Dashboard

Upload Documents

Drop files here or click to browse
PDF, DOCX, XLSX, PNG, JPG, JPEG, TIFF  ·  Up to 10 files  ·  100 MB each

Recent 5 Uploads

Files

Settings

Appearance
Color theme
Choose your preferred color scheme
Processing & LLM
Settings saved.
Parsing Mode
Local: MarkItDown + RapidOCR. LLM: vision model for image OCR.
Classification Mode
Local: keyword rule-based. LLM: text model classifies all docs.

LiteLLM-compatible endpoint. Auto-filled when selecting a preset provider.
Write-only. Leave blank to keep the existing stored key.
None — local processing
Configure an API key above and save — models will load automatically.
Used when Classification Mode is set to LLM.
None — use local RapidOCR
Configure an API key above and save — models will load automatically.
Used when Parsing Mode is set to LLM. Shows vision-capable models only.
Default — falls back to Vision / Text model
Configure an API key above and save — models will load automatically.
Used to extract ERP fields from invoices via vision. Pick a strong multimodal model (e.g. Claude Opus 4.8, or Sonnet 4.6 for lower cost).

The categories used by the LLM classifier. The last category acts as the fallback (e.g. "Other").

Mail Analysis

Microsoft connection