Struct Classification

pub struct Classification<'a> {

    pub model: Option<Model>,
    pub query: Cow<'a, str>,
    pub examples: Vec<[Cow<'a, str>; 2]>,
    pub file: Option<Cow<'a, str>>,
    pub labels: Vec<Cow<'a, str>>,
    pub search_model: Option<Model>,
    pub temperature: Option<f32>,
    pub logprobs: Option<u32>,
    pub max_examples: Option<u32>,
    pub logit_bias: HashMap<Cow<'a, str>, i32>,
    pub return_prompt: Option<bool>,
    pub return_metadata: Option<bool>,
    pub expand: Vec<Cow<'a, str>>,
    pub user: Option<Cow<'a, str>>,
}

Given a query and a set of labeled examples, the model will predict the most likely label for the query. Useful as a drop-in replacement for any ML classification or text-to-label task.

Fields

model: Option<Model>

ID of the engine to use for completion. You can select one of ada, babbage, curie, or davinci.

query: Cow<'a, str>

Query to be classified.

examples: Vec<[Cow<'a, str>; 2]>

A list of examples with labels, in the following format: [["The movie is so interesting.", "Positive"], ["It is quite boring.", "Negative"], ...] All the label strings will be normalized to be capitalized. You should specify either examples or file, but not both.

file: Option<Cow<'a, str>>

The ID of the uploaded file that contains training examples. See upload file for how to upload a file of the desired format and purpose. You should specify either examples or file, but not both.

labels: Vec<Cow<'a, str>>

The set of categories being classified. If not specified, candidate labels will be automatically collected from the examples you provide. All the label strings will be normalized to be capitalized.

search_model: Option<Model>

ID of the engine to use for Search. You can select one of ada, babbage, curie, or davinci

temperature: Option<f32>

What sampling temperature to use. Higher values mean the model will take more risks. Try 0.9 for more creative applications, and 0 (argmax sampling) for ones with a well-defined answer.

logprobs: Option<u32>

Include the log probabilities on the logprobs most likely tokens, as well the chosen tokens. For example, if logprobs is 5, the API will return a list of the 5 most likely tokens. The API will always return the logprob of the sampled token, so there may be up to logprobs+1 elements in the response. The maximum value for logprobs is 5. If you need more than this, please contact support@openai.com and describe your use case.

max_examples: Option<u32>

The maximum number of examples to be ranked by Search when using file. Setting it to a higher value leads to improved accuracy but with increased latency and cost.

logit_bias: HashMap<Cow<'a, str>, i32>

Modify the likelihood of specified tokens appearing in the completion. Accepts a json object that maps tokens (specified by their token ID in the GPT tokenizer) to an associated bias value from -100 to 100. You can use this tokenizer tool (which works for both GPT-2 and GPT-3) to convert text to token IDs. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token.

return_prompt: Option<bool>

If set to true, the returned JSON will include a “prompt” field containing the final prompt that was used to request a completion. This is mainly useful for debugging purposes.

return_metadata: Option<bool>

A special boolean flag for showing metadata. If set to true, each document entry in the returned JSON will contain a “metadata” field. This flag only takes effect when file is set.

expand: Vec<Cow<'a, str>>

If set to true, the returned JSON will include a “prompt” field containing the final prompt that was used to request a completion. This is mainly useful for debugging purposes.

user: Option<Cow<'a, str>>

A unique identifier representing your end-user, which will help OpenAI to monitor and detect abuse.

Trait Implementations

impl<'a> Clone for Classification<'a>

fn clone(&self) -> Classification<'a>

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl<'a> Debug for Classification<'a>

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for Classification<'_>

fn default() -> Self

Returns the “default value” for a type.

impl<'a> Serialize for Classification<'a>

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.