Struct FIMCompletionRequestBuilder 

pub struct FIMCompletionRequestBuilder { /* private fields */ }

Builder for FIMCompletionRequest.

Implementations

impl FIMCompletionRequestBuilder

pub fn client<VALUE: Into<DeepSeekClient>>(self, value: VALUE) -> Self

pub fn model<VALUE: Into<String>>(self, value: VALUE) -> Self

Possible values: [deepseek-v4-pro]

ID of the model to use.

pub fn prompt<VALUE: Into<String>>(self, value: VALUE) -> Self

The prompt to generate completions for.

pub fn echo<VALUE: Into<bool>>(self, value: VALUE) -> Self

Echo back the prompt in addition to the completion

pub fn logprobs<VALUE: Into<u32>>(self, value: VALUE) -> Self

Possible values: <= 20

Include the log probabilities on the logprobs most likely output tokens, as well the chosen tokens. For example, if logprobs is 20, the API will return a list of the 20 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 20.

pub fn max_tokens<VALUE: Into<u32>>(self, value: VALUE) -> Self

The maximum number of tokens that can be generated in the completion.

pub fn stop<VALUE: Into<Stop>>(self, value: VALUE) -> Self

Up to 16 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.

pub fn stream<VALUE: Into<bool>>(self, value: VALUE) -> Self

Whether to stream back partial progress. If set, tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a · message. Example Python code.

pub fn stream_options<VALUE: Into<StreamOptions>>(self, value: VALUE) -> Self

Options for streaming response. Only set this when you set stream: true.

pub fn suffix<VALUE: Into<String>>(self, value: VALUE) -> Self

The suffix that comes after a completion of inserted text.

pub fn temperature<VALUE: Into<f64>>(self, value: VALUE) -> Self

Possible values: <= 2

Default value: 1

What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or top_p but not both.

pub fn top_p<VALUE: Into<f64>>(self, value: VALUE) -> Self

Possible values: <= 1

Default value: 1

An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both.

pub fn build( self, ) -> Result<FIMCompletionRequest, FIMCompletionRequestBuilderError>

Builds a new FIMCompletionRequest.

Errors

If a required field has not been initialized.

Trait Implementations

impl Default for FIMCompletionRequestBuilder

fn default() -> Self

Returns the “default value” for a type.