Qwen

OverviewCopy Anchor Link

Alibaba Cloud's Qwen models, through DashScope's OpenAI-compatible mode.

• QwenLLMService: an OpenAILLMService subclass with Qwen's base URL and default model.

InstallationCopy Anchor Link

bun add @pipedog/qwen

It depends on @pipedog/openai, which is installed with it.

import { QwenLLMService } from "@pipedog/qwen/llm";

PrerequisitesCopy Anchor Link

• An Alibaba Cloud account and a DashScope API key from Alibaba Cloud Model Studio.
• Pass the key as apiKey. It is required, and the service never falls back to OPENAI_API_KEY. The examples read it from QWEN_API_KEY.

QwenLLMServiceCopy Anchor Link

ConfigurationCopy Anchor Link

The other options (organization, project, defaultHeaders, serviceTier, retryOnTimeout, retryTimeoutSecs, function calling) are OpenAILLMService's. See OpenAI.

SettingsCopy Anchor Link

Runtime-updatable settings, passed as settings: new QwenLLMService.Settings({...}) (QwenLLMSettings). They are OpenAI's settings, with these defaults:

Every other setting keeps OpenAI's default. Unset sampling settings are left out of the request, so the provider's own defaults apply. extra carries provider-specific request fields.

UsageCopy Anchor Link

import { LLMUpdateSettingsFrame } from "@pipedog/core/frames/frames";
import { QwenLLMService } from "@pipedog/qwen/llm";

const llm = new QwenLLMService({
  apiKey: process.env.QWEN_API_KEY ?? "",
  settings: new QwenLLMService.Settings({
    model: "qwen-plus",
    systemInstruction: "You are a helpful assistant in a voice conversation.",
    temperature: 0.7,
  }),
});

Change settings mid-call with an LLMUpdateSettingsFrame. The next completion uses them:

// Queue it on the worker, or push it from a processor upstream of the service.
const update = new LLMUpdateSettingsFrame({
  delta: new QwenLLMService.Settings({ temperature: 0.2, maxTokens: 300 }),
});

NotesCopy Anchor Link

• Runs a completion for each LLMContextFrame, between an LLMFullResponseStartFrame and an LLMFullResponseEndFrame, and streams the reply as LLMTextFrames, as OpenAILLMService does. Function calls, token usage metrics and runInference work the same way.
• "developer" messages are sent as "user" messages, since the API doesn't support that role (supportsDeveloperRole is false).
• The default baseUrl is DashScope's international endpoint. Pass your region's endpoint as baseUrl if your key belongs to another one.

Runtime notesCopy Anchor Link

Generated from pipecat.runtimes and pipecat.compat in packages/qwen/package.json: ✅ means the compat smoke test passes on that runtime.

• The client is the official openai JS SDK (through @pipedog/openai), which talks through fetch. It works on Bun, Node, Deno and Cloudflare Workers.
• The deprecated model constructor option is not ported. Use settings.
• Tested against a local OpenAI-compatible mock server, not against Qwen itself.