Vertex AI V1 API - Class Google::Cloud::AIPlatform::V1::GenerationConfig (v1.27.0)

Reference documentation and code samples for the Vertex AI V1 API class Google::Cloud::AIPlatform::V1::GenerationConfig.

Generation config.

Inherits

• Object

Extended By

• Google::Protobuf::MessageExts::ClassMethods

Includes

• Google::Protobuf::MessageExts

Methods

#candidate_count

def candidate_count() -> ::Integer

Returns

• (::Integer) — Optional. Number of candidates to generate.

#candidate_count=

def candidate_count=(value) -> ::Integer

Parameter

• value (::Integer) — Optional. Number of candidates to generate.

Returns

• (::Integer) — Optional. Number of candidates to generate.

#frequency_penalty

def frequency_penalty() -> ::Float

Returns

• (::Float) — Optional. Frequency penalties.

#frequency_penalty=

def frequency_penalty=(value) -> ::Float

Parameter

• value (::Float) — Optional. Frequency penalties.

Returns

• (::Float) — Optional. Frequency penalties.

#logprobs

def logprobs() -> ::Integer

Returns

• (::Integer) — Optional. Logit probabilities.

#logprobs=

def logprobs=(value) -> ::Integer

Parameter

• value (::Integer) — Optional. Logit probabilities.

Returns

• (::Integer) — Optional. Logit probabilities.

#max_output_tokens

def max_output_tokens() -> ::Integer

Returns

• (::Integer) — Optional. The maximum number of output tokens to generate per message.

#max_output_tokens=

def max_output_tokens=(value) -> ::Integer

Parameter

• value (::Integer) — Optional. The maximum number of output tokens to generate per message.

Returns

• (::Integer) — Optional. The maximum number of output tokens to generate per message.

#presence_penalty

def presence_penalty() -> ::Float

Returns

• (::Float) — Optional. Positive penalties.

#presence_penalty=

def presence_penalty=(value) -> ::Float

Parameter

• value (::Float) — Optional. Positive penalties.

Returns

• (::Float) — Optional. Positive penalties.

#response_json_schema

def response_json_schema() -> ::Google::Protobuf::Value

Returns

• (::Google::Protobuf::Value) — Optional. Output schema of the generated response. This is an alternative to response_schema that accepts JSON Schema.

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

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

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

  The non-standard propertyOrdering property may also be set.

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

#response_json_schema=

def response_json_schema=(value) -> ::Google::Protobuf::Value

Parameter

• value (::Google::Protobuf::Value) — Optional. Output schema of the generated response. This is an alternative to response_schema that accepts JSON Schema.

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

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

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

  The non-standard propertyOrdering property may also be set.

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

Returns

• (::Google::Protobuf::Value) — Optional. Output schema of the generated response. This is an alternative to response_schema that accepts JSON Schema.

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

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

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

  The non-standard propertyOrdering property may also be set.

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

#response_logprobs

def response_logprobs() -> ::Boolean

Returns

• (::Boolean) — Optional. If true, export the logprobs results in response.

#response_logprobs=

def response_logprobs=(value) -> ::Boolean

Parameter

• value (::Boolean) — Optional. If true, export the logprobs results in response.

Returns

• (::Boolean) — Optional. If true, export the logprobs results in response.

#response_mime_type

def response_mime_type() -> ::String

Returns

• (::String) —

  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.

#response_mime_type=

def response_mime_type=(value) -> ::String

Parameter

• value (::String) —

  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.

Returns

• (::String) —

  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.

#response_schema

def response_schema() -> ::Google::Cloud::AIPlatform::V1::Schema

Returns

• (::Google::Cloud::AIPlatform::V1::Schema) — 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. If set, a compatible response_mime_type must also be set. Compatible mimetypes: application/json: Schema for JSON response.

#response_schema=

def response_schema=(value) -> ::Google::Cloud::AIPlatform::V1::Schema

Parameter

• value (::Google::Cloud::AIPlatform::V1::Schema) — 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. If set, a compatible response_mime_type must also be set. Compatible mimetypes: application/json: Schema for JSON response.

Returns

• (::Google::Cloud::AIPlatform::V1::Schema) — 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. If set, a compatible response_mime_type must also be set. Compatible mimetypes: application/json: Schema for JSON response.

#routing_config

def routing_config() -> ::Google::Cloud::AIPlatform::V1::GenerationConfig::RoutingConfig

Returns

• (::Google::Cloud::AIPlatform::V1::GenerationConfig::RoutingConfig) — Optional. Routing configuration.

#routing_config=

def routing_config=(value) -> ::Google::Cloud::AIPlatform::V1::GenerationConfig::RoutingConfig

Parameter

• value (::Google::Cloud::AIPlatform::V1::GenerationConfig::RoutingConfig) — Optional. Routing configuration.

Returns

• (::Google::Cloud::AIPlatform::V1::GenerationConfig::RoutingConfig) — Optional. Routing configuration.

#seed

def seed() -> ::Integer

Returns

• (::Integer) — Optional. Seed.

#seed=

def seed=(value) -> ::Integer

Parameter

• value (::Integer) — Optional. Seed.

Returns

• (::Integer) — Optional. Seed.

#stop_sequences

def stop_sequences() -> ::Array<::String>

Returns

• (::Array<::String>) — Optional. Stop sequences.

#stop_sequences=

def stop_sequences=(value) -> ::Array<::String>

Parameter

• value (::Array<::String>) — Optional. Stop sequences.

Returns

• (::Array<::String>) — Optional. Stop sequences.

#temperature

def temperature() -> ::Float

Returns

• (::Float) — Optional. Controls the randomness of predictions.

#temperature=

def temperature=(value) -> ::Float

Parameter

• value (::Float) — Optional. Controls the randomness of predictions.

Returns

• (::Float) — Optional. Controls the randomness of predictions.

#thinking_config

def thinking_config() -> ::Google::Cloud::AIPlatform::V1::GenerationConfig::ThinkingConfig

Returns

• (::Google::Cloud::AIPlatform::V1::GenerationConfig::ThinkingConfig) — Optional. Config for thinking features. An error will be returned if this field is set for models that don't support thinking.

#thinking_config=

def thinking_config=(value) -> ::Google::Cloud::AIPlatform::V1::GenerationConfig::ThinkingConfig

Parameter

• value (::Google::Cloud::AIPlatform::V1::GenerationConfig::ThinkingConfig) — Optional. Config for thinking features. An error will be returned if this field is set for models that don't support thinking.

Returns

• (::Google::Cloud::AIPlatform::V1::GenerationConfig::ThinkingConfig) — Optional. Config for thinking features. An error will be returned if this field is set for models that don't support thinking.

#top_k

def top_k() -> ::Float

Returns

• (::Float) — Optional. If specified, top-k sampling will be used.

#top_k=

def top_k=(value) -> ::Float

Parameter

• value (::Float) — Optional. If specified, top-k sampling will be used.

Returns

• (::Float) — Optional. If specified, top-k sampling will be used.

#top_p

def top_p() -> ::Float

Returns

• (::Float) — Optional. If specified, nucleus sampling will be used.

#top_p=

def top_p=(value) -> ::Float

Parameter

• value (::Float) — Optional. If specified, nucleus sampling will be used.

Returns

• (::Float) — Optional. If specified, nucleus sampling will be used.