LOCAL RAG OVER YOUR OWN DOCUMENTS
Local retrieval over your own documents, as a finished product
You know the pattern: chunk the documents, embed them, store the vectors, retrieve on a question, ground the generation, cite what was used. GI JI is that, shipped as an application you install rather than a stack you assemble. This page is written so you can decide against it quickly if it is the wrong shape for you, because for a good number of people reading this, it is.
Where building your own is the better answer — said first, on purpose
If you want to choose your own embedding model, swap the reranker, tune the chunking, or measure a change against your own evaluation set, build your own. GI JI's retrieval behaviour is fixed and not exposed for tuning — that is a deliberate product decision, and it is exactly the decision that makes it useless to you if tuning is the point. If you need to read the source, audit it, or fork it, build your own: GI JI is not open source. If you need OCR, or a team sharing one index, or a service another program calls, build your own. And if the assembly is the part you enjoy, that is a perfectly good reason on its own.
What GI JI actually is, in mechanism terms
A desktop application with a local web interface. It serves its own screens over loopback. The configuration check rejects any listen address that is not 127.0.0.1, ::1 or localhost, and the server refuses to start rather than binding somewhere another machine could reach it. You cannot turn it into a shared server, and that is the point rather than an oversight.
It brings its own models. The installer sets up the private local AI (Ollama) — about 180 MB on a Mac, 1.5 GB on Windows, 1.4 GB on Linux — and GI JI fetches the two models it uses, about 4 GB, the first time you open it. You need roughly 6 GiB of free disk and an internet connection for that one setup. After it, GI JI reads, indexes and answers with no connection at all.
The index is yours and it is local. Documents, the search index, your questions, your saved notes and the backups all live in the GI JI folder on your own disk. There is no account and no cloud library to sign into. Licence activation is the one routine exception: it contacts Freemius with what is needed to verify the licence, and nothing of your documents goes with it.
Retrieval is bounded by an explicit mode. Sources only answers from your imported material and stops when it cannot attach enough usable evidence — no answer-writing call is made. Guided adds Working Knowledge you have reviewed and approved. Open may add clearly marked general context, which is never cited to your documents. The boundary is a visible control, not a hidden prompt setting.
Generation stays local unless you say otherwise. Connected AI is optional, uses your own OpenAI API key, keeps that key in the current session only, and shows you the exact outbound packet for one-time approval before any content-bearing request leaves.
The input formats, exactly
Text-based .pdf, .docx, .txt, .md, .html and .htm, folders of them, and permitted websites. PDF text extraction goes through Poppler's pdftotext. There is no OCR: a scan-only PDF has no text layer to index, so GI JI refuses it rather than importing an empty document and pretending it worked.
The platform truth
macOS is the supported release. The Windows version on the Microsoft Store is signed by Microsoft; the direct Windows download and Linux are technical previews, less tested than the macOS release. If you are on Linux and expect a supported experience, take that at face value.
The one-line version
If you want control over the retrieval pipeline, build your own — genuinely, and this page has tried to make that easy to decide. If you want a local, cited, refusing document assistant that already works and that you never have to maintain, that is GI JI, for $79 once.
WATCH IT WORK
Answer, cited passage, and an honest refusal.
Ask a question of your own documents, open the exact cited passage, then ask something your library does not contain and watch it stop instead of inventing.
HOW GI JI COMPARES
Where GI JI wins, and where it does not.
Three comparisons with the tools you are most likely choosing between, each one naming the case where the other tool is the better buy.
WRITTEN FOR ONE READER
Four pages that answer one question properly instead of all of them briefly — what a citation is actually worth, what GI JI is and is not for a technical reader, how it stands beside a note library, and what it does for work whose material cannot leave the computer.