CentML · anandj91 · Jan 10, 2025 · Jan 10, 2025
diff --git a/README.md b/README.md
@@ -4,7 +4,7 @@ No description provided (generated by Openapi Generator https://github.com/opena
 This Python package is automatically generated by the [OpenAPI Generator](https://openapi-generator.tech) project:
 
 - API version: 0.1.0
-- Package version: 0.3.1
+- Package version: 3.1.6
 - Generator version: 7.9.0
 - Build package: org.openapitools.codegen.languages.PythonClientCodegen
 
@@ -99,43 +99,55 @@ Class | Method | HTTP request | Description
 *EXTERNALApi* | [**create_checkout_payments_checkout_post**](docs/EXTERNALApi.md#create_checkout_payments_checkout_post) | **POST** /payments/checkout | Create Checkout
 *EXTERNALApi* | [**create_compute_deployment_deployments_compute_post**](docs/EXTERNALApi.md#create_compute_deployment_deployments_compute_post) | **POST** /deployments/compute | Create Compute Deployment
 *EXTERNALApi* | [**create_cserve_deployment_deployments_cserve_post**](docs/EXTERNALApi.md#create_cserve_deployment_deployments_cserve_post) | **POST** /deployments/cserve | Create Cserve Deployment
+*EXTERNALApi* | [**create_cserve_v2_deployment_deployments_cserve_v2_post**](docs/EXTERNALApi.md#create_cserve_v2_deployment_deployments_cserve_v2_post) | **POST** /deployments/cserve_v2 | Create Cserve V2 Deployment
 *EXTERNALApi* | [**create_inference_deployment_deployments_inference_post**](docs/EXTERNALApi.md#create_inference_deployment_deployments_inference_post) | **POST** /deployments/inference | Create Inference Deployment
+*EXTERNALApi* | [**create_rag_deployment_deployments_rag_post**](docs/EXTERNALApi.md#create_rag_deployment_deployments_rag_post) | **POST** /deployments/rag | Create Rag Deployment
 *EXTERNALApi* | [**delete_api_key_credentials_api_key_id_delete**](docs/EXTERNALApi.md#delete_api_key_credentials_api_key_id_delete) | **DELETE** /credentials/api-key/{id} | Delete Api Key
+*EXTERNALApi* | [**delete_user_vault_item_endpoint_user_vault_delete**](docs/EXTERNALApi.md#delete_user_vault_item_endpoint_user_vault_delete) | **DELETE** /user_vault | Delete User Vault Item Endpoint
+*EXTERNALApi* | [**get_all_user_vault_items_endpoint_user_vault_get**](docs/EXTERNALApi.md#get_all_user_vault_items_endpoint_user_vault_get) | **GET** /user_vault | Get All User Vault Items Endpoint
 *EXTERNALApi* | [**get_api_keys_credentials_api_key_get**](docs/EXTERNALApi.md#get_api_keys_credentials_api_key_get) | **GET** /credentials/api-key | Get Api Keys
 *EXTERNALApi* | [**get_clusters_clusters_get**](docs/EXTERNALApi.md#get_clusters_clusters_get) | **GET** /clusters | Get Clusters
 *EXTERNALApi* | [**get_compute_deployment_deployments_compute_deployment_id_get**](docs/EXTERNALApi.md#get_compute_deployment_deployments_compute_deployment_id_get) | **GET** /deployments/compute/{deployment_id} | Get Compute Deployment
 *EXTERNALApi* | [**get_credits_credits_get**](docs/EXTERNALApi.md#get_credits_credits_get) | **GET** /credits | Get Credits
 *EXTERNALApi* | [**get_cserve_deployment_deployments_cserve_deployment_id_get**](docs/EXTERNALApi.md#get_cserve_deployment_deployments_cserve_deployment_id_get) | **GET** /deployments/cserve/{deployment_id} | Get Cserve Deployment
 *EXTERNALApi* | [**get_cserve_recipe_deployments_cserve_recipes_get**](docs/EXTERNALApi.md#get_cserve_recipe_deployments_cserve_recipes_get) | **GET** /deployments/cserve/recipes | Get Cserve Recipe
+*EXTERNALApi* | [**get_cserve_v2_deployment_deployments_cserve_v2_deployment_id_get**](docs/EXTERNALApi.md#get_cserve_v2_deployment_deployments_cserve_v2_deployment_id_get) | **GET** /deployments/cserve_v2/{deployment_id} | Get Cserve V2 Deployment
 *EXTERNALApi* | [**get_deployment_logs_deployments_logs_deployment_id_get**](docs/EXTERNALApi.md#get_deployment_logs_deployments_logs_deployment_id_get) | **GET** /deployments/logs/{deployment_id} | Get Deployment Logs
 *EXTERNALApi* | [**get_deployment_status_deployments_status_deployment_id_get**](docs/EXTERNALApi.md#get_deployment_status_deployments_status_deployment_id_get) | **GET** /deployments/status/{deployment_id} | Get Deployment Status
 *EXTERNALApi* | [**get_deployments_deployments_get**](docs/EXTERNALApi.md#get_deployments_deployments_get) | **GET** /deployments | Get Deployments
 *EXTERNALApi* | [**get_hardware_instances_hardware_instances_get**](docs/EXTERNALApi.md#get_hardware_instances_hardware_instances_get) | **GET** /hardware-instances | Get Hardware Instances
 *EXTERNALApi* | [**get_inference_deployment_deployments_inference_deployment_id_get**](docs/EXTERNALApi.md#get_inference_deployment_deployments_inference_deployment_id_get) | **GET** /deployments/inference/{deployment_id} | Get Inference Deployment
 *EXTERNALApi* | [**get_payments_payments_get**](docs/EXTERNALApi.md#get_payments_payments_get) | **GET** /payments | Get Payments
 *EXTERNALApi* | [**get_prebuilt_images_prebuilt_images_get**](docs/EXTERNALApi.md#get_prebuilt_images_prebuilt_images_get) | **GET** /prebuilt-images | Get Prebuilt Images
+*EXTERNALApi* | [**get_rag_deployment_deployments_rag_deployment_id_get**](docs/EXTERNALApi.md#get_rag_deployment_deployments_rag_deployment_id_get) | **GET** /deployments/rag/{deployment_id} | Get Rag Deployment
 *EXTERNALApi* | [**get_usage_daily_bills_get**](docs/EXTERNALApi.md#get_usage_daily_bills_get) | **GET** /daily_bills | Get Usage
 *EXTERNALApi* | [**get_usage_deployments_usage_deployment_id_get**](docs/EXTERNALApi.md#get_usage_deployments_usage_deployment_id_get) | **GET** /deployments/usage/{deployment_id} | Get Usage
 *EXTERNALApi* | [**setup_stripe_customer_payments_setup_post**](docs/EXTERNALApi.md#setup_stripe_customer_payments_setup_post) | **POST** /payments/setup | Setup Stripe Customer
 *EXTERNALApi* | [**update_deployment_status_deployments_status_deployment_id_put**](docs/EXTERNALApi.md#update_deployment_status_deployments_status_deployment_id_put) | **PUT** /deployments/status/{deployment_id} | Update Deployment Status
+*EXTERNALApi* | [**update_user_vault_item_endpoint_user_vault_put**](docs/EXTERNALApi.md#update_user_vault_item_endpoint_user_vault_put) | **PUT** /user_vault | Update User Vault Item Endpoint
 
 
 ## Documentation For Models
 
  - [APIKeyRequest](docs/APIKeyRequest.md)
  - [APIKeyResponse](docs/APIKeyResponse.md)
- - [CServeRecipeInput](docs/CServeRecipeInput.md)
- - [CServeRecipeOutput](docs/CServeRecipeOutput.md)
+ - [CServeRecipe](docs/CServeRecipe.md)
  - [CServeRecipePerf](docs/CServeRecipePerf.md)
  - [CServeRecipeResponse](docs/CServeRecipeResponse.md)
+ - [CServeV2RecipeInput](docs/CServeV2RecipeInput.md)
+ - [CServeV2RecipeOutput](docs/CServeV2RecipeOutput.md)
  - [CreateCServeDeploymentRequest](docs/CreateCServeDeploymentRequest.md)
  - [CreateCServeDeploymentResponse](docs/CreateCServeDeploymentResponse.md)
+ - [CreateCServeV2DeploymentRequest](docs/CreateCServeV2DeploymentRequest.md)
+ - [CreateCServeV2DeploymentResponse](docs/CreateCServeV2DeploymentResponse.md)
  - [CreateCheckoutRequest](docs/CreateCheckoutRequest.md)
  - [CreateCheckoutResponse](docs/CreateCheckoutResponse.md)
  - [CreateComputeDeploymentRequest](docs/CreateComputeDeploymentRequest.md)
  - [CreateComputeDeploymentResponse](docs/CreateComputeDeploymentResponse.md)
  - [CreateInferenceDeploymentRequest](docs/CreateInferenceDeploymentRequest.md)
  - [CreateInferenceDeploymentResponse](docs/CreateInferenceDeploymentResponse.md)
+ - [CreateRagDeploymentRequest](docs/CreateRagDeploymentRequest.md)
+ - [CreateRagDeploymentResponse](docs/CreateRagDeploymentResponse.md)
  - [CreditsResponse](docs/CreditsResponse.md)
  - [DailyBillResponse](docs/DailyBillResponse.md)
  - [DeploymentStatus](docs/DeploymentStatus.md)
@@ -144,13 +156,15 @@ Class | Method | HTTP request | Description
  - [DeploymentType](docs/DeploymentType.md)
  - [DeploymentUsageValue](docs/DeploymentUsageValue.md)
  - [GetCServeDeploymentResponse](docs/GetCServeDeploymentResponse.md)
+ - [GetCServeV2DeploymentResponse](docs/GetCServeV2DeploymentResponse.md)
  - [GetClusterResponse](docs/GetClusterResponse.md)
  - [GetComputeDeploymentResponse](docs/GetComputeDeploymentResponse.md)
  - [GetDeploymentLogResponse](docs/GetDeploymentLogResponse.md)
  - [GetDeploymentResponse](docs/GetDeploymentResponse.md)
  - [GetDeploymentUsageResponse](docs/GetDeploymentUsageResponse.md)
  - [GetInferenceDeploymentResponse](docs/GetInferenceDeploymentResponse.md)
  - [GetPaymentsResponse](docs/GetPaymentsResponse.md)
+ - [GetRagDeploymentResponse](docs/GetRagDeploymentResponse.md)
  - [HTTPValidationError](docs/HTTPValidationError.md)
  - [HardwareInstanceResponse](docs/HardwareInstanceResponse.md)
  - [ListAPIKeyResponse](docs/ListAPIKeyResponse.md)
@@ -160,10 +174,14 @@ Class | Method | HTTP request | Description
  - [ListGetDeploymentResponse](docs/ListGetDeploymentResponse.md)
  - [ListHardwareInstanceResponse](docs/ListHardwareInstanceResponse.md)
  - [ListPrebuiltImageResponse](docs/ListPrebuiltImageResponse.md)
+ - [ListUserVaultItemsResponse](docs/ListUserVaultItemsResponse.md)
  - [Metric](docs/Metric.md)
  - [PrebuiltImageResponse](docs/PrebuiltImageResponse.md)
  - [ServiceStatus](docs/ServiceStatus.md)
  - [UserSupportEmailRequest](docs/UserSupportEmailRequest.md)
+ - [UserVaultItemInput](docs/UserVaultItemInput.md)
+ - [UserVaultItemOutput](docs/UserVaultItemOutput.md)
+ - [UserVaultType](docs/UserVaultType.md)
  - [ValidationError](docs/ValidationError.md)
  - [ValidationErrorLocInner](docs/ValidationErrorLocInner.md)
 

diff --git a/docs/CServeRecipeInput.md → docs/CServeRecipe.md b/docs/CServeRecipeInput.md → docs/CServeRecipe.md
@@ -1,4 +1,4 @@
-# CServeRecipeInput
+# CServeRecipe
 
 Base class for deployment planner
 
@@ -14,8 +14,12 @@ Name | Type | Description | Notes
 **swap_space** | **int** |  | [optional] [default to 0]
 **gpu_mem_util** | **float** |  | [optional] [default to 0.95]
 **max_num_seqs** | **int** |  | [optional] [default to 256]
-**use_prefix_caching** | **bool** |  | [optional] 
 **offloading_num** | **int** |  | [optional] [default to 0]
+**use_prefix_caching** | **bool** |  | [optional] 
+**use_chunked_prefill** | **bool** |  | [optional] 
+**chunked_prefill_size** | **int** |  | [optional] 
+**eager_execution** | **bool** |  | [optional] 
+**num_scheduler_steps** | **int** |  | [optional] 
 **use_flashinfer** | **bool** |  | [optional] [default to False]
 **max_model_len** | **int** |  | [optional] 
 **dtype** | **str** |  | [optional] [default to 'auto']
@@ -30,19 +34,19 @@ Name | Type | Description | Notes
 ## Example
 
 ```python
-from platform_api_python_client.models.c_serve_recipe_input import CServeRecipeInput
+from platform_api_python_client.models.c_serve_recipe import CServeRecipe
 
 # TODO update the JSON string below
 json = "{}"
-# create an instance of CServeRecipeInput from a JSON string
-c_serve_recipe_input_instance = CServeRecipeInput.from_json(json)
+# create an instance of CServeRecipe from a JSON string
+c_serve_recipe_instance = CServeRecipe.from_json(json)
 # print the JSON string representation of the object
-print(CServeRecipeInput.to_json())
+print(CServeRecipe.to_json())
 
 # convert the object into a dict
-c_serve_recipe_input_dict = c_serve_recipe_input_instance.to_dict()
-# create an instance of CServeRecipeInput from a dict
-c_serve_recipe_input_from_dict = CServeRecipeInput.from_dict(c_serve_recipe_input_dict)
+c_serve_recipe_dict = c_serve_recipe_instance.to_dict()
+# create an instance of CServeRecipe from a dict
+c_serve_recipe_from_dict = CServeRecipe.from_dict(c_serve_recipe_dict)
 ```
 [[Back to Model list]](../README.md#documentation-for-models) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to README]](../README.md)
 

diff --git a/docs/CServeRecipePerf.md b/docs/CServeRecipePerf.md
@@ -5,7 +5,7 @@
 
 Name | Type | Description | Notes
 ------------ | ------------- | ------------- | -------------
-**recipe** | [**CServeRecipeOutput**](CServeRecipeOutput.md) |  | 
+**recipe** | [**CServeV2RecipeOutput**](CServeV2RecipeOutput.md) |  | 
 **hardware_instance_id** | **int** |  | 
 **output_tp** | **List[List[object]]** |  | 
 **mean_ttft** | **List[List[object]]** |  | 

diff --git a/docs/CServeRecipeOutput.md → docs/CServeV2Recipe.md b/docs/CServeRecipeOutput.md → docs/CServeV2Recipe.md
@@ -1,48 +1,56 @@
-# CServeRecipeOutput
+# CServeV2Recipe
 
-Base class for deployment planner
+Inputs to start deployment
 
 ## Properties
 
 Name | Type | Description | Notes
 ------------ | ------------- | ------------- | -------------
 **model** | **str** |  | 
+**max_model_len** | **int** |  | 
 **is_embedding_model** | **bool** |  | [default to False]
+**tokenizer** | **str** |  | 
 **tensor_parallel_size** | **int** |  | 
 **pipeline_parallel_size** | **int** |  | 
+**gpu_mem_util** | **float** |  | [default to 0.95]
 **block_size** | **int** |  | [default to 32]
 **swap_space** | **int** |  | [default to 0]
-**gpu_mem_util** | **float** |  | [default to 0.95]
+**quantization** | **str** |  | 
+**dtype** | **str** |  | [default to 'auto']
+**cache_dtype** | **str** |  | [default to 'auto']
 **max_num_seqs** | **int** |  | [default to 256]
-**use_prefix_caching** | **bool** |  | 
-**offloading_num** | **int** |  | [default to 0]
+**eager_execution** | **bool** |  | [default to True]
 **use_flashinfer** | **bool** |  | [default to False]
-**max_model_len** | **int** |  | 
-**dtype** | **str** |  | [default to 'auto']
-**tokenizer** | **str** |  | 
-**spec_proposer** | **str** |  | 
+**offloading_num** | **float** |  | [default to 0]
 **spec_draft_model** | **str** |  | 
 **spec_tokens** | **int** |  | 
-**spec_prompt_lookup_min** | **int** |  | 
 **spec_prompt_lookup_max** | **int** |  | 
-**seed** | **int** |  | [default to 0]
+**spec_prompt_lookup_min** | **int** |  | 
+**use_prefix_caching** | **bool** |  | [default to False]
+**use_chunked_prefill** | **bool** |  | [default to False]
+**chunked_prefill_size** | **int** |  | 
+**max_seq_len_to_capture** | **int** |  | [default to 1024]
+**distributed_executor_backend** | **str** |  | [default to 'ray']
+**spec_max_batch_size** | **int** |  | 
+**spec_max_seq_len** | **int** |  | 
+**num_scheduler_steps** | **int** |  | [default to 1]
 
 ## Example
 
 ```python
-from platform_api_python_client.models.c_serve_recipe_output import CServeRecipeOutput
+from platform_api_python_client.models.c_serve_v2_recipe import CServeV2Recipe
 
 # TODO update the JSON string below
 json = "{}"
-# create an instance of CServeRecipeOutput from a JSON string
-c_serve_recipe_output_instance = CServeRecipeOutput.from_json(json)
+# create an instance of CServeV2Recipe from a JSON string
+c_serve_v2_recipe_instance = CServeV2Recipe.from_json(json)
 # print the JSON string representation of the object
-print(CServeRecipeOutput.to_json())
+print(CServeV2Recipe.to_json())
 
 # convert the object into a dict
-c_serve_recipe_output_dict = c_serve_recipe_output_instance.to_dict()
-# create an instance of CServeRecipeOutput from a dict
-c_serve_recipe_output_from_dict = CServeRecipeOutput.from_dict(c_serve_recipe_output_dict)
+c_serve_v2_recipe_dict = c_serve_v2_recipe_instance.to_dict()
+# create an instance of CServeV2Recipe from a dict
+c_serve_v2_recipe_from_dict = CServeV2Recipe.from_dict(c_serve_v2_recipe_dict)
 ```
 [[Back to Model list]](../README.md#documentation-for-models) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to README]](../README.md)
 

diff --git a/docs/CServeV2RecipeInput.md b/docs/CServeV2RecipeInput.md
@@ -0,0 +1,57 @@
+# CServeV2RecipeInput
+
+Inputs to start deployment
+
+## Properties
+
+Name | Type | Description | Notes
+------------ | ------------- | ------------- | -------------
+**model** | **str** |  | 
+**max_model_len** | **int** |  | [optional] 
+**is_embedding_model** | **bool** |  | [optional] [default to False]
+**tokenizer** | **str** |  | 
+**tensor_parallel_size** | **int** |  | 
+**pipeline_parallel_size** | **int** |  | 
+**gpu_mem_util** | **float** |  | [optional] [default to 0.95]
+**block_size** | **int** |  | [optional] [default to 16]
+**swap_space** | **int** |  | [optional] [default to 0]
+**quantization** | **str** |  | [optional] 
+**dtype** | **str** |  | [optional] [default to 'auto']
+**cache_dtype** | **str** |  | [optional] [default to 'auto']
+**max_num_seqs** | **int** |  | [optional] [default to 256]
+**eager_execution** | **bool** |  | [optional] [default to True]
+**use_flashinfer** | **bool** |  | [optional] [default to False]
+**offloading_num** | **float** |  | [optional] [default to 0]
+**spec_draft_model** | **str** |  | [optional] 
+**spec_tokens** | **int** |  | [optional] 
+**spec_prompt_lookup_max** | **int** |  | [optional] 
+**spec_prompt_lookup_min** | **int** |  | [optional] 
+**use_prefix_caching** | **bool** |  | [optional] [default to False]
+**use_chunked_prefill** | **bool** |  | [optional] [default to False]
+**chunked_prefill_size** | **int** |  | [optional] 
+**max_seq_len_to_capture** | **int** |  | [optional] [default to 8192]
+**distributed_executor_backend** | **str** |  | [optional] [default to 'mp']
+**spec_max_batch_size** | **int** |  | [optional] 
+**spec_max_seq_len** | **int** |  | [optional] 
+**num_scheduler_steps** | **int** |  | [optional] [default to 1]
+
+## Example
+
+```python
+from platform_api_python_client.models.c_serve_v2_recipe_input import CServeV2RecipeInput
+
+# TODO update the JSON string below
+json = "{}"
+# create an instance of CServeV2RecipeInput from a JSON string
+c_serve_v2_recipe_input_instance = CServeV2RecipeInput.from_json(json)
+# print the JSON string representation of the object
+print(CServeV2RecipeInput.to_json())
+
+# convert the object into a dict
+c_serve_v2_recipe_input_dict = c_serve_v2_recipe_input_instance.to_dict()
+# create an instance of CServeV2RecipeInput from a dict
+c_serve_v2_recipe_input_from_dict = CServeV2RecipeInput.from_dict(c_serve_v2_recipe_input_dict)
+```
+[[Back to Model list]](../README.md#documentation-for-models) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to README]](../README.md)
+
+
diff --git a/docs/CServeV2RecipeOutput.md b/docs/CServeV2RecipeOutput.md
@@ -0,0 +1,57 @@
+# CServeV2RecipeOutput
+
+Inputs to start deployment
+
+## Properties
+
+Name | Type | Description | Notes
+------------ | ------------- | ------------- | -------------
+**model** | **str** |  | 
+**max_model_len** | **int** |  | 
+**is_embedding_model** | **bool** |  | [default to False]
+**tokenizer** | **str** |  | 
+**tensor_parallel_size** | **int** |  | 
+**pipeline_parallel_size** | **int** |  | 
+**gpu_mem_util** | **float** |  | [default to 0.95]
+**block_size** | **int** |  | [default to 16]
+**swap_space** | **int** |  | [default to 0]
+**quantization** | **str** |  | 
+**dtype** | **str** |  | [default to 'auto']
+**cache_dtype** | **str** |  | [default to 'auto']
+**max_num_seqs** | **int** |  | [default to 256]
+**eager_execution** | **bool** |  | [default to True]
+**use_flashinfer** | **bool** |  | [default to False]
+**offloading_num** | **float** |  | [default to 0]
+**spec_draft_model** | **str** |  | 
+**spec_tokens** | **int** |  | 
+**spec_prompt_lookup_max** | **int** |  | 
+**spec_prompt_lookup_min** | **int** |  | 
+**use_prefix_caching** | **bool** |  | [default to False]
+**use_chunked_prefill** | **bool** |  | [default to False]
+**chunked_prefill_size** | **int** |  | 
+**max_seq_len_to_capture** | **int** |  | [default to 8192]
+**distributed_executor_backend** | **str** |  | [default to 'mp']
+**spec_max_batch_size** | **int** |  | 
+**spec_max_seq_len** | **int** |  | 
+**num_scheduler_steps** | **int** |  | [default to 1]
+
+## Example
+
+```python
+from platform_api_python_client.models.c_serve_v2_recipe_output import CServeV2RecipeOutput
+
+# TODO update the JSON string below
+json = "{}"
+# create an instance of CServeV2RecipeOutput from a JSON string
+c_serve_v2_recipe_output_instance = CServeV2RecipeOutput.from_json(json)
+# print the JSON string representation of the object
+print(CServeV2RecipeOutput.to_json())
+
+# convert the object into a dict
+c_serve_v2_recipe_output_dict = c_serve_v2_recipe_output_instance.to_dict()
+# create an instance of CServeV2RecipeOutput from a dict
+c_serve_v2_recipe_output_from_dict = CServeV2RecipeOutput.from_dict(c_serve_v2_recipe_output_dict)
+```
+[[Back to Model list]](../README.md#documentation-for-models) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to README]](../README.md)
+
+