@cotofe/service-of-litellm
Version:
OpenAPI client for @cotofe/service-of-litellm
112 lines (111 loc) • 18.3 kB
TypeScript
/**
* Platform
* No description provided (generated by Openapi Generator https://github.com/openapitools/openapi-generator)
*
* The version of the OpenAPI document: 1.0.0
*
*
* NOTE: This class is auto generated by OpenAPI Generator (https://openapi-generator.tech).
* https://openapi-generator.tech
* Do not edit the class manually.
*/
import type { Deployment, ModelInfoDelete, UpdateDeployment } from '../models/index';
import * as runtime from '../runtime';
export interface LitellmModelManagementApiAddNewModelModelNewPostRequest {
deployment?: Deployment;
}
export interface LitellmModelManagementApiDeleteModelModelDeletePostRequest {
modelInfoDelete?: ModelInfoDelete;
}
export interface LitellmModelManagementApiModelGroupInfoModelGroupInfoGetRequest {
modelGroup?: string | null;
}
export interface LitellmModelManagementApiModelInfoV1ModelInfoGetRequest {
litellmModelId?: string | null;
}
export interface LitellmModelManagementApiModelListModelsGetRequest {
returnWildcardRoutes?: boolean | null;
teamId?: string | null;
}
export interface LitellmModelManagementApiPatchModelModelModelIdUpdatePatchRequest {
modelId: string;
updateDeployment?: UpdateDeployment;
}
export interface LitellmModelManagementApiUpdateModelModelUpdatePostRequest {
updateDeployment?: UpdateDeployment;
}
/**
*
*/
export declare class LitellmModelManagementApi extends runtime.BaseAPI {
/**
* Allows adding new models to the model list in the config.yaml
* Add New Model
*/
addNewModelModelNewPostRaw(requestParameters: LitellmModelManagementApiAddNewModelModelNewPostRequest, initOverrides?: RequestInit | runtime.InitOverrideFunction): Promise<runtime.ApiResponse<string>>;
/**
* Allows adding new models to the model list in the config.yaml
* Add New Model
*/
addNewModelModelNewPost(requestParameters?: LitellmModelManagementApiAddNewModelModelNewPostRequest, initOverrides?: RequestInit | runtime.InitOverrideFunction): Promise<string>;
/**
* Allows deleting models in the model list in the config.yaml
* Delete Model
*/
deleteModelModelDeletePostRaw(requestParameters: LitellmModelManagementApiDeleteModelModelDeletePostRequest, initOverrides?: RequestInit | runtime.InitOverrideFunction): Promise<runtime.ApiResponse<string>>;
/**
* Allows deleting models in the model list in the config.yaml
* Delete Model
*/
deleteModelModelDeletePost(requestParameters?: LitellmModelManagementApiDeleteModelModelDeletePostRequest, initOverrides?: RequestInit | runtime.InitOverrideFunction): Promise<string>;
/**
* Get information about all the deployments on litellm proxy, including config.yaml descriptions (except api key and api base) - /model_group/info returns all model groups. End users of proxy should use /model_group/info since those models will be used for /chat/completions, /embeddings, etc. - /model_group/info?model_group=rerank-english-v3.0 returns all model groups for a specific model group (`model_name` in config.yaml) Example Request (All Models): ```shell curl -X \'GET\' \'http://localhost:4000/model_group/info\' -H \'accept: application/json\' -H \'x-api-key: sk-1234\' ``` Example Request (Specific Model Group): ```shell curl -X \'GET\' \'http://localhost:4000/model_group/info?model_group=rerank-english-v3.0\' -H \'accept: application/json\' -H \'Authorization: Bearer sk-1234\' ``` Example Request (Specific Wildcard Model Group): (e.g. `model_name: openai/_*` on config.yaml) ```shell curl -X \'GET\' \'http://localhost:4000/model_group/info?model_group=openai/tts-1\' -H \'accept: application/json\' -H \'Authorization: Bearersk-1234\' ``` Learn how to use and set wildcard models [here](https://docs.litellm.ai/docs/wildcard_routing) Example Response: ```json { \"data\": [ { \"model_group\": \"rerank-english-v3.0\", \"providers\": [ \"cohere\" ], \"max_input_tokens\": null, \"max_output_tokens\": null, \"input_cost_per_token\": 0.0, \"output_cost_per_token\": 0.0, \"mode\": null, \"tpm\": null, \"rpm\": null, \"supports_parallel_function_calling\": false, \"supports_vision\": false, \"supports_function_calling\": false, \"supported_openai_params\": [ \"stream\", \"temperature\", \"max_tokens\", \"logit_bias\", \"top_p\", \"frequency_penalty\", \"presence_penalty\", \"stop\", \"n\", \"extra_headers\" ] }, { \"model_group\": \"gpt-3.5-turbo\", \"providers\": [ \"openai\" ], \"max_input_tokens\": 16385.0, \"max_output_tokens\": 4096.0, \"input_cost_per_token\": 1.5e-06, \"output_cost_per_token\": 2e-06, \"mode\": \"chat\", \"tpm\": null, \"rpm\": null, \"supports_parallel_function_calling\": false, \"supports_vision\": false, \"supports_function_calling\": true, \"supported_openai_params\": [ \"frequency_penalty\", \"logit_bias\", \"logprobs\", \"top_logprobs\", \"max_tokens\", \"max_completion_tokens\", \"n\", \"presence_penalty\", \"seed\", \"stop\", \"stream\", \"stream_options\", \"temperature\", \"top_p\", \"tools\", \"tool_choice\", \"function_call\", \"functions\", \"max_retries\", \"extra_headers\", \"parallel_tool_calls\", \"response_format\" ] }, { \"model_group\": \"llava-hf\", \"providers\": [ \"openai\" ], \"max_input_tokens\": null, \"max_output_tokens\": null, \"input_cost_per_token\": 0.0, \"output_cost_per_token\": 0.0, \"mode\": null, \"tpm\": null, \"rpm\": null, \"supports_parallel_function_calling\": false, \"supports_vision\": true, \"supports_function_calling\": false, \"supported_openai_params\": [ \"frequency_penalty\", \"logit_bias\", \"logprobs\", \"top_logprobs\", \"max_tokens\", \"max_completion_tokens\", \"n\", \"presence_penalty\", \"seed\", \"stop\", \"stream\", \"stream_options\", \"temperature\", \"top_p\", \"tools\", \"tool_choice\", \"function_call\", \"functions\", \"max_retries\", \"extra_headers\", \"parallel_tool_calls\", \"response_format\" ] } ] } ```
* Model Group Info
*/
modelGroupInfoModelGroupInfoGetRaw(requestParameters: LitellmModelManagementApiModelGroupInfoModelGroupInfoGetRequest, initOverrides?: RequestInit | runtime.InitOverrideFunction): Promise<runtime.ApiResponse<string>>;
/**
* Get information about all the deployments on litellm proxy, including config.yaml descriptions (except api key and api base) - /model_group/info returns all model groups. End users of proxy should use /model_group/info since those models will be used for /chat/completions, /embeddings, etc. - /model_group/info?model_group=rerank-english-v3.0 returns all model groups for a specific model group (`model_name` in config.yaml) Example Request (All Models): ```shell curl -X \'GET\' \'http://localhost:4000/model_group/info\' -H \'accept: application/json\' -H \'x-api-key: sk-1234\' ``` Example Request (Specific Model Group): ```shell curl -X \'GET\' \'http://localhost:4000/model_group/info?model_group=rerank-english-v3.0\' -H \'accept: application/json\' -H \'Authorization: Bearer sk-1234\' ``` Example Request (Specific Wildcard Model Group): (e.g. `model_name: openai/_*` on config.yaml) ```shell curl -X \'GET\' \'http://localhost:4000/model_group/info?model_group=openai/tts-1\' -H \'accept: application/json\' -H \'Authorization: Bearersk-1234\' ``` Learn how to use and set wildcard models [here](https://docs.litellm.ai/docs/wildcard_routing) Example Response: ```json { \"data\": [ { \"model_group\": \"rerank-english-v3.0\", \"providers\": [ \"cohere\" ], \"max_input_tokens\": null, \"max_output_tokens\": null, \"input_cost_per_token\": 0.0, \"output_cost_per_token\": 0.0, \"mode\": null, \"tpm\": null, \"rpm\": null, \"supports_parallel_function_calling\": false, \"supports_vision\": false, \"supports_function_calling\": false, \"supported_openai_params\": [ \"stream\", \"temperature\", \"max_tokens\", \"logit_bias\", \"top_p\", \"frequency_penalty\", \"presence_penalty\", \"stop\", \"n\", \"extra_headers\" ] }, { \"model_group\": \"gpt-3.5-turbo\", \"providers\": [ \"openai\" ], \"max_input_tokens\": 16385.0, \"max_output_tokens\": 4096.0, \"input_cost_per_token\": 1.5e-06, \"output_cost_per_token\": 2e-06, \"mode\": \"chat\", \"tpm\": null, \"rpm\": null, \"supports_parallel_function_calling\": false, \"supports_vision\": false, \"supports_function_calling\": true, \"supported_openai_params\": [ \"frequency_penalty\", \"logit_bias\", \"logprobs\", \"top_logprobs\", \"max_tokens\", \"max_completion_tokens\", \"n\", \"presence_penalty\", \"seed\", \"stop\", \"stream\", \"stream_options\", \"temperature\", \"top_p\", \"tools\", \"tool_choice\", \"function_call\", \"functions\", \"max_retries\", \"extra_headers\", \"parallel_tool_calls\", \"response_format\" ] }, { \"model_group\": \"llava-hf\", \"providers\": [ \"openai\" ], \"max_input_tokens\": null, \"max_output_tokens\": null, \"input_cost_per_token\": 0.0, \"output_cost_per_token\": 0.0, \"mode\": null, \"tpm\": null, \"rpm\": null, \"supports_parallel_function_calling\": false, \"supports_vision\": true, \"supports_function_calling\": false, \"supported_openai_params\": [ \"frequency_penalty\", \"logit_bias\", \"logprobs\", \"top_logprobs\", \"max_tokens\", \"max_completion_tokens\", \"n\", \"presence_penalty\", \"seed\", \"stop\", \"stream\", \"stream_options\", \"temperature\", \"top_p\", \"tools\", \"tool_choice\", \"function_call\", \"functions\", \"max_retries\", \"extra_headers\", \"parallel_tool_calls\", \"response_format\" ] } ] } ```
* Model Group Info
*/
modelGroupInfoModelGroupInfoGet(requestParameters?: LitellmModelManagementApiModelGroupInfoModelGroupInfoGetRequest, initOverrides?: RequestInit | runtime.InitOverrideFunction): Promise<string>;
/**
* Provides more info about each model in /models, including config.yaml descriptions (except api key and api base) Parameters: litellm_model_id: Optional[str] = None (this is the value of `x-litellm-model-id` returned in response headers) - When litellm_model_id is passed, it will return the info for that specific model - When litellm_model_id is not passed, it will return the info for all models Returns: Returns a dictionary containing information about each model. Example Response: ```json { \"data\": [ { \"model_name\": \"fake-openai-endpoint\", \"litellm_params\": { \"api_base\": \"https://exampleopenaiendpoint-production.up.railway.app/\", \"model\": \"openai/fake\" }, \"model_info\": { \"id\": \"112f74fab24a7a5245d2ced3536dd8f5f9192c57ee6e332af0f0512e08bed5af\", \"db_model\": false } } ] } ```
* Model Info V1
*/
modelInfoV1ModelInfoGetRaw(requestParameters: LitellmModelManagementApiModelInfoV1ModelInfoGetRequest, initOverrides?: RequestInit | runtime.InitOverrideFunction): Promise<runtime.ApiResponse<string>>;
/**
* Provides more info about each model in /models, including config.yaml descriptions (except api key and api base) Parameters: litellm_model_id: Optional[str] = None (this is the value of `x-litellm-model-id` returned in response headers) - When litellm_model_id is passed, it will return the info for that specific model - When litellm_model_id is not passed, it will return the info for all models Returns: Returns a dictionary containing information about each model. Example Response: ```json { \"data\": [ { \"model_name\": \"fake-openai-endpoint\", \"litellm_params\": { \"api_base\": \"https://exampleopenaiendpoint-production.up.railway.app/\", \"model\": \"openai/fake\" }, \"model_info\": { \"id\": \"112f74fab24a7a5245d2ced3536dd8f5f9192c57ee6e332af0f0512e08bed5af\", \"db_model\": false } } ] } ```
* Model Info V1
*/
modelInfoV1ModelInfoGet(requestParameters?: LitellmModelManagementApiModelInfoV1ModelInfoGetRequest, initOverrides?: RequestInit | runtime.InitOverrideFunction): Promise<string>;
/**
* Use `/model/info` - to get detailed model information, example - pricing, mode, etc. This is just for compatibility with openai projects like aider.
* Model List
*/
modelListModelsGetRaw(requestParameters: LitellmModelManagementApiModelListModelsGetRequest, initOverrides?: RequestInit | runtime.InitOverrideFunction): Promise<runtime.ApiResponse<string>>;
/**
* Use `/model/info` - to get detailed model information, example - pricing, mode, etc. This is just for compatibility with openai projects like aider.
* Model List
*/
modelListModelsGet(requestParameters?: LitellmModelManagementApiModelListModelsGetRequest, initOverrides?: RequestInit | runtime.InitOverrideFunction): Promise<string>;
/**
* PATCH Endpoint for partial model updates. Only updates the fields specified in the request while preserving other existing values. Follows proper PATCH semantics by only modifying provided fields. Args: model_id: The ID of the model to update patch_data: The fields to update and their new values user_api_key_dict: User authentication information Returns: Updated model information Raises: ProxyException: For various error conditions including authentication and database errors
* Patch Model
*/
patchModelModelModelIdUpdatePatchRaw(requestParameters: LitellmModelManagementApiPatchModelModelModelIdUpdatePatchRequest, initOverrides?: RequestInit | runtime.InitOverrideFunction): Promise<runtime.ApiResponse<string>>;
/**
* PATCH Endpoint for partial model updates. Only updates the fields specified in the request while preserving other existing values. Follows proper PATCH semantics by only modifying provided fields. Args: model_id: The ID of the model to update patch_data: The fields to update and their new values user_api_key_dict: User authentication information Returns: Updated model information Raises: ProxyException: For various error conditions including authentication and database errors
* Patch Model
*/
patchModelModelModelIdUpdatePatch(requestParameters: LitellmModelManagementApiPatchModelModelModelIdUpdatePatchRequest, initOverrides?: RequestInit | runtime.InitOverrideFunction): Promise<string>;
/**
* Edit existing model params
* Update Model
*/
updateModelModelUpdatePostRaw(requestParameters: LitellmModelManagementApiUpdateModelModelUpdatePostRequest, initOverrides?: RequestInit | runtime.InitOverrideFunction): Promise<runtime.ApiResponse<string>>;
/**
* Edit existing model params
* Update Model
*/
updateModelModelUpdatePost(requestParameters?: LitellmModelManagementApiUpdateModelModelUpdatePostRequest, initOverrides?: RequestInit | runtime.InitOverrideFunction): Promise<string>;
}