AnyscaleEmbeddings

Base URL path for API requests, leave blank if not using a proxy or service

Automatically inferred from env var OPENAI_API_KEY if not provided.

Automatically inferred from env var OPENAI_ORG_ID if not provided.

Maximum number of texts to embed in each batch

Maximum number of retries to make when generating.

Timeout for requests to OpenAI completion API. Can be float, httpx.Timeout or

The model name to pass to tiktoken when using this class.

Whether to show a progress bar when embedding.

Holds any model parameters valid for create call not explicitly specified.

Whether to skip empty strings when embedding or raise an error.

Min number of seconds to wait between retries

Max number of seconds to wait between retries

Optional httpx.Client.