ragflow

mirror of https://github.com/infiniflow/ragflow.git synced 2026-05-24 09:57:36 +08:00

Files

刘康伟 c6e3a2e713 Fix: MinerU vlm-http-client backend output file detection (#14240 )

## Problem
When using MinerU with `vlm-http-client` backend, the parser fails to
find the output files because they are located in a `vlm/` subdirectory,
but the `_read_output`
  method doesn't check this location.

  ## Error Message
  [ERROR]MinerU not found.
  [MinerU] Missing output file, tried: ...

  ## Root Cause
The MinerU API with `vlm-http-client` backend returns output files in
the following structure:
  output_dir/
    vlm/
      filename_content_list.json
      filename.md
      images/

  However, the `_read_output` method in `mineru_parser.py` only checks:
  1. `output_dir/filename_content_list.json`
  2. `output_dir/sanitized_filename_content_list.json`
3. `output_dir/sanitized_filename/sanitized_filename_content_list.json`

  It doesn't check the `vlm/` subdirectory.

  ## Solution
  Added two additional fallback paths to check the `vlm/` subdirectory:
  - `output_dir/vlm/filename_content_list.json`
  - `output_dir/vlm/sanitized_filename_content_list.json`

  ## Testing
Tested with MinerU API using `vlm-http-client` backend. The parser now
successfully finds and processes the output files.

  ## Related
  This issue occurs specifically when using:
  - MinerU backend: `vlm-http-client`
  - MinerU server URL configured for remote vLLM inference

2026-05-19 12:28:31 +08:00

resume

fix: close file handles in json.load() calls in resume parser (#14061 )

2026-04-14 11:43:58 +08:00

__init__.py

Feat: support epub parsing (#13650 )

2026-03-17 20:14:06 +08:00

docling_parser.py

Fix: Remove hardcoded page limits causing parsing failures on large PDFs (>300 pages) (#14382 )

2026-04-27 14:57:20 +08:00

docx_parser.py

Fix: Remove hardcoded page limits causing parsing failures on large PDFs (>300 pages) (#14382 )