aws-sdk-bedrockruntime 1.130.0

AWS SDK for Amazon Bedrock Runtime
Documentation 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178

// Code generated by software.amazon.smithy.rust.codegen.smithy-rs. DO NOT EDIT.
pub use crate::operation::count_tokens::_count_tokens_input::CountTokensInputBuilder;

pub use crate::operation::count_tokens::_count_tokens_output::CountTokensOutputBuilder;

impl crate::operation::count_tokens::builders::CountTokensInputBuilder {
    /// Sends a request with this input using the given client.
    pub async fn send_with(
        self,
        client: &crate::Client,
    ) -> ::std::result::Result<
        crate::operation::count_tokens::CountTokensOutput,
        ::aws_smithy_runtime_api::client::result::SdkError<
            crate::operation::count_tokens::CountTokensError,
            ::aws_smithy_runtime_api::client::orchestrator::HttpResponse,
        >,
    > {
        let mut fluent_builder = client.count_tokens();
        fluent_builder.inner = self;
        fluent_builder.send().await
    }
}
/// Fluent builder constructing a request to `CountTokens`.
///
/// <p>Returns the token count for a given inference request. This operation helps you estimate token usage before sending requests to foundation models by returning the token count that would be used if the same input were sent to the model in an inference request.</p>
/// <p>Token counting is model-specific because different models use different tokenization strategies. The token count returned by this operation will match the token count that would be charged if the same input were sent to the model in an <code>InvokeModel</code> or <code>Converse</code> request.</p>
/// <p>You can use this operation to:</p>
/// <ul>
/// <li>
/// <p>Estimate costs before sending inference requests.</p></li>
/// <li>
/// <p>Optimize prompts to fit within token limits.</p></li>
/// <li>
/// <p>Plan for token usage in your applications.</p></li>
/// </ul>
/// <p>This operation accepts the same input formats as <code>InvokeModel</code> and <code>Converse</code>, allowing you to count tokens for both raw text inputs and structured conversation formats.</p>
/// <p>The following operations are related to <code>CountTokens</code>:</p>
/// <ul>
/// <li>
/// <p><a href="https://docs.aws.amazon.com/bedrock/latest/API/API_runtime_InvokeModel.html">InvokeModel</a> - Sends inference requests to foundation models</p></li>
/// <li>
/// <p><a href="https://docs.aws.amazon.com/bedrock/latest/API/API_runtime_Converse.html">Converse</a> - Sends conversation-based inference requests to foundation models</p></li>
/// </ul>
#[derive(::std::clone::Clone, ::std::fmt::Debug)]
pub struct CountTokensFluentBuilder {
    handle: ::std::sync::Arc<crate::client::Handle>,
    inner: crate::operation::count_tokens::builders::CountTokensInputBuilder,
    config_override: ::std::option::Option<crate::config::Builder>,
}
impl
    crate::client::customize::internal::CustomizableSend<
        crate::operation::count_tokens::CountTokensOutput,
        crate::operation::count_tokens::CountTokensError,
    > for CountTokensFluentBuilder
{
    fn send(
        self,
        config_override: crate::config::Builder,
    ) -> crate::client::customize::internal::BoxFuture<
        crate::client::customize::internal::SendResult<
            crate::operation::count_tokens::CountTokensOutput,
            crate::operation::count_tokens::CountTokensError,
        >,
    > {
        ::std::boxed::Box::pin(async move { self.config_override(config_override).send().await })
    }
}
impl CountTokensFluentBuilder {
    /// Creates a new `CountTokensFluentBuilder`.
    pub(crate) fn new(handle: ::std::sync::Arc<crate::client::Handle>) -> Self {
        Self {
            handle,
            inner: ::std::default::Default::default(),
            config_override: ::std::option::Option::None,
        }
    }
    /// Access the CountTokens as a reference.
    pub fn as_input(&self) -> &crate::operation::count_tokens::builders::CountTokensInputBuilder {
        &self.inner
    }
    /// Sends the request and returns the response.
    ///
    /// If an error occurs, an `SdkError` will be returned with additional details that
    /// can be matched against.
    ///
    /// By default, any retryable failures will be retried twice. Retry behavior
    /// is configurable with the [RetryConfig](aws_smithy_types::retry::RetryConfig), which can be
    /// set when configuring the client.
    pub async fn send(
        self,
    ) -> ::std::result::Result<
        crate::operation::count_tokens::CountTokensOutput,
        ::aws_smithy_runtime_api::client::result::SdkError<
            crate::operation::count_tokens::CountTokensError,
            ::aws_smithy_runtime_api::client::orchestrator::HttpResponse,
        >,
    > {
        let input = self
            .inner
            .build()
            .map_err(::aws_smithy_runtime_api::client::result::SdkError::construction_failure)?;
        let runtime_plugins = crate::operation::count_tokens::CountTokens::operation_runtime_plugins(
            self.handle.runtime_plugins.clone(),
            &self.handle.conf,
            self.config_override,
        );
        crate::operation::count_tokens::CountTokens::orchestrate(&runtime_plugins, input).await
    }

    /// Consumes this builder, creating a customizable operation that can be modified before being sent.
    pub fn customize(
        self,
    ) -> crate::client::customize::CustomizableOperation<
        crate::operation::count_tokens::CountTokensOutput,
        crate::operation::count_tokens::CountTokensError,
        Self,
    > {
        crate::client::customize::CustomizableOperation::new(self)
    }
    pub(crate) fn config_override(mut self, config_override: impl ::std::convert::Into<crate::config::Builder>) -> Self {
        self.set_config_override(::std::option::Option::Some(config_override.into()));
        self
    }

    pub(crate) fn set_config_override(&mut self, config_override: ::std::option::Option<crate::config::Builder>) -> &mut Self {
        self.config_override = config_override;
        self
    }
    /// <p>The unique identifier or ARN of the foundation model to use for token counting. Each model processes tokens differently, so the token count is specific to the model you specify.</p>
    pub fn model_id(mut self, input: impl ::std::convert::Into<::std::string::String>) -> Self {
        self.inner = self.inner.model_id(input.into());
        self
    }
    /// <p>The unique identifier or ARN of the foundation model to use for token counting. Each model processes tokens differently, so the token count is specific to the model you specify.</p>
    pub fn set_model_id(mut self, input: ::std::option::Option<::std::string::String>) -> Self {
        self.inner = self.inner.set_model_id(input);
        self
    }
    /// <p>The unique identifier or ARN of the foundation model to use for token counting. Each model processes tokens differently, so the token count is specific to the model you specify.</p>
    pub fn get_model_id(&self) -> &::std::option::Option<::std::string::String> {
        self.inner.get_model_id()
    }
    /// <p>The input for which to count tokens. The structure of this parameter depends on whether you're counting tokens for an <code>InvokeModel</code> or <code>Converse</code> request:</p>
    /// <ul>
    /// <li>
    /// <p>For <code>InvokeModel</code> requests, provide the request body in the <code>invokeModel</code> field</p></li>
    /// <li>
    /// <p>For <code>Converse</code> requests, provide the messages and system content in the <code>converse</code> field</p></li>
    /// </ul>
    /// <p>The input format must be compatible with the model specified in the <code>modelId</code> parameter.</p>
    pub fn input(mut self, input: crate::types::CountTokensInput) -> Self {
        self.inner = self.inner.input(input);
        self
    }
    /// <p>The input for which to count tokens. The structure of this parameter depends on whether you're counting tokens for an <code>InvokeModel</code> or <code>Converse</code> request:</p>
    /// <ul>
    /// <li>
    /// <p>For <code>InvokeModel</code> requests, provide the request body in the <code>invokeModel</code> field</p></li>
    /// <li>
    /// <p>For <code>Converse</code> requests, provide the messages and system content in the <code>converse</code> field</p></li>
    /// </ul>
    /// <p>The input format must be compatible with the model specified in the <code>modelId</code> parameter.</p>
    pub fn set_input(mut self, input: ::std::option::Option<crate::types::CountTokensInput>) -> Self {
        self.inner = self.inner.set_input(input);
        self
    }
    /// <p>The input for which to count tokens. The structure of this parameter depends on whether you're counting tokens for an <code>InvokeModel</code> or <code>Converse</code> request:</p>
    /// <ul>
    /// <li>
    /// <p>For <code>InvokeModel</code> requests, provide the request body in the <code>invokeModel</code> field</p></li>
    /// <li>
    /// <p>For <code>Converse</code> requests, provide the messages and system content in the <code>converse</code> field</p></li>
    /// </ul>
    /// <p>The input format must be compatible with the model specified in the <code>modelId</code> parameter.</p>
    pub fn get_input(&self) -> &::std::option::Option<crate::types::CountTokensInput> {
        self.inner.get_input()
    }
}