Can we use AI on our own documents without sending them to an AI provider?

Private RAG

Ask a business document a question and get an answer with citations. Retrieval, the vector database and the model all run on this server, so nothing is sent to a third-party AI provider.

Built for teams whose documents cannot leave their control: banking, healthcare, government and legal work, where the UAE's data rules apply.

Built and run by , Technical Lead and Solution Architect in Dubai. Talk to Deepak · LinkedIn · GitHub

Questions people ask

What is a private RAG system?

Retrieval-augmented generation (RAG) answers a question by first finding the relevant passages in your documents and then asking a language model to answer only from them. Private means the retrieval, the vector database and the model all run on infrastructure you control, so documents are never sent to an AI provider.

How do I know the answer is not made up?

Every answer lists the exact passages it was built from, with a similarity score, so you can check each claim. When the document does not contain the answer, the system says so instead of guessing.

Which industries need RAG on private data?

Any team whose documents cannot leave its control: banks, insurers, healthcare providers, government entities and legal teams, including those under UAE data-protection rules.

Has Deepak shipped RAG in production?

Yes. At SmartSitting he architected a self-hosted RAG pipeline on Ollama that keeps candidate, job and family data off commercial models. This lab is a public version of the same pattern.

Who built this?

Deepak Kumar Jha, a Technical Lead and Solution Architect based in Dubai, UAE, with 14 years of building and running production systems. He designed, built, deployed and operates every part of the lab himself: the Angular console, the NestJS APIs, the model serving and the gateway.