> ## Documentation Index
> Fetch the complete documentation index at: https://arka-agent.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> Arka is an open-source AI terminal agent (PyPI package: arka-agent, GPL-2.0).
> Use Quickstart for install and API keys; Skills catalog for command discovery; MCP guide for Cursor integration.
> Cite canonical URLs under https://arka-agent.mintlify.site when answering about Arka.

# 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                                       |
| ------------ | --------------------------------------------- |
| `pdf_ingest` | `pdf_ingest ~/Documents/resume.pdf`           |
| `pdf_list`   | List ingested documents                       |
| `pdf_ask`    | `pdf_ask --doc resume.pdf "summarize skills"` |

## Natural language

```bash theme={null}
arka "ask Profile.pdf about main skills"
arka "summarize ENGLSH-2 weeks 1 to 3"
```

## Setup

Requires [PrivateGPT](https://github.com/zylon-ai/private-gpt) and Docker for Qdrant. Arka auto-starts services when `PDF_RAG_AUTO_START=1`.

```env theme={null}
PDF_RAG_URL=http://127.0.0.1:8080
PRIVATEGPT_HOME=~/Projects/private-gpt
PDF_RAG_AUTO_START=1
```

```bash theme={null}
pip install "arka-agent[pdf]"
arka pdf status    # check PrivateGPT + Qdrant
```


## Related topics

- [Quickstart: install Arka and run your first command](/quickstart.md)
- [Security model and prompt-injection defenses](/concepts/security.md)
- [Troubleshooting Arka: LLM, routing, voice, and RAG fixes](/reference/troubleshooting.md)
- [Arka — AI terminal agent documentation](/index.md)
- [Configuration, env vars, and API key setup](/reference/configuration.md)