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
179
180
181
182
use chrono::{DateTime, Utc, serde::ts_seconds};
use serde::{Deserialize, Serialize};
use std::collections::HashMap;
use crate::types::OutputContent;
use super::{
InputItem, OutputItem, ReasoningConfig, ServiceTier, TextConfig, Tool, ToolChoice, Truncation,
};
/// The Response object.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct Response {
/// When this Response was created.
#[serde(with = "ts_seconds")]
pub created_at: DateTime<Utc>,
/// Unique identifier for this Response.
pub id: String,
/// Details about why the response is incomplete.
pub incomplete_details: Option<IncompleteDetails>,
/// Inserts a system (or developer) message as the first item in the model's context.
/// When using along with `previous_response_id`, the instructions from a previous response will be not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses.
pub instructions: Option<String>,
/// An upper bound for the number of tokens that can be generated for a response, including visible output tokens and [reasoning tokens](https://platform.openai.com/docs/guides/reasoning).
pub max_output_tokens: Option<u64>,
/// Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
/// Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
pub metadata: HashMap<String, String>,
/// Model ID used to generate the response, like gpt-4o or o1. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points.
/// Refer to the [model guide](https://platform.openai.com/docs/models) to browse and compare available models.
pub model: String,
/// An array of content items generated by the model.
/// - The length and order of items in the `output` array is dependent on the model's response.
/// - Rather than accessing the first item in the `output` array and assuming it's an assistant message with the content generated by the model, you might consider using the `output_text` function.
pub output: Vec<OutputItem>,
/// Whether to allow the model to run tool calls in parallel.
pub parallel_tool_calls: bool,
/// The unique ID of the previous response to the model. Use this to create multi-turn conversations.
/// Learn more about [conversation state](https://platform.openai.com/docs/guides/conversation-state).
pub previous_response_id: Option<String>,
/// Configuration options for [reasoning models](https://platform.openai.com/docs/guides/reasoning).
/// Only available for o-series models.
pub reasoning: ReasoningConfig,
/// Specifies the latency tier to use for processing the request.
pub service_tier: Option<ServiceTier>,
/// The status of the response generation.
pub status: ResponseStatus,
/// What sampling temperature to use, between 0 and 2.
/// Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.
/// We generally recommend altering this or `top_p` but not both.
pub temperature: f32,
/// Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more:
/// - [Text inputs and outputs](https://platform.openai.com/docs/guides/text)
/// - [Structured Outputs](https://platform.openai.com/docs/guides/structured-outputs)
pub text: TextConfig,
/// How the model should select which tool (or tools) to use when generating a response.
/// See the `tools` parameter to see how to specify which tools the model can call.
pub tool_choice: ToolChoice,
/// An array of tools the model may call while generating a response. You can specify which tool to use by setting the `tool_choice` parameter.
/// The two categories of tools you can provide the model are:
/// - **Built-in tools**: Tools that are provided by OpenAI that extend the model's capabilities, like [web search](https://platform.openai.com/docs/guides/tools-web-search) or [file search](https://platform.openai.com/docs/guides/tools-file-search). Learn more about [built-in tools](https://platform.openai.com/docs/guides/tools).
/// - **Function calls (custom tools)**: Functions that are defined by you, enabling the model to call your own code. Learn more about [function calling](https://platform.openai.com/docs/guides/function-calling).
pub tools: Vec<Tool>,
/// An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.
/// We generally recommend altering this or `temperature` but not both.
pub top_p: f32,
/// The truncation strategy to use for the model response.
pub truncation: Truncation,
/// Represents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used.
pub usage: Option<Usage>,
/// Whether the response was stored on OpenAI's server for later retrieval.
pub store: bool,
/// A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#end-user-ids).
pub user: Option<String>,
}
impl Response {
#[must_use]
pub fn output_text(&self) -> String {
self.output
.iter()
.filter_map(|output| match output {
OutputItem::Message(message) => Some(message),
_ => None,
})
.flat_map(|message| &message.content)
.map(|content| match content {
OutputContent::Text { text, .. } => text.to_owned(),
OutputContent::Refusal { refusal } => refusal.to_owned(),
})
.collect::<String>()
}
}
/// Represents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct Usage {
/// The number of input tokens.
pub input_tokens: u64,
/// A detailed breakdown of the input tokens.
pub input_tokens_details: InputTokensDetails,
/// The number of output tokens.
pub output_tokens: u64,
/// A detailed breakdown of the output tokens.
pub output_tokens_details: OutputTokensDetails,
/// The total number of tokens used.
pub total_tokens: u64,
}
/// A detailed breakdown of the input tokens.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct InputTokensDetails {
/// The number of cached tokens.
pub cached_tokens: u64,
}
/// A detailed breakdown of the output tokens.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct OutputTokensDetails {
/// The number of reasoning tokens.
pub reasoning_tokens: u64,
}
/// Details about why a response is incomplete.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct IncompleteDetails {
/// The reason why the response is incomplete.
pub reason: String,
}
/// The status of the response generation.
#[derive(Debug, Clone, Copy, Serialize, Deserialize, PartialEq, Eq)]
#[serde(rename_all = "snake_case")]
pub enum ResponseStatus {
Failed,
Completed,
Incomplete,
InProgress,
}
/// An error object returned when the model fails to generate a Response.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct Error {
/// The type of error.
pub r#type: String,
/// A human-readable description of the error.
pub message: String,
/// The error code for the response.
pub code: Option<String>,
/// The parameter that caused the error.
pub param: Option<String>,
}
/// A list of items used to generate a model response.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct InputItemList {
/// A list of items used to generate this response.
data: Vec<InputItem>,
/// The ID of the first item in the list.
first_id: String,
/// The ID of the last item in the list.
last_id: String,
/// Whether there are more items available.
has_more: bool,
}
#[allow(clippy::redundant_pub_crate)]
#[derive(Debug, Clone, Serialize, Deserialize)]
#[serde(untagged)]
pub(crate) enum ResponseResult {
Ok(Box<Response>),
Err { error: Error },
}
impl From<ResponseResult> for Result<Response, Error> {
fn from(val: ResponseResult) -> Self {
match val {
ResponseResult::Err { error } => Err(error),
ResponseResult::Ok(response) => Ok(*response),
}
}
}