Document Converter
Tenant-level settings for advanced PDF conversion, including large document splitting, complex layouts, and high-accuracy table extraction.
The Settings > Configuration > Parser section includes Document Converter settings that control how the Aisera platform processes PDFs using Docling, an advanced conversion service. These are tenant-level defaults. You can override them at the data source level.
Document Converter
Type
Checkbox
Default
Disabled
When enabled, Aisera routes PDFs through an advanced conversion service that produces structured HTML with better recognition of complex layouts, multi-column text, and tables. Conversion results are cached per document, so subsequent parses of the same file do not re-process it. If the service is unavailable or conversion fails, the parser falls back to the standard converter automatically. Enable this for data sources containing PDFs with complex layouts or tables that the standard converter does not parse well, such as multi-column technical documents, financial reports, or forms.
The advanced converter splits large PDFs at 250-page boundaries, compared to 500 pages with the standard converter. The Accurate Table Parse, Force OCR, and Pdf Names settings apply to this converter and control per-document parsing behavior. Use Bypass Cache to force re-conversion of a document if its content has changed since it was last parsed. This setting only affects PDF documents.
See also: Accurate Table Parse, Force OCR, Bypass Cache, Pdf Names
Accurate Table Parse
When enabled, each PDF processed through the advanced converter receives more thorough table detection. By default, accurate table parsing applies to every PDF in the data source. If Pdf Names is also configured, only PDFs whose filenames appear in that list receive accurate table parsing; all other PDFs use standard table extraction. Enable this for data sources containing PDFs with dense, merged, or multi-level tables that standard parsing misrepresents, such as financial statements, compliance documents, or technical specifications.
See also: Pdf Names
Bypass Cache
When enabled, Aisera skips the cache check and triggers a fresh conversion for every parse, replacing the previous cached result. When disabled, the parser returns the cached HTML from the previous conversion. Enable this after source content has changed and you need the parsed output to reflect the updated document.
Re-converting documents increases parsing time and may affect processing throughput when you enable it on large data sources. Disable this setting once the refresh is complete. Subsequent parses will use the newly written cache.
See also: Document Converter
Force OCR
When enabled, optical character recognition runs on every PDF in the data source unconditionally, bypassing the normal detection that limits OCR to image-only documents. When disabled, the parser applies OCR automatically only where needed, to image-only PDFs or to specific files listed in Pdf Names. Enable this when PDFs appear to have selectable text but standard extraction produces poor results, such as scanned PDFs with a flawed embedded text layer or documents where the selectable text does not match visible content.
OCR is slower and more resource-intensive than direct text extraction. Enabling this on a large data source of text-native PDFs increases parsing time without quality benefit. Use Pdf Names instead if only specific files need OCR.
See also: Pdf Names
Last updated
Was this helpful?