• If you followed along with my blog, you’d have a chatbot running on your local Fedora machine. • (And if not, no worries as the scripts below implement this chatbot!) Our chatbot talks, and has a refined personality, but does it know anything about the topics we’re interested in? • Unless it has been trained on those topics, the answer is “no”. • I think it would be great if our chatbot could answer questions about Fedora. • I’d like to give it access to all of the Fedora documentation. • How does an AI know things it wasn’t trained on?
Article Summaries:
- A developer has extended a locally hosted AI chatbot on Fedora to answer Fedora‑specific questions by integrating Retrieval‑Augmented Generation (RAG). The chatbot, which already runs on a Fedora machine, previously produced confident but incorrect answers about Fedora Silverblue upgrades. To give it accurate knowledge, the author uses Docs2DB-a free RAG tool that ingests source documents, stores them in a PostgreSQL database, and retrieves relevant text for queries. Users can download a pre‑built database of Fedora documentation, install required packages (uv, podman, PostgreSQL), and restore the data with simple commands. Once integrated, the bot should provide correct, document‑based responses.
Sources: