crewAIInc/crewAI · error · ValueError

Error fetching content from URL {url}: {e!s}

Error message

Error fetching content from URL {url}: {e!s}

What it means

Raised by DOCXLoader._download_from_url() when anything fails while fetching a remote .docx: the safe_get request, raise_for_status(), or writing the response to the temp file. The broad `except Exception` wraps the whole block and re-raises as ValueError with the URL and stringified cause, so network errors, HTTP error statuses, and local tempfile failures all surface through this one message.

Source

Thrown at lib/crewai-tools/src/crewai_tools/rag/loaders/docx_loader.py:53

    def _download_from_url(url: str, kwargs: dict[str, Any]) -> str:
        headers = kwargs.get(
            "headers",
            {
                "Accept": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
                "User-Agent": "Mozilla/5.0 (compatible; crewai-tools DOCXLoader)",
            },
        )

        try:
            response = safe_get(url, headers=headers, timeout=30)
            response.raise_for_status()

            # Create temporary file to save the DOCX content
            with tempfile.NamedTemporaryFile(suffix=".docx", delete=False) as temp_file:
                temp_file.write(response.content)
                return temp_file.name
        except Exception as e:
            raise ValueError(f"Error fetching content from URL {url}: {e!s}") from e

    def _load_from_file(
        self,
        file_path: str,
        source_ref: str,
        DocxDocument: Any,  # noqa: N803
    ) -> LoaderResult:
        try:
            doc = DocxDocument(file_path)

            text_parts = []
            for paragraph in doc.paragraphs:
                if paragraph.text.strip():
                    text_parts.append(paragraph.text)  # noqa: PERF401

            content = "\n".join(text_parts)

            metadata = {

View on GitHub (pinned to 754d7323be)

Solutions

1. Fetch the URL manually (curl -I) to confirm it returns 200 with content-type wordprocessingml.document; fix dead or expired links.
2. If the link is a pre-signed URL, regenerate it closer to load time or download via your storage SDK and pass the local path.
3. Check TMPDIR is writable and has space if the request itself succeeds.
4. Retry transient network failures once before giving up.

Example fix

# before
result = DOCXLoader().load(SourceContent(signed_url))  # expired link -> ValueError

# after
import requests
r = requests.head(signed_url, timeout=10)
if r.status_code != 200:
    signed_url = regenerate_presigned_url(key)
result = DOCXLoader().load(SourceContent(signed_url))

import requests\n\ndef url_serves_docx(url: str) -> bool:\n    try:\n        r = requests.head(url, timeout=10, allow_redirects=True)\n        return r.ok and 'wordprocessingml' in r.headers.get('Content-Type', '')\n    except requests.RequestException:\n        return False

try:\n    result = DOCXLoader().load(source)\nexcept ValueError as e:\n    if 'Error fetching content' in str(e) and attempts_left():\n        schedule_retry(source)\n    else:\n        raise

When it happens

Trigger: DOCXLoader().load(SourceContent('https://example.com/file.docx')) where the URL 404s, the host is unreachable, TLS fails, the request exceeds the 30-second timeout, or the disk is full so tempfile.NamedTemporaryFile raises.

Common situations: Expired/pre-signed S3 links; docs portals that return HTML login pages instead of the file (then saved as .docx and rejected later); corporate proxies; URLs from user input that were never validated; read-only temp directories (TMPDIR misconfigured).

Related errors

• Unable to fetch documentation from {docs_url}: {e}
• Failed to download PDF from {url}: {e!s}
• python-docx is required for DOCX loading. Install with: 'uv
• Source must be a valid file path or URL, got: {source_conten
• Error loading DOCX file: {e!s}

AI-assisted analysis of crewAIInc/crewAI@754d7323be (2026-08-15). Data as JSON: /api/errors/b4a16949a47a1f17. Report an issue: GitHub.