pub struct CreateRunRequestArgs { /* private fields */ }
Expand description
Builder for CreateRunRequest
.
Implementations§
Source§impl CreateRunRequestArgs
impl CreateRunRequestArgs
Sourcepub fn assistant_id<VALUE: Into<String>>(&mut self, value: VALUE) -> &mut Self
pub fn assistant_id<VALUE: Into<String>>(&mut self, value: VALUE) -> &mut Self
The ID of the assistant to use to execute this run.
Sourcepub fn model<VALUE: Into<String>>(&mut self, value: VALUE) -> &mut Self
pub fn model<VALUE: Into<String>>(&mut self, value: VALUE) -> &mut Self
The ID of the Model to be used to execute this run. If a value is provided here, it will override the model associated with the assistant. If not, the model associated with the assistant will be used.
Sourcepub fn instructions<VALUE: Into<String>>(&mut self, value: VALUE) -> &mut Self
pub fn instructions<VALUE: Into<String>>(&mut self, value: VALUE) -> &mut Self
Overrides the instructions of the assistant. This is useful for modifying the behavior on a per-run basis.
Sourcepub fn additional_instructions<VALUE: Into<String>>(
&mut self,
value: VALUE,
) -> &mut Self
pub fn additional_instructions<VALUE: Into<String>>( &mut self, value: VALUE, ) -> &mut Self
Appends additional instructions at the end of the instructions for the run. This is useful for modifying the behavior on a per-run basis without overriding other instructions.
Sourcepub fn additional_messages<VALUE: Into<Vec<CreateMessageRequest>>>(
&mut self,
value: VALUE,
) -> &mut Self
pub fn additional_messages<VALUE: Into<Vec<CreateMessageRequest>>>( &mut self, value: VALUE, ) -> &mut Self
Adds additional messages to the thread before creating the run.
Sourcepub fn tools<VALUE: Into<Vec<AssistantTools>>>(
&mut self,
value: VALUE,
) -> &mut Self
pub fn tools<VALUE: Into<Vec<AssistantTools>>>( &mut self, value: VALUE, ) -> &mut Self
Override the tools the assistant can use for this run. This is useful for modifying the behavior on a per-run basis.
pub fn metadata<VALUE: Into<HashMap<String, Value>>>( &mut self, value: VALUE, ) -> &mut Self
Sourcepub fn temperature<VALUE: Into<f32>>(&mut self, value: VALUE) -> &mut Self
pub fn temperature<VALUE: Into<f32>>(&mut self, value: VALUE) -> &mut Self
The sampling temperature used for this run. If not set, defaults to 1.
Sourcepub fn top_p<VALUE: Into<f32>>(&mut self, value: VALUE) -> &mut Self
pub fn top_p<VALUE: Into<f32>>(&mut self, value: VALUE) -> &mut Self
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.
Sourcepub fn stream<VALUE: Into<bool>>(&mut self, value: VALUE) -> &mut Self
pub fn stream<VALUE: Into<bool>>(&mut self, value: VALUE) -> &mut Self
If true
, returns a stream of events that happen during the Run as server-sent events, terminating when the Run enters a terminal state with a data: [DONE]
message.
Sourcepub fn max_prompt_tokens<VALUE: Into<u32>>(&mut self, value: VALUE) -> &mut Self
pub fn max_prompt_tokens<VALUE: Into<u32>>(&mut self, value: VALUE) -> &mut Self
The maximum number of prompt tokens that may be used over the course of the run. The run will make a best effort to use only the number of prompt tokens specified, across multiple turns of the run. If the run exceeds the number of prompt tokens specified, the run will end with status incomplete
. See incomplete_details
for more info.
Sourcepub fn max_completion_tokens<VALUE: Into<u32>>(
&mut self,
value: VALUE,
) -> &mut Self
pub fn max_completion_tokens<VALUE: Into<u32>>( &mut self, value: VALUE, ) -> &mut Self
The maximum number of completion tokens that may be used over the course of the run. The run will make a best effort to use only the number of completion tokens specified, across multiple turns of the run. If the run exceeds the number of completion tokens specified, the run will end with status incomplete
. See incomplete_details
for more info.
Sourcepub fn truncation_strategy<VALUE: Into<TruncationObject>>(
&mut self,
value: VALUE,
) -> &mut Self
pub fn truncation_strategy<VALUE: Into<TruncationObject>>( &mut self, value: VALUE, ) -> &mut Self
Controls for how a thread will be truncated prior to the run. Use this to control the intial context window of the run.
pub fn tool_choice<VALUE: Into<AssistantsApiToolChoiceOption>>( &mut self, value: VALUE, ) -> &mut Self
Sourcepub fn parallel_tool_calls<VALUE: Into<bool>>(
&mut self,
value: VALUE,
) -> &mut Self
pub fn parallel_tool_calls<VALUE: Into<bool>>( &mut self, value: VALUE, ) -> &mut Self
Whether to enable parallel function calling during tool use.
pub fn response_format<VALUE: Into<AssistantsApiResponseFormatOption>>( &mut self, value: VALUE, ) -> &mut Self
Sourcepub fn build(&self) -> Result<CreateRunRequest, OpenAIError>
pub fn build(&self) -> Result<CreateRunRequest, OpenAIError>
Trait Implementations§
Source§impl Clone for CreateRunRequestArgs
impl Clone for CreateRunRequestArgs
Source§fn clone(&self) -> CreateRunRequestArgs
fn clone(&self) -> CreateRunRequestArgs
1.0.0 · Source§fn clone_from(&mut self, source: &Self)
fn clone_from(&mut self, source: &Self)
source
. Read more