gcore 0.4.0__py3-none-any.whl → 0.6.0__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Potentially problematic release.


This version of gcore might be problematic. Click here for more details.

Files changed (145) hide show
  1. gcore/_base_client.py +9 -2
  2. gcore/_client.py +9 -0
  3. gcore/_constants.py +2 -2
  4. gcore/_models.py +8 -5
  5. gcore/_version.py +1 -1
  6. gcore/pagination.py +192 -1
  7. gcore/resources/__init__.py +14 -0
  8. gcore/resources/cloud/__init__.py +14 -0
  9. gcore/resources/cloud/audit_logs.py +480 -0
  10. gcore/resources/cloud/baremetal/servers.py +2 -2
  11. gcore/resources/cloud/cloud.py +32 -0
  12. gcore/resources/cloud/file_shares/file_shares.py +64 -9
  13. gcore/resources/cloud/gpu_baremetal_clusters/gpu_baremetal_clusters.py +2 -2
  14. gcore/resources/cloud/inference/__init__.py +14 -0
  15. gcore/resources/cloud/inference/api_keys.py +621 -0
  16. gcore/resources/cloud/inference/deployments/deployments.py +66 -33
  17. gcore/resources/cloud/inference/deployments/logs.py +7 -7
  18. gcore/resources/cloud/inference/inference.py +37 -5
  19. gcore/resources/cloud/inference/models.py +16 -15
  20. gcore/resources/cloud/inference/registry_credentials.py +16 -16
  21. gcore/resources/cloud/inference/secrets.py +4 -5
  22. gcore/resources/cloud/instances/instances.py +2 -2
  23. gcore/resources/cloud/load_balancers/pools/members.py +22 -6
  24. gcore/resources/cloud/secrets.py +14 -224
  25. gcore/resources/cloud/tasks.py +30 -28
  26. gcore/resources/fastedge/__init__.py +103 -0
  27. gcore/resources/fastedge/apps/__init__.py +33 -0
  28. gcore/resources/fastedge/apps/apps.py +932 -0
  29. gcore/resources/fastedge/apps/logs.py +248 -0
  30. gcore/resources/fastedge/binaries.py +286 -0
  31. gcore/resources/fastedge/fastedge.py +327 -0
  32. gcore/resources/fastedge/kv_stores.py +523 -0
  33. gcore/resources/fastedge/secrets.py +687 -0
  34. gcore/resources/fastedge/statistics.py +347 -0
  35. gcore/resources/fastedge/templates.py +652 -0
  36. gcore/types/cloud/__init__.py +4 -28
  37. gcore/types/cloud/audit_log_entry.py +254 -0
  38. gcore/types/cloud/audit_log_list_params.py +158 -0
  39. gcore/types/cloud/baremetal/server_create_params.py +1 -1
  40. gcore/types/cloud/file_share_update_params.py +29 -3
  41. gcore/types/cloud/gpu_baremetal_cluster_create_params.py +1 -1
  42. gcore/types/cloud/inference/__init__.py +17 -8
  43. gcore/types/cloud/inference/api_key_create_params.py +21 -0
  44. gcore/types/cloud/inference/api_key_list_params.py +21 -0
  45. gcore/types/cloud/inference/api_key_update_params.py +16 -0
  46. gcore/types/cloud/inference/deployment_create_params.py +224 -7
  47. gcore/types/cloud/inference/deployment_update_params.py +24 -3
  48. gcore/types/cloud/inference/deployments/__init__.py +1 -0
  49. gcore/types/cloud/inference/{inference_log.py → deployments/inference_deployment_log.py} +3 -3
  50. gcore/types/cloud/inference/inference_api_key.py +24 -0
  51. gcore/types/cloud/inference/inference_api_key_create.py +27 -0
  52. gcore/types/cloud/inference/inference_deployment.py +266 -0
  53. gcore/types/cloud/inference/{inference_apikey_secret.py → inference_deployment_api_key.py} +2 -2
  54. gcore/types/cloud/inference/{mlcatalog_model_card.py → inference_model.py} +2 -2
  55. gcore/types/cloud/inference/{inference_registry_credential.py → inference_registry_credentials.py} +2 -2
  56. gcore/types/cloud/inference/{inference_registry_credential_full.py → inference_registry_credentials_create.py} +2 -2
  57. gcore/types/cloud/inference/inference_secret.py +10 -3
  58. gcore/types/cloud/inference/model_list_params.py +2 -4
  59. gcore/types/cloud/{container_probe.py → inference/probe.py} +9 -9
  60. gcore/types/cloud/{container_probe_config.py → inference/probe_config.py} +5 -5
  61. gcore/types/cloud/{container_probe_exec.py → inference/probe_exec.py} +3 -3
  62. gcore/types/cloud/{container_probe_http_get.py → inference/probe_http_get.py} +3 -3
  63. gcore/types/cloud/{container_probe_tcp_socket.py → inference/probe_tcp_socket.py} +3 -3
  64. gcore/types/cloud/inference/secret_create_params.py +10 -4
  65. gcore/types/cloud/inference/secret_replace_params.py +10 -4
  66. gcore/types/cloud/{region_capacity.py → inference_region_capacity.py} +10 -3
  67. gcore/types/cloud/{region_capacity_list.py → inference_region_capacity_list.py} +4 -4
  68. gcore/types/cloud/instance_create_params.py +1 -1
  69. gcore/types/cloud/load_balancer_create_params.py +14 -3
  70. gcore/types/cloud/load_balancers/pool_create_params.py +14 -3
  71. gcore/types/cloud/load_balancers/pool_update_params.py +14 -3
  72. gcore/types/cloud/load_balancers/pools/member_add_params.py +14 -3
  73. gcore/types/cloud/member.py +12 -4
  74. gcore/types/cloud/task_list_params.py +15 -14
  75. gcore/types/fastedge/__init__.py +48 -0
  76. gcore/types/fastedge/app.py +81 -0
  77. gcore/types/fastedge/app_create_params.py +56 -0
  78. gcore/types/fastedge/app_list_params.py +50 -0
  79. gcore/types/fastedge/app_param.py +56 -0
  80. gcore/types/fastedge/app_replace_params.py +17 -0
  81. gcore/types/fastedge/app_short.py +60 -0
  82. gcore/types/fastedge/app_update_params.py +56 -0
  83. gcore/types/fastedge/apps/__init__.py +6 -0
  84. gcore/types/fastedge/apps/log.py +28 -0
  85. gcore/types/fastedge/apps/log_list_params.py +37 -0
  86. gcore/types/fastedge/binary.py +40 -0
  87. gcore/types/fastedge/binary_list_response.py +12 -0
  88. gcore/types/fastedge/binary_short.py +32 -0
  89. gcore/types/fastedge/call_status.py +24 -0
  90. gcore/types/fastedge/client.py +57 -0
  91. gcore/types/fastedge/duration_stats.py +30 -0
  92. gcore/types/fastedge/kv_store.py +33 -0
  93. gcore/types/fastedge/kv_store_create_params.py +23 -0
  94. gcore/types/fastedge/kv_store_get_response.py +10 -0
  95. gcore/types/fastedge/kv_store_list_params.py +12 -0
  96. gcore/types/fastedge/kv_store_list_response.py +15 -0
  97. gcore/types/fastedge/kv_store_replace_params.py +23 -0
  98. gcore/types/fastedge/kv_store_short.py +19 -0
  99. gcore/types/fastedge/kv_store_stats.py +26 -0
  100. gcore/types/fastedge/secret.py +29 -0
  101. gcore/types/fastedge/secret_create_params.py +27 -0
  102. gcore/types/fastedge/secret_create_response.py +12 -0
  103. gcore/types/fastedge/secret_delete_params.py +12 -0
  104. gcore/types/fastedge/secret_list_params.py +15 -0
  105. gcore/types/{cloud → fastedge}/secret_list_response.py +2 -6
  106. gcore/types/fastedge/secret_replace_params.py +27 -0
  107. gcore/types/fastedge/secret_short.py +21 -0
  108. gcore/types/fastedge/secret_update_params.py +27 -0
  109. gcore/types/fastedge/statistic_get_call_series_params.py +28 -0
  110. gcore/types/fastedge/statistic_get_call_series_response.py +12 -0
  111. gcore/types/fastedge/statistic_get_duration_series_params.py +28 -0
  112. gcore/types/fastedge/statistic_get_duration_series_response.py +12 -0
  113. gcore/types/fastedge/template.py +31 -0
  114. gcore/types/fastedge/template_create_params.py +30 -0
  115. gcore/types/fastedge/template_delete_params.py +12 -0
  116. gcore/types/fastedge/template_list_params.py +25 -0
  117. gcore/types/fastedge/template_parameter.py +22 -0
  118. gcore/types/fastedge/template_parameter_param.py +21 -0
  119. gcore/types/fastedge/template_replace_params.py +30 -0
  120. gcore/types/fastedge/template_short.py +27 -0
  121. {gcore-0.4.0.dist-info → gcore-0.6.0.dist-info}/METADATA +8 -7
  122. {gcore-0.4.0.dist-info → gcore-0.6.0.dist-info}/RECORD +124 -80
  123. gcore/types/cloud/aws_iam_data.py +0 -13
  124. gcore/types/cloud/aws_iam_data_param.py +0 -15
  125. gcore/types/cloud/capacity.py +0 -13
  126. gcore/types/cloud/container_probe_config_create_param.py +0 -17
  127. gcore/types/cloud/container_probe_create_param.py +0 -38
  128. gcore/types/cloud/container_probe_exec_create_param.py +0 -13
  129. gcore/types/cloud/container_probe_http_get_create_param.py +0 -25
  130. gcore/types/cloud/container_probe_tcp_socket_create_param.py +0 -12
  131. gcore/types/cloud/container_scale.py +0 -25
  132. gcore/types/cloud/container_scale_trigger_rate.py +0 -13
  133. gcore/types/cloud/container_scale_trigger_sqs.py +0 -33
  134. gcore/types/cloud/container_scale_trigger_threshold.py +0 -10
  135. gcore/types/cloud/container_scale_triggers.py +0 -36
  136. gcore/types/cloud/deploy_status.py +0 -13
  137. gcore/types/cloud/inference/container.py +0 -26
  138. gcore/types/cloud/inference/inference.py +0 -95
  139. gcore/types/cloud/inference/mlcatalog_order_by_choices.py +0 -7
  140. gcore/types/cloud/inference_probes.py +0 -19
  141. gcore/types/cloud/ingress_opts_out.py +0 -16
  142. gcore/types/cloud/ingress_opts_param.py +0 -18
  143. gcore/types/cloud/secret_create_params.py +0 -66
  144. {gcore-0.4.0.dist-info → gcore-0.6.0.dist-info}/WHEEL +0 -0
  145. {gcore-0.4.0.dist-info → gcore-0.6.0.dist-info}/licenses/LICENSE +0 -0
@@ -0,0 +1,21 @@
1
+ # File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
2
+
3
+ from __future__ import annotations
4
+
5
+ from typing_extensions import Required, TypedDict
6
+
7
+ __all__ = ["APIKeyCreateParams"]
8
+
9
+
10
+ class APIKeyCreateParams(TypedDict, total=False):
11
+ project_id: int
12
+ """Project ID"""
13
+
14
+ name: Required[str]
15
+ """Name of the API Key."""
16
+
17
+ description: str
18
+ """Description of the API Key."""
19
+
20
+ expires_at: str
21
+ """Expiration date of the API Key in ISO 8601 format."""
@@ -0,0 +1,21 @@
1
+ # File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
2
+
3
+ from __future__ import annotations
4
+
5
+ from typing_extensions import TypedDict
6
+
7
+ __all__ = ["APIKeyListParams"]
8
+
9
+
10
+ class APIKeyListParams(TypedDict, total=False):
11
+ project_id: int
12
+ """Project ID"""
13
+
14
+ limit: int
15
+ """Optional. Limit the number of returned items"""
16
+
17
+ offset: int
18
+ """Optional.
19
+
20
+ Offset value is used to exclude the first set of records from the result
21
+ """
@@ -0,0 +1,16 @@
1
+ # File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
2
+
3
+ from __future__ import annotations
4
+
5
+ from typing import Optional
6
+ from typing_extensions import TypedDict
7
+
8
+ __all__ = ["APIKeyUpdateParams"]
9
+
10
+
11
+ class APIKeyUpdateParams(TypedDict, total=False):
12
+ project_id: int
13
+ """Project ID"""
14
+
15
+ description: Optional[str]
16
+ """Description of the API Key."""
@@ -6,9 +6,7 @@ from typing import Dict, List, Iterable, Optional
6
6
  from typing_extensions import Required, Annotated, TypedDict
7
7
 
8
8
  from ...._utils import PropertyInfo
9
- from ..ingress_opts_param import IngressOptsParam
10
9
  from ..laas_index_retention_policy_param import LaasIndexRetentionPolicyParam
11
- from ..container_probe_config_create_param import ContainerProbeConfigCreateParam
12
10
 
13
11
  __all__ = [
14
12
  "DeploymentCreateParams",
@@ -21,8 +19,24 @@ __all__ = [
21
19
  "ContainerScaleTriggersHTTP",
22
20
  "ContainerScaleTriggersMemory",
23
21
  "ContainerScaleTriggersSqs",
22
+ "IngressOpts",
24
23
  "Logging",
25
24
  "Probes",
25
+ "ProbesLivenessProbe",
26
+ "ProbesLivenessProbeProbe",
27
+ "ProbesLivenessProbeProbeExec",
28
+ "ProbesLivenessProbeProbeHTTPGet",
29
+ "ProbesLivenessProbeProbeTcpSocket",
30
+ "ProbesReadinessProbe",
31
+ "ProbesReadinessProbeProbe",
32
+ "ProbesReadinessProbeProbeExec",
33
+ "ProbesReadinessProbeProbeHTTPGet",
34
+ "ProbesReadinessProbeProbeTcpSocket",
35
+ "ProbesStartupProbe",
36
+ "ProbesStartupProbeProbe",
37
+ "ProbesStartupProbeProbeExec",
38
+ "ProbesStartupProbeProbeHTTPGet",
39
+ "ProbesStartupProbeProbeTcpSocket",
26
40
  ]
27
41
 
28
42
 
@@ -50,11 +64,20 @@ class DeploymentCreateParams(TypedDict, total=False):
50
64
  name: Required[str]
51
65
  """Inference instance name."""
52
66
 
67
+ api_keys: List[str]
68
+ """List of API keys for the inference instance.
69
+
70
+ Multiple keys can be attached to one deployment.If `auth_enabled` and `api_keys`
71
+ are both specified, a ValidationError will be raised.
72
+ """
73
+
53
74
  auth_enabled: bool
54
75
  """Set to `true` to enable API key authentication for the inference instance.
55
76
 
56
77
  `"Authorization": "Bearer ****\\**"` or `"X-Api-Key": "****\\**"` header is required
57
- for the requests to the instance if enabled
78
+ for the requests to the instance if enabled. This field is deprecated and will
79
+ be removed in the future. Use `api_keys` field instead.If `auth_enabled` and
80
+ `api_keys` are both specified, a ValidationError will be raised.
58
81
  """
59
82
 
60
83
  command: Optional[List[str]]
@@ -69,7 +92,7 @@ class DeploymentCreateParams(TypedDict, total=False):
69
92
  envs: Dict[str, str]
70
93
  """Environment variables for the inference instance."""
71
94
 
72
- ingress_opts: Optional[IngressOptsParam]
95
+ ingress_opts: Optional[IngressOpts]
73
96
  """Ingress options for the inference instance"""
74
97
 
75
98
  logging: Optional[Logging]
@@ -197,6 +220,17 @@ class Container(TypedDict, total=False):
197
220
  """Scale for the container"""
198
221
 
199
222
 
223
+ class IngressOpts(TypedDict, total=False):
224
+ disable_response_buffering: bool
225
+ """Disable response buffering if true.
226
+
227
+ A client usually has a much slower connection and can not consume the response
228
+ data as fast as it is produced by an upstream application. Ingress tries to
229
+ buffer the whole response in order to release the upstream application as soon
230
+ as possible.By default, the response buffering is enabled.
231
+ """
232
+
233
+
200
234
  class Logging(TypedDict, total=False):
201
235
  destination_region_id: Optional[int]
202
236
  """ID of the region in which the logs will be stored"""
@@ -211,12 +245,195 @@ class Logging(TypedDict, total=False):
211
245
  """The topic name to stream logs to"""
212
246
 
213
247
 
248
+ class ProbesLivenessProbeProbeExec(TypedDict, total=False):
249
+ command: Required[List[str]]
250
+ """Command to be executed inside the running container."""
251
+
252
+
253
+ class ProbesLivenessProbeProbeHTTPGet(TypedDict, total=False):
254
+ port: Required[int]
255
+ """Port number the probe should connect to."""
256
+
257
+ headers: Dict[str, str]
258
+ """HTTP headers to be sent with the request."""
259
+
260
+ host: Optional[str]
261
+ """Host name to send HTTP request to."""
262
+
263
+ path: str
264
+ """The endpoint to send the HTTP request to."""
265
+
266
+ schema: str
267
+ """Schema to use for the HTTP request."""
268
+
269
+
270
+ class ProbesLivenessProbeProbeTcpSocket(TypedDict, total=False):
271
+ port: Required[int]
272
+ """Port number to check if it's open."""
273
+
274
+
275
+ class ProbesLivenessProbeProbe(TypedDict, total=False):
276
+ exec: Optional[ProbesLivenessProbeProbeExec]
277
+ """Exec probe configuration"""
278
+
279
+ failure_threshold: int
280
+ """The number of consecutive probe failures that mark the container as unhealthy."""
281
+
282
+ http_get: Optional[ProbesLivenessProbeProbeHTTPGet]
283
+ """HTTP GET probe configuration"""
284
+
285
+ initial_delay_seconds: int
286
+ """The initial delay before starting the first probe."""
287
+
288
+ period_seconds: int
289
+ """How often (in seconds) to perform the probe."""
290
+
291
+ success_threshold: int
292
+ """The number of consecutive successful probes that mark the container as healthy."""
293
+
294
+ tcp_socket: Optional[ProbesLivenessProbeProbeTcpSocket]
295
+ """TCP socket probe configuration"""
296
+
297
+ timeout_seconds: int
298
+ """The timeout for each probe."""
299
+
300
+
301
+ class ProbesLivenessProbe(TypedDict, total=False):
302
+ enabled: Required[bool]
303
+ """Whether the probe is enabled or not."""
304
+
305
+ probe: ProbesLivenessProbeProbe
306
+ """Probe configuration (exec, `http_get` or `tcp_socket`)"""
307
+
308
+
309
+ class ProbesReadinessProbeProbeExec(TypedDict, total=False):
310
+ command: Required[List[str]]
311
+ """Command to be executed inside the running container."""
312
+
313
+
314
+ class ProbesReadinessProbeProbeHTTPGet(TypedDict, total=False):
315
+ port: Required[int]
316
+ """Port number the probe should connect to."""
317
+
318
+ headers: Dict[str, str]
319
+ """HTTP headers to be sent with the request."""
320
+
321
+ host: Optional[str]
322
+ """Host name to send HTTP request to."""
323
+
324
+ path: str
325
+ """The endpoint to send the HTTP request to."""
326
+
327
+ schema: str
328
+ """Schema to use for the HTTP request."""
329
+
330
+
331
+ class ProbesReadinessProbeProbeTcpSocket(TypedDict, total=False):
332
+ port: Required[int]
333
+ """Port number to check if it's open."""
334
+
335
+
336
+ class ProbesReadinessProbeProbe(TypedDict, total=False):
337
+ exec: Optional[ProbesReadinessProbeProbeExec]
338
+ """Exec probe configuration"""
339
+
340
+ failure_threshold: int
341
+ """The number of consecutive probe failures that mark the container as unhealthy."""
342
+
343
+ http_get: Optional[ProbesReadinessProbeProbeHTTPGet]
344
+ """HTTP GET probe configuration"""
345
+
346
+ initial_delay_seconds: int
347
+ """The initial delay before starting the first probe."""
348
+
349
+ period_seconds: int
350
+ """How often (in seconds) to perform the probe."""
351
+
352
+ success_threshold: int
353
+ """The number of consecutive successful probes that mark the container as healthy."""
354
+
355
+ tcp_socket: Optional[ProbesReadinessProbeProbeTcpSocket]
356
+ """TCP socket probe configuration"""
357
+
358
+ timeout_seconds: int
359
+ """The timeout for each probe."""
360
+
361
+
362
+ class ProbesReadinessProbe(TypedDict, total=False):
363
+ enabled: Required[bool]
364
+ """Whether the probe is enabled or not."""
365
+
366
+ probe: ProbesReadinessProbeProbe
367
+ """Probe configuration (exec, `http_get` or `tcp_socket`)"""
368
+
369
+
370
+ class ProbesStartupProbeProbeExec(TypedDict, total=False):
371
+ command: Required[List[str]]
372
+ """Command to be executed inside the running container."""
373
+
374
+
375
+ class ProbesStartupProbeProbeHTTPGet(TypedDict, total=False):
376
+ port: Required[int]
377
+ """Port number the probe should connect to."""
378
+
379
+ headers: Dict[str, str]
380
+ """HTTP headers to be sent with the request."""
381
+
382
+ host: Optional[str]
383
+ """Host name to send HTTP request to."""
384
+
385
+ path: str
386
+ """The endpoint to send the HTTP request to."""
387
+
388
+ schema: str
389
+ """Schema to use for the HTTP request."""
390
+
391
+
392
+ class ProbesStartupProbeProbeTcpSocket(TypedDict, total=False):
393
+ port: Required[int]
394
+ """Port number to check if it's open."""
395
+
396
+
397
+ class ProbesStartupProbeProbe(TypedDict, total=False):
398
+ exec: Optional[ProbesStartupProbeProbeExec]
399
+ """Exec probe configuration"""
400
+
401
+ failure_threshold: int
402
+ """The number of consecutive probe failures that mark the container as unhealthy."""
403
+
404
+ http_get: Optional[ProbesStartupProbeProbeHTTPGet]
405
+ """HTTP GET probe configuration"""
406
+
407
+ initial_delay_seconds: int
408
+ """The initial delay before starting the first probe."""
409
+
410
+ period_seconds: int
411
+ """How often (in seconds) to perform the probe."""
412
+
413
+ success_threshold: int
414
+ """The number of consecutive successful probes that mark the container as healthy."""
415
+
416
+ tcp_socket: Optional[ProbesStartupProbeProbeTcpSocket]
417
+ """TCP socket probe configuration"""
418
+
419
+ timeout_seconds: int
420
+ """The timeout for each probe."""
421
+
422
+
423
+ class ProbesStartupProbe(TypedDict, total=False):
424
+ enabled: Required[bool]
425
+ """Whether the probe is enabled or not."""
426
+
427
+ probe: ProbesStartupProbeProbe
428
+ """Probe configuration (exec, `http_get` or `tcp_socket`)"""
429
+
430
+
214
431
  class Probes(TypedDict, total=False):
215
- liveness_probe: Optional[ContainerProbeConfigCreateParam]
432
+ liveness_probe: Optional[ProbesLivenessProbe]
216
433
  """Liveness probe configuration"""
217
434
 
218
- readiness_probe: Optional[ContainerProbeConfigCreateParam]
435
+ readiness_probe: Optional[ProbesReadinessProbe]
219
436
  """Readiness probe configuration"""
220
437
 
221
- startup_probe: Optional[ContainerProbeConfigCreateParam]
438
+ startup_probe: Optional[ProbesStartupProbe]
222
439
  """Startup probe configuration"""
@@ -6,7 +6,6 @@ from typing import Dict, List, Iterable, Optional
6
6
  from typing_extensions import Required, Annotated, TypedDict
7
7
 
8
8
  from ...._utils import PropertyInfo
9
- from ..ingress_opts_param import IngressOptsParam
10
9
  from ..laas_index_retention_policy_param import LaasIndexRetentionPolicyParam
11
10
 
12
11
  __all__ = [
@@ -20,6 +19,7 @@ __all__ = [
20
19
  "ContainerScaleTriggersHTTP",
21
20
  "ContainerScaleTriggersMemory",
22
21
  "ContainerScaleTriggersSqs",
22
+ "IngressOpts",
23
23
  "Logging",
24
24
  "Probes",
25
25
  "ProbesLivenessProbe",
@@ -44,11 +44,21 @@ class DeploymentUpdateParams(TypedDict, total=False):
44
44
  project_id: int
45
45
  """Project ID"""
46
46
 
47
+ api_keys: Optional[List[str]]
48
+ """List of API keys for the inference instance.
49
+
50
+ Multiple keys can be attached to one deployment.If `auth_enabled` and `api_keys`
51
+ are both specified, a ValidationError will be raised.If `[]` is provided, the
52
+ API keys will be removed and auth will be disabled on the deployment.
53
+ """
54
+
47
55
  auth_enabled: bool
48
56
  """Set to `true` to enable API key authentication for the inference instance.
49
57
 
50
58
  `"Authorization": "Bearer ****\\**"` or `"X-Api-Key": "****\\**"` header is required
51
- for the requests to the instance if enabled
59
+ for the requests to the instance if enabled. This field is deprecated and will
60
+ be removed in the future. Use `api_keys` field instead.If `auth_enabled` and
61
+ `api_keys` are both specified, a ValidationError will be raised.
52
62
  """
53
63
 
54
64
  command: Optional[List[str]]
@@ -77,7 +87,7 @@ class DeploymentUpdateParams(TypedDict, total=False):
77
87
  accessible Docker image URL can be specified.
78
88
  """
79
89
 
80
- ingress_opts: Optional[IngressOptsParam]
90
+ ingress_opts: Optional[IngressOpts]
81
91
  """Ingress options for the inference instance"""
82
92
 
83
93
  listening_port: Optional[int]
@@ -204,6 +214,17 @@ class Container(TypedDict, total=False):
204
214
  """Scale for the container"""
205
215
 
206
216
 
217
+ class IngressOpts(TypedDict, total=False):
218
+ disable_response_buffering: bool
219
+ """Disable response buffering if true.
220
+
221
+ A client usually has a much slower connection and can not consume the response
222
+ data as fast as it is produced by an upstream application. Ingress tries to
223
+ buffer the whole response in order to release the upstream application as soon
224
+ as possible.By default, the response buffering is enabled.
225
+ """
226
+
227
+
207
228
  class Logging(TypedDict, total=False):
208
229
  destination_region_id: Optional[int]
209
230
  """ID of the region in which the logs will be stored"""
@@ -3,3 +3,4 @@
3
3
  from __future__ import annotations
4
4
 
5
5
  from .log_list_params import LogListParams as LogListParams
6
+ from .inference_deployment_log import InferenceDeploymentLog as InferenceDeploymentLog
@@ -2,12 +2,12 @@
2
2
 
3
3
  from datetime import datetime
4
4
 
5
- from ...._models import BaseModel
5
+ from ....._models import BaseModel
6
6
 
7
- __all__ = ["InferenceLog"]
7
+ __all__ = ["InferenceDeploymentLog"]
8
8
 
9
9
 
10
- class InferenceLog(BaseModel):
10
+ class InferenceDeploymentLog(BaseModel):
11
11
  message: str
12
12
  """Log message."""
13
13
 
@@ -0,0 +1,24 @@
1
+ # File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
2
+
3
+ from typing import List, Optional
4
+
5
+ from ...._models import BaseModel
6
+
7
+ __all__ = ["InferenceAPIKey"]
8
+
9
+
10
+ class InferenceAPIKey(BaseModel):
11
+ created_at: str
12
+ """Timestamp when the API Key was created."""
13
+
14
+ deployment_names: List[str]
15
+ """List of inference deployment names to which this API Key has been attached."""
16
+
17
+ description: Optional[str] = None
18
+ """Description of the API Key."""
19
+
20
+ expires_at: Optional[str] = None
21
+ """Timestamp when the API Key will expire."""
22
+
23
+ name: str
24
+ """API Key name."""
@@ -0,0 +1,27 @@
1
+ # File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
2
+
3
+ from typing import List, Optional
4
+
5
+ from ...._models import BaseModel
6
+
7
+ __all__ = ["InferenceAPIKeyCreate"]
8
+
9
+
10
+ class InferenceAPIKeyCreate(BaseModel):
11
+ created_at: str
12
+ """Timestamp when the API Key was created."""
13
+
14
+ deployment_names: List[str]
15
+ """List of inference deployment names to which this API Key has been attached."""
16
+
17
+ description: Optional[str] = None
18
+ """Description of the API Key."""
19
+
20
+ expires_at: Optional[str] = None
21
+ """Timestamp when the API Key will expire."""
22
+
23
+ name: str
24
+ """API Key name."""
25
+
26
+ secret: str
27
+ """The actual API Key secret."""