zylon-ai/private-gpt · error · ValueError

Document conversion failed with status: {conversion_result.s

Error message

Document conversion failed with status: {conversion_result.status}. Errors: {conversion_result.errors}

What it means

Raised by DoclingApiReader.lazy_load_data when the conversion result's status is neither 'success' nor 'partial_success'. Unlike the async-client failure path (error 181), this is the synchronous response from Docling already carrying a failure status — typically 'failure' — and the message appends the server's own errors list, which is the primary diagnostic.

Source

Thrown at private_gpt/components/readers/docling/docling_api_reader.py:173

        **load_kwargs: Any,
    ) -> AsyncIterator[BaseNode]:
        """Lazy load file data into LlamaIndex Documents."""
        logger.debug("Starting Docling API parsing of file: %s", file_info.file_name)

        file_name = file_info.file_name or file_info.file_data.name
        file_data = file_info.file_data
        file_bytes = await asyncio.to_thread(file_data.read_bytes)
        pages = file_info.config.get("pages", None)

        try:
            conversion_result = await self.client.convert_from_bytes(
                file_name, file_bytes, to_formats=["md"], pages=pages, **load_kwargs
            )
        except Exception as e:
            raise ValueError(f"Document conversion failed: {e}") from e

        if conversion_result.status not in ["success", "partial_success"]:
            raise ValueError(
                f"Document conversion failed with status: {conversion_result.status}. "
                f"Errors: {conversion_result.errors}"
            )

        contents = self._get_content(conversion_result)
        valid_contents = [content for content in contents if content]
        if not valid_contents:
            raise ValueError("No valid document content found after conversion")
        if self._is_extraction_unsuccessful(valid_contents):
            raise ExtractionUnsuccessfulError(
                f"Document extraction unsuccessful for '{file_name}': unmapped-glyph "
                f"ratio exceeded threshold ({self.config.failure_threshold})."
            )

        docs = [
            self._page_to_doc(
                content=content,
                index=idx,

View on GitHub (pinned to 4a030776a3)

Solutions

1. Read the Errors: [...] portion of the message — it is the server's own error list and names the failing component directly.
2. Retry the file against the server API directly with the same options to reproduce and iterate quickly.
3. For page-level errors, ingest a page subset (pages config) to isolate the bad pages, or relax options (disable OCR/table structure enrichment).
4. If the file itself is corrupt (common for downloaded/merged PDFs), repair or skip it; no server config will help.
5. Move the file to a dead-letter/quarantine path so one bad file does not stop the batch.

def is_acceptable_status(status: str) -> bool:
    return status in {"success", "partial_success"}

try:
    nodes = [n async for n in reader.lazy_load_data(file_info)]
except ValueError as e:
    msg = str(e)
    if "failed with status" in msg:
        server_errors = msg.split("Errors:", 1)[-1]
        quarantine(file_info, reason=server_errors)  # terminal; log server's errors list
        return []
    raise

When it happens

Trigger: POST /convert/source (sync path) returning JSON with status: 'failure' and a populated errors array: unparseable document, invalid pdf_backend for the file type, OCR engine crash on the server, abort_on_error triggered by a page-level error.

Common situations: Corrupt/encrypted PDFs; documents in from_formats not enabled server-side; pdf_backend mismatch (e.g., file needs a different parser); partial failures when abort_on_error defaults to true; Docling server version changes altering error semantics.

Related errors

• Task failed with status: {status.task_status}
• No valid content found in the conversion result
• Document conversion failed: {e}
• No valid document content found after conversion
• Document extraction unsuccessful for '{file_name}': unmapped

AI-assisted analysis of zylon-ai/private-gpt@4a030776a3 (2026-08-15). Data as JSON: /api/errors/f0f269f83e390c2f. Report an issue: GitHub.