Querying PDFs with PrivateGPT and Qdrant RAG

Ingest PDFs into a local vector store and ask natural-language questions using Arka’s PrivateGPT and Qdrant-powered retrieval-augmented generation pipeline.

Ask questions about your PDFs using PrivateGPT + Qdrant vector search.

Commands

Command	Example
arka pdf_ingest	pdf_ingest ~/Documents/resume.pdf
pdf_list	List ingested documents
arka pdf_ask	pdf_ask --doc resume.pdf "summarize skills"

Natural language

arka "ask Profile.pdf about main skills"
arka "summarize ENGLSH-2 weeks 1 to 3"

Setup

Requires PrivateGPT and Docker for Qdrant. Arka auto-starts services when PDF_RAG_AUTO_START=1.

PDF_RAG_URL=http://127.0.0.1:8080
PRIVATEGPT_HOME=~/Projects/private-gpt
PDF_RAG_AUTO_START=1

pip install "arka-agent[pdf]"
arka pdf status    # check PrivateGPT + Qdrant