Tencent/WeKnora · error

PaddleOCR-VL Cloud poll: %w

Error message

PaddleOCR-VL Cloud poll: %w

What it means

After a successful submit, Read polls the PaddleOCR-VL Cloud job until the result JSONL URL is available. If pollJob fails — HTTP errors while checking status, job failure reported by the API, or the polling deadline/context expiring — the error is wrapped as 'PaddleOCR-VL Cloud poll'. The document was accepted but the asynchronous job did not produce a usable result URL in time.

Source

Thrown at internal/infrastructure/docparser/paddleocr_vl_cloud_converter.go:73

		return &types.ReadResult{Error: fmt.Sprintf("PaddleOCR-VL Cloud base URL blocked by SSRF policy: %v", err)}, nil
	}

	content := req.FileContent
	if len(content) == 0 {
		return &types.ReadResult{Error: "no file content provided"}, nil
	}

	logger.Infof(context.Background(), "[PaddleOCR-VL Cloud] Parsing file=%s size=%d model=%s",
		req.FileName, len(content), c.model)

	jobID, err := c.submitJob(ctx, req, content)
	if err != nil {
		return nil, fmt.Errorf("PaddleOCR-VL Cloud submit: %w", err)
	}

	jsonlURL, err := c.pollJob(ctx, jobID)
	if err != nil {
		return nil, fmt.Errorf("PaddleOCR-VL Cloud poll: %w", err)
	}

	mdContent, imagesURL, err := c.fetchResults(jsonlURL)
	if err != nil {
		return nil, fmt.Errorf("PaddleOCR-VL Cloud fetch results: %w", err)
	}

	mdContent = normalizeHTMLTables(mdContent)

	imageRefs := c.downloadImages(mdContent, imagesURL)
	mdContent, imageRefs = ensureOriginalImageRef(req, mdContent, imageRefs)

	logger.Infof(context.Background(), "[PaddleOCR-VL Cloud] Parsed successfully, markdown=%d chars, images=%d",
		len(mdContent), len(imageRefs))

	return &types.ReadResult{
		MarkdownContent: mdContent,
		ImageRefs:       imageRefs,

View on GitHub (pinned to 988cbb0330)

Solutions

1. Check the wrapped cause for whether the job explicitly failed vs. timed out
2. If timeout, increase poll interval/deadline or process smaller documents
3. Log the job ID and check its status directly against the PaddleOCR-VL cloud console/API
4. Retry the whole Read on transient cloud errors
5. Verify service status/quota of your PaddleOCR-VL cloud account

ctx, cancel := context.WithTimeout(ctx, 10*time.Minute) // allow long jobs
defer cancel()

func isPollFailure(err error) bool {
    return err != nil && strings.Contains(err.Error(), "PaddleOCR-VL Cloud poll")
}

out, err := reader.Read(ctx, req)
if isPollFailure(err) && errors.Is(err, context.DeadlineExceeded) {
    return fmt.Errorf("job %s still running; resume or re-poll later", jobID)
}

When it happens

Trigger: Read -> pollJob returns error: job status endpoint returns non-200, job transitions to a failed state, all poll attempts time out before completion, or ctx is cancelled.

Common situations: Very large/multi-page documents exceeding the poll window; PaddleOCR cloud outage or degraded service; invalid job ID handling after submit returned an unexpected shape; rate limiting on status checks.

Related errors

• MinerU Cloud poll: %w
• PaddleOCR-VL Cloud submit: %w
• PaddleOCR-VL Cloud fetch results: %w
• task timed out after %d polls
• E2B timeout must be at least one second

AI-assisted analysis of Tencent/WeKnora@988cbb0330 (2026-09-02). Data as JSON: /api/errors/4d2f73f34604415c. Report an issue: GitHub.