OpenAIAssistantAdapter.mdx

import { PropertyReference, LinkToCopilotCloud } from "@/components";

import { Tabs } from "nextra/components";

import { Callout } from "nextra/components";

OpenAIAssistantAdapter

Copilot Runtime adapter for the OpenAI Assistant API.

Example

import { CopilotRuntime, OpenAIAssistantAdapter } from "@copilotkit/runtime";
import OpenAI from "openai";
 
const copilotKit = new CopilotRuntime();
 
const openai = new OpenAI({
  organization: "<your-organization-id>",
  apiKey: "<your-api-key>",
});
 
const llmAdapter = new OpenAIAssistantAdapter({
  openai,
  assistantId: "<your-assistant-id>",
  codeInterpreterEnabled: true,
  fileSearchEnabled: true,
});
 
return copilotKit.streamHttpServerResponse(req, res, llmAdapter);

Constructor Parameters

The ID of the assistant to use. An optional OpenAI instance to use. If not provided, a new instance will be created. Whether to enable code interpretation. Whether to enable file search. Whether to disable parallel tool calls. You can disable parallel tool calls to force the model to execute tool calls sequentially. This is useful if you want to execute tool calls in a specific order so that the state changes introduced by one tool call are visible to the next tool call. (i.e. new actions or readables)