[Bug]: Performance Issue: Financial PDF ingestion with multiple tables takes more than 5 minutes to process

[sreedevi-m-2026]

OpenRAG Version

0.3.0

Deployment Method

uv add (installed in project)

Operating System

macOs 15.6

Python Version

3.13

Affected Area

Ingestion (document processing, upload, Docling)

Bug Description

Financial PDF documents containing multiple tables (FinanceBench dataset) take approximately 5 minutes to complete ingestion in OpenRAG.

Although the ingestion eventually completes successfully, the processing duration is significantly long and the UI does not display progress indicators during this time.

This may affect usability when ingesting complex financial reports.

Steps to Reproduce

1. Open Knowledge → Add Knowledge
2. Upload a financial PDF from the FinanceBench dataset
3. Start ingestion
4. Observe the ingestion duration

Expected Behavior

Large financial documents should ingest within a reasonable time frame
or display progress indicators for long-running processing tasks.

Actual Behavior

File ingestion completes successfully but takes approximately 5 minutes.

Relevant Logs

Screenshots

financial doc.zip

Additional Context

No response

Checklist

• I have searched existing issues to ensure this bug hasn't been reported before.
• I have provided all the requested information.

[Revathypv]

20 MB file took 40 minutes to upload