BerriAI/litellm · error · ValueError

Invalid document type: {doc_type}. Must be 'document_url' or

Error message

Invalid document type: {doc_type}. Must be 'document_url' or 'image_url'

What it means

Raised when the document dict's `type` field is neither 'document_url' nor 'image_url'. Azure DI transformation only maps these two Mistral-style document kinds onto its analyze request; any other type value (including None when the key is missing) is rejected before the request is built.

Source

Thrown at litellm/llms/azure_ai/ocr/document_intelligence/transformation.py:370

        Returns:
            OCRRequestData with JSON data
        """
        verbose_logger.debug("Azure Document Intelligence transform_ocr_request - model: %s", model)

        if not isinstance(document, dict):
            raise ValueError(f"Expected document dict, got {type(document)}")

        # Extract document URL from Mistral format
        doc_type: Final = document.get("type")
        document_url = None

        if doc_type == "document_url":
            document_url = document.get("document_url", "")
        elif doc_type == "image_url":
            document_url = document.get("image_url", "")
        else:
            raise ValueError(f"Invalid document type: {doc_type}. Must be 'document_url' or 'image_url'")

        if not document_url:
            raise ValueError("Document URL is required")

        # Build Azure DI request
        data: Final[dict[str, Any]] = {}

        # Check if it's a data URI (base64)
        if document_url.startswith("data:"):
            # Extract base64 content
            base64_content: Final = self._extract_base64_from_data_uri(document_url)
            data["base64Source"] = base64_content
            verbose_logger.debug("Using base64Source for Azure Document Intelligence")
        else:
            # Regular URL
            data["urlSource"] = document_url
            verbose_logger.debug("Using urlSource for Azure Document Intelligence")

View on GitHub (pinned to 6c2dcb801b)

Solutions

1. Set type to exactly 'document_url' (with a 'document_url' key) or 'image_url' (with an 'image_url' key).
2. Validate/whitelist the type field when building the dict from user input.
3. Ensure the discriminator key 'type' is present at the top level of the dict.

Example fix

# before
doc = {"type": "pdf", "url": "https://x.com/f.pdf"}

# after
doc = {"type": "document_url", "document_url": "https://x.com/f.pdf"}

def make_document(url: str, *, image: bool = False) -> dict:
    t = "image_url" if image else "document_url"
    if t not in ("document_url", "image_url"):
        raise ValueError("bad type")
    return {"type": t, t: url}

def has_valid_doc_type(doc: object) -> bool:
    return isinstance(doc, dict) and doc.get("type") in ("document_url", "image_url")

When it happens

Trigger: Calling azure_ai doc-intelligence OCR with document={'type': 'file', ...}, {'type': 'pdf', ...}, or a dict missing the 'type' key entirely (doc_type becomes None).

Common situations: Guessing type names ('url', 'file_url', 'document'); typos; upstream schema changes renaming the discriminator field; constructing the dict from unvalidated user JSON.

Related errors

• Expected document dict, got {type(document)}
• Document URL is required
• Invalid `pages` string for Azure Document Intelligence: {pag
• `pages` integers must be >= 0 (Mistral 0-based indices)
• Invalid `pages` list for Azure Document Intelligence: {pages

AI-assisted analysis of BerriAI/litellm@6c2dcb801b (2026-08-15). Data as JSON: /api/errors/eb9ab6405eb6b0d3. Report an issue: GitHub.