File size: 5,432 Bytes
8655a4b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
from typing import Literal, Optional, List, Dict, Any, Union

import time

import shortuuid
from pydantic import BaseModel, Field


class ErrorResponse(BaseModel):
    object: str = "error"
    message: str
    code: int


class ModelPermission(BaseModel):
    id: str = Field(default_factory=lambda: f"modelperm-{shortuuid.random()}")
    object: str = "model_permission"
    created: int = Field(default_factory=lambda: int(time.time()))
    allow_create_engine: bool = False
    allow_sampling: bool = True
    allow_logprobs: bool = True
    allow_search_indices: bool = True
    allow_view: bool = True
    allow_fine_tuning: bool = False
    organization: str = "*"
    group: Optional[str] = None
    is_blocking: str = False


class ModelCard(BaseModel):
    id: str
    object: str = "model"
    created: int = Field(default_factory=lambda: int(time.time()))
    owned_by: str = "fastchat"
    root: Optional[str] = None
    parent: Optional[str] = None
    permission: List[ModelPermission] = []


class ModelList(BaseModel):
    object: str = "list"
    data: List[ModelCard] = []


class UsageInfo(BaseModel):
    prompt_tokens: int = 0
    total_tokens: int = 0
    completion_tokens: Optional[int] = 0


class LogProbs(BaseModel):
    text_offset: List[int] = Field(default_factory=list)
    token_logprobs: List[Optional[float]] = Field(default_factory=list)
    tokens: List[str] = Field(default_factory=list)
    top_logprobs: List[Optional[Dict[str, float]]] = Field(default_factory=list)


class ChatCompletionRequest(BaseModel):
    model: str
    messages: Union[
        str,
        List[Dict[str, str]],
        List[Dict[str, Union[str, List[Dict[str, Union[str, Dict[str, str]]]]]]],
    ]
    temperature: Optional[float] = 0.7
    top_p: Optional[float] = 1.0
    top_k: Optional[int] = -1
    n: Optional[int] = 1
    max_tokens: Optional[int] = None
    stop: Optional[Union[str, List[str]]] = None
    stream: Optional[bool] = False
    presence_penalty: Optional[float] = 0.0
    frequency_penalty: Optional[float] = 0.0
    user: Optional[str] = None


class ChatMessage(BaseModel):
    role: str
    content: str


class ChatCompletionResponseChoice(BaseModel):
    index: int
    message: ChatMessage
    finish_reason: Optional[Literal["stop", "length"]] = None


class ChatCompletionResponse(BaseModel):
    id: str = Field(default_factory=lambda: f"chatcmpl-{shortuuid.random()}")
    object: str = "chat.completion"
    created: int = Field(default_factory=lambda: int(time.time()))
    model: str
    choices: List[ChatCompletionResponseChoice]
    usage: UsageInfo


class DeltaMessage(BaseModel):
    role: Optional[str] = None
    content: Optional[str] = None


class ChatCompletionResponseStreamChoice(BaseModel):
    index: int
    delta: DeltaMessage
    finish_reason: Optional[Literal["stop", "length"]] = None


class ChatCompletionStreamResponse(BaseModel):
    id: str = Field(default_factory=lambda: f"chatcmpl-{shortuuid.random()}")
    object: str = "chat.completion.chunk"
    created: int = Field(default_factory=lambda: int(time.time()))
    model: str
    choices: List[ChatCompletionResponseStreamChoice]


class TokenCheckRequestItem(BaseModel):
    model: str
    prompt: str
    max_tokens: int


class TokenCheckRequest(BaseModel):
    prompts: List[TokenCheckRequestItem]


class TokenCheckResponseItem(BaseModel):
    fits: bool
    tokenCount: int
    contextLength: int


class TokenCheckResponse(BaseModel):
    prompts: List[TokenCheckResponseItem]


class EmbeddingsRequest(BaseModel):
    model: Optional[str] = None
    engine: Optional[str] = None
    input: Union[str, List[Any]]
    user: Optional[str] = None
    encoding_format: Optional[str] = None


class EmbeddingsResponse(BaseModel):
    object: str = "list"
    data: List[Dict[str, Any]]
    model: str
    usage: UsageInfo


class CompletionRequest(BaseModel):
    model: str
    prompt: Union[str, List[Any]]
    suffix: Optional[str] = None
    temperature: Optional[float] = 0.7
    n: Optional[int] = 1
    max_tokens: Optional[int] = 16
    stop: Optional[Union[str, List[str]]] = None
    stream: Optional[bool] = False
    top_p: Optional[float] = 1.0
    top_k: Optional[int] = -1
    logprobs: Optional[int] = None
    echo: Optional[bool] = False
    presence_penalty: Optional[float] = 0.0
    frequency_penalty: Optional[float] = 0.0
    user: Optional[str] = None
    use_beam_search: Optional[bool] = False
    best_of: Optional[int] = None


class CompletionResponseChoice(BaseModel):
    index: int
    text: str
    logprobs: Optional[LogProbs] = None
    finish_reason: Optional[Literal["stop", "length"]] = None


class CompletionResponse(BaseModel):
    id: str = Field(default_factory=lambda: f"cmpl-{shortuuid.random()}")
    object: str = "text_completion"
    created: int = Field(default_factory=lambda: int(time.time()))
    model: str
    choices: List[CompletionResponseChoice]
    usage: UsageInfo


class CompletionResponseStreamChoice(BaseModel):
    index: int
    text: str
    logprobs: Optional[LogProbs] = None
    finish_reason: Optional[Literal["stop", "length"]] = None


class CompletionStreamResponse(BaseModel):
    id: str = Field(default_factory=lambda: f"cmpl-{shortuuid.random()}")
    object: str = "text_completion"
    created: int = Field(default_factory=lambda: int(time.time()))
    model: str
    choices: List[CompletionResponseStreamChoice]