Ask questions of your own documents and websites and get answers with cited sources, from a private local model that keeps your content on your server.
This product is available in the build below. Open it for the operating system, cloud and version detail, or read its deployment guide.
| Product | Cloud | Operating system | Version | |
|---|---|---|---|---|
| DocsGPT on Ubuntu 24.04 | Azure | Ubuntu 24.04 | Standard | View · Guide |
DocsGPT is an open source, MIT licensed assistant that answers questions from your own content. You upload documents (PDF, Word, Markdown, spreadsheets, slides and more) or point it at a website, and DocsGPT splits and indexes them; when you ask a question it finds the relevant passages and writes an answer that cites the sources it used. Conversations, multiple sources, prompts and agents are managed from the web interface, and the same capabilities are available through a REST API.
It suits teams that want a private knowledge assistant over manuals, policies, product documentation or internal wikis without sending those documents to a third party.
The image answers questions the moment you sign in: a small local language model (Qwen2.5 1.5B on the CPU through Ollama) and the embedding model are already set up, so nothing you upload leaves the VM and no API key is needed. DocsGPT's hosted model, its version check and other third party calls are switched off by default, and the guide explains how to connect Azure OpenAI or another provider for faster answers when you choose to. First boot generates the sign in password, database and cache passwords, signing and encryption keys, model key and TLS certificate uniquely for each VM, and nothing serves until it has done so. Every page and API call sits behind HTTPS and your password, the containers cannot reach the Azure metadata service or your private network, and a step by step deployment guide and 24/7 support come with it.