Dialogflow V2 API - Class Google::Cloud::Dialogflow::V2::InferenceParameter (v1.1.0)

Reference documentation and code samples for the Dialogflow V2 API class Google::Cloud::Dialogflow::V2::InferenceParameter.

The parameters of inference.

Inherits

  • Object

Extended By

  • Google::Protobuf::MessageExts::ClassMethods

Includes

  • Google::Protobuf::MessageExts

Methods

#max_output_tokens

def max_output_tokens() -> ::Integer
Returns
  • (::Integer) — Optional. Maximum number of the output tokens for the generator.

#max_output_tokens=

def max_output_tokens=(value) -> ::Integer
Parameter
  • value (::Integer) — Optional. Maximum number of the output tokens for the generator.
Returns
  • (::Integer) — Optional. Maximum number of the output tokens for the generator.

#temperature

def temperature() -> ::Float
Returns
  • (::Float) — Optional. Controls the randomness of LLM predictions. Low temperature = less random. High temperature = more random. If unset (or 0), uses a default value of 0.

#temperature=

def temperature=(value) -> ::Float
Parameter
  • value (::Float) — Optional. Controls the randomness of LLM predictions. Low temperature = less random. High temperature = more random. If unset (or 0), uses a default value of 0.
Returns
  • (::Float) — Optional. Controls the randomness of LLM predictions. Low temperature = less random. High temperature = more random. If unset (or 0), uses a default value of 0.

#top_k

def top_k() -> ::Integer
Returns
  • (::Integer) — Optional. Top-k changes how the model selects tokens for output. A top-k of 1 means the selected token is the most probable among all tokens in the model's vocabulary (also called greedy decoding), while a top-k of 3 means that the next token is selected from among the 3 most probable tokens (using temperature). For each token selection step, the top K tokens with the highest probabilities are sampled. Then tokens are further filtered based on topP with the final token selected using temperature sampling. Specify a lower value for less random responses and a higher value for more random responses. Acceptable value is [1, 40], default to 40.

#top_k=

def top_k=(value) -> ::Integer
Parameter
  • value (::Integer) — Optional. Top-k changes how the model selects tokens for output. A top-k of 1 means the selected token is the most probable among all tokens in the model's vocabulary (also called greedy decoding), while a top-k of 3 means that the next token is selected from among the 3 most probable tokens (using temperature). For each token selection step, the top K tokens with the highest probabilities are sampled. Then tokens are further filtered based on topP with the final token selected using temperature sampling. Specify a lower value for less random responses and a higher value for more random responses. Acceptable value is [1, 40], default to 40.
Returns
  • (::Integer) — Optional. Top-k changes how the model selects tokens for output. A top-k of 1 means the selected token is the most probable among all tokens in the model's vocabulary (also called greedy decoding), while a top-k of 3 means that the next token is selected from among the 3 most probable tokens (using temperature). For each token selection step, the top K tokens with the highest probabilities are sampled. Then tokens are further filtered based on topP with the final token selected using temperature sampling. Specify a lower value for less random responses and a higher value for more random responses. Acceptable value is [1, 40], default to 40.

#top_p

def top_p() -> ::Float
Returns
  • (::Float) — Optional. Top-p changes how the model selects tokens for output. Tokens are selected from most K (see topK parameter) probable to least until the sum of their probabilities equals the top-p value. For example, if tokens A, B, and C have a probability of 0.3, 0.2, and 0.1 and the top-p value is 0.5, then the model will select either A or B as the next token (using temperature) and doesn't consider C. The default top-p value is 0.95. Specify a lower value for less random responses and a higher value for more random responses. Acceptable value is [0.0, 1.0], default to 0.95.

#top_p=

def top_p=(value) -> ::Float
Parameter
  • value (::Float) — Optional. Top-p changes how the model selects tokens for output. Tokens are selected from most K (see topK parameter) probable to least until the sum of their probabilities equals the top-p value. For example, if tokens A, B, and C have a probability of 0.3, 0.2, and 0.1 and the top-p value is 0.5, then the model will select either A or B as the next token (using temperature) and doesn't consider C. The default top-p value is 0.95. Specify a lower value for less random responses and a higher value for more random responses. Acceptable value is [0.0, 1.0], default to 0.95.
Returns
  • (::Float) — Optional. Top-p changes how the model selects tokens for output. Tokens are selected from most K (see topK parameter) probable to least until the sum of their probabilities equals the top-p value. For example, if tokens A, B, and C have a probability of 0.3, 0.2, and 0.1 and the top-p value is 0.5, then the model will select either A or B as the next token (using temperature) and doesn't consider C. The default top-p value is 0.95. Specify a lower value for less random responses and a higher value for more random responses. Acceptable value is [0.0, 1.0], default to 0.95.