infiniflow/ragflow · error · ValueError

Querit format must be text, markdown, or html.

Error message

Querit format must be text, markdown, or html.

What it means

ValueError from _validate_contents_inputs(): the 'format' parameter of the Querit contents tool must be one of QUERIT_CONTENT_FORMATS — text, markdown, or html (case-sensitive). Any other string, None, or non-string type raises.

Source

Thrown at agent/tools/querit.py:380

        "extrasMeta": extras_meta,
    }


def _normalize_contents_urls(urls: Any) -> Any:
    if isinstance(urls, str):
        return [url.strip() for url in urls.split(",") if url.strip()]
    return urls


def _validate_contents_inputs(urls: Any, format: Any, crawl_timeout: Any, extras_meta: Any) -> None:
    if not isinstance(urls, list) or not 1 <= len(urls) <= 10 or any(not isinstance(url, str) or not url.strip() for url in urls):
        raise ValueError("Querit urls must contain between 1 and 10 non-empty strings.")
    for url in urls:
        parsed = urlparse(url)
        if parsed.scheme not in {"http", "https"} or not parsed.netloc:
            raise ValueError("Querit urls must be absolute HTTP or HTTPS URLs.")
    if format not in QUERIT_CONTENT_FORMATS:
        raise ValueError("Querit format must be text, markdown, or html.")
    if type(crawl_timeout) is not int or not 1 <= crawl_timeout <= 60:
        raise ValueError("Querit crawl_timeout must be an integer from 1 to 60.")
    if type(extras_meta) is not bool:
        raise ValueError("Querit extras_meta must be a boolean.")


def _validate_contents_response(response_data: Any) -> None:
    if not isinstance(response_data, dict):
        raise TypeError("Querit API response must be a JSON object.")
    if "results" in response_data and not isinstance(response_data["results"], list):
        raise TypeError("Querit API response field results must be an array.")
    if "statuses" in response_data and not isinstance(response_data["statuses"], list):
        raise TypeError("Querit API response field statuses must be an array.")


def _validate_search_inputs(
    count: Any,
    chunks_per_doc: Any,

View on GitHub (pinned to 554fb1133a)

Solutions

1. Use exactly one of: 'text', 'markdown', 'html'.
2. Map common aliases in your caller: {'md': 'markdown', 'plain': 'text', 'htm': 'html'}.
3. Lowercase the value before passing it in.
4. Ensure the parameter is always provided — there is no default inside the validator.

Example fix

# before
format = "md"  # ValueError

# after
aliases = {"md": "markdown", "plain": "text", "htm": "html"}
format = aliases.get(user_format.lower(), user_format.lower())  # -> "markdown"

QUERIT_FORMATS = {"text", "markdown", "html"}
def safe_querit_format(v) -> str:
    v = str(v or "text").strip().lower()
    return v if v in QUERIT_FORMATS else "text"

def is_querit_format(v) -> bool:
    return v in {"text", "markdown", "html"}

try:
    querit_contents._invoke(urls=urls, format=fmt)
except ValueError as e:
    if "format" in str(e):
        fmt = "markdown"; querit_contents._invoke(urls=urls, format=fmt)
    raise

When it happens

Trigger: Calling contents with format='md' or 'MD' (unrecognized abbreviation/case), format=None because the workflow omitted an optional-looking field, or a numeric/bool value bound from an upstream component output.

Common situations: Users assuming 'md' is accepted for markdown; canvas UI passing an empty string when the field is cleared; LLM-generated parameters using 'plain' or 'raw' instead of 'text'.

Related errors

• Querit urls must contain between 1 and 10 non-empty strings.
• Querit urls must be absolute HTTP or HTTPS URLs.
• Querit crawl_timeout must be an integer from 1 to 60.
• Querit extras_meta must be a boolean.
• Querit count must be an integer greater than or equal to 1.

AI-assisted analysis of infiniflow/ragflow@554fb1133a (2026-08-15). Data as JSON: /api/errors/cee60e5922540c63. Report an issue: GitHub.