pautobot

📦 Archived (May 2026) — see nrl-ai/nom-vn for active work.

PAutoBot was our 2023-era prototype of a private, document-grounded AI assistant. The local-first, on-prem ideas behind it have been rebuilt and extended in nom-vn — a Vietnamese-first AI toolkit covering RAG, OCR, document extraction, and (since 2026-05) nom.compliance for Vietnam’s AI Law 134/2025/QH15.

Existing forks and issues remain readable; no further updates will land here. New issues / PRs / questions, please file against nom-vn.

---

🔥 PⒶutoBot 🔥

Private AutoGPT Robot - Your private task assistant with GPT!

• 🔥 Chat to your offline LLMs on CPU Only. 100% private, no data leaves your execution environment at any point.
• 🔥 Ask questions to your documents without an internet connection. Engine developed based on PrivateGPT.
• 🔥 Easy coding structure with Next.js and Python. Easy to understand and modify.
• 🔥 Built with LangChain, GPT4All, Chroma, SentenceTransformers, PrivateGPT.

The supported extensions are:

• .csv: CSV,
• .docx: Word Document,
• .doc: Word Document,
• .enex: EverNote,
• .eml: Email,
• .epub: EPub,
• .html: HTML File,
• .md: Markdown,
• .msg: Outlook Message,
• .odt: Open Document Text,
• .pdf: Portable Document Format (PDF),
• .pptx: PowerPoint Document,
• .ppt: PowerPoint Document,
• .txt: Text file (UTF-8),

I. Installation and Usage

1. Installation

• Python 3.8 or higher.
• Install PAutoBot:

pip install pautobot

2. Usage

• Run the app:

python -m pautobot.app

or just:

pautobot

• Go to http://localhost:5678/ to see the user interface. You can choose one of the two modes:
  • Chat Only
  • Documents Q&A
• Upload some documents to the app (see the supported extensions above). You can try docs/python3.11.3_lite.zip for a quick start. This zip file contains 45 files from the Python 3.11.3 documentation.
• Force ingesting documents with Ingest Data button.

You can also run PAutoBot publicly to your network or change the port with parameters. Example:

pautobot --host 0.0.0.0 --port 8080

II. Development

1. Clone the source code

git clone https://github.com/nrl-ai/pautobot
cd pautobot

2. Run your backend

• Python 3.8 or higher.
• To install Pautobot from source, from pautobot source code directory, run:

pip install -e .

• Run the app:

python -m pautobot.app

• Go to http://localhost:5678/ to see the user interface.

2. Run your frontend

• Install the dependencies:

cd frontend
npm install

• Run the app:

npm run dev

• Go to http://localhost:3000/ to see the user interface. Use this address to develop the frontend.