Skip to content

Commit 6de15e9

Browse files
scaleway-botLaure-di
scaleway-bot
and
Laure-di
authored
feat(inference): update endpoints (#567)
Co-authored-by: Laure-di <62625835+Laure-di@users.noreply.github.com>
1 parent 7be7a6f commit 6de15e9

File tree

2 files changed

+36
-36
lines changed
  • scaleway/scaleway/inference/v1beta1
  • scaleway-async/scaleway_async/inference/v1beta1

2 files changed

+36
-36
lines changed

‎scaleway-async/scaleway_async/inference/v1beta1/api.py

Lines changed: 18 additions & 18 deletions
Original file line numberDiff line numberDiff line change
@@ -105,7 +105,7 @@ async def list_deployments(
105105

106106
res = self._request(
107107
"GET",
108-
f"/llm-inference/v1beta1/regions/{param_region}/deployments",
108+
f"/inference/v1beta1/regions/{param_region}/deployments",
109109
params={
110110
"name": name,
111111
"order_by": order_by,
@@ -196,7 +196,7 @@ async def get_deployment(
196196

197197
res = self._request(
198198
"GET",
199-
f"/llm-inference/v1beta1/regions/{param_region}/deployments/{param_deployment_id}",
199+
f"/inference/v1beta1/regions/{param_region}/deployments/{param_deployment_id}",
200200
)
201201

202202
self._throw_on_error(res)
@@ -287,14 +287,14 @@ async def create_deployment(
287287

288288
res = self._request(
289289
"POST",
290-
f"/llm-inference/v1beta1/regions/{param_region}/deployments",
290+
f"/inference/v1beta1/regions/{param_region}/deployments",
291291
body=marshal_CreateDeploymentRequest(
292292
CreateDeploymentRequest(
293293
model_name=model_name,
294294
node_type=node_type,
295295
endpoints=endpoints,
296296
region=region,
297-
name=name or random_name(prefix="llm"),
297+
name=name or random_name(prefix="inference"),
298298
project_id=project_id,
299299
accept_eula=accept_eula,
300300
tags=tags,
@@ -344,7 +344,7 @@ async def update_deployment(
344344

345345
res = self._request(
346346
"PATCH",
347-
f"/llm-inference/v1beta1/regions/{param_region}/deployments/{param_deployment_id}",
347+
f"/inference/v1beta1/regions/{param_region}/deployments/{param_deployment_id}",
348348
body=marshal_UpdateDeploymentRequest(
349349
UpdateDeploymentRequest(
350350
deployment_id=deployment_id,
@@ -389,7 +389,7 @@ async def delete_deployment(
389389

390390
res = self._request(
391391
"DELETE",
392-
f"/llm-inference/v1beta1/regions/{param_region}/deployments/{param_deployment_id}",
392+
f"/inference/v1beta1/regions/{param_region}/deployments/{param_deployment_id}",
393393
)
394394

395395
self._throw_on_error(res)
@@ -424,7 +424,7 @@ async def get_deployment_certificate(
424424

425425
res = self._request(
426426
"GET",
427-
f"/llm-inference/v1beta1/regions/{param_region}/deployments/{param_deployment_id}/certificate",
427+
f"/inference/v1beta1/regions/{param_region}/deployments/{param_deployment_id}/certificate",
428428
)
429429

430430
self._throw_on_error(res)
@@ -460,7 +460,7 @@ async def create_endpoint(
460460

461461
res = self._request(
462462
"POST",
463-
f"/llm-inference/v1beta1/regions/{param_region}/endpoints",
463+
f"/inference/v1beta1/regions/{param_region}/endpoints",
464464
body=marshal_CreateEndpointRequest(
465465
CreateEndpointRequest(
466466
deployment_id=deployment_id,
@@ -505,7 +505,7 @@ async def update_endpoint(
505505

506506
res = self._request(
507507
"PATCH",
508-
f"/llm-inference/v1beta1/regions/{param_region}/endpoints/{param_endpoint_id}",
508+
f"/inference/v1beta1/regions/{param_region}/endpoints/{param_endpoint_id}",
509509
body=marshal_UpdateEndpointRequest(
510510
UpdateEndpointRequest(
511511
endpoint_id=endpoint_id,
@@ -546,7 +546,7 @@ async def delete_endpoint(
546546

547547
res = self._request(
548548
"DELETE",
549-
f"/llm-inference/v1beta1/regions/{param_region}/endpoints/{param_endpoint_id}",
549+
f"/inference/v1beta1/regions/{param_region}/endpoints/{param_endpoint_id}",
550550
)
551551

552552
self._throw_on_error(res)
@@ -583,7 +583,7 @@ async def list_deployment_acl_rules(
583583

584584
res = self._request(
585585
"GET",
586-
f"/llm-inference/v1beta1/regions/{param_region}/deployments/{param_deployment_id}/acls",
586+
f"/inference/v1beta1/regions/{param_region}/deployments/{param_deployment_id}/acls",
587587
params={
588588
"page": page,
589589
"page_size": page_size or self.client.default_page_size,
@@ -660,7 +660,7 @@ async def add_deployment_acl_rules(
660660

661661
res = self._request(
662662
"POST",
663-
f"/llm-inference/v1beta1/regions/{param_region}/deployments/{param_deployment_id}/acls",
663+
f"/inference/v1beta1/regions/{param_region}/deployments/{param_deployment_id}/acls",
664664
body=marshal_AddDeploymentACLRulesRequest(
665665
AddDeploymentACLRulesRequest(
666666
deployment_id=deployment_id,
@@ -704,7 +704,7 @@ async def set_deployment_acl_rules(
704704

705705
res = self._request(
706706
"PUT",
707-
f"/llm-inference/v1beta1/regions/{param_region}/deployments/{param_deployment_id}/acls",
707+
f"/inference/v1beta1/regions/{param_region}/deployments/{param_deployment_id}/acls",
708708
body=marshal_SetDeploymentACLRulesRequest(
709709
SetDeploymentACLRulesRequest(
710710
deployment_id=deployment_id,
@@ -744,7 +744,7 @@ async def delete_deployment_acl_rule(
744744

745745
res = self._request(
746746
"DELETE",
747-
f"/llm-inference/v1beta1/regions/{param_region}/acls/{param_acl_id}",
747+
f"/inference/v1beta1/regions/{param_region}/acls/{param_acl_id}",
748748
)
749749

750750
self._throw_on_error(res)
@@ -784,7 +784,7 @@ async def list_models(
784784

785785
res = self._request(
786786
"GET",
787-
f"/llm-inference/v1beta1/regions/{param_region}/models",
787+
f"/inference/v1beta1/regions/{param_region}/models",
788788
params={
789789
"name": name,
790790
"order_by": order_by,
@@ -870,7 +870,7 @@ async def get_model(
870870

871871
res = self._request(
872872
"GET",
873-
f"/llm-inference/v1beta1/regions/{param_region}/models/{param_model_id}",
873+
f"/inference/v1beta1/regions/{param_region}/models/{param_model_id}",
874874
)
875875

876876
self._throw_on_error(res)
@@ -902,7 +902,7 @@ async def get_model_eula(
902902

903903
res = self._request(
904904
"GET",
905-
f"/llm-inference/v1beta1/regions/{param_region}/models/{param_model_id}/eula",
905+
f"/inference/v1beta1/regions/{param_region}/models/{param_model_id}/eula",
906906
)
907907

908908
self._throw_on_error(res)
@@ -939,7 +939,7 @@ async def list_node_types(
939939

940940
res = self._request(
941941
"GET",
942-
f"/llm-inference/v1beta1/regions/{param_region}/node-types",
942+
f"/inference/v1beta1/regions/{param_region}/node-types",
943943
params={
944944
"include_disabled_types": include_disabled_types,
945945
"page": page,

‎scaleway/scaleway/inference/v1beta1/api.py

Lines changed: 18 additions & 18 deletions
Original file line numberDiff line numberDiff line change
@@ -105,7 +105,7 @@ def list_deployments(
105105

106106
res = self._request(
107107
"GET",
108-
f"/llm-inference/v1beta1/regions/{param_region}/deployments",
108+
f"/inference/v1beta1/regions/{param_region}/deployments",
109109
params={
110110
"name": name,
111111
"order_by": order_by,
@@ -196,7 +196,7 @@ def get_deployment(
196196

197197
res = self._request(
198198
"GET",
199-
f"/llm-inference/v1beta1/regions/{param_region}/deployments/{param_deployment_id}",
199+
f"/inference/v1beta1/regions/{param_region}/deployments/{param_deployment_id}",
200200
)
201201

202202
self._throw_on_error(res)
@@ -285,14 +285,14 @@ def create_deployment(
285285

286286
res = self._request(
287287
"POST",
288-
f"/llm-inference/v1beta1/regions/{param_region}/deployments",
288+
f"/inference/v1beta1/regions/{param_region}/deployments",
289289
body=marshal_CreateDeploymentRequest(
290290
CreateDeploymentRequest(
291291
model_name=model_name,
292292
node_type=node_type,
293293
endpoints=endpoints,
294294
region=region,
295-
name=name or random_name(prefix="llm"),
295+
name=name or random_name(prefix="inference"),
296296
project_id=project_id,
297297
accept_eula=accept_eula,
298298
tags=tags,
@@ -342,7 +342,7 @@ def update_deployment(
342342

343343
res = self._request(
344344
"PATCH",
345-
f"/llm-inference/v1beta1/regions/{param_region}/deployments/{param_deployment_id}",
345+
f"/inference/v1beta1/regions/{param_region}/deployments/{param_deployment_id}",
346346
body=marshal_UpdateDeploymentRequest(
347347
UpdateDeploymentRequest(
348348
deployment_id=deployment_id,
@@ -387,7 +387,7 @@ def delete_deployment(
387387

388388
res = self._request(
389389
"DELETE",
390-
f"/llm-inference/v1beta1/regions/{param_region}/deployments/{param_deployment_id}",
390+
f"/inference/v1beta1/regions/{param_region}/deployments/{param_deployment_id}",
391391
)
392392

393393
self._throw_on_error(res)
@@ -422,7 +422,7 @@ def get_deployment_certificate(
422422

423423
res = self._request(
424424
"GET",
425-
f"/llm-inference/v1beta1/regions/{param_region}/deployments/{param_deployment_id}/certificate",
425+
f"/inference/v1beta1/regions/{param_region}/deployments/{param_deployment_id}/certificate",
426426
)
427427

428428
self._throw_on_error(res)
@@ -458,7 +458,7 @@ def create_endpoint(
458458

459459
res = self._request(
460460
"POST",
461-
f"/llm-inference/v1beta1/regions/{param_region}/endpoints",
461+
f"/inference/v1beta1/regions/{param_region}/endpoints",
462462
body=marshal_CreateEndpointRequest(
463463
CreateEndpointRequest(
464464
deployment_id=deployment_id,
@@ -503,7 +503,7 @@ def update_endpoint(
503503

504504
res = self._request(
505505
"PATCH",
506-
f"/llm-inference/v1beta1/regions/{param_region}/endpoints/{param_endpoint_id}",
506+
f"/inference/v1beta1/regions/{param_region}/endpoints/{param_endpoint_id}",
507507
body=marshal_UpdateEndpointRequest(
508508
UpdateEndpointRequest(
509509
endpoint_id=endpoint_id,
@@ -544,7 +544,7 @@ def delete_endpoint(
544544

545545
res = self._request(
546546
"DELETE",
547-
f"/llm-inference/v1beta1/regions/{param_region}/endpoints/{param_endpoint_id}",
547+
f"/inference/v1beta1/regions/{param_region}/endpoints/{param_endpoint_id}",
548548
)
549549

550550
self._throw_on_error(res)
@@ -581,7 +581,7 @@ def list_deployment_acl_rules(
581581

582582
res = self._request(
583583
"GET",
584-
f"/llm-inference/v1beta1/regions/{param_region}/deployments/{param_deployment_id}/acls",
584+
f"/inference/v1beta1/regions/{param_region}/deployments/{param_deployment_id}/acls",
585585
params={
586586
"page": page,
587587
"page_size": page_size or self.client.default_page_size,
@@ -658,7 +658,7 @@ def add_deployment_acl_rules(
658658

659659
res = self._request(
660660
"POST",
661-
f"/llm-inference/v1beta1/regions/{param_region}/deployments/{param_deployment_id}/acls",
661+
f"/inference/v1beta1/regions/{param_region}/deployments/{param_deployment_id}/acls",
662662
body=marshal_AddDeploymentACLRulesRequest(
663663
AddDeploymentACLRulesRequest(
664664
deployment_id=deployment_id,
@@ -702,7 +702,7 @@ def set_deployment_acl_rules(
702702

703703
res = self._request(
704704
"PUT",
705-
f"/llm-inference/v1beta1/regions/{param_region}/deployments/{param_deployment_id}/acls",
705+
f"/inference/v1beta1/regions/{param_region}/deployments/{param_deployment_id}/acls",
706706
body=marshal_SetDeploymentACLRulesRequest(
707707
SetDeploymentACLRulesRequest(
708708
deployment_id=deployment_id,
@@ -742,7 +742,7 @@ def delete_deployment_acl_rule(
742742

743743
res = self._request(
744744
"DELETE",
745-
f"/llm-inference/v1beta1/regions/{param_region}/acls/{param_acl_id}",
745+
f"/inference/v1beta1/regions/{param_region}/acls/{param_acl_id}",
746746
)
747747

748748
self._throw_on_error(res)
@@ -782,7 +782,7 @@ def list_models(
782782

783783
res = self._request(
784784
"GET",
785-
f"/llm-inference/v1beta1/regions/{param_region}/models",
785+
f"/inference/v1beta1/regions/{param_region}/models",
786786
params={
787787
"name": name,
788788
"order_by": order_by,
@@ -868,7 +868,7 @@ def get_model(
868868

869869
res = self._request(
870870
"GET",
871-
f"/llm-inference/v1beta1/regions/{param_region}/models/{param_model_id}",
871+
f"/inference/v1beta1/regions/{param_region}/models/{param_model_id}",
872872
)
873873

874874
self._throw_on_error(res)
@@ -900,7 +900,7 @@ def get_model_eula(
900900

901901
res = self._request(
902902
"GET",
903-
f"/llm-inference/v1beta1/regions/{param_region}/models/{param_model_id}/eula",
903+
f"/inference/v1beta1/regions/{param_region}/models/{param_model_id}/eula",
904904
)
905905

906906
self._throw_on_error(res)
@@ -937,7 +937,7 @@ def list_node_types(
937937

938938
res = self._request(
939939
"GET",
940-
f"/llm-inference/v1beta1/regions/{param_region}/node-types",
940+
f"/inference/v1beta1/regions/{param_region}/node-types",
941941
params={
942942
"include_disabled_types": include_disabled_types,
943943
"page": page,

0 commit comments

Comments
 (0)