completion.rs 7.16 KB
Newer Older
1
2
use std::collections::HashMap;

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
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
use serde::{Deserialize, Serialize};
use serde_json::{Map, Value};

use super::common::*;

// ============================================================================
// Completions API (v1/completions) - DEPRECATED but still supported
// ============================================================================

#[derive(Debug, Clone, Deserialize, Serialize)]
pub struct CompletionRequest {
    /// ID of the model to use (required for OpenAI, optional for some implementations, such as SGLang)
    pub model: String,

    /// The prompt(s) to generate completions for
    pub prompt: StringOrArray,

    /// The suffix that comes after a completion of inserted text
    #[serde(skip_serializing_if = "Option::is_none")]
    pub suffix: Option<String>,

    /// The maximum number of tokens to generate
    #[serde(skip_serializing_if = "Option::is_none")]
    pub max_tokens: Option<u32>,

    /// What sampling temperature to use, between 0 and 2
    #[serde(skip_serializing_if = "Option::is_none")]
    pub temperature: Option<f32>,

    /// An alternative to sampling with temperature (nucleus sampling)
    #[serde(skip_serializing_if = "Option::is_none")]
    pub top_p: Option<f32>,

    /// How many completions to generate for each prompt
    #[serde(skip_serializing_if = "Option::is_none")]
    pub n: Option<u32>,

    /// Whether to stream back partial progress
    #[serde(default)]
    pub stream: bool,

    /// Options for streaming response
    #[serde(skip_serializing_if = "Option::is_none")]
    pub stream_options: Option<StreamOptions>,

    /// Include the log probabilities on the logprobs most likely tokens
    #[serde(skip_serializing_if = "Option::is_none")]
    pub logprobs: Option<u32>,

    /// Echo back the prompt in addition to the completion
    #[serde(default)]
    pub echo: bool,

    /// Up to 4 sequences where the API will stop generating further tokens
    #[serde(skip_serializing_if = "Option::is_none")]
    pub stop: Option<StringOrArray>,

    /// Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far
    #[serde(skip_serializing_if = "Option::is_none")]
    pub presence_penalty: Option<f32>,

    /// Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far
    #[serde(skip_serializing_if = "Option::is_none")]
    pub frequency_penalty: Option<f32>,

    /// Generates best_of completions server-side and returns the "best"
    #[serde(skip_serializing_if = "Option::is_none")]
    pub best_of: Option<u32>,

    /// Modify the likelihood of specified tokens appearing in the completion
    #[serde(skip_serializing_if = "Option::is_none")]
    pub logit_bias: Option<HashMap<String, f32>>,

    /// A unique identifier representing your end-user
    #[serde(skip_serializing_if = "Option::is_none")]
    pub user: Option<String>,

    /// If specified, our system will make a best effort to sample deterministically
    #[serde(skip_serializing_if = "Option::is_none")]
    pub seed: Option<i64>,

    // -------- Engine Specific Sampling Parameters --------
    /// Top-k sampling parameter (-1 to disable)
    #[serde(skip_serializing_if = "Option::is_none")]
    pub top_k: Option<i32>,

    /// Min-p nucleus sampling parameter
    #[serde(skip_serializing_if = "Option::is_none")]
    pub min_p: Option<f32>,

    /// Minimum number of tokens to generate
    #[serde(skip_serializing_if = "Option::is_none")]
    pub min_tokens: Option<u32>,

    /// Repetition penalty for reducing repetitive text
    #[serde(skip_serializing_if = "Option::is_none")]
    pub repetition_penalty: Option<f32>,

    /// Regex constraint for output generation
    #[serde(skip_serializing_if = "Option::is_none")]
    pub regex: Option<String>,

    /// EBNF grammar constraint for structured output
    #[serde(skip_serializing_if = "Option::is_none")]
    pub ebnf: Option<String>,

    /// JSON schema constraint for structured output
    #[serde(skip_serializing_if = "Option::is_none")]
    pub json_schema: Option<String>,

    /// Specific token IDs to use as stop conditions
    #[serde(skip_serializing_if = "Option::is_none")]
    pub stop_token_ids: Option<Vec<u32>>,

    /// Skip trimming stop tokens from output
    #[serde(default)]
    pub no_stop_trim: bool,

    /// Ignore end-of-sequence tokens during generation
    #[serde(default)]
    pub ignore_eos: bool,

    /// Skip special tokens during detokenization
    #[serde(default = "default_true")]
    pub skip_special_tokens: bool,

    /// Path to LoRA adapter(s) for model customization
    #[serde(skip_serializing_if = "Option::is_none")]
    pub lora_path: Option<String>,

    /// Session parameters for continual prompting
    #[serde(skip_serializing_if = "Option::is_none")]
    pub session_params: Option<HashMap<String, Value>>,

    /// Return model hidden states
    #[serde(default)]
    pub return_hidden_states: bool,

    /// Sampling seed for deterministic outputs
    #[serde(skip_serializing_if = "Option::is_none")]
    pub sampling_seed: Option<u64>,

    /// Additional fields including bootstrap info for PD routing
    #[serde(flatten)]
    pub other: Map<String, Value>,
}

impl GenerationRequest for CompletionRequest {
    fn is_stream(&self) -> bool {
        self.stream
    }

    fn get_model(&self) -> Option<&str> {
        Some(&self.model)
    }

    fn extract_text_for_routing(&self) -> String {
        match &self.prompt {
            StringOrArray::String(s) => s.clone(),
            StringOrArray::Array(v) => v.join(" "),
        }
    }
}

// ============================================================================
// Response Types
// ============================================================================

#[derive(Debug, Clone, Deserialize, Serialize)]
pub struct CompletionResponse {
    pub id: String,
    pub object: String, // "text_completion"
    pub created: u64,
    pub model: String,
    pub choices: Vec<CompletionChoice>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub usage: Option<Usage>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub system_fingerprint: Option<String>,
}

#[derive(Debug, Clone, Deserialize, Serialize)]
pub struct CompletionChoice {
    pub text: String,
    pub index: u32,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub logprobs: Option<LogProbs>,
    pub finish_reason: Option<String>, // "stop", "length", "content_filter", etc.
    /// Information about which stop condition was matched
    #[serde(skip_serializing_if = "Option::is_none")]
    pub matched_stop: Option<Value>, // Can be string or integer
}

#[derive(Debug, Clone, Deserialize, Serialize)]
pub struct CompletionStreamResponse {
    pub id: String,
    pub object: String, // "text_completion"
    pub created: u64,
    pub choices: Vec<CompletionStreamChoice>,
    pub model: String,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub system_fingerprint: Option<String>,
}

#[derive(Debug, Clone, Deserialize, Serialize)]
pub struct CompletionStreamChoice {
    pub text: String,
    pub index: u32,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub logprobs: Option<LogProbs>,
    pub finish_reason: Option<String>,
}