/
generate_rest.yaml
255 lines (254 loc) · 7.46 KB
/
generate_rest.yaml
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
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
openapi: 3.1.0
info:
title: Open Inference API for text generation
description: Open Inference API for text generation
version: 1.0.0
components:
schemas:
Details:
type: object
required:
- finish_reason
- logprobs
additionalProperties: {}
properties:
finish_reason:
$ref: '#/components/schemas/Finish_Reason'
logprobs:
$ref: '#/components/schemas/Logprobs'
Finish_Reason:
type: string
enum:
- length
- eos_token
- stop_sequence
description: The reason the model stopped generating tokens. `length` if number of generated tokens == `max_tokens`. `eos_token` if the model generated its end of sequence token and `stop_sequence` if the model generated a text included in `stop` array
GenerateErrorResponse:
type: object
required:
- error
properties:
error:
type: string
GenerateParameters:
type: object
additionalProperties: {}
properties:
temperature:
type: number
format: float
default: 1
minimum: 0
description: What sampling temperature to use, higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.
top_p:
type: number
format: float
maximum: 1
minimum: 0
description: 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.
max_tokens:
type: integer
format: int32
default: 20
minimum: 1
description: The maximum number of tokens to generate in the completion.
stop:
type: array
items:
type: string
description: Sequences where the API will stop generating further tokens.
details:
type: boolean
description: Flag to request for detailed response body that would include finish_reason and logprobs.
GenerateRequest:
type: object
required:
- text_input
properties:
text_input:
type: string
parameters:
allOf:
- $ref: '#/components/schemas/GenerateParameters'
GenerateResponse:
type: object
required:
- text_output
- model_name
properties:
text_output:
type: string
model_name:
type: string
model_version:
type: string
details:
$ref: '#/components/schemas/Details'
GenerateStreamResponse:
type: object
required:
- text_output
- model_name
properties:
text_output:
type: string
model_name:
type: string
model_version:
type: string
details:
$ref: '#/components/schemas/StreamDetails'
Logprobs:
type: array
items:
$ref: '#/components/schemas/Token'
description: Log probability information for the tokens.
StreamDetails:
type: object
required:
- finish_reason
- token
additionalProperties: {}
properties:
finish_reason:
$ref: '#/components/schemas/Finish_Reason'
token:
$ref: '#/components/schemas/Token'
Token:
type: object
required:
- id
- text
- logprob
- special
properties:
id:
type: integer
format: int32
minimum: 0
description: Id of the token.
logprob:
type: number
format: float
description: The log probability of this token.
special:
type: boolean
description: Describes if the token is a special token. Can be used to ignore tokens when concatenating
text:
type: string
description: The token text value.
paths:
/v2/models/${MODEL_NAME}/versions/${MODEL_VERSION}/generate:
post:
parameters:
- name: MODEL_NAME
required: true
in: path
schema:
type: string
- name: MODEL_VERSION
required: true
in: path
schema:
type: string
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/GenerateRequest'
responses:
'200':
description: generated text
content:
application/json:
schema:
$ref: '#/components/schemas/GenerateResponse'
'422':
description: Input validation error
content:
application/json:
schema:
$ref: '#/components/schemas/GenerateErrorResponse'
example:
error: Input validation error
'424':
description: Generation Error
content:
application/json:
schema:
$ref: '#/components/schemas/GenerateErrorResponse'
example:
error: Request failed during generation
'429':
description: Model is overloaded
content:
application/json:
schema:
$ref: '#/components/schemas/GenerateErrorResponse'
example:
error: Model is overloaded
'500':
description: Incomplete generation
content:
application/json:
schema:
$ref: '#/components/schemas/GenerateErrorResponse'
example:
error: Incomplete generation
/v2/models/${MODEL_NAME}/versions/${MODEL_VERSION}/generate_stream:
post:
parameters:
- name: MODEL_NAME
required: true
in: path
schema:
type: string
- name: MODEL_VERSION
required: true
in: path
schema:
type: string
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/GenerateRequest'
responses:
'200':
description: generated text stream
content:
text/event-stream:
schema:
$ref: '#/components/schemas/GenerateStreamResponse'
'422':
description: Input validation error
content:
text/event-stream:
schema:
$ref: '#/components/schemas/GenerateErrorResponse'
example:
error: Input validation error
'424':
description: Generation Error
content:
text/event-stream:
schema:
$ref: '#/components/schemas/GenerateErrorResponse'
example:
error: Request failed during generation
'429':
description: Model is overloaded
content:
text/event-stream:
schema:
$ref: '#/components/schemas/GenerateErrorResponse'
example:
error: Model is overloaded
'500':
description: Incomplete generation
content:
text/event-stream:
schema:
$ref: '#/components/schemas/GenerateErrorResponse'
example:
error: Incomplete generation