跳到主要内容
版本:v0.8.1

OpenAPIEmbeddingDeployModelParameters Configuration

OpenAPI embedding deploy model parameters.

Parameters

NameTypeRequiredDescription
namestring✅
The name of the model.
providerstring❌
The provider of the model. If model is deployed in local, this is the inference type. If model is deployed in third-party service, this is platform name('proxy/<platform>')
Defaults:proxy/openai
verboseboolean❌
Show verbose output.
Defaults:False
concurrencyinteger❌
Model concurrency limit
Defaults:100
api_urlstring❌
The URL of the embeddings API.
Defaults:http://localhost:8100/api/v1/embeddings
api_keystring❌
The API key for the embeddings API.
backendstring❌
The real model name to pass to the provider, default is None. If backend is None, use name as the real model name.
timeoutinteger❌
The timeout for the request in seconds.
Defaults:60