forked from bombastictranz/mistral-inference
-
Notifications
You must be signed in to change notification settings - Fork 0
/
plugin-redoc-0.yaml
787 lines (767 loc) · 23.9 KB
/
plugin-redoc-0.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
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
openapi: 3.0.0
info:
title: Mistral AI API
description: >-
Our Chat Completion and Embeddings APIs specification. Create your account
on [La Plateforme](https://console.mistral.ai) to get access and read the
[docs](https://docs.mistral.ai) to learn how to use it.
version: 0.0.2
servers:
- url: https://api.mistral.ai/v1
paths:
/chat/completions:
post:
operationId: createChatCompletion
summary: Create Chat Completions
requestBody:
required: true
content:
application/json:
schema:
anyOf:
- $ref: '#/components/schemas/ChatCompletionRequest'
- $ref: '#/components/schemas/ChatCompletionRequestFunctionCall'
- $ref: '#/components/schemas/ChatCompletionRequestJSONMode'
responses:
'200':
description: OK
content:
application/json:
schema:
oneOf:
- $ref: '#/components/schemas/ChatCompletionResponse'
- $ref: '#/components/schemas/ChatCompletionResponseFunctionCall'
- $ref: '#/components/schemas/ChatCompletionResponseJSONMode'
/embeddings:
post:
operationId: createEmbedding
summary: Create Embeddings
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/EmbeddingRequest'
responses:
'200':
description: OK
content:
application/json:
schema:
$ref: '#/components/schemas/EmbeddingResponse'
/models:
get:
operationId: listModels
summary: List Available Models
responses:
'200':
description: OK
content:
application/json:
schema:
$ref: '#/components/schemas/ModelList'
components:
schemas:
Error:
type: object
properties:
type:
type: string
nullable: false
message:
type: string
nullable: false
param:
type: string
nullable: true
code:
type: string
nullable: true
required:
- type
- message
- param
- code
ErrorResponse:
type: object
properties:
error:
$ref: '#/components/schemas/Error'
required:
- error
ModelList:
type: object
properties:
object:
type: string
data:
type: array
items:
$ref: '#/components/schemas/Model'
required:
- object
- data
ChatCompletionRequest:
type: object
title: Regular
properties:
model:
description: >
ID of the model to use. You can use the [List Available
Models](/api#operation/listModels) API to see all of your available
models, or see our [Model overview](/models) for model descriptions.
type: string
example: mistral-small-latest
messages:
description: >
The prompt(s) to generate completions for, encoded as a list of dict
with role and content. The first prompt role should be `user` or
`system`.
type: array
items:
type: object
properties:
role:
type: string
enum:
- system
- user
- assistant
- tool
content:
type: string
example:
role: user
content: Who is the best French painter? Answer in one short sentence.
temperature:
type: number
minimum: 0
maximum: 1
default: 0.7
nullable: true
description: >
What sampling temperature to use, between 0.0 and 1.0. 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.
top_p:
type: number
minimum: 0
maximum: 1
default: 1
nullable: true
description: >
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.
max_tokens:
type: integer
minimum: 0
default: null
nullable: true
example: 512
description: >
The maximum number of tokens to generate in the completion.
The token count of your prompt plus `max_tokens` cannot exceed the
model's context length.
stream:
type: boolean
default: false
nullable: true
description: >
Whether to stream back partial progress. If set, tokens will be sent
as data-only server-sent events as they become available, with the
stream terminated by a data: [DONE] message. Otherwise, the server
will hold the request open until the timeout or until completion,
with the response containing the full result as JSON.
safe_prompt:
type: boolean
default: false
description: |
Whether to inject a safety prompt before all conversations.
random_seed:
type: integer
default: null
example: 1337
description: >
The seed to use for random sampling. If set, different calls will
generate deterministic results.
required:
- model
- messages
ChatCompletionRequestJSONMode:
type: object
title: JSON mode
properties:
model:
description: >
ID of the model to use. You can use the [List Available
Models](/api#operation/listModels) API to see all of your available
models, or see our [Model overview](/models) for model descriptions.
type: string
example: mistral-small-latest
messages:
description: >
The prompt(s) to generate completions for, encoded as a list of dict
with role and content. The first prompt role should be `user` or
`system`.
type: array
items:
type: object
properties:
role:
type: string
enum:
- system
- user
- assistant
- tool
content:
type: string
example:
role: user
content: Who is the best French painter? Answer in JSON.
response_format:
type: object
description: >
An object specifying the format that the model must output. Setting
to `{ "type": "json_object" }` enables JSON mode, which guarantees
the message the model generates is in JSON.
When using JSON mode you MUST also instruct the model to produce
JSON yourself with a system or a user message.
properties:
type:
type: string
example: json_object
temperature:
type: number
minimum: 0
maximum: 1
default: 0.7
nullable: true
description: >
What sampling temperature to use, between 0.0 and 1.0. 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.
top_p:
type: number
minimum: 0
maximum: 1
default: 1
nullable: true
description: >
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.
max_tokens:
type: integer
minimum: 0
default: null
nullable: true
example: 512
description: >
The maximum number of tokens to generate in the completion.
The token count of your prompt plus `max_tokens` cannot exceed the
model's context length.
stream:
type: boolean
default: false
nullable: true
description: >
Whether to stream back partial progress. If set, tokens will be sent
as data-only server-sent events as they become available, with the
stream terminated by a data: [DONE] message. Otherwise, the server
will hold the request open until the timeout or until completion,
with the response containing the full result as JSON.
safe_prompt:
type: boolean
default: false
description: |
Whether to inject a safety prompt before all conversations.
random_seed:
type: integer
default: null
example: 1337
description: >
The seed to use for random sampling. If set, different calls will
generate deterministic results.
required:
- model
- messages
ChatCompletionRequestFunctionCall:
type: object
title: Function calling
properties:
model:
description: >
ID of the model to use. You can use the [List Available
Models](/api#operation/listModels) API to see all of your available
models, or see our [Model overview](/models) for model descriptions.
type: string
example: mistral-small-latest
messages:
description: >
The prompt(s) to generate completions for, encoded as a list of dict
with role and content. The first prompt role should be `user` or
`system`.
When role is `tool`, the properties should contain `tool_call_id`
(string or `null`).
type: array
items:
type: object
properties:
role:
type: string
enum:
- system
- user
- assistant
- tool
content:
type: string
example:
role: user
content: What is the weather like in Paris?
temperature:
type: number
minimum: 0
maximum: 1
default: 0.7
nullable: true
description: >
What sampling temperature to use, between 0.0 and 1.0. 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.
top_p:
type: number
minimum: 0
maximum: 1
default: 1
nullable: true
description: >
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.
max_tokens:
type: integer
minimum: 0
default: null
example: 64
nullable: true
description: >
The maximum number of tokens to generate in the completion.
The token count of your prompt plus `max_tokens` cannot exceed the
model's context length.
stream:
type: boolean
default: false
nullable: true
description: >
Whether to stream back partial progress. If set, tokens will be sent
as data-only server-sent events as they become available, with the
stream terminated by a data: [DONE] message. Otherwise, the server
will hold the request open until the timeout or until completion,
with the response containing the full result as JSON.
safe_prompt:
type: boolean
default: false
description: |
Whether to inject a safety prompt before all conversations.
tools:
type: array
description: >
A list of available tools for the model. Use this to specify
functions for which the model can generate JSON inputs.
items:
type: object
required:
- type
- function
properties:
type:
type: string
description: |
The type of the tool. Currently, only `function` is supported.
example: function
function:
type: object
required:
- name
description: |
The function properties.
properties:
description:
type: string
description: >
The description of the function to help the model
determine when and how to invoke it.
example: Get the current weather in a given location.
name:
type: string
required: true
description: >
The name of the function to be called. Must be a-z,A-Z,0-9
or contain underscores and dashes, with a maximum length
of 64.
example: get_weather
parameters:
type: object
description: >
The function parameters, defined using a JSON Schema
object. If omitted, the function is considered to have an
empty parameter list.
example:
type: object
properties:
location:
type: string
description: The city and department, e.g. Marseille, 13
unit:
type: string
enum:
- celsius
- fahrenheit
required:
- location
tool_choice:
type: string
default: auto
description: >
Specifies if/how functions are called. If set to `none` the model
won't call a function and will generate a message instead. If set to
`auto` the model can choose to either generate a message or call a
function. If set to `any` the model is forced to call a function.
example: auto
random_seed:
type: integer
default: null
example: 1337
description: >
The seed to use for random sampling. If set, different calls will
generate deterministic results.
required:
- model
- messages
ChatCompletionResponse:
type: object
title: Regular
properties:
id:
type: string
example: cmpl-e5cc70bb28c444948073e77776eb30ef
object:
type: string
example: chat.completion
created:
type: integer
example: 1702256327
model:
type: string
example: mistral-small-latest
choices:
type: array
items:
type: object
required:
- index
- text
- finish_reason
properties:
index:
type: integer
example: 0
message:
type: object
properties:
role:
type: string
enum:
- user
- assistant
example: assistant
content:
type: string
example: >-
Claude Monet is often considered one of the best French
painters due to his significant role in the Impressionist
movement.
finish_reason:
type: string
enum:
- stop
- length
- model_length
- error
- tool_calls
example: stop
usage:
type: object
properties:
prompt_tokens:
type: integer
example: 16
completion_tokens:
type: integer
example: 34
total_tokens:
type: integer
example: 50
required:
- prompt_tokens
- completion_tokens
- total_tokens
ChatCompletionResponseJSONMode:
type: object
title: JSON mode
properties:
id:
type: string
example: cmpl-e5cc70bb28c444948073e77776eb30ef
object:
type: string
example: chat.completion
created:
type: integer
example: 1702256327
model:
type: string
example: mistral-small-latest
choices:
type: array
items:
type: object
required:
- index
- text
- finish_reason
properties:
index:
type: integer
example: 0
message:
type: object
properties:
role:
type: string
enum:
- user
- assistant
example: assistant
content:
type: string
example: >-
{"name": "Claude Monet", "reason": "Claude Monet is often
considered one of the best French painters due to his
significant role in the development of Impressionism, a
major art movement that originated in France. His water
lily paintings are among the most famous works in the
history of art."}
finish_reason:
type: string
enum:
- stop
- length
- model_length
- error
- tool_calls
example: stop
usage:
type: object
properties:
prompt_tokens:
type: integer
example: 14
completion_tokens:
type: integer
example: 83
total_tokens:
type: integer
example: 69
required:
- prompt_tokens
- completion_tokens
- total_tokens
ChatCompletionResponseFunctionCall:
type: object
title: Function calling
properties:
id:
type: string
example: cmpl-e5cc70bb28c444948073e77776eb30ef
object:
type: string
example: chat.completion
created:
type: integer
example: 1702256327
model:
type: string
example: mistral-large-latest
choices:
type: array
items:
type: object
required:
- index
- text
- finish_reason
properties:
index:
type: integer
example: 0
message:
type: object
properties:
role:
type: string
example: assistant
content:
type: string
example: ''
tool_calls:
type: array
items:
type: object
properties:
function:
type: object
properties:
name:
type: string
arguments:
type: str
example:
- function:
name: get_current_weather
arguments: '{"location": "Paris, 75"}'
finish_reason:
type: string
enum:
- stop
- length
- model_length
- error
- tool_calls
example: tool_calls
usage:
type: object
properties:
prompt_tokens:
type: integer
example: 118
completion_tokens:
type: integer
example: 35
total_tokens:
type: integer
example: 153
required:
- prompt_tokens
- completion_tokens
- total_tokens
EmbeddingRequest:
type: object
properties:
model:
type: string
example: mistral-embed
description: |
The ID of the model to use for this request.
input:
type: array
items:
type: string
example:
- Hello
- world
description: |
The list of strings to embed.
encoding_format:
type: string
enum:
- float
example: float
description: |
The format of the output data.
EmbeddingResponse:
type: object
properties:
id:
type: string
example: embd-aad6fc62b17349b192ef09225058bc45
object:
type: string
example: list
data:
type: array
items:
type: object
properties:
object:
type: string
example: embedding
embedding:
type: array
items:
type: number
example:
- 0.1
- 0.2
- 0.3
index:
type: int
example: 0
example:
- object: embedding
embedding:
- 0.1
- 0.2
- 0.3
index: 0
- object: embedding
embedding:
- 0.4
- 0.5
- 0.6
index: 1
model:
type: string
usage:
type: object
properties:
prompt_tokens:
type: integer
example: 9
total_tokens:
type: integer
example: 9
required:
- prompt_tokens
- total_tokens
required:
- id
- object
- data
- model
- usage
Model:
title: Model
properties:
id:
type: string
object:
type: string
created:
type: integer
owned_by:
type: string
required:
- id
- object
- created
- owned_by