Share via

AgentsClient.CreateRun Method

  • Reference

Definition

Namespace:
Azure.AI.Projects
Assembly:
Azure.AI.Projects.dll
Package:
Azure.AI.Projects v1.0.0-beta.1

Overloads

CreateRun(AgentThread, Agent, CancellationToken)

Creates a new run of the specified thread using a specified agent.
CreateRun(String, RequestContent, RequestContext)

[Protocol Method] Creates a new run for an agent thread.
CreateRun(String, String, String, String, String, IEnumerable<ThreadMessage>, IEnumerable<ToolDefinition>, Nullable<Boolean>, Nullable<Single>, Nullable<Single>, Nullable<Int32>, Nullable<Int32>, TruncationObject, BinaryData, BinaryData, IReadOnlyDictionary<String,String>, CancellationToken)

Creates a new run for an agent thread.

CreateRun(AgentThread, Agent, CancellationToken)

Source:
AgentsClient.cs

Creates a new run of the specified thread using a specified agent.

public virtual Azure.Response<Azure.AI.Projects.ThreadRun> CreateRun (Azure.AI.Projects.AgentThread thread, Azure.AI.Projects.Agent agent, System.Threading.CancellationToken cancellationToken = default);
abstract member CreateRun : Azure.AI.Projects.AgentThread * Azure.AI.Projects.Agent * System.Threading.CancellationToken -> Azure.Response<Azure.AI.Projects.ThreadRun>
override this.CreateRun : Azure.AI.Projects.AgentThread * Azure.AI.Projects.Agent * System.Threading.CancellationToken -> Azure.Response<Azure.AI.Projects.ThreadRun>
Public Overridable Function CreateRun (thread As AgentThread, agent As Agent, Optional cancellationToken As CancellationToken = Nothing) As Response(Of ThreadRun)

Parameters

thread
AgentThread

The thread that should be run.

agent
Agent

The agent that should run the thread.

cancellationToken
CancellationToken

The cancellation token to use.

Returns

Response<ThreadRun>

A new ThreadRun instance.

Remarks

This method will create the run with default configuration.

Applies to

CreateRun(String, RequestContent, RequestContext)

Source:
AgentsClient.cs

[Protocol Method] Creates a new run for an agent thread.

public virtual Azure.Response CreateRun (string threadId, Azure.Core.RequestContent content, Azure.RequestContext context = default);
abstract member CreateRun : string * Azure.Core.RequestContent * Azure.RequestContext -> Azure.Response
override this.CreateRun : string * Azure.Core.RequestContent * Azure.RequestContext -> Azure.Response
Public Overridable Function CreateRun (threadId As String, content As RequestContent, Optional context As RequestContext = Nothing) As Response

Parameters

threadId
String

Identifier of the thread.

content
RequestContent

The content to send as the body of the request.

context
RequestContext

The request context, which can override default behaviors of the client pipeline on a per-call basis.

Returns

Response

The response returned from the service.

Exceptions

ArgumentNullException

threadId or content is null.

ArgumentException

threadId is an empty string, and was expected to be non-empty.

RequestFailedException

Service returned a non-success status code.

Applies to

CreateRun(String, String, String, String, String, IEnumerable<ThreadMessage>, IEnumerable<ToolDefinition>, Nullable<Boolean>, Nullable<Single>, Nullable<Single>, Nullable<Int32>, Nullable<Int32>, TruncationObject, BinaryData, BinaryData, IReadOnlyDictionary<String,String>, CancellationToken)

Source:
AgentsClient.cs

Creates a new run for an agent thread.

public virtual Azure.Response<Azure.AI.Projects.ThreadRun> CreateRun (string threadId, string assistantId, string overrideModelName = default, string overrideInstructions = default, string additionalInstructions = default, System.Collections.Generic.IEnumerable<Azure.AI.Projects.ThreadMessage> additionalMessages = default, System.Collections.Generic.IEnumerable<Azure.AI.Projects.ToolDefinition> overrideTools = default, bool? stream = default, float? temperature = default, float? topP = default, int? maxPromptTokens = default, int? maxCompletionTokens = default, Azure.AI.Projects.TruncationObject truncationStrategy = default, BinaryData toolChoice = default, BinaryData responseFormat = default, System.Collections.Generic.IReadOnlyDictionary<string,string> metadata = default, System.Threading.CancellationToken cancellationToken = default);
abstract member CreateRun : string * string * string * string * string * seq<Azure.AI.Projects.ThreadMessage> * seq<Azure.AI.Projects.ToolDefinition> * Nullable<bool> * Nullable<single> * Nullable<single> * Nullable<int> * Nullable<int> * Azure.AI.Projects.TruncationObject * BinaryData * BinaryData * System.Collections.Generic.IReadOnlyDictionary<string, string> * System.Threading.CancellationToken -> Azure.Response<Azure.AI.Projects.ThreadRun>
override this.CreateRun : string * string * string * string * string * seq<Azure.AI.Projects.ThreadMessage> * seq<Azure.AI.Projects.ToolDefinition> * Nullable<bool> * Nullable<single> * Nullable<single> * Nullable<int> * Nullable<int> * Azure.AI.Projects.TruncationObject * BinaryData * BinaryData * System.Collections.Generic.IReadOnlyDictionary<string, string> * System.Threading.CancellationToken -> Azure.Response<Azure.AI.Projects.ThreadRun>
Public Overridable Function CreateRun (threadId As String, assistantId As String, Optional overrideModelName As String = Nothing, Optional overrideInstructions As String = Nothing, Optional additionalInstructions As String = Nothing, Optional additionalMessages As IEnumerable(Of ThreadMessage) = Nothing, Optional overrideTools As IEnumerable(Of ToolDefinition) = Nothing, Optional stream As Nullable(Of Boolean) = Nothing, Optional temperature As Nullable(Of Single) = Nothing, Optional topP As Nullable(Of Single) = Nothing, Optional maxPromptTokens As Nullable(Of Integer) = Nothing, Optional maxCompletionTokens As Nullable(Of Integer) = Nothing, Optional truncationStrategy As TruncationObject = Nothing, Optional toolChoice As BinaryData = Nothing, Optional responseFormat As BinaryData = Nothing, Optional metadata As IReadOnlyDictionary(Of String, String) = Nothing, Optional cancellationToken As CancellationToken = Nothing) As Response(Of ThreadRun)

Parameters

threadId
String

Identifier of the thread.

assistantId
String

The ID of the agent that should run the thread.

overrideModelName
String

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

overrideInstructions
String

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

additionalInstructions
String

Additional instructions to append 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.

additionalMessages
IEnumerable<ThreadMessage>

Adds additional messages to the thread before creating the run.

overrideTools
IEnumerable<ToolDefinition>

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

stream
Nullable<Boolean>

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
Nullable<Single>

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.

topP
Nullable<Single>

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.

maxPromptTokens
Nullable<Int32>

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.

maxCompletionTokens
Nullable<Int32>

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.

truncationStrategy
TruncationObject

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

toolChoice
BinaryData

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

responseFormat
BinaryData

Specifies the format that the model must output.

metadata
IReadOnlyDictionary<String,String>

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.

cancellationToken
CancellationToken

The cancellation token to use.

Returns

Response<ThreadRun>

Exceptions

ArgumentNullException

threadId or assistantId is null.

ArgumentException

threadId is an empty string, and was expected to be non-empty.

Applies to