-
Notifications
You must be signed in to change notification settings - Fork 2.2k
/
Copy pathconfig_schema.json
3384 lines (3384 loc) · 122 KB
/
config_schema.json
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
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"title": "config.json",
"$ref": "#/$defs/SerializedContinueConfig",
"$defs": {
"BaseCompletionOptions": {
"title": "BaseCompletionOptions",
"type": "object",
"properties": {
"stream": {
"title": "Stream",
"description": "Whether to stream the LLM response. Currently only respected by the 'anthropic' provider. Otherwise will always stream.",
"type": "boolean",
"default": true
},
"temperature": {
"title": "Temperature",
"description": "The temperature of the completion.",
"type": "number"
},
"topP": {
"title": "Top P",
"description": "The topP of the completion.",
"type": "number"
},
"topK": {
"title": "Top K",
"description": "The topK of the completion.",
"type": "integer"
},
"presencePenalty": {
"title": "Presence Penalty",
"description": "The presence penalty Aof the completion.",
"type": "number"
},
"frequencePenalty": {
"title": "Frequency Penalty",
"description": "The frequency penalty of the completion.",
"type": "number"
},
"mirostat": {
"title": "Mirostat",
"description": "Enable Mirostat sampling, controlling perplexity during text generation (default: 0, 0 = disabled, 1 = Mirostat, 2 = Mirostat 2.0). Only available for Ollama, LM Studio, and llama.cpp providers",
"type": "number"
},
"stop": {
"title": "Stop",
"description": "The stop tokens of the completion.",
"type": "array",
"items": {
"type": "string"
}
},
"maxTokens": {
"title": "Max Tokens",
"description": "The maximum number of tokens to generate.",
"default": 600,
"type": "integer"
},
"numThreads": {
"title": "Number of threads",
"description": "The number of threads used in the generation process. Only available for Ollama (this is the num_thread parameter)",
"type": "integer"
},
"useMmap": {
"title": "Use Memory Map",
"description": "Allows the model to be mapped into memory. If disabled can enhance response time on low end devices. Only available for Ollama (this is the use_mmap parameter)",
"type": "boolean"
},
"keepAlive": {
"title": "Ollama keep_alive",
"description": "The number of seconds after no requests are made to unload the model from memory. Defaults to 60*30 = 30min",
"type": "integer"
}
}
},
"ClientCertificateOptions": {
"title": "ClientCertificateOptions",
"type": "object",
"properties": {
"cert": {
"title": "Cert Path",
"description": "Path to the client certificate file",
"type": "string"
},
"key": {
"title": "Key Path",
"description": "Path to the client certificate key file",
"type": "string"
},
"passphrase": {
"title": "Passphrase",
"description": "Passphrase for the client certificate key file",
"type": "string"
}
},
"required": ["cert", "key"]
},
"RequestOptions": {
"title": "RequestOptions",
"type": "object",
"properties": {
"timeout": {
"title": "Timeout",
"description": "Set the timeout for each request to the LLM. If you are running a local LLM that takes a while to respond, you might want to set this to avoid timeouts.",
"default": 7200,
"type": "integer"
},
"verifySsl": {
"title": "Verify Ssl",
"description": "Whether to verify SSL certificates for requests.",
"type": "boolean"
},
"caBundlePath": {
"title": "Ca Bundle Path",
"description": "Path to a custom CA bundle to use when making the HTTP request",
"anyOf": [
{
"type": "string"
},
{
"type": "array",
"items": {
"type": "string"
}
}
]
},
"proxy": {
"title": "Proxy",
"description": "Proxy URL to use when making the HTTP request",
"type": "string"
},
"headers": {
"title": "Headers",
"description": "Headers to use when making the HTTP request",
"type": "object",
"additionalProperties": {
"type": "string"
}
},
"extraBodyProperties": {
"title": "Extra Body Properties",
"description": "This object will be merged with the body when making the HTTP requests",
"type": "object"
},
"noProxy": {
"title": "No Proxy",
"description": "A list of hostnames for which Continue should not use the proxy specified in requestOptions.proxy",
"type": "array",
"items": {
"type": "string"
}
},
"clientCertificate": {
"title": "Client Certificate",
"description": "Client certificate to use when making the HTTP request",
"$ref": "#/$defs/ClientCertificateOptions"
}
}
},
"ModelDescription": {
"title": "ModelDescription",
"type": "object",
"properties": {
"title": {
"title": "Title",
"description": "The title you wish to give your model.",
"type": "string"
},
"provider": {
"title": "Provider",
"description": "The provider of the model. This is used to determine the type of model, and how to interact with it.",
"enum": [
"openai",
"free-trial",
"anthropic",
"cohere",
"bedrock",
"bedrockimport",
"sagemaker",
"together",
"novita",
"ollama",
"huggingface-tgi",
"huggingface-inference-api",
"llama.cpp",
"replicate",
"gemini",
"lmstudio",
"llamafile",
"mistral",
"deepinfra",
"groq",
"fireworks",
"cloudflare",
"deepseek",
"azure",
"msty",
"watsonx",
"openrouter",
"sambanova",
"nvidia",
"vllm",
"cerebras",
"askSage",
"nebius",
"vertexai",
"xAI",
"kindo",
"moonshot",
"siliconflow",
"function-network",
"scaleway"
],
"markdownEnumDescriptions": [
"### OpenAI\nUse gpt-4, gpt-3.5-turbo, or any other OpenAI model. See [here](https://openai.com/product#made-for-developers) to obtain an API key.\n\n> [Reference](https://docs.continue.dev/reference/Model%20Providers/openai)",
"### Free Trial\nNew users can try out Continue for free using a proxy server that securely makes calls to OpenAI using our API key. If you are ready to use your own API key or have used all 250 free uses, you can enter your API key in config.json where it says `apiKey=\"\"` or select another model provider.\n> [Reference](https://docs.continue.dev/reference/Model%20Providers/freetrial)",
"### Anthropic\nTo get started with Anthropic models, you first need to sign up for the open beta [here](https://claude.ai/login) to obtain an API key.\n> [Reference](https://docs.continue.dev/reference/Model%20Providers/anthropicllm)",
"### Anthropic Vertex AI\nTo get started you need to enable the [Vertex AI API](https://console.cloud.google.com/marketplace/product/google/aiplatform.googleapis.com) and set up the [Google Application Default Credentials](https://cloud.google.com/docs/authentication/provide-credentials-adc).",
"### Cohere\nTo use Cohere, visit the [Cohere dashboard](https://dashboard.cohere.com/api-keys) to create an API key.\n\n> [Reference](https://docs.continue.dev/reference/Model%20Providers/cohere)",
"### Bedrock\nTo get started with Bedrock you need to sign up on AWS [here](https://aws.amazon.com/bedrock)",
"### Bedrock Imported Models\nTo get started with Bedrock you need to sign up on AWS [here](https://aws.amazon.com/bedrock)",
"### Sagemaker\nSagemaker is AWS' machine learning platform.",
"### Together\nTogether is a hosted service that provides extremely fast streaming of open-source language models. To get started with Together:\n1. Obtain an API key from [here](https://together.ai)\n2. Paste below\n3. Select a model preset\n> [Reference](https://docs.continue.dev/reference/Model%20Providers/togetherllm)",
"### Novita AI\n[Novita AI](https://novita.ai?utm_source=github_continuedev&utm_medium=github_readme&utm_campaign=github_link) offers an affordable, reliable, and simple inference platform with scalable [LLM APIs](https://novita.ai/docs/model-api/reference/introduction.html), empowering developers to build AI applications. To get started with Novita AI:\n1. Obtain an API key from [here](https://novita.ai/settings/key-management?utm_source=github_continuedev&utm_medium=github_readme&utm_campaign=github_link)\n2. Paste below\n3. Select a model preset\n> [Reference](https://docs.continue.dev/reference/Model%20Providers/novita)",
"### Ollama\nTo get started with Ollama, follow these steps:\n1. Download from [ollama.ai](https://ollama.ai/) and open the application\n2. Open a terminal and run `ollama run <MODEL_NAME>`. Example model names are `codellama:7b-instruct` or `llama2:7b-text`. You can find the full list [here](https://ollama.ai/library).\n3. Make sure that the model name used in step 2 is the same as the one in config.json (e.g. `model=\"codellama:7b-instruct\"`)\n4. Once the model has finished downloading, you can start asking questions through Continue.\n> [Reference](https://docs.continue.dev/reference/Model%20Providers/ollama)",
"### Huggingface TGI\n\n> [Reference](https://docs.continue.dev/reference/Model%20Providers/huggingfacetgi)",
"### Huggingface Inference API\n\n> [Reference](https://docs.continue.dev/reference/Model%20Providers/huggingfaceinferenceapi)",
"### Llama.cpp\nllama.cpp comes with a [built-in server](https://github.com/ggerganov/llama.cpp/tree/master/examples/server#llamacppexampleserver) that can be run from source. To do this:\n\n1. Clone the repository with `git clone https://github.com/ggerganov/llama.cpp`.\n2. `cd llama.cpp`\n3. Run `make` to build the server.\n4. Download the model you'd like to use and place it in the `llama.cpp/models` directory (the best place to find models is [The Bloke on HuggingFace](https://huggingface.co/TheBloke))\n5. Run the llama.cpp server with the command below (replacing with the model you downloaded):\n\n```shell\n.\\server.exe -c 4096 --host 0.0.0.0 -t 16 --mlock -m models/codellama-7b-instruct.Q8_0.gguf\n```\n\nAfter it's up and running, you can start using Continue.\n> [Reference](https://docs.continue.dev/reference/Model%20Providers/llamacpp)",
"### Replicate\nReplicate is a hosted service that makes it easy to run ML models. To get started with Replicate:\n1. Obtain an API key from [here](https://replicate.com)\n2. Paste below\n3. Select a model preset\n> [Reference](https://docs.continue.dev/reference/Model%20Providers/replicatellm)",
"### Gemini API\nTo get started with Google Makersuite, obtain your API key from [here](https://makersuite.google.com) and paste it below.\n> [Reference](https://docs.continue.dev/reference/Model%20Providers/geminiapi)",
"### Gemini API on Vertex AI\nTo get started you need to enable the [Vertex AI API](https://console.cloud.google.com/marketplace/product/google/aiplatform.googleapis.com) and set up the [Google Application Default Credentials](https://cloud.google.com/docs/authentication/provide-credentials-adc).",
"### LMStudio\nLMStudio provides a professional and well-designed GUI for exploring, configuring, and serving LLMs. It is available on both Mac and Windows. To get started:\n1. Download from [lmstudio.ai](https://lmstudio.ai/) and open the application\n2. Search for and download the desired model from the home screen of LMStudio.\n3. In the left-bar, click the '<->' icon to open the Local Inference Server and press 'Start Server'.\n4. Once your model is loaded and the server has started, you can begin using Continue.\n> [Reference](https://docs.continue.dev/reference/Model%20Providers/lmstudio)",
"### Llamafile\nTo get started with llamafiles, find and download a binary on their [GitHub repo](https://github.com/Mozilla-Ocho/llamafile#binary-instructions). Then run it with the following command:\n\n```shell\nchmod +x ./llamafile\n./llamafile\n```\n> [Reference](https://docs.continue.dev/reference/Model%20Providers/llamafile)",
"### Mistral API\n\nTo get access to the Mistral API, obtain your API key from the [Mistral platform](https://docs.mistral.ai/)",
"### Mistral API on Vertex AI\nTo get started you need to enable the [Vertex AI API](https://console.cloud.google.com/marketplace/product/google/aiplatform.googleapis.com) and set up the [Google Application Default Credentials](https://cloud.google.com/docs/authentication/provide-credentials-adc).",
"### DeepInfra\n\n> [Reference](https://docs.continue.dev/reference/Model%20Providers/deepinfra)",
"### Groq\nGroq provides extremely fast inference of open-source language models. To get started, obtain an API key from [their console](https://console.groq.com/keys).",
"### Fireworks\nFireworks is a fast inference engine for open-source language models. To get started, obtain an API key from [their console](https://fireworks.ai/api-keys).",
"### Cloudflare Workers AI\n\n[Reference](https://developers.cloudflare.com/workers-ai/)",
"### Deepseek\n Deepseek's API provides the best pricing for their state-of-the-art Deepseek Coder models. To get started, obtain an API key from [their console](https://platform.deepseek.com/api_keys)",
"### Azure OpenAI\n Azure OpenAI lets you securely run OpenAI's models on Azure. To get started, follow the steps [here](https://docs.continue.dev/reference/Model%20Providers/azure)",
"### Msty\nMsty is the simplest way to get started with online or local LLMs on all desktop platforms - Windows, Mac, and Linux. No fussing around, one-click and you are up and running. To get started, follow these steps:\n1. Download from [Msty.app](https://msty.app/), open the application, and click 'Setup Local AI'.\n2. Go to the Local AI Module page and download a model of your choice.\n3. Once the model has finished downloading, you can start asking questions through Continue.\n> [Reference](https://continue.dev/docs/reference/Model%20Providers/Msty)",
"### IBM watsonx\nwatsonx, developed by IBM, offers a variety of pre-trained AI foundation models that can be used for natural language processing (NLP), computer vision, and speech recognition tasks.",
"### OpenRouter\nOpenRouter offers a single API to access almost any language model. To get started, obtain an API key from [their console](https://openrouter.ai/settings/keys).",
"### NVIDIA NIMs\nNVIDIA offers a single API to access almost any language model. To find out more, visit the [LLM APIs Documentation](https://docs.api.nvidia.com/nim/reference/llm-apis).\nFor information specific to getting a key, please check out the [docs here](https://docs.nvidia.com/nim/large-language-models/latest/getting-started.html#option-1-from-api-catalog)",
"### vLLM\nvLLM is a highly performant way of hosting LLMs for a team. To get started, follow their [quickstart](https://docs.vllm.ai/en/latest/getting_started/quickstart.html) to set up your server.",
"### Cerebras\nCerebras Inference uses specialized silicon to provides superfast inference. To get started, get your API keys from [their console](https://cloud.cerebras.ai/).",
"### Ask Sage\nAsk Sage is an agnostic hosted service that provides language models. To get started with Ask Sage:\n1. Obtain an API key from your account. For more information, visit [Ask Sage](https://docs.asksage.ai/).\n2. Paste the API key below.\n3. Select a model preset.\n> [Reference](https://docs.asksage.ai/)",
"### xAI offers a world class developer tool set to build scalable applications powered by Grok. To get started, obtain an API key from [the x Console](https://console.x.ai/), and see the [docs](https://docs.x.ai/docs/)",
"### Secure AI management software that helps enterprises adopt and manage AI across their workforce. To get started, obtain an API key from [the Kindo console](https://app.kindo.ai/settings/api), and see the [website](https://app.kindo.ai//)",
"### Moonshot\nTo get started with Moonshot AI, obtain your API key from [Moonshot AI](https://platform.moonshot.cn/). Moonshot AI provides high-quality large language models with competitive pricing.\n> [Reference](https://platform.moonshot.cn/docs/api)",
"### SiliconFlow\nTo get started with SiliconFlow, obtain your API key from [SiliconCloud](https://cloud.siliconflow.cn/account/ak). SiliconCloud provides cost-effective GenAI services based on excellent open source basic models.\n> [Models](https://siliconflow.cn/zh-cn/models)",
"### Function Network offers private, affordable user-owned AI\nTo get started with Function Network, obtain your API key from [Function Network](https://www.function.network/join-waitlist). Function Network provides a variety of models for chat, completion, and embeddings.",
"### Scaleway\n Generative APIs are serverless endpoints for the most popular AI models.\nHosted in European data centers and priced competitively per million tokens used, models served by Scaleway are ideal for users requiring low latency, full data privacy, and 100% compliance with EU AI Act. To get access to the Scaleway Generative APIs, read the [Quickstart guide](https://www.scaleway.com/en/docs/ai-data/generative-apis/quickstart/) and get a [valid API key](https://www.scaleway.com/en/docs/identity-and-access-management/iam/how-to/create-api-keys/)."
],
"type": "string"
},
"model": {
"title": "Model",
"description": "The name of the model. Used to autodetect prompt template.",
"type": "string"
},
"apiKey": {
"title": "Api Key",
"description": "OpenAI, Anthropic, Cohere, Together, Novita AI, or other API key",
"type": "string"
},
"apiBase": {
"title": "Api Base",
"description": "The base URL of the LLM API.",
"type": "string"
},
"region": {
"title": "Region",
"description": "The region where the model is hosted",
"anyOf": [
{
"enum": [
"us-east-1",
"us-east-2",
"us-west-1",
"us-west-2",
"eu-west-1",
"eu-central-1",
"ap-southeast-1",
"ap-northeast-1",
"ap-south-1",
"us-central1",
"us-east1",
"us-east4",
"us-east5",
"us-west1",
"us-west4",
"us-south1",
"northamerica-northeast1",
"southamerica-east1",
"europe-central2",
"europe-north1",
"europe-west1",
"europe-west2",
"europe-west3",
"europe-west4",
"europe-west6",
"europe-west8",
"europe-west9",
"europe-southwest1",
"asia-east1",
"asia-east2",
"asia-south1",
"asia-northeast1",
"asia-northeast3",
"asia-southeast1",
"australia-southeast1",
"me-central1",
"me-central2",
"me-west1"
],
"type": "string"
},
{
"type": "string"
}
]
},
"profile": {
"title": "Profile",
"description": "The AWS security profile to use",
"type": "string"
},
"modelArn": {
"title": "Profile",
"description": "The AWS arn for the imported model",
"type": "string"
},
"contextLength": {
"title": "Context Length",
"description": "The maximum context length of the LLM in tokens, as counted by countTokens.",
"default": 2048,
"type": "integer"
},
"maxStopWords": {
"title": "Max Stop Words",
"description": "The maximum number of stop words that the API will accept. You can set this if you are receiving an error about the number of stop words, but otherwise should leave it undefined.",
"type": "integer"
},
"template": {
"title": "Template",
"description": "The chat template used to format messages. This is auto-detected for most models, but can be overridden here. Choose none if you are using vLLM or another server that automatically handles prompting.",
"enum": [
"llama2",
"alpaca",
"zephyr",
"phi2",
"phind",
"anthropic",
"chatml",
"none",
"deepseek",
"openchat",
"xwin-coder",
"neural-chat",
"codellama-70b",
"llava",
"gemma",
"llama3"
],
"type": "string"
},
"promptTemplates": {
"title": "Prompt Templates",
"markdownDescription": "A mapping of prompt template name ('edit' is currently the only one used in Continue) to a string giving the prompt template. See [here](https://docs.continue.dev/model-setup/configuration#customizing-the-edit-prompt) for an example.",
"x-intellij-html-description": "A mapping of prompt template name ('edit' is currently the only one used in Continue) to a string giving the prompt template. See <a href='https://docs.continue.dev/model-setup/configuration#customizing-the-edit-prompt'>here</a> for an example.",
"type": "object",
"additionalProperties": {
"type": "string"
}
},
"completionOptions": {
"title": "Completion Options",
"description": "Options for the completion endpoint. Read more about the completion options in the documentation.",
"default": {
"temperature": null,
"topP": null,
"topK": null,
"presencePenalty": null,
"frequencyPenalty": null,
"stop": null,
"maxTokens": 2048
},
"allOf": [
{
"$ref": "#/$defs/BaseCompletionOptions"
}
]
},
"systemMessage": {
"title": "System Message",
"description": "A system message that will always be followed by the LLM",
"type": "string"
},
"requestOptions": {
"title": "Request Options",
"description": "Options for the HTTP request to the LLM.",
"default": {
"timeout": 7200,
"verifySsl": null,
"caBundlePath": null,
"proxy": null,
"headers": null,
"extraBodyProperties": null
},
"allOf": [
{
"$ref": "#/$defs/RequestOptions"
}
]
},
"apiType": {
"title": "Api Type",
"markdownDescription": "OpenAI API type, either `openai` or `azure`",
"x-intellij-html-description": "OpenAI API type, either <code>openai</code> or <code>azure</code>",
"enum": ["openai", "azure"]
},
"apiVersion": {
"title": "Api Version",
"description": "Azure OpenAI API version (e.g. 2023-07-01-preview)",
"type": "string"
},
"deployment": {
"title": "Deployment",
"description": "Azure OpenAI deployment",
"type": "string"
},
"capabilities": {
"type": "object",
"description": "We will attempt to automatically detect the capabilities of the model based on its title and provider, but this may not always be accurate. You can override the model's capabilities here.",
"properties": {
"uploadImage": {
"type": "boolean",
"description": "Indicates whether the model can upload images."
}
}
}
},
"required": ["title", "provider", "model"],
"allOf": [
{
"if": {
"properties": {
"provider": {
"type": "str"
}
},
"not": {
"required": ["provider"]
}
},
"then": {
"properties": {
"model": {
"description": "Choose a provider first, then model options will be shown here."
}
}
}
},
{
"if": {
"properties": {
"provider": {
"enum": [
"openai",
"anthropic",
"cohere",
"gemini",
"huggingface-inference-api",
"replicate",
"together",
"novita",
"cloudflare",
"sambanova",
"nebius",
"xAI",
"kindo",
"scaleway"
]
}
},
"required": ["provider"]
},
"then": {
"required": ["apiKey"]
}
},
{
"if": {
"properties": {
"provider": {
"enum": ["bedrockimport"]
}
},
"required": ["provider"]
},
"then": {
"required": ["modelArn"]
}
},
{
"if": {
"properties": {
"provider": {
"enum": ["huggingface-tgi", "huggingface-inference-api"]
}
}
},
"then": {
"required": ["apiBase"]
},
"required": ["provider"]
},
{
"if": {
"properties": {
"provider": {
"enum": ["openai"]
}
},
"required": ["provider"]
},
"then": {
"properties": {
"deployment": {
"type": "string"
},
"apiType": {
"type": "string"
},
"apiVersion": {
"type": "string"
}
}
}
},
{
"if": {
"properties": {
"provider": {
"enum": ["cloudflare"]
}
},
"required": ["provider"]
},
"then": {
"properties": {
"accountId": {
"type": "string"
},
"aiGatewaySlug": {
"type": "string"
},
"model": {
"anyOf": [
{
"enum": [
"@cf/meta/llama-3-8b-instruct",
"@hf/thebloke/deepseek-coder-6.7b-instruct-awq",
"@cf/deepseek-ai/deepseek-math-7b-instruct",
"@cf/thebloke/discolm-german-7b-v1-awq",
"@cf/tiiuae/falcon-7b-instruct",
"@cf/google/gemma-2b-it-lora",
"@hf/google/gemma-7b-it",
"@cf/google/gemma-7b-it-lora",
"@hf/nousresearch/hermes-2-pro-mistral-7b",
"@cf/meta/llama-2-7b-chat-fp16",
"@cf/meta/llama-2-7b-chat-int8",
"@cf/meta-llama/llama-2-7b-chat-hf-lora",
"@hf/thebloke/llama-2-13b-chat-awq",
"@hf/thebloke/llamaguard-7b-awq",
"@cf/mistral/mistral-7b-instruct-v0.1",
"@hf/mistral/mistral-7b-instruct-v0.2",
"@cf/mistral/mistral-7b-instruct-v0.2-lora",
"@hf/thebloke/neural-chat-7b-v3-1-awq",
"@cf/openchat/openchat-3.5-0106",
"@hf/thebloke/openhermes-2.5-mistral-7b-awq",
"@cf/microsoft/phi-2",
"@cf/qwen/qwen1.5-0.5b-chat",
"@cf/qwen/qwen1.5-1.8b-chat",
"@cf/qwen/qwen1.5-7b-chat-awq",
"@cf/qwen/qwen1.5-14b-chat-awq",
"@cf/defog/sqlcoder-7b-2",
"@hf/nexusflow/starling-lm-7b-beta",
"@cf/tinyllama/tinyllama-1.1b-chat-v1.0",
"@hf/thebloke/zephyr-7b-beta-awq",
"@hf/thebloke/deepseek-coder-6.7b-base-awq"
]
},
{
"type": "string"
}
]
}
}
}
},
{
"if": {
"properties": {
"provider": {
"enum": ["openai"]
}
},
"required": ["provider"]
},
"then": {
"properties": {
"model": {
"anyOf": [
{
"enum": [
"gpt-3.5-turbo",
"gpt-3.5-turbo-16k",
"gpt-4o",
"gpt-4o-mini",
"gpt-4",
"gpt-3.5-turbo-0613",
"gpt-4-32k",
"gpt-4-0125-preview",
"gpt-4-turbo",
"AUTODETECT"
]
},
{
"type": "string"
}
]
}
}
}
},
{
"if": {
"properties": {
"provider": {
"enum": ["xAI"]
}
},
"required": ["provider"]
},
"then": {
"properties": {
"model": {
"anyOf": [
{
"enum": ["grok-beta", "AUTODETECT"]
},
{
"type": "string"
}
]
}
}
}
},
{
"if": {
"properties": {
"provider": {
"enum": ["replicate"]
}
},
"required": ["provider"]
},
"then": {
"properties": {
"model": {
"anyOf": [
{
"enum": [
"llama3.1-8b",
"llama3.1-70b",
"llama3.1-405b",
"llama3-8b",
"llama3-70b",
"codellama-7b",
"codellama-13b",
"codellama-34b",
"llama2-7b",
"llama2-13b"
]
},
{
"type": "string"
}
]
},
"markdownDescription": "Select a pre-defined option, or find an exact model ID from Replicate [here](https://replicate.com/collections/streaming-language-models).",
"x-intellij-html-description": "Select a pre-defined option, or find an exact model ID from Replicate <a href='https://replicate.com/collections/streaming-language-models'>here</a>."
}
}
},
{
"if": {
"properties": {
"provider": {
"enum": ["free-trial"]
}
},
"required": ["provider"]
},
"then": {
"properties": {
"model": {
"enum": [
"gpt-4o",
"codestral-latest",
"llama3.1-70b",
"llama3.1-405b",
"gpt-3.5-turbo",
"gemini-pro",
"claude-3-5-sonnet-latest",
"claude-3-haiku-20240307",
"AUTODETECT"
]
}
}
}
},
{
"if": {
"properties": {
"provider": {
"enum": ["openai"]
},
"apiType": {
"not": {
"const": "azure"
}
}
},
"required": ["provider"]
},
"then": {
"properties": {
"model": {
"anyOf": [
{
"enum": [
"gpt-3.5-turbo",
"gpt-3.5-turbo-16k",
"gpt-4o",
"gpt-4o-mini",
"gpt-4",
"gpt-3.5-turbo-0613",
"gpt-4-32k",
"gpt-4-turbo",
"gpt-4-vision-preview",
"mistral-7b",
"mistral-8x7b",
"llama2-7b",
"llama2-13b",
"codellama-7b",
"codellama-13b",
"codellama-34b",
"codellama-70b",
"llama3-8b",
"llama3-70b",
"llama3.1-8b",
"llama3.1-70b",
"llama3.1-405b",
"phind-codellama-34b",
"wizardcoder-7b",
"wizardcoder-13b",
"wizardcoder-34b",
"zephyr-7b",
"codeup-13b",
"deepseek-7b",
"deepseek-33b",
"neural-chat-7b",
"deepseek-1b",
"stable-code-3b",
"starcoder-1b",
"starcoder-3b",
"starcoder2-3b",
"mistral-tiny",
"mistral-small",
"mistral-medium",
"qwen2.5-coder:1.5b",
"qwen2.5-coder:3b",
"qwen2.5-coder:7b",
"qwen2.5-coder:14b",
"qwen2.5-coder:32b",
"AUTODETECT"
]
},
{
"type": "string"
}
]
}
}
}
},
{
"if": {
"properties": {
"provider": {
"enum": ["anthropic"]
}
},
"required": ["provider"]
},
"then": {
"properties": {
"cacheBehavior": {
"title": "Caching Behavior",
"description": "Options for the prompt caching",
"properties": {
"cacheSystemMessage": {
"type": "boolean"
},
"cacheConversation": {
"type": "boolean"
}
}
},
"model": {
"anyOf": [
{
"enum": [
"claude-2",
"claude-instant-1",
"claude-3-5-sonnet-latest",
"claude-3-opus-20240229",
"claude-3-sonnet-20240229",
"claude-3-haiku-20240307",
"claude-2.1"
]
},
{
"type": "string"
}
]
}
}
}
},
{
"if": {
"properties": {
"provider": {
"enum": ["cohere"]
}
},
"required": ["provider"]
},
"then": {
"properties": {
"model": {
"enum": ["command-r", "command-r-plus"]
}
}
}
},
{
"if": {
"properties": {
"provider": {
"enum": ["bedrock"]
}
},
"required": ["provider"]
},
"then": {
"properties": {
"model": {
"anyOf": [
{
"enum": [
"claude-3-sonnet-20240229",
"claude-3-haiku-20240307",
"claude-2"
]
},
{
"type": "string"
}
]
}
}
}
},
{
"if": {
"properties": {
"provider": {
"enum": ["sagemaker"]
}
},
"required": ["provider"]
},
"then": {
"properties": {
"model": {
"description": "SageMaker endpoint name"
}
}
}
},
{
"if": {
"properties": {
"provider": {
"enum": ["gemini"]
}
},
"required": ["provider"]
},
"then": {
"properties": {
"cacheBehavior": {
"title": "Caching Behavior",
"description": "Options for the prompt caching",
"properties": {
"cacheSystemMessage": {
"type": "boolean"
}
}
},
"model": {
"enum": [
"chat-bison-001",
"gemini-pro",
"gemini-1.5-pro-latest",
"gemini-1.5-pro",
"gemini-1.5-flash-latest",
"gemini-1.5-flash",
"gemini-1.5-flash-8b",
"gemini-2.0-flash-exp",
"gemini-2.0-flash"
]
}
}
}
},
{
"if": {
"properties": {
"provider": {
"enum": ["together"]
}
},
"required": ["provider"]
},
"then": {
"properties": {
"model": {
"anyOf": [
{
"enum": [
"mistral-7b",
"mistral-8x7b",
"llama2-7b",
"llama2-13b",
"llama3-8b",
"llama3-70b",
"llama3.1-8b",
"llama3.1-70b",
"llama3.1-405b",
"codellama-7b",
"codellama-13b",
"codellama-34b",
"codellama-70b",
"phind-codellama-34b"
]
},
{
"type": "string"
}
],
"markdownDescription": "Select a pre-defined option, or find an exact model string from Together AI [here](https://docs.together.ai/docs/inference-models).",
"x-intellij-html-description": "Select a pre-defined option, or find an exact model string from Together AI <a href='https://docs.together.ai/docs/inference-models'>here</a>."
}
}
}
},
{
"if": {
"properties": {
"provider": {
"enum": ["novita"]
}
},
"required": ["provider"]
},
"then": {
"properties": {
"model": {
"anyOf": [
{