@dhbw-cloud/llm-client 0.1.0-test.14 → 0.1.1

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.
package/dist/index.d.ts CHANGED
@@ -1,2 +1,2 @@
1
- export { blockMachine, createAccessRule, createGpuEnvironment, createKey, deleteAccessRule, deleteFleetPackage, deleteGpuEnvironment, deleteKey, forgetMachine, getFleet, getFleetInventoryCsv, getFleetPackage, getFleetProfile, getFleetReadme, getGpuEnvironment, getGpuEnvironmentLog, getMe, getUsage, listAccessRules, listGpuEnvironments, listGpuServers, listGpuTiers, listKeys, listTiers, type Options, rebuildGpuEnvironment, searchPrincipals, startGpuEnvironment, stopGpuServer, unblockMachine, updateAccessRule } from './sdk.gen';
2
- export type { AccessRole, AccessRule, BlockMachineData, BlockMachineError, BlockMachineErrors, BlockMachineResponse, BlockMachineResponses, ClientOptions, CreateAccessRuleData, CreateAccessRuleError, CreateAccessRuleErrors, CreateAccessRuleResponse, CreateAccessRuleResponses, CreateGpuEnvironmentData, CreateGpuEnvironmentError, CreateGpuEnvironmentErrors, CreateGpuEnvironmentResponse, CreateGpuEnvironmentResponses, CreateKeyData, CreateKeyError, CreateKeyErrors, CreateKeyResponse, CreateKeyResponses, DeleteAccessRuleData, DeleteAccessRuleError, DeleteAccessRuleErrors, DeleteAccessRuleResponse, DeleteAccessRuleResponses, DeleteFleetPackageData, DeleteFleetPackageResponse, DeleteFleetPackageResponses, DeleteGpuEnvironmentData, DeleteGpuEnvironmentError, DeleteGpuEnvironmentErrors, DeleteGpuEnvironmentResponse, DeleteGpuEnvironmentResponses, DeleteKeyData, DeleteKeyError, DeleteKeyErrors, DeleteKeyResponse, DeleteKeyResponses, FleetFleetView, FleetPackageInfo, FleetPeerView, FleetProfile, ForgetMachineData, ForgetMachineError, ForgetMachineErrors, ForgetMachineResponse, ForgetMachineResponses, GetFleetData, GetFleetError, GetFleetErrors, GetFleetInventoryCsvData, GetFleetInventoryCsvResponse, GetFleetInventoryCsvResponses, GetFleetPackageData, GetFleetPackageError, GetFleetPackageErrors, GetFleetPackageResponse, GetFleetPackageResponses, GetFleetProfileData, GetFleetProfileResponse, GetFleetProfileResponses, GetFleetReadmeData, GetFleetReadmeResponse, GetFleetReadmeResponses, GetFleetResponse, GetFleetResponses, GetGpuEnvironmentData, GetGpuEnvironmentError, GetGpuEnvironmentErrors, GetGpuEnvironmentLogData, GetGpuEnvironmentLogError, GetGpuEnvironmentLogErrors, GetGpuEnvironmentLogResponse, GetGpuEnvironmentLogResponses, GetGpuEnvironmentResponse, GetGpuEnvironmentResponses, GetMeData, GetMeError, GetMeErrors, GetMeResponse, GetMeResponses, GetUsageData, GetUsageError, GetUsageErrors, GetUsageResponse, GetUsageResponses, GpuEnvironment, GpuServer, GpuStatus, KeysKeyView, KeysUsage, ListAccessRulesData, ListAccessRulesError, ListAccessRulesErrors, ListAccessRulesResponse, ListAccessRulesResponses, ListGpuEnvironmentsData, ListGpuEnvironmentsError, ListGpuEnvironmentsErrors, ListGpuEnvironmentsResponse, ListGpuEnvironmentsResponses, ListGpuServersData, ListGpuServersError, ListGpuServersErrors, ListGpuServersResponse, ListGpuServersResponses, ListGpuTiersData, ListGpuTiersResponse, ListGpuTiersResponses, ListKeysData, ListKeysError, ListKeysErrors, ListKeysResponse, ListKeysResponses, ListTiersData, ListTiersResponse, ListTiersResponses, RebuildGpuEnvironmentData, RebuildGpuEnvironmentError, RebuildGpuEnvironmentErrors, RebuildGpuEnvironmentResponse, RebuildGpuEnvironmentResponses, RoleproviderGroup, SearchPrincipalsData, SearchPrincipalsError, SearchPrincipalsErrors, SearchPrincipalsResponse, SearchPrincipalsResponses, StartGpuEnvironmentData, StartGpuEnvironmentError, StartGpuEnvironmentErrors, StartGpuEnvironmentResponse, StartGpuEnvironmentResponses, StopGpuServerData, StopGpuServerError, StopGpuServerErrors, StopGpuServerResponse, StopGpuServerResponses, UnblockMachineData, UnblockMachineError, UnblockMachineErrors, UnblockMachineResponse, UnblockMachineResponses, UpdateAccessRuleData, UpdateAccessRuleError, UpdateAccessRuleErrors, UpdateAccessRuleResponse, UpdateAccessRuleResponses, WebserverBuildLogResponse, WebserverCreateKeyRequest, WebserverCreateKeyResponse, WebserverEnvironmentRequest, WebserverErrorResponse, WebserverMeResponse, WebserverPrincipalSearchResponse, WebserverRuleRequest, WebserverRuleRequest2, WebserverStartRequest, WebserverStartResponse } from './types.gen';
1
+ export { blockMachine, createAccessRule, createGpuEnvironment, createKey, deleteAccessRule, deleteFleetPackage, deleteGpuEnvironment, deleteKey, forgetMachine, getFleet, getFleetInference, getFleetInventoryCsv, getFleetPackage, getFleetProfile, getFleetReadme, getGpuEnvironment, getGpuEnvironmentLog, getMe, getUsage, listAccessRules, listGpuEnvironments, listGpuServers, listGpuTiers, listKeys, listTiers, type Options, rebuildGpuEnvironment, searchPrincipals, startGpuEnvironment, stopGpuServer, unblockMachine, updateAccessRule } from './sdk.gen';
2
+ export type { AccessRole, AccessRule, BlockMachineData, BlockMachineError, BlockMachineErrors, BlockMachineResponse, BlockMachineResponses, ClientOptions, CreateAccessRuleData, CreateAccessRuleError, CreateAccessRuleErrors, CreateAccessRuleResponse, CreateAccessRuleResponses, CreateGpuEnvironmentData, CreateGpuEnvironmentError, CreateGpuEnvironmentErrors, CreateGpuEnvironmentResponse, CreateGpuEnvironmentResponses, CreateKeyData, CreateKeyError, CreateKeyErrors, CreateKeyResponse, CreateKeyResponses, DeleteAccessRuleData, DeleteAccessRuleError, DeleteAccessRuleErrors, DeleteAccessRuleResponse, DeleteAccessRuleResponses, DeleteFleetPackageData, DeleteFleetPackageResponse, DeleteFleetPackageResponses, DeleteGpuEnvironmentData, DeleteGpuEnvironmentError, DeleteGpuEnvironmentErrors, DeleteGpuEnvironmentResponse, DeleteGpuEnvironmentResponses, DeleteKeyData, DeleteKeyError, DeleteKeyErrors, DeleteKeyResponse, DeleteKeyResponses, FleetFleetView, FleetPackageInfo, FleetPeerView, FleetProfile, ForgetMachineData, ForgetMachineError, ForgetMachineErrors, ForgetMachineResponse, ForgetMachineResponses, GetFleetData, GetFleetError, GetFleetErrors, GetFleetInferenceData, GetFleetInferenceError, GetFleetInferenceErrors, GetFleetInferenceResponse, GetFleetInferenceResponses, GetFleetInventoryCsvData, GetFleetInventoryCsvResponse, GetFleetInventoryCsvResponses, GetFleetPackageData, GetFleetPackageError, GetFleetPackageErrors, GetFleetPackageResponse, GetFleetPackageResponses, GetFleetProfileData, GetFleetProfileResponse, GetFleetProfileResponses, GetFleetReadmeData, GetFleetReadmeResponse, GetFleetReadmeResponses, GetFleetResponse, GetFleetResponses, GetGpuEnvironmentData, GetGpuEnvironmentError, GetGpuEnvironmentErrors, GetGpuEnvironmentLogData, GetGpuEnvironmentLogError, GetGpuEnvironmentLogErrors, GetGpuEnvironmentLogResponse, GetGpuEnvironmentLogResponses, GetGpuEnvironmentResponse, GetGpuEnvironmentResponses, GetMeData, GetMeError, GetMeErrors, GetMeResponse, GetMeResponses, GetUsageData, GetUsageError, GetUsageErrors, GetUsageResponse, GetUsageResponses, GpuEnvironment, GpuInferencePod, GpuInferencePool, GpuServer, GpuStatus, KeysKeyView, KeysUsage, ListAccessRulesData, ListAccessRulesError, ListAccessRulesErrors, ListAccessRulesResponse, ListAccessRulesResponses, ListGpuEnvironmentsData, ListGpuEnvironmentsError, ListGpuEnvironmentsErrors, ListGpuEnvironmentsResponse, ListGpuEnvironmentsResponses, ListGpuServersData, ListGpuServersError, ListGpuServersErrors, ListGpuServersResponse, ListGpuServersResponses, ListGpuTiersData, ListGpuTiersResponse, ListGpuTiersResponses, ListKeysData, ListKeysError, ListKeysErrors, ListKeysResponse, ListKeysResponses, ListTiersData, ListTiersResponse, ListTiersResponses, RebuildGpuEnvironmentData, RebuildGpuEnvironmentError, RebuildGpuEnvironmentErrors, RebuildGpuEnvironmentResponse, RebuildGpuEnvironmentResponses, RoleproviderGroup, SearchPrincipalsData, SearchPrincipalsError, SearchPrincipalsErrors, SearchPrincipalsResponse, SearchPrincipalsResponses, StartGpuEnvironmentData, StartGpuEnvironmentError, StartGpuEnvironmentErrors, StartGpuEnvironmentResponse, StartGpuEnvironmentResponses, StopGpuServerData, StopGpuServerError, StopGpuServerErrors, StopGpuServerResponse, StopGpuServerResponses, UnblockMachineData, UnblockMachineError, UnblockMachineErrors, UnblockMachineResponse, UnblockMachineResponses, UpdateAccessRuleData, UpdateAccessRuleError, UpdateAccessRuleErrors, UpdateAccessRuleResponse, UpdateAccessRuleResponses, WebserverBuildLogResponse, WebserverCreateKeyRequest, WebserverCreateKeyResponse, WebserverEnvironmentRequest, WebserverErrorResponse, WebserverMeResponse, WebserverPrincipalSearchResponse, WebserverRuleRequest, WebserverRuleRequest2, WebserverStartRequest, WebserverStartResponse } from './types.gen';
package/dist/index.mjs CHANGED
@@ -820,6 +820,11 @@ var getFleet = (options) => (options?.client ?? client).get({
820
820
  url: "/v1/fleet",
821
821
  ...options
822
822
  });
823
+ var getFleetInference = (options) => (options?.client ?? client).get({
824
+ security: [{ name: "Authorization", type: "apiKey" }],
825
+ url: "/v1/fleet/inference",
826
+ ...options
827
+ });
823
828
  var getFleetInventoryCsv = (options) => (options?.client ?? client).get({
824
829
  security: [{ name: "Authorization", type: "apiKey" }],
825
830
  url: "/v1/fleet/inventory.csv",
@@ -969,6 +974,7 @@ export {
969
974
  deleteKey,
970
975
  forgetMachine,
971
976
  getFleet,
977
+ getFleetInference,
972
978
  getFleetInventoryCsv,
973
979
  getFleetPackage,
974
980
  getFleetProfile,
package/dist/sdk.gen.d.ts CHANGED
@@ -1,5 +1,5 @@
1
1
  import type { Client, ClientMeta, Options as Options2, RequestResult, TDataShape } from './client';
2
- import type { BlockMachineData, BlockMachineErrors, BlockMachineResponses, CreateAccessRuleData, CreateAccessRuleErrors, CreateAccessRuleResponses, CreateGpuEnvironmentData, CreateGpuEnvironmentErrors, CreateGpuEnvironmentResponses, CreateKeyData, CreateKeyErrors, CreateKeyResponses, DeleteAccessRuleData, DeleteAccessRuleErrors, DeleteAccessRuleResponses, DeleteFleetPackageData, DeleteFleetPackageResponses, DeleteGpuEnvironmentData, DeleteGpuEnvironmentErrors, DeleteGpuEnvironmentResponses, DeleteKeyData, DeleteKeyErrors, DeleteKeyResponses, ForgetMachineData, ForgetMachineErrors, ForgetMachineResponses, GetFleetData, GetFleetErrors, GetFleetInventoryCsvData, GetFleetInventoryCsvResponses, GetFleetPackageData, GetFleetPackageErrors, GetFleetPackageResponses, GetFleetProfileData, GetFleetProfileResponses, GetFleetReadmeData, GetFleetReadmeResponses, GetFleetResponses, GetGpuEnvironmentData, GetGpuEnvironmentErrors, GetGpuEnvironmentLogData, GetGpuEnvironmentLogErrors, GetGpuEnvironmentLogResponses, GetGpuEnvironmentResponses, GetMeData, GetMeErrors, GetMeResponses, GetUsageData, GetUsageErrors, GetUsageResponses, ListAccessRulesData, ListAccessRulesErrors, ListAccessRulesResponses, ListGpuEnvironmentsData, ListGpuEnvironmentsErrors, ListGpuEnvironmentsResponses, ListGpuServersData, ListGpuServersErrors, ListGpuServersResponses, ListGpuTiersData, ListGpuTiersResponses, ListKeysData, ListKeysErrors, ListKeysResponses, ListTiersData, ListTiersResponses, RebuildGpuEnvironmentData, RebuildGpuEnvironmentErrors, RebuildGpuEnvironmentResponses, SearchPrincipalsData, SearchPrincipalsErrors, SearchPrincipalsResponses, StartGpuEnvironmentData, StartGpuEnvironmentErrors, StartGpuEnvironmentResponses, StopGpuServerData, StopGpuServerErrors, StopGpuServerResponses, UnblockMachineData, UnblockMachineErrors, UnblockMachineResponses, UpdateAccessRuleData, UpdateAccessRuleErrors, UpdateAccessRuleResponses } from './types.gen';
2
+ import type { BlockMachineData, BlockMachineErrors, BlockMachineResponses, CreateAccessRuleData, CreateAccessRuleErrors, CreateAccessRuleResponses, CreateGpuEnvironmentData, CreateGpuEnvironmentErrors, CreateGpuEnvironmentResponses, CreateKeyData, CreateKeyErrors, CreateKeyResponses, DeleteAccessRuleData, DeleteAccessRuleErrors, DeleteAccessRuleResponses, DeleteFleetPackageData, DeleteFleetPackageResponses, DeleteGpuEnvironmentData, DeleteGpuEnvironmentErrors, DeleteGpuEnvironmentResponses, DeleteKeyData, DeleteKeyErrors, DeleteKeyResponses, ForgetMachineData, ForgetMachineErrors, ForgetMachineResponses, GetFleetData, GetFleetErrors, GetFleetInferenceData, GetFleetInferenceErrors, GetFleetInferenceResponses, GetFleetInventoryCsvData, GetFleetInventoryCsvResponses, GetFleetPackageData, GetFleetPackageErrors, GetFleetPackageResponses, GetFleetProfileData, GetFleetProfileResponses, GetFleetReadmeData, GetFleetReadmeResponses, GetFleetResponses, GetGpuEnvironmentData, GetGpuEnvironmentErrors, GetGpuEnvironmentLogData, GetGpuEnvironmentLogErrors, GetGpuEnvironmentLogResponses, GetGpuEnvironmentResponses, GetMeData, GetMeErrors, GetMeResponses, GetUsageData, GetUsageErrors, GetUsageResponses, ListAccessRulesData, ListAccessRulesErrors, ListAccessRulesResponses, ListGpuEnvironmentsData, ListGpuEnvironmentsErrors, ListGpuEnvironmentsResponses, ListGpuServersData, ListGpuServersErrors, ListGpuServersResponses, ListGpuTiersData, ListGpuTiersResponses, ListKeysData, ListKeysErrors, ListKeysResponses, ListTiersData, ListTiersResponses, RebuildGpuEnvironmentData, RebuildGpuEnvironmentErrors, RebuildGpuEnvironmentResponses, SearchPrincipalsData, SearchPrincipalsErrors, SearchPrincipalsResponses, StartGpuEnvironmentData, StartGpuEnvironmentErrors, StartGpuEnvironmentResponses, StopGpuServerData, StopGpuServerErrors, StopGpuServerResponses, UnblockMachineData, UnblockMachineErrors, UnblockMachineResponses, UpdateAccessRuleData, UpdateAccessRuleErrors, UpdateAccessRuleResponses } from './types.gen';
3
3
  export type Options<TData extends TDataShape = TDataShape, ThrowOnError extends boolean = boolean, TResponse = unknown> = Options2<TData, ThrowOnError, TResponse> & {
4
4
  /**
5
5
  * You can provide a client instance returned by `createClient()` instead of
@@ -37,6 +37,12 @@ export declare const updateAccessRule: <ThrowOnError extends boolean = false>(op
37
37
  * Machines with enrolment state, LiteLLM health, script state and the JAMF onboarding data.
38
38
  */
39
39
  export declare const getFleet: <ThrowOnError extends boolean = false>(options?: Options<GetFleetData, ThrowOnError>) => RequestResult<GetFleetResponses, GetFleetErrors, ThrowOnError>;
40
+ /**
41
+ * The GPU cluster's inference pool
42
+ *
43
+ * vLLM replicas (one gap filler per GPU node, the base load) with node, model and state. enabled=false without the GPU part or without an inference pool.
44
+ */
45
+ export declare const getFleetInference: <ThrowOnError extends boolean = false>(options?: Options<GetFleetInferenceData, ThrowOnError>) => RequestResult<GetFleetInferenceResponses, GetFleetInferenceErrors, ThrowOnError>;
40
46
  /**
41
47
  * Fleet inventory as CSV
42
48
  */
@@ -70,6 +70,10 @@ export type FleetPeerView = {
70
70
  operator?: string;
71
71
  os?: string;
72
72
  pkg_version?: string;
73
+ /**
74
+ * the machine's own address in its local network (default route), as it reports it at enrolment; empty until a script that sends it has enrolled
75
+ */
76
+ primary_ip?: string;
73
77
  profile?: string;
74
78
  quiet_seconds?: number;
75
79
  ram_gb?: number;
@@ -101,6 +105,28 @@ export type GpuEnvironment = {
101
105
  status?: GpuStatus;
102
106
  updated_at?: string;
103
107
  };
108
+ export type GpuInferencePod = {
109
+ gpu_class?: string;
110
+ model?: string;
111
+ node?: string;
112
+ pod?: string;
113
+ replica?: string;
114
+ role?: 'gap-filler' | 'base-load';
115
+ /**
116
+ * start on the node, or creation while it still waits
117
+ */
118
+ since?: string;
119
+ /**
120
+ * name in the discovery job and in LiteLLM
121
+ */
122
+ site?: string;
123
+ state?: 'bereit' | 'startet' | 'wartet auf GPU' | 'wird beendet';
124
+ };
125
+ export type GpuInferencePool = {
126
+ enabled?: boolean;
127
+ pods?: Array<GpuInferencePod>;
128
+ url?: string;
129
+ };
104
130
  export type GpuServer = {
105
131
  image?: string;
106
132
  name?: string;
@@ -333,6 +359,26 @@ export type GetFleetResponses = {
333
359
  200: FleetFleetView;
334
360
  };
335
361
  export type GetFleetResponse = GetFleetResponses[keyof GetFleetResponses];
362
+ export type GetFleetInferenceData = {
363
+ body?: never;
364
+ path?: never;
365
+ query?: never;
366
+ url: '/v1/fleet/inference';
367
+ };
368
+ export type GetFleetInferenceErrors = {
369
+ /**
370
+ * Forbidden
371
+ */
372
+ 403: WebserverErrorResponse;
373
+ };
374
+ export type GetFleetInferenceError = GetFleetInferenceErrors[keyof GetFleetInferenceErrors];
375
+ export type GetFleetInferenceResponses = {
376
+ /**
377
+ * OK
378
+ */
379
+ 200: GpuInferencePool;
380
+ };
381
+ export type GetFleetInferenceResponse = GetFleetInferenceResponses[keyof GetFleetInferenceResponses];
336
382
  export type GetFleetInventoryCsvData = {
337
383
  body?: never;
338
384
  path?: never;
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@dhbw-cloud/llm-client",
3
- "version": "0.1.0-test.14",
3
+ "version": "0.1.1",
4
4
  "description": "Generated TypeScript client for the DHBW Cloud llm-management-api.",
5
5
  "license": "Apache-2.0",
6
6
  "type": "module",