Share via

CreateThreadAndRunOptionalParams interface

Package:
@azure/ai-agents

Optional parameters.

Extends
OperationOptions

Properties

instructions

The overridden system instructions the agent should use to run the thread.
maxCompletionTokens

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.
maxPromptTokens

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.
metadata

A set of up to 16 key/value pairs that can be attached to an object, used for storing additional information about that object in a structured format. Keys may be up to 64 characters in length and values may be up to 512 characters in length.
model

The overridden model that the agent should use to run the thread.
parallelToolCalls

If true functions will run in parallel during tool use.
responseFormat

Specifies the format that the model must output.
stream

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.
temperature

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.
thread

The details used to create the new thread. If no thread is provided, an empty one will be created.
toolChoice

Controls whether or not and which tool is called by the model.
toolResources

Override the tools the agent can use for this run. This is useful for modifying the behavior on a per-run basis
tools

The overridden list of enabled tools the agent should use to run the thread.
topP

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.
truncationStrategy

The strategy to use for dropping messages as the context windows moves forward.

Inherited Properties

abortSignal

The signal which can be used to abort requests.
onResponse

A function to be called each time a response is received from the server while performing the requested operation. May be called multiple times.
requestOptions

Options used when creating and sending HTTP requests for this operation.
tracingOptions

Options used when tracing is enabled.

Property Details

instructions

The overridden system instructions the agent should use to run the thread.

instructions?: null | string

Property Value

null | string

maxCompletionTokens

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.

maxCompletionTokens?: null | number

Property Value

null | number

maxPromptTokens

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.

maxPromptTokens?: null | number

Property Value

null | number

metadata

A set of up to 16 key/value pairs that can be attached to an object, used for storing additional information about that object in a structured format. Keys may be up to 64 characters in length and values may be up to 512 characters in length.

metadata?: null | Record<string, string>

Property Value

null | Record<string, string>

model

The overridden model that the agent should use to run the thread.

model?: null | string

Property Value

null | string

parallelToolCalls

If true functions will run in parallel during tool use.

parallelToolCalls?: boolean

Property Value

boolean

responseFormat

Specifies the format that the model must output.

responseFormat?: null | AgentsResponseFormatOption

Property Value

null | AgentsResponseFormatOption

stream

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.

stream?: boolean

Property Value

boolean

temperature

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.

temperature?: null | number

Property Value

null | number

thread

The details used to create the new thread. If no thread is provided, an empty one will be created.

thread?: AgentThreadCreationOptions

Property Value

AgentThreadCreationOptions

toolChoice

Controls whether or not and which tool is called by the model.

toolChoice?: null | AgentsToolChoiceOption

Property Value

null | AgentsToolChoiceOption

toolResources

Override the tools the agent can use for this run. This is useful for modifying the behavior on a per-run basis

toolResources?: null | UpdateToolResourcesOptions

Property Value

null | UpdateToolResourcesOptions

tools

The overridden list of enabled tools the agent should use to run the thread.

tools?: null | ToolDefinitionUnion[]

Property Value

null | ToolDefinitionUnion[]

topP

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.

topP?: null | number

Property Value

null | number

truncationStrategy

The strategy to use for dropping messages as the context windows moves forward.

truncationStrategy?: null | TruncationObject

Property Value

null | TruncationObject

Inherited Property Details

abortSignal

The signal which can be used to abort requests.

abortSignal?: AbortSignalLike

Property Value

AbortSignalLike

Inherited From OperationOptions.abortSignal

onResponse

A function to be called each time a response is received from the server while performing the requested operation. May be called multiple times.

onResponse?: RawResponseCallback

Property Value

RawResponseCallback

Inherited From OperationOptions.onResponse

requestOptions

Options used when creating and sending HTTP requests for this operation.

requestOptions?: OperationRequestOptions

Property Value

OperationRequestOptions

Inherited From OperationOptions.requestOptions

tracingOptions

Options used when tracing is enabled.

tracingOptions?: OperationTracingOptions

Property Value

OperationTracingOptions

Inherited From OperationOptions.tracingOptions