      },
    ],
    &quot;totalTokenCount&quot;: 42, # Total token count for prompt, response candidates, and tool-use prompts (if present).
    &quot;trafficType&quot;: &quot;A String&quot;, # Output only. Traffic type. This shows whether a request consumes Pay-As-You-Go or Provisioned Throughput quota.
  },
}</pre>
</div>

<div class="method">
    <code class="details" id="streamRawPredict">streamRawPredict(endpoint, body=None, x__xgafv=None)</code>
  <pre>Perform a streaming online prediction with an arbitrary HTTP payload.

Args:
  endpoint: string, Required. The name of the Endpoint requested to serve the prediction. Format: `projects/{project}/locations/{location}/endpoints/{endpoint}` (required)
  body: object, The request body.
    The object takes the form of:

{ # Request message for PredictionService.StreamRawPredict.
  &quot;httpBody&quot;: { # Message that represents an arbitrary HTTP body. It should only be used for payload formats that can&#x27;t be represented as JSON, such as raw binary or an HTML page. This message can be used both in streaming and non-streaming API methods in the request as well as the response. It can be used as a top-level request field, which is convenient if one wants to extract parameters from either the URL or HTTP template into the request fields and also want access to the raw HTTP body. Example: message GetResourceRequest { // A unique request id. string request_id = 1; // The raw HTTP body is bound to this field. google.api.HttpBody http_body = 2; } service ResourceService { rpc GetResource(GetResourceRequest) returns (google.api.HttpBody); rpc UpdateResource(google.api.HttpBody) returns (google.protobuf.Empty); } Example with streaming methods: service CaldavService { rpc GetCalendar(stream google.api.HttpBody) returns (stream google.api.HttpBody); rpc UpdateCalendar(stream google.api.HttpBody) returns (stream google.api.HttpBody); } Use of this type only changes how the request and response bodies are handled, all other features will continue to work unchanged. # The prediction input. Supports HTTP headers and arbitrary data payload.
    &quot;contentType&quot;: &quot;A String&quot;, # The HTTP Content-Type header value specifying the content type of the body.
    &quot;data&quot;: &quot;A String&quot;, # The HTTP request/response body as raw binary.
    &quot;extensions&quot;: [ # Application specific response metadata. Must be set in the first response for streaming APIs.
      {
        &quot;a_key&quot;: &quot;&quot;, # Properties of the object. Contains field @type with type URL.
      },
    ],
  },
}

  x__xgafv: string, V1 error format.
    Allowed values
      1 - v1 error format
      2 - v2 error format

Returns:
  An object of the form:

    { # Message that represents an arbitrary HTTP body. It should only be used for payload formats that can&#x27;t be represented as JSON, such as raw binary or an HTML page. This message can be used both in streaming and non-streaming API methods in the request as well as the response. It can be used as a top-level request field, which is convenient if one wants to extract parameters from either the URL or HTTP template into the request fields and also want access to the raw HTTP body. Example: message GetResourceRequest { // A unique request id. string request_id = 1; // The raw HTTP body is bound to this field. google.api.HttpBody http_body = 2; } service ResourceService { rpc GetResource(GetResourceRequest) returns (google.api.HttpBody); rpc UpdateResource(google.api.HttpBody) returns (google.protobuf.Empty); } Example with streaming methods: service CaldavService { rpc GetCalendar(stream google.api.HttpBody) returns (stream google.api.HttpBody); rpc UpdateCalendar(stream google.api.HttpBody) returns (stream google.api.HttpBody); } Use of this type only changes how the request and response bodies are handled, all other features will continue to work unchanged.
  &quot;contentType&quot;: &quot;A String&quot;, # The HTTP Content-Type header value specifying the content type of the body.
  &quot;data&quot;: &quot;A String&quot;, # The HTTP request/response body as raw binary.
  &quot;extensions&quot;: [ # Application specific response metadata. Must be set in the first response for streaming APIs.
    {
      &quot;a_key&quot;: &quot;&quot;, # Properties of the object. Contains field @type with type URL.
    },
  ],
}</pre>
</div>

</body></html>