Skip to content

InferenceConfiguration

Used by
Source code in docs_src/capo_bedrock_runtime/types/inference_configuration.py 
11
12
13
14
15
16
17
18
19
20
21
class InferenceConfiguration(TypedDict, closed=True):
    max_tokens: NotRequired["int"]
    """<p>The maximum number of tokens to allow in the generated response. The default value is the maximum allowed value for the model that you are using. For more information, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters.html">Inference parameters for foundation models</a>. </p>"""
    temperature: NotRequired["float"]
    """<p>The likelihood of the model selecting higher-probability options while generating a response. A lower value makes the model more likely to choose higher-probability options, while a higher value makes the model more likely to choose lower-probability options.</p> <p>The default value is the default value for the model that you are using. For more information, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters.html">Inference parameters for foundation models</a>. </p>"""
    top_p: NotRequired["float"]
    """<p>The percentage of most-likely candidates that the model considers for the next token. For example, if you choose a value of 0.8 for <code>topP</code>, the model selects from the top 80% of the probability distribution of tokens that could be next in the sequence.</p> <p>The default value is the default value for the model that you are using. For more information, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters.html">Inference parameters for foundation models</a>. </p>"""
    stop_sequences: NotRequired[
        "capo_bedrock_runtime.types.non_empty_string_list.NonEmptyStringList"
    ]
    """<p>A list of stop sequences. A stop sequence is a sequence of characters that causes the model to stop generating the response. </p>"""

max_tokens instance-attribute 

max_tokens: NotRequired[int]

The maximum number of tokens to allow in the generated response. The default value is the maximum allowed value for the model that you are using. For more information, see Inference parameters for foundation models.

stop_sequences instance-attribute 

stop_sequences: NotRequired[NonEmptyStringList]

A list of stop sequences. A stop sequence is a sequence of characters that causes the model to stop generating the response.

temperature instance-attribute 

temperature: NotRequired[float]

The likelihood of the model selecting higher-probability options while generating a response. A lower value makes the model more likely to choose higher-probability options, while a higher value makes the model more likely to choose lower-probability options.

The default value is the default value for the model that you are using. For more information, see Inference parameters for foundation models.

top_p instance-attribute 

top_p: NotRequired[float]

The percentage of most-likely candidates that the model considers for the next token. For example, if you choose a value of 0.8 for topP, the model selects from the top 80% of the probability distribution of tokens that could be next in the sequence.

The default value is the default value for the model that you are using. For more information, see Inference parameters for foundation models.