Skip to content

[Bug]: Ingesting folder doesn't seem to work #821

@philnash

Description

@philnash

OpenRAG Version

0.2.0

Deployment Method

uvx (uvx openrag)

Operating System

macOS 26.2

Python Version

3.13.11

Affected Area

Ingestion (document processing, upload, Docling)

Bug Description

I am trying to ingest the 368 documents from https://github.com/patronus-ai/financebench.

The first 268 files failed almost immediately with the 500 error from #820.

Then the Frontend interface and Langflow were both inaccessible for a while. Eventually some files started to process, out of 368 files, 4 successfully processed.

I was under the impression that OpenRAG would queue files to be ingested. From what I can tell, it appears that both docling and langflow got overwhelmed.

Steps to Reproduce

  1. Clone https://github.com/patronus-ai/financebench
  2. Open the OpenRAG knowledge page
  3. Upload a folder
  4. Choose the pdfs directory from financebench

Expected Behavior

Files should be ingested into OpenSearch over time.

Actual Behavior

Many files failed immediately. The OpenRAG frontend interface hung. Langflow hung. The TUI was unable to show any useful logs. Eventually 4 files were successfully processed.

Relevant Logs

:(

Screenshots

Image

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.

Metadata

Metadata

Assignees

No one assigned

    Labels

    bugSomething isn't working

    Type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions