mirror of
https://github.com/open-webui/open-webui.git
synced 2026-10-02 02:12:25 +00:00
f956f7adc0
With the Docling content extraction engine, every conversion request carried the server's full internal upload path (for example /app/backend/data/uploads/<id>_report.pdf) as the multipart file name. Docling only needs a bare file name, and a hosted Docling instance has no business learning where Open WebUI keeps its files on disk. The loader now sends the base name of the stored file, which is what the MinerU, Datalab and Mistral loaders already do. Nothing else in the request or the parsed result changes, verified against a capturing mock server before and after. Fixes #30352 |
||
|---|---|---|
| .. | ||
| datalab_marker.py | ||
| external_document.py | ||
| external_web.py | ||
| local.py | ||
| main.py | ||
| microsoft_web_iq.py | ||
| mineru.py | ||
| mistral.py | ||
| paddleocr_vl.py | ||
| pdf.py | ||
| tavily.py | ||
| youtube.py | ||