AlQasmi القاسمي
العربية Contact me
Work
RAG

Ask your documents in Arabic

An Arabic RAG system that reads laws, contracts and notes, and answers with the source of each point.

An example I built for my own documents

Your documents stay on your server: reading, search and answers all happen in house, and nothing is sent to a cloud service.

Arabic RAG system: an Arabic question about a financing contract, answered with quotes from the contract and their source

The idea

I built it because I need it: I use it to review my documents, contracts and obligations, and to answer some legal questions from Arabic laws and regulations.

Many of these documents are scanned, and searching them by hand is slow. The system reads and indexes them, then answers the question and says where the answer came from.

How it works

  1. 1

    Reads scanned documents with PaddleOCR-VL, then a local model classifies them automatically: law, contract, letter, invoice.

  2. 2

    Splits notes by their headings, then nomic-embed-text turns each chunk into a vector.

  3. 3

    Searches by meaning and by keywords together and merges the results. For Arabic questions it weights keywords higher, because they are more precise in Arabic.

  4. 4

    Qwen 3.8 27B writes the answer and cites the source of each point.

  5. 5

    All of it runs on my machines, so the documents never leave them.

PaddleOCR-VL nomic-embed-text Paperless-ngx Qwen 3.8 27B Runs locally
Each question
Document prep
Arabic question
"What do I owe under the contract?"
nomic-embed-text
Embeds the question
Hybrid search
Meaning and keywords
Documents
Laws, contracts, notes
PaddleOCR-VL
Reads and classifies
Index
Documents and notes archive
Qwen 3.8 27B
Writes the answer with a source for each point

Let's run a solution like it on your documents, inside your organization

Contact me
Next projectRecording transcription and summaries