ATH-MaaS/Pixelle-Video · critical · RuntimeError

DashScope VLM API key is not configured.

Error message

DashScope VLM API key is not configured.

What it means

query raises RuntimeError when self.dashscope_client is None, meaning the DashScope SDK client was never constructed because DASHSCOPE_API_KEY was not configured at initialization time. No chat request can be made without it.

Source

Thrown at pixelle_video/services/api_services/vlm_client.py:58

            print(f"Prompt: {prompt}")
            if image_paths:
                print(f"Images: {len(image_paths)}")
                for p in image_paths:
                    if p.startswith("data:"):
                        print(f" - [Base64图片]")
                    else:
                        print(f" - {p}")
            if video_paths:
                print(f"Videos: {len(video_paths)}")
                for p in video_paths:
                    print(f" - {p}")
            print(f"Model: {selected_model}")
            if session_id:
                print(f"Session ID: {session_id}")
            print("-" * 30)

        if self.dashscope_client is None:
            raise RuntimeError("DashScope VLM API key is not configured.")

        image_urls = [self._to_dashscope_file_url(path, allow_data_url=True) for path in image_paths or []]
        video_urls = [self._to_dashscope_file_url(path, allow_data_url=False) for path in video_paths or []]
        return self.dashscope_client.chat(
            text=prompt,
            images=image_urls,
            videos=video_urls,
            model=selected_model,
            stream=False,
        )

    def _to_dashscope_file_url(self, path: str, allow_data_url: bool) -> str:
        if path.startswith("data:"):
            if not allow_data_url:
                raise ValueError("DashScope video input does not support data URLs in this adapter.")

            import base64 as b64
            import tempfile

View on GitHub (pinned to 848b054e4f)

Solutions

1. Set DASHSCOPE_API_KEY in the environment before creating VlmClient
2. Ensure load_dotenv()/secret loading runs before client construction, not after
3. Re-instantiate VlmClient after fixing configuration — it does not hot-reload credentials
4. Verify with: python -c "import os; print(bool(os.environ.get('DASHSCOPE_API_KEY')))"

Example fix

// before
client = VlmClient()          # key not loaded yet
load_dotenv()
// after
load_dotenv()
client = VlmClient()

import os
if not os.environ.get("DASHSCOPE_API_KEY"):
    raise SystemExit("Set DASHSCOPE_API_KEY before initializing VlmClient")

try:
    answer = vlm.query(prompt=p, model="qwen-vl-max")
except RuntimeError as e:
    if "API key is not configured" in str(e):
        logging.critical("DASHSCOPE_API_KEY missing; re-create VlmClient after loading secrets")
    else:
        raise

When it happens

Trigger: Constructing VlmClient without a DashScope API key (client stays None) and then calling query() with a valid model.

Common situations: DASHSCOPE_API_KEY missing from environment/.env; key loaded after VlmClient was instantiated (load_dotenv called too late); different process/container lacking the secret; SDK init silently skipped on import error.

Understand the failure class

Background: "environment variable is not set" and "Missing keys in environment" errors: what missing required env var messages mean and how to fix them — this error's family across 28 libraries.

Related errors

• ARK_API_KEY not set.
• str(e)
• Image edit failed: {response.code}, {response.message}, stat
• DASHSCOPE_API_KEY 未设置，无法使用图片上传服务
• Failed to get upload policy: {response.text}

AI-assisted analysis of ATH-MaaS/Pixelle-Video@848b054e4f (2026-08-30). Data as JSON: /api/errors/67ecd3a2c74cb401. Report an issue: GitHub.