@inductiv/node-red-openai-api

<section> <details> <summary style="font-weight: bold;">🔄 Runs</summary> <a href="https://developers.openai.com/api/reference/typescript/resources/beta/threads/runs/" target="_blank">Official Documentation</a> <h4 style="font-weight: bolder;"> ⋙ Create Thread and Run</h4> <p>Create a thread and run it in one request.</p> <dl class="message-properties"> <h4>msg.payload Properties</h4> <dt> assistant_id <span class="property-type">string</span> </dt> <dd>The ID of the assistant to use to execute this run.</dd> <dt class="optional"> thread <span class="property-type">object</span> </dt> <dd>A thread object to create with the run.</dd> <dt class="optional"> model <span class="property-type">string</span> </dt> <dd>The ID of the Model to be used to execute this run.</dd> <dt class="optional"> instructions <span class="property-type">string</span> </dt> <dd>Override the default system message of the assistant.</dd> <dt class="optional"> tools <span class="property-type">array</span> </dt> <dd>Override the tools the assistant can use for this run.</dd> <dt class="optional"> tool_resources <span class="property-type">object or null</span> </dt> <dd>A set of resources that are used by the assistant's tools.</dd> <dt class="optional"> metadata <span class="property-type">object</span> </dt> <dd>Set of 16 key-value pairs that can be attached to an object.</dd> <dt class="optional"> temperature <span class="property-type">number</span> </dt> <dd>What sampling temperature to use, between 0 and 2.</dd> <dt class="optional"> top_p <span class="property-type">number or null</span> </dt> <dd>An alternative to sampling with temperature.</dd> <dt class="optional"> stream <span class="property-type">boolean</span> </dt> <dd>If <code>true</code>, returns a stream of events that happen during the Run as server-sent events, terminating when the Run enters a terminal state with a <code>data: [DONE]</code> message.</dd> <dt class="optional"> max_prompt_tokens <span class="property-type">integer</span> </dt> <dd>The maximum number of prompt tokens that may be used over the course of the run.</dd> <dt class="optional"> max_completion_tokens <span class="property-type">integer</span> </dt> <dd>The maximum number of completion tokens that may be used over the course of the run.</dd> <dt class="optional"> truncation_strategy <span class="property-type">object</span> <dd> <strong><code>@property {string} type</code></strong> - The truncation strategy to use for the thread. The default is <code>auto</code>. If set to <code>last_messages</code>, the thread will be truncated to the n most recent messages in the thread. When set to <code>auto</code>, messages in the middle of the thread will be dropped to fit the context length of the model, <code>max_prompt_tokens</code>. </dd> <dd> <strong><code>@property {integer} [last_messages]</code></strong> - The number of most recent messages from the thread when constructing the context for the run. </dd> </dt> <dt class="optional"> tool_choice <span class="property-type">string | object</span> </dt> <dd>Controls which (if any) tool is called by the model. <code>none</code> means the model will not call any tools and instead generates a message. <code>auto</code> is the default value and means the model can pick between generating a message or calling a tool. Specifying a particular tool like <code>{"type": "TOOL_TYPE"}</code> forces the model to call that tool.</dd> <dt class="optional"> parallel_tool_calls <span class="property-type">boolean</span> </dt> <dd>Whether to enable parallel function calling during tool use.</dd> <dt class="optional"> response_format <span class="property-type">string | object</span> </dt> <dd>Specifies the format that the model must output.</dd> </dl> <h4 style="font-weight: bolder;"> ⋙ List Runs</h4> <p>Returns a list of runs belonging to a thread.</p> <dl class="message-properties"> <h4>msg.payload Properties</h4> <dt> thread_id <span class="property-type">string</span> </dt> <dd>The ID of the thread the run belongs to.</dd> <dt class="optional"> limit <span class="property-type">integer</span> </dt> <dd>A limit on the number of objects to be returned.</dd> <dt class="optional"> order <span class="property-type">string</span> </dt> <dd>Sort order by the created_at timestamp of the objects.</dd> <dt class="optional"> after <span class="property-type">string</span> </dt> <dd>A cursor for use in pagination.</dd> <dt class="optional"> before <span class="property-type">string</span> </dt> <dd>A cursor for use in pagination.</dd> </dl> <h4 style="font-weight: bolder;"> ⋙ Create Run</h4> <p>Create a run.</p> <dl class="message-properties"> <h4>msg.payload Properties</h4> <dt> thread_id <span class="property-type">string</span> </dt> <dd>The ID of the thread to run.</dd> <dt> include <span class="property-type">array</span> </dt> <dd>A list of additional fields to include in the response.</dd> <dt> assistant_id <span class="property-type">string</span> </dt> <dd>The ID of the assistant to use to execute this run.</dd> <dt class="optional"> model <span class="property-type">string</span> </dt> <dd>The ID of the Model to be used to execute this run.</dd> <dt class="optional"> instructions <span class="property-type">string</span> </dt> <dd> Overrides the instructions of the assistant. This is useful for modifying the behavior on a per-run basis. </dd> <dt class="optional"> additional_instructions <span class="property-type">string</span> </dt> <dd> 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. </dd> <dt class="optional"> additional_messages <span class="property-type">array</span> </dt> <dd> Adds additional messages to the thread before creating the run. </dd> <dt class="optional"> tools <span class="property-type">array</span> </dt> <dd>Override the tools the assistant can use for this run.</dd> <dt class="optional"> metadata <span class="property-type">object</span> </dt> <dd>Set of 16 key-value pairs that can be attached to an object.</dd> <dt class="optional"> temperature <span class="property-type">number</span> </dt> <dd>What sampling temperature to use, between 0 and 2.</dd> <dt class="optional"> top_p <span class="property-type">number</span> </dt> <dd>An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass.</dd> <dt class="optional"> stream <span class="property-type">boolean</span> </dt> <dd>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.</dd> <dt class="optional"> max_prompt_tokens <span class="property-type">integer</span> </dt> <dd>The maximum number of prompt tokens that may be used over the course of the run.</dd> <dt class="optional"> max_completion_tokens <span class="property-type">integer</span> </dt> <dd>The maximum number of completion tokens that may be used over the course of the run.</dd> <dt class="optional"> truncation_strategy <span class="property-type">object</span> </dt> <dd>Controls for how a thread will be truncated prior to the run.</dd> <dt class="optional"> tool_choice <span class="property-type">string or object</span> </dt> <dd>Controls for how a thread will be truncated prior to the run.</dd> <dt class="optional"> parallel_tool_calls <span class="property-type">boolean</span> </dt> <dd>Whether to enable parallel function calling during tool use.</dd> <dt class="optional"> response_format <span class="property-type">string or object</span> </dt> <dd>Specifies the format that the model must output.</dd> </dl> <h4 style="font-weight: bolder;"> ⋙ Retrieve Run</h4> <p>Retrieves a run.</p> <dl class="message-properties"> <h4>msg.payload Properties</h4> <dt>thread_id <span class="property-type">string</span> </dt> <dd>The ID of the thread that was run.</dd> <dt>run_id <span class="property-type">string</span> </dt> <dd>The ID of the run to retrieve.</dd> </dl> <h4 style="font-weight: bolder;"> ⋙ Modify Run</h4> <p>Modifies a run.</p> <dl class="message-properties"> <h4>msg.payload Properties</h4> <dt> thread_id <span class="property-type">string</span> </dt> <dd>The ID of the thread that was run.</dd> <dt> run_id <span class="property-type">string</span> </dt> <dd>The ID of the run to modify.</dd> <dt class="optional"> metadata <span class="property-type">object</span> </dt> <dd>Set of 16 key-value pairs that can be attached to an object.</dd> </dl> <h4 style="font-weight: bolder;"> ⋙ Submit Tool Outputs to Run</h4> <p> When a run has the `status: "requires_action"` and `required_action.type` is `submit_tool_outputs`, this endpoint can be used to submit the outputs from the tool calls once they're all completed. All outputs must be submitted in a single request. </p> <dl class="message-properties"> <h4>msg.payload Properties</h4> <dt> thread_id <span class="property-type">string</span> </dt> <dd>The ID of the thread to which this run belongs.</dd> <dt> run_id <span class="property-type">string</span> </dt> <dd>The ID of the run that requires the tool output submission.</dd> <dt> tool_outputs <span class="property-type">array</span> </dt> <dd>A list of tools for which the outputs are being submitted.</dd> <dt class="optional"> stream <span class="property-type">boolean</span> </dt> <dd>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.</dd> </dl> <h4 style="font-weight: bolder;"> ⋙ Cancel Run</h4> <p>Cancels a run that is `in_progress`.</p> <dl class="message-properties"> <h4>msg.payload Properties</h4> <dt> thread_id <span class="property-type">string</span> </dt> <dd>The ID of the thread to which this run belongs.</dd> <dt> run_id <span class="property-type">string</span> </dt> <dd>The ID of the run to cancel.</dd> </dl> <h4 style="font-weight: bolder;"> ⋙ List Run Steps</h4> <p>Returns a list of run steps belonging to a run.</p> <dl class="message-properties"> <h4>msg.payload Properties</h4> <dt> thread_id <span class="property-type">string</span> </dt> <dd>The ID of the thread the run and run steps belong to.</dd> <dt> run_id <span class="property-type">string</span> </dt> <dd>The ID of the run the run steps belong to.</dd> <dt class="optional"> limit <span class="property-type">integer</span> </dt> <dd>A limit on the number of objects to be returned.</dd> <dt class="optional"> order <span class="property-type">string</span> </dt> <dd>Sort order by the created_at timestamp of the objects.</dd> <dt class="optional"> after <span class="property-type">string</span> </dt> <dd>A cursor for use in pagination.</dd> <dt class="optional"> before <span class="property-type">string</span> </dt> <dd>A cursor for use in pagination.</dd> <dt class="optional"> include <span class="property-type">array</span> </dt> <dd>A list of additional fields to include in the response.</dd> </dl> <h4 style="font-weight: bolder;"> ⋙ Retrieve Run Step</h4> <p>Retrieves a run step.</p> <dl class="message-properties"> <h4>msg.payload Properties</h4> <dt> thread_id <span class="property-type">string</span> </dt> <dd>The ID of the thread to which the run and run step belongs.</dd> <dt> run_id <span class="property-type">string</span> </dt> <dd>The ID of the run to which the run step belongs.</dd> <dt> step_id <span class="property-type">string</span> </dt> <dd>The ID of the run step to retrieve.</dd> <dt> include <span class="property-type">array</span> </dt> <dd>A list of additional fields to include in the response.</dd> </dl> </details> </section>