Get a vector representation of a given input that can be easily consumed by machine learning models and algorithms.
oai_create_embeddings(): Creates an embedding vector representing the input text.
Usage
oai_create_embeddings(
input,
model,
encoding_format = c("float", "base64"),
dimensions = NULL,
user = NULL,
.classify_response = TRUE,
.async = FALSE
)Arguments
- input
Character. Input text to embed, encoded as a string or array of tokens. To embed multiple inputs in a single request, pass an array of strings or array of token arrays. The input must not exceed the max input tokens for the model (8192 tokens for text-embedding-ada-002), cannot be an empty string, and any array must be 2048 dimensions or less. Example Python code for counting tokens.
- model
Character. ID of the model to use. You can use the
oai_list_models()function to see all of your available models.- encoding_format
Character. Defaults to "float". The format to return the embeddings in. Can be either "float" or "base64".
- dimensions
Integer. The number of dimensions the resulting output embeddings should have. Only supported in text-embedding-3 and later models.
- user
Character. A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.
- .classify_response
Logical. If
TRUE(default), the response is classified as an R6 object. IfFALSE, the response is returned as a list.- .async
Logical. If
TRUE, the request is performed asynchronously.