ParsRAG
Persian Install

Guide

Add documents

Each conversation has its own documents. You add them in the Documents panel, choose which ones answers may use, and can bring in a file already indexed in another conversation.

Upload

  • Drop files or choose them. Each file shows three steps: Transfer file, Extract and index, Ready to ask, followed by the number of passages indexed.
  • Default capacity: 10 files per conversation, 100 MiB per file, 500 MiB per upload. The interface reads the real limits from the service, and you can change them in Settings → Documents & speed.
  • A batch is all or nothing: if one file fails, nothing from that request is left half-indexed.

Supported files

FamilyExtensionsHow it is read
Documents.pdf .docx .pptxStructured extraction; OCR for scanned or image-heavy PDF pages and embedded images
Images.png .jpg .jpeg .webp .bmp .tif .tiffValidated and read with OCR
Text and data.txt .md .markdown .json .csv .tsv .logUTF-8, UTF-16 with BOM, Windows-1256 (Persian) or Windows-1252; JSON is validated
Markup and config.html .htm .xml .yaml .yml .toml .ini .cfgVisible text from markup; plain text from config
Source code.py .js .jsx .ts .tsx .css .sqlText with section metadata

Checks before reading

  • File names must be plain names up to 255 characters, without paths.
  • A PDF must really be a PDF, and a Word or PowerPoint file a real Office archive. Password-protected files are named as such.
  • Office archives are limited to 10,000 entries, 200 MiB expanded and a compression ratio of 200 per entry.
  • A file with the same content as one already in the conversation is recognized and not added twice.

When a file is only partly read

NoticeMeaning
OCR limitOnly the first scanned pages were read (30 by default).
OCR image limitSome images inside a Word or PowerPoint file were skipped (200 by default).
OCR partialOCR couldn't read some pages or images.
OCR unavailableTesseract isn't installed; text pages were still indexed.

Managing documents

  • Use in answers: tick or clear each document; you can clear every selection.
  • From earlier conversations: add an indexed file without uploading it again. The copy becomes independent once it finishes.
  • Delete a document with a two-step confirmation; its passages and image previews are removed from the index.

Documents indexed by 1.0.0 keep working. Upload Word and PowerPoint files again to gain image and table citations, image previews next to sources, images past the 30th and better OCR of screenshots.

Loading…