BerriAI/litellm · error · ValueError

Invalid `pages` list for Azure Document Intelligence: {pages

Error message

Invalid `pages` list for Azure Document Intelligence: {pages!r}. Expected tokens like '1' or '3-5'.

What it means

Raised when `pages` is a list of strings but the comma-joined result fails Azure's page-range regex — i.e. the individual tokens are not plain page numbers or hyphenated ranges. List[str] input is treated as Azure-native 1-based tokens, stripped, joined, and validated as a whole before being sent. Tokens like '1..3', '1;', 'page1', or an empty string trigger this.

Source

Thrown at litellm/llms/azure_ai/ocr/document_intelligence/transformation.py:164

                    f"Invalid `pages` string for Azure Document Intelligence: "
                    f"{pages!r}. Expected format like '1-3,5,7-9'."
                )
            return pages.replace(" ", "")

        if isinstance(pages, list):
            if len(pages) == 0:
                return ""
            if any(isinstance(p, bool) for p in pages):
                raise ValueError("`pages` must be integers, not booleans")
            if all(isinstance(p, int) for p in pages):
                if any(p < 0 for p in pages):
                    raise ValueError("`pages` integers must be >= 0 (Mistral 0-based indices)")
                # Mistral 0-based -> Azure 1-based.
                return ",".join(str(p + 1) for p in sorted(set(pages)))
            if all(isinstance(p, str) for p in pages):
                joined: Final = ",".join(p.strip() for p in pages)
                if not pages_pattern.match(joined):
                    raise ValueError(
                        f"Invalid `pages` list for Azure Document Intelligence: "
                        f"{pages!r}. Expected tokens like '1' or '3-5'."
                    )
                return joined

        raise ValueError("`pages` must be a list[int] (0-based, Mistral-style) or a string like '1-3,5,7-9'.")

    @staticmethod
    def _normalize_features_param(features: object) -> str:
        """
        Convert a caller-provided `features` value to Azure DI's query-string
        form (comma-joined feature names, e.g. "keyValuePairs,languages").

        Accepted inputs:
          - list[str]: feature names like ["keyValuePairs", "languages"].
          - str: a single feature name or comma-separated names.
        """
        invalid_features_error: Final = ValueError(

View on GitHub (pinned to 6c2dcb801b)

Solutions

1. Use tokens that are single 1-based page numbers or ranges: ['1', '3-5'] or ['1-3', '7'].
2. If you have 0-based indices, switch to list[int] and let LiteLLM convert.
3. Validate/clean tokens before the call: strip whitespace, drop empties, ensure digits-only or digit-digit.

Example fix

# before
pages = [p.strip() for p in user_input.split(",") if True]  # may leave '' or '1..2'
litellm.aocr_document(model=..., document=doc, pages=pages)

# after
import re
pages = [p.strip() for p in user_input.split(",") if re.fullmatch(r"\d+(-\d+)?", p.strip())]
litellm.aocr_document(model=..., document=doc, pages=pages)

import re
TOKEN_RE = re.compile(r"^\d+(-\d+)?$")
def valid_pages_tokens(pages: list[str]) -> bool:
    return all(isinstance(p, str) and TOKEN_RE.match(p.strip()) for p in pages)

def is_str_pages_list(v: object) -> bool:
    import re
    return isinstance(v, list) and all(
        isinstance(p, str) and re.fullmatch(r"\d+(-\d+)?", p.strip()) for p in v
    )

When it happens

Trigger: Calling azure_ai doc-intelligence OCR with pages=["1..3"], ["1", ""], ["page 2"], or ["1-3", "abc"] — any list[str] whose joined form doesn't match ^\d+(-\d+)?(,\d+(-\d+)?)*$ after stripping.

Common situations: Splitting a user-supplied string on commas without validating tokens (leaving empties); forwarding tokens from another API's syntax; shell/env-var parsing inserting stray characters.

Related errors

• Invalid `pages` string for Azure Document Intelligence: {pag
• `pages` integers must be >= 0 (Mistral 0-based indices)
• `pages` must be integers, not booleans
• `pages` must be a list[int] (0-based, Mistral-style) or a st
• Expected document dict, got {type(document)}

AI-assisted analysis of BerriAI/litellm@6c2dcb801b (2026-08-15). Data as JSON: /api/errors/0975e8c5b1edbd7b. Report an issue: GitHub.