inference-gateway-sdk 0.9.1

Rust SDK for interacting with various language models through the Inference Gateway
Documentation
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
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
---
openapi: 3.1.0
info:
  title: Inference Gateway API
  description: |
    The API for interacting with various language models and other AI services.
    OpenAI, Groq, Ollama, and other providers are supported.
    OpenAI compatible API for using with existing clients.
    Unified API for all providers.
  version: 1.0.0
  license:
    name: MIT
    url: https://github.com/inference-gateway/inference-gateway/blob/main/LICENSE
servers:
  - url: http://localhost:8080
tags:
  - name: Models
    description: List and describe the various models available in the API.
  - name: Completions
    description: Generate completions from the models.
  - name: Proxy
    description: Proxy requests to provider endpoints.
  - name: Health
    description: Health check
paths:
  /v1/models:
    get:
      operationId: listModels
      tags:
        - Models
      summary:
        Lists the currently available models, and provides basic information
        about each one such as the owner and availability.
      security:
        - bearerAuth: []
      parameters:
        - name: provider
          in: query
          required: false
          schema:
            $ref: "#/components/schemas/Providers"
          description: Specific provider to query (optional)
      responses:
        "200":
          description: List of available models
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/ListModelsResponse"
              examples:
                allProviders:
                  summary: Models from all providers
                  value:
                    object: "list"
                    data:
                      - id: "gpt-4o"
                        object: "model"
                        created: 1686935002
                        owned_by: "openai"
                      - id: "llama-3.3-70b-versatile"
                        object: "model"
                        created: 1723651281
                        owned_by: "groq"
                      - id: "claude-3-opus-20240229"
                        object: "model"
                        created: 1708905600
                        owned_by: "anthropic"
                      - id: "command-r"
                        object: "model"
                        created: 1707868800
                        owned_by: "cohere"
                      - id: "phi3:3.8b"
                        object: "model"
                        created: 1718441600
                        owned_by: "ollama"
                singleProvider:
                  summary: Models from a specific provider
                  value:
                    object: "list"
                    data:
                      - id: "gpt-4o"
                        object: "model"
                        created: 1686935002
                        owned_by: "openai"
                      - id: "gpt-4-turbo"
                        object: "model"
                        created: 1687882410
                        owned_by: "openai"
                      - id: "gpt-3.5-turbo"
                        object: "model"
                        created: 1677649963
                        owned_by: "openai"
        "401":
          $ref: "#/components/responses/Unauthorized"
        "500":
          $ref: "#/components/responses/InternalError"
  /v1/chat/completions:
    post:
      summary: Create a chat completion
      description: Creates a completion for the chat message with the specified provider
      tags:
        - Completions
      security:
        - bearerAuth: []
      parameters:
        - name: provider
          in: query
          required: false
          schema:
            $ref: "#/components/schemas/Providers"
          description: Specific provider to use (default determined by model)
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required:
                - model
                - messages
              properties:
                model:
                  type: string
                  description: Model ID to use
                messages:
                  type: array
                  items:
                    $ref: "#/components/schemas/Message"
                temperature:
                  type: number
                  format: float
                  default: 0.7
                stream:
                  type: boolean
                  default: false
                tools:
                  type: array
                  items:
                    type: object
                max_tokens:
                  type: integer
      responses:
        "200":
          description: Successful response
          content:
            application/json:
              schema:
                type: object
                properties:
                  id:
                    type: string
                  object:
                    type: string
                    example: "chat.completion"
                  created:
                    type: integer
                    format: int64
                  model:
                    type: string
                  choices:
                    type: array
                    items:
                      type: object
                      properties:
                        index:
                          type: integer
                        message:
                          $ref: "#/components/schemas/Message"
                        finish_reason:
                          type: string
                          enum: [stop, length, tool_calls, content_filter]
                  usage:
                    type: object
                    properties:
                      prompt_tokens:
                        type: integer
                      completion_tokens:
                        type: integer
                      total_tokens:
                        type: integer
            text/event-stream:
              schema:
                type: string
        "400":
          $ref: "#/components/responses/BadRequest"
        "401":
          $ref: "#/components/responses/Unauthorized"
        "500":
          $ref: "#/components/responses/InternalError"
  /proxy/{provider}/{path}:
    parameters:
      - name: provider
        in: path
        required: true
        schema:
          $ref: "#/components/schemas/Providers"
      - name: path
        in: path
        required: true
        style: simple
        explode: false
        schema:
          type: string
        description: The remaining path to proxy to the provider
    get:
      summary: Proxy GET request to provider
      operationId: proxyGet
      tags:
        - Proxy
      responses:
        "200":
          $ref: "#/components/responses/ProviderResponse"
        "400":
          $ref: "#/components/responses/BadRequest"
        "401":
          $ref: "#/components/responses/Unauthorized"
        "500":
          $ref: "#/components/responses/InternalError"
      security:
        - bearerAuth: []
    post:
      summary: Proxy POST request to provider
      operationId: proxyPost
      tags:
        - Proxy
      requestBody:
        $ref: "#/components/requestBodies/ProviderRequest"
      responses:
        "200":
          $ref: "#/components/responses/ProviderResponse"
        "400":
          $ref: "#/components/responses/BadRequest"
        "401":
          $ref: "#/components/responses/Unauthorized"
        "500":
          $ref: "#/components/responses/InternalError"
      security:
        - bearerAuth: []
    put:
      summary: Proxy PUT request to provider
      operationId: proxyPut
      tags:
        - Proxy
      requestBody:
        $ref: "#/components/requestBodies/ProviderRequest"
      responses:
        "200":
          $ref: "#/components/responses/ProviderResponse"
        "400":
          $ref: "#/components/responses/BadRequest"
        "401":
          $ref: "#/components/responses/Unauthorized"
        "500":
          $ref: "#/components/responses/InternalError"
      security:
        - bearerAuth: []
    delete:
      summary: Proxy DELETE request to provider
      operationId: proxyDelete
      tags:
        - Proxy
      responses:
        "200":
          $ref: "#/components/responses/ProviderResponse"
        "400":
          $ref: "#/components/responses/BadRequest"
        "401":
          $ref: "#/components/responses/Unauthorized"
        "500":
          $ref: "#/components/responses/InternalError"
      security:
        - bearerAuth: []
    patch:
      summary: Proxy PATCH request to provider
      operationId: proxyPatch
      tags:
        - Proxy
      requestBody:
        $ref: "#/components/requestBodies/ProviderRequest"
      responses:
        "200":
          $ref: "#/components/responses/ProviderResponse"
        "400":
          $ref: "#/components/responses/BadRequest"
        "401":
          $ref: "#/components/responses/Unauthorized"
        "500":
          $ref: "#/components/responses/InternalError"
      security:
        - bearerAuth: []
  /health:
    get:
      operationId: healthCheck
      summary: Health check
      tags:
        - Health
      responses:
        "200":
          description: Health check successful
components:
  requestBodies:
    ProviderRequest:
      required: true
      description: |
        ProviderRequest depends on the specific provider and endpoint being called
        If you decide to use this approach, please follow the provider-specific documentations.
      content:
        application/json:
          schema:
            type: object
            properties:
              model:
                type: string
              messages:
                type: array
                items:
                  type: object
                  properties:
                    role:
                      type: string
                    content:
                      type: string
              temperature:
                type: number
                format: float64
                default: 0.7
          examples:
            openai:
              summary: OpenAI chat completion request
              value:
                model: "gpt-3.5-turbo"
                messages:
                  - role: "user"
                    content: "Hello! How can I assist you today?"
                temperature: 0.7
            anthropic:
              summary: Anthropic Claude request
              value:
                model: "claude-3-opus-20240229"
                messages:
                  - role: "user"
                    content: "Explain quantum computing"
                temperature: 0.5
    CreateChatCompletionRequest:
      required: true
      description: |
        ProviderRequest depends on the specific provider and endpoint being called
        If you decide to use this approach, please follow the provider-specific documentations.
      content:
        application/json:
          schema:
            $ref: "#/components/schemas/CreateChatCompletionRequest"
  responses:
    BadRequest:
      description: Bad request
      content:
        application/json:
          schema:
            $ref: "#/components/schemas/Error"
    Unauthorized:
      description: Unauthorized
      content:
        application/json:
          schema:
            $ref: "#/components/schemas/Error"
    InternalError:
      description: Internal server error
      content:
        application/json:
          schema:
            $ref: "#/components/schemas/Error"
    ProviderResponse:
      description: |
        ProviderResponse depends on the specific provider and endpoint being called
        If you decide to use this approach, please follow the provider-specific documentations.
      content:
        application/json:
          schema:
            $ref: "#/components/schemas/ProviderSpecificResponse"
          examples:
            openai:
              summary: OpenAI API response
              value:
                {
                  "id": "chatcmpl-123",
                  "object": "chat.completion",
                  "created": 1677652288,
                  "model": "gpt-3.5-turbo",
                  "choices":
                    [
                      {
                        "index": 0,
                        "message":
                          {
                            "role": "assistant",
                            "content": "Hello! How can I help you today?",
                          },
                        "finish_reason": "stop",
                      },
                    ],
                }
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      bearerFormat: JWT
      description: |
        Authentication is optional by default.
        To enable authentication, set ENABLE_AUTH to true.
        When enabled, requests must include a valid JWT token in the Authorization header.
  schemas:
    Endpoints:
      type: object
      properties:
        models:
          type: string
        chat:
          type: string
    Providers:
      type: string
      enum:
        - ollama
        - groq
        - openai
        - cloudflare
        - cohere
        - anthropic
      x-provider-configs:
        ollama:
          id: "ollama"
          url: "http://ollama:8080/v1"
          auth_type: "none"
          endpoints:
            models:
              name: "list_models"
              method: "GET"
              endpoint: "/models"
            chat:
              name: "chat_completions"
              method: "POST"
              endpoint: "/chat/completions"
        anthropic:
          id: "anthropic"
          url: "https://api.anthropic.com/v1"
          auth_type: "bearer"
          endpoints:
            models:
              name: "list_models"
              method: "GET"
              endpoint: "/models"
            chat:
              name: "chat_completions"
              method: "POST"
              endpoint: "/chat/completions"
        cohere:
          id: "cohere"
          url: "https://api.cohere.ai"
          auth_type: "bearer"
          endpoints:
            models:
              name: "list_models"
              method: "GET"
              endpoint: "/v1/models"
            chat:
              name: "chat_completions"
              method: "POST"
              endpoint: "/compatibility/v1/chat/completions"
        groq:
          id: "groq"
          url: "https://api.groq.com/openai/v1"
          auth_type: "bearer"
          endpoints:
            models:
              name: "list_models"
              method: "GET"
              endpoint: "/models"
            chat:
              name: "chat_completions"
              method: "POST"
              endpoint: "/chat/completions"
        openai:
          id: "openai"
          url: "https://api.openai.com/v1"
          auth_type: "bearer"
          endpoints:
            models:
              name: "list_models"
              method: "GET"
              endpoint: "/models"
            chat:
              name: "chat_completions"
              method: "POST"
              endpoint: "/chat/completions"
        cloudflare:
          id: "cloudflare"
          url: "https://api.cloudflare.com/client/v4/accounts/{ACCOUNT_ID}/ai"
          auth_type: "bearer"
          endpoints:
            models:
              name: "list_models"
              method: "GET"
              endpoint: "/finetunes/public?limit=1000"
            chat:
              name: "chat_completions"
              method: "POST"
              endpoint: "/v1/chat/completions"
    ProviderSpecificResponse:
      type: object
      description: |
        Provider-specific response format. Examples:

        OpenAI GET /v1/models?provider=openai response:
        ```json
        {
          "provider": "openai",
          "object": "list",
          "data": [
            {
              "id": "gpt-4",
              "object": "model",
              "created": 1687882410,
              "owned_by": "openai",
              "served_by": "openai"
            }
          ]
        }
        ```

        Anthropic GET /v1/models?provider=anthropic response:
        ```json
        {
          "provider": "anthropic",
          "object": "list",
          "data": [
            {
              "id": "gpt-4",
              "object": "model",
              "created": 1687882410,
              "owned_by": "openai",
              "served_by": "openai"
            }
          ]
        }
        ```
      additionalProperties: true
    ProviderAuthType:
      type: string
      description: Authentication type for providers
      enum:
        - bearer
        - xheader
        - query
        - none
    Error:
      type: object
      properties:
        error:
          type: string
    MessageRole:
      type: string
      description: Role of the message sender
      enum:
        - system
        - user
        - assistant
        - tool
    Message:
      type: object
      description: Message structure for provider requests
      properties:
        role:
          $ref: "#/components/schemas/MessageRole"
        content:
          type: string
        tool_calls:
          type: array
          items:
            $ref: "#/components/schemas/ChatCompletionMessageToolCall"
        tool_call_id:
          type: string
        reasoning:
          type: string
      required:
        - role
        - content
    Model:
      type: object
      description: Common model information
      properties:
        id:
          type: string
        object:
          type: string
        created:
          type: integer
          format: int64
        owned_by:
          type: string
        served_by:
          type: string
    ListModelsResponse:
      type: object
      description: Response structure for listing models
      properties:
        provider:
          type: string
        object:
          type: string
        data:
          type: array
          items:
            $ref: "#/components/schemas/Model"
          default: []
    FunctionObject:
      type: object
      properties:
        description:
          type: string
          description:
            A description of what the function does, used by the model to
            choose when and how to call the function.
        name:
          type: string
          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.
        parameters:
          $ref: "#/components/schemas/FunctionParameters"
        strict:
          type: boolean
          default: false
          description:
            Whether to enable strict schema adherence when generating the
            function call. If set to true, the model will follow the exact
            schema defined in the `parameters` field. Only a subset of JSON
            Schema is supported when `strict` is `true`. Learn more about
            Structured Outputs in the [function calling
            guide](docs/guides/function-calling).
      required:
        - name
    ChatCompletionTool:
      type: object
      properties:
        type:
          $ref: "#/components/schemas/ChatCompletionToolType"
        function:
          $ref: "#/components/schemas/FunctionObject"
      required:
        - type
        - function
    FunctionParameters:
      type: object
      description: >-
        The parameters the functions accepts, described as a JSON Schema object.
        See the [guide](/docs/guides/function-calling) for examples, and the
        [JSON Schema
        reference](https://json-schema.org/understanding-json-schema/) for
        documentation about the format. 

        Omitting `parameters` defines a function with an empty parameter list.
      properties:
        type:
          type: string
          description: The type of the parameters. Currently, only `object` is supported.
        properties:
          type: object
          description: The properties of the parameters.
          additionalProperties:
            type: object
            description: The schema for the parameter.
            additionalProperties: true
        required:
          type: array
          items:
            type: string
          description: The required properties of the parameters.
        additionalProperties:
          type: boolean
          default: false
          description: Whether additional properties are allowed.
      additionalProperties: true
    ChatCompletionToolType:
      type: string
      description: The type of the tool. Currently, only `function` is supported.
      enum:
        - function
    CompletionUsage:
      type: object
      description: Usage statistics for the completion request.
      properties:
        completion_tokens:
          type: integer
          default: 0
          format: int64
          description: Number of tokens in the generated completion.
        prompt_tokens:
          type: integer
          default: 0
          format: int64
          description: Number of tokens in the prompt.
        total_tokens:
          type: integer
          default: 0
          format: int64
          description: Total number of tokens used in the request (prompt + completion).
      required:
        - prompt_tokens
        - completion_tokens
        - total_tokens
    ChatCompletionStreamOptions:
      description: >
        Options for streaming response. Only set this when you set `stream:
        true`.
      type: object
      properties:
        include_usage:
          type: boolean
          description: >
            If set, an additional chunk will be streamed before the `data:
            [DONE]` message. The `usage` field on this chunk shows the token
            usage statistics for the entire request, and the `choices` field
            will always be an empty array. All other chunks will also include a
            `usage` field, but with a null value.
          default: true
    CreateChatCompletionRequest:
      type: object
      properties:
        model:
          type: string
          description: Model ID to use
        messages:
          description: >
            A list of messages comprising the conversation so far.
          type: array
          minItems: 1
          items:
            $ref: "#/components/schemas/Message"
        max_tokens:
          description: >
            An upper bound for the number of tokens that can be generated
            for a completion, including visible output tokens and reasoning tokens.
          type: integer
        stream:
          description: >
            If set to true, the model response data will be streamed to the
            client as it is generated using [server-sent
            events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format).
          type: boolean
          default: false
        stream_options:
          $ref: "#/components/schemas/ChatCompletionStreamOptions"
        tools:
          type: array
          description: >
            A list of tools the model may call. Currently, only functions
            are supported as a tool. Use this to provide a list of functions
            the model may generate JSON inputs for. A max of 128 functions
            are supported.
          items:
            $ref: "#/components/schemas/ChatCompletionTool"
      required:
        - model
        - messages
    ChatCompletionMessageToolCallFunction:
      type: object
      description: The function that the model called.
      properties:
        name:
          type: string
          description: The name of the function to call.
        arguments:
          type: string
          description:
            The arguments to call the function with, as generated by the model
            in JSON format. Note that the model does not always generate
            valid JSON, and may hallucinate parameters not defined by your
            function schema. Validate the arguments in your code before
            calling your function.
      required:
        - name
        - arguments
    ChatCompletionMessageToolCall:
      type: object
      properties:
        id:
          type: string
          description: The ID of the tool call.
        type:
          $ref: "#/components/schemas/ChatCompletionToolType"
        function:
          $ref: "#/components/schemas/ChatCompletionMessageToolCallFunction"
      required:
        - id
        - type
        - function
    EventType:
      type: string
      enum:
        - message-start
        - stream-start
        - content-start
        - content-delta
        - content-end
        - message-end
        - stream-end
    ChatCompletionChoice:
      type: object
      properties:
        finish_reason:
          type: string
          description: >
            The reason the model stopped generating tokens. This will be
            `stop` if the model hit a natural stop point or a provided
            stop sequence,

            `length` if the maximum number of tokens specified in the
            request was reached,

            `content_filter` if content was omitted due to a flag from our
            content filters,

            `tool_calls` if the model called a tool.
          enum:
            - stop
            - length
            - tool_calls
            - content_filter
            - function_call
        index:
          type: integer
          description: The index of the choice in the list of choices.
        message:
          $ref: "#/components/schemas/Message"
      required:
        - finish_reason
        - index
        - message
        - logprobs
    ChatCompletionStreamChoice:
      type: object
      required:
        - delta
        - finish_reason
        - index
      properties:
        delta:
          $ref: "#/components/schemas/ChatCompletionStreamResponseDelta"
        logprobs:
          description: Log probability information for the choice.
          type: object
          properties:
            content:
              description: A list of message content tokens with log probability information.
              type: array
              items:
                $ref: "#/components/schemas/ChatCompletionTokenLogprob"
            refusal:
              description: A list of message refusal tokens with log probability information.
              type: array
              items:
                $ref: "#/components/schemas/ChatCompletionTokenLogprob"
          required:
            - content
            - refusal
        finish_reason:
          $ref: "#/components/schemas/FinishReason"
        index:
          type: integer
          description: The index of the choice in the list of choices.
    CreateChatCompletionResponse:
      type: object
      description:
        Represents a chat completion response returned by model, based on
        the provided input.
      properties:
        id:
          type: string
          description: A unique identifier for the chat completion.
        choices:
          type: array
          description:
            A list of chat completion choices. Can be more than one if `n` is
            greater than 1.
          items:
            $ref: "#/components/schemas/ChatCompletionChoice"
        created:
          type: integer
          description:
            The Unix timestamp (in seconds) of when the chat completion was
            created.
        model:
          type: string
          description: The model used for the chat completion.
        object:
          type: string
          description: The object type, which is always `chat.completion`.
          x-stainless-const: true
        usage:
          $ref: "#/components/schemas/CompletionUsage"
      required:
        - choices
        - created
        - id
        - model
        - object
    ChatCompletionStreamResponseDelta:
      type: object
      description: A chat completion delta generated by streamed model responses.
      properties:
        content:
          type: string
          description: The contents of the chunk message.
        tool_calls:
          type: array
          items:
            $ref: "#/components/schemas/ChatCompletionMessageToolCallChunk"
        role:
          $ref: "#/components/schemas/MessageRole"
        refusal:
          type: string
          description: The refusal message generated by the model.
    ChatCompletionMessageToolCallChunk:
      type: object
      properties:
        index:
          type: integer
        id:
          type: string
          description: The ID of the tool call.
        type:
          type: string
          description: The type of the tool. Currently, only `function` is supported.
        function:
          type: object
          properties:
            name:
              type: string
              description: The name of the function to call.
            arguments:
              type: string
              description:
                The arguments to call the function with, as generated by the model
                in JSON format. Note that the model does not always generate
                valid JSON, and may hallucinate parameters not defined by your
                function schema. Validate the arguments in your code before
                calling your function.
      required:
        - index
    ChatCompletionTokenLogprob:
      type: object
      properties:
        token: &a1
          description: The token.
          type: string
        logprob: &a2
          description:
            The log probability of this token, if it is within the top 20 most
            likely tokens. Otherwise, the value `-9999.0` is used to signify
            that the token is very unlikely.
          type: number
        bytes: &a3
          description:
            A list of integers representing the UTF-8 bytes representation of
            the token. Useful in instances where characters are represented by
            multiple tokens and their byte representations must be combined to
            generate the correct text representation. Can be `null` if there is
            no bytes representation for the token.
          type: array
          items:
            type: integer
        top_logprobs:
          description:
            List of the most likely tokens and their log probability, at this
            token position. In rare cases, there may be fewer than the number of
            requested `top_logprobs` returned.
          type: array
          items:
            type: object
            properties:
              token: *a1
              logprob: *a2
              bytes: *a3
            required:
              - token
              - logprob
              - bytes
      required:
        - token
        - logprob
        - bytes
        - top_logprobs
    FinishReason:
      type: string
      description: >
        The reason the model stopped generating tokens. This will be
        `stop` if the model hit a natural stop point or a provided
        stop sequence,

        `length` if the maximum number of tokens specified in the
        request was reached,

        `content_filter` if content was omitted due to a flag from our
        content filters,

        `tool_calls` if the model called a tool.
      enum:
        - stop
        - length
        - tool_calls
        - content_filter
        - function_call
    CreateChatCompletionStreamResponse:
      type: object
      description: |
        Represents a streamed chunk of a chat completion response returned
        by the model, based on the provided input.
      properties:
        id:
          type: string
          description:
            A unique identifier for the chat completion. Each chunk has the
            same ID.
        choices:
          type: array
          description: >
            A list of chat completion choices. Can contain more than one
            elements if `n` is greater than 1. Can also be empty for the

            last chunk if you set `stream_options: {"include_usage": true}`.
          items:
            $ref: "#/components/schemas/ChatCompletionStreamChoice"
        created:
          type: integer
          description:
            The Unix timestamp (in seconds) of when the chat completion was
            created. Each chunk has the same timestamp.
        model:
          type: string
          description: The model to generate the completion.
        system_fingerprint:
          type: string
          description: >
            This fingerprint represents the backend configuration that the model
            runs with.

            Can be used in conjunction with the `seed` request parameter to
            understand when backend changes have been made that might impact
            determinism.
        object:
          type: string
          description: The object type, which is always `chat.completion.chunk`.
        usage:
          $ref: "#/components/schemas/CompletionUsage"
      required:
        - choices
        - created
        - id
        - model
        - object
    CreateCompletionResponse:
      type: object
      description: >
        Represents a completion response from the API. Note: both the streamed
        and non-streamed response objects share the same shape (unlike the chat
        endpoint).
      properties:
        id:
          type: string
          description: A unique identifier for the completion.
        choices:
          type: array
          description:
            The list of completion choices the model generated for the input
            prompt.
          items:
            type: object
            required:
              - finish_reason
              - index
              - logprobs
              - text
            properties:
              finish_reason:
                type: string
                description: >
                  The reason the model stopped generating tokens. This will be
                  `stop` if the model hit a natural stop point or a provided
                  stop sequence,

                  `length` if the maximum number of tokens specified in the
                  request was reached,

                  or `content_filter` if content was omitted due to a flag from
                  our content filters.
                enum:
                  - stop
                  - length
                  - content_filter
              index:
                type: integer
              logprobs:
                type: object
                properties:
                  text_offset:
                    type: array
                    items:
                      type: integer
                  token_logprobs:
                    type: array
                    items:
                      type: number
                  tokens:
                    type: array
                    items:
                      type: string
                  top_logprobs:
                    type: array
                    items:
                      type: object
                      additionalProperties:
                        type: number
              text:
                type: string
        created:
          type: integer
          description: The Unix timestamp (in seconds) of when the completion was created.
        model:
          type: string
          description: The model used for completion.
        object:
          type: string
          description: The object type, which is always "text_completion"
          enum:
            - text_completion
        usage:
          $ref: "#/components/schemas/CompletionUsage"
      required:
        - id
        - object
        - created
        - model
        - choices
    Config:
      x-config:
        sections:
          - general:
              title: "General settings"
              settings:
                - name: application_name
                  env: "APPLICATION_NAME"
                  type: string
                  default: "inference-gateway"
                  description: "The name of the application"
                - name: environment
                  env: "ENVIRONMENT"
                  type: string
                  default: "production"
                  description: "The environment"
                - name: enable_telemetry
                  env: "ENABLE_TELEMETRY"
                  type: bool
                  default: "false"
                  description: "Enable telemetry"
                - name: enable_auth
                  env: "ENABLE_AUTH"
                  type: bool
                  default: "false"
                  description: "Enable authentication"
          - oidc:
              title: "OpenID Connect"
              settings:
                - name: issuer_url
                  env: "OIDC_ISSUER_URL"
                  type: string
                  default: "http://keycloak:8080/realms/inference-gateway-realm"
                  description: "OIDC issuer URL"
                - name: client_id
                  env: "OIDC_CLIENT_ID"
                  type: string
                  default: "inference-gateway-client"
                  description: "OIDC client ID"
                  secret: true
                - name: client_secret
                  env: "OIDC_CLIENT_SECRET"
                  type: string
                  description: "OIDC client secret"
                  secret: true
          - server:
              title: "Server settings"
              settings:
                - name: host
                  env: "SERVER_HOST"
                  type: string
                  default: "0.0.0.0"
                  description: "Server host"
                - name: port
                  env: "SERVER_PORT"
                  type: string
                  default: "8080"
                  description: "Server port"
                - name: read_timeout
                  env: "SERVER_READ_TIMEOUT"
                  type: time.Duration
                  default: "30s"
                  description: "Read timeout"
                - name: write_timeout
                  env: "SERVER_WRITE_TIMEOUT"
                  type: time.Duration
                  default: "30s"
                  description: "Write timeout"
                - name: idle_timeout
                  env: "SERVER_IDLE_TIMEOUT"
                  type: time.Duration
                  default: "120s"
                  description: "Idle timeout"
                - name: tls_cert_path
                  env: "SERVER_TLS_CERT_PATH"
                  type: string
                  description: "TLS certificate path"
                - name: tls_key_path
                  env: "SERVER_TLS_KEY_PATH"
                  type: string
                  description: "TLS key path"
          - client:
              title: "Client settings"
              settings:
                - name: timeout
                  env: "CLIENT_TIMEOUT"
                  type: time.Duration
                  default: "30s"
                  description: "Client timeout"
                - name: max_idle_conns
                  env: "CLIENT_MAX_IDLE_CONNS"
                  type: int
                  default: "20"
                  description: "Maximum idle connections"
                - name: max_idle_conns_per_host
                  env: "CLIENT_MAX_IDLE_CONNS_PER_HOST"
                  type: int
                  default: "20"
                  description: "Maximum idle connections per host"
                - name: idle_conn_timeout
                  env: "CLIENT_IDLE_CONN_TIMEOUT"
                  type: time.Duration
                  default: "30s"
                  description: "Idle connection timeout"
                - name: tls_min_version
                  env: "CLIENT_TLS_MIN_VERSION"
                  type: string
                  default: "TLS12"
                  description: "Minimum TLS version"
          - providers:
              title: "Providers"
              settings:
                - name: anthropic_api_url
                  env: "ANTHROPIC_API_URL"
                  type: string
                  default: "https://api.anthropic.com/v1"
                  description: "Anthropic API URL"
                - name: anthropic_api_key
                  env: "ANTHROPIC_API_KEY"
                  type: string
                  description: "Anthropic API Key"
                  secret: true
                - name: cloudflare_api_url
                  env: "CLOUDFLARE_API_URL"
                  type: string
                  default: "https://api.cloudflare.com/client/v4/accounts/{ACCOUNT_ID}/ai"
                  description: "Cloudflare API URL"
                - name: cloudflare_api_key
                  env: "CLOUDFLARE_API_KEY"
                  type: string
                  description: "Cloudflare API Key"
                  secret: true
                - name: cohere_api_url
                  env: "COHERE_API_URL"
                  type: string
                  default: "https://api.cohere.ai"
                  description: "Cohere API URL"
                - name: cohere_api_key
                  env: "COHERE_API_KEY"
                  type: string
                  description: "Cohere API Key"
                  secret: true
                - name: groq_api_url
                  env: "GROQ_API_URL"
                  type: string
                  default: "https://api.groq.com/openai/v1"
                  description: "Groq API URL"
                - name: groq_api_key
                  env: "GROQ_API_KEY"
                  type: string
                  description: "Groq API Key"
                  secret: true
                - name: ollama_api_url
                  env: "OLLAMA_API_URL"
                  type: string
                  default: "http://ollama:8080/v1"
                  description: "Ollama API URL"
                - name: ollama_api_key
                  env: "OLLAMA_API_KEY"
                  type: string
                  description: "Ollama API Key"
                  secret: true
                - name: openai_api_url
                  env: "OPENAI_API_URL"
                  type: string
                  default: "https://api.openai.com/v1"
                  description: "OpenAI API URL"
                - name: openai_api_key
                  env: "OPENAI_API_KEY"
                  type: string
                  description: "OpenAI API Key"
                  secret: true