Privacy Policy

CiteSeek stores the text extracted from documents you upload, never the original files. Everything is hosted in the EU. Answers are generated by Google’s Gemini API, which means the text of your documents and your questions is sent to Google. This deployment runs on Google’s free tier, so do not upload anything confidential. Deleting your account deletes everything, immediately and for real.

• Your account — the email address and profile name your sign-in provider gives us, and a session record.
• Extracted text — when you upload a document, it is parsed and the text is stored. The uploaded file itself is discarded once parsing finishes and is never written to disk or object storage.
• Passages and embeddings — the text split into chunks, each with a numeric vector used to find relevant passages. The vectors are derived from your text and are stored alongside it.
• Conversations — your questions, the answers, and which passages each answer cited.
• Usage counts — how many provider calls were made and how many tokens they used, kept for 30 days and then deleted. These carry no document or message content.

Guests are the exception: a guest session is a signed cookie with a 24-hour expiry and nothing about a guest is written to the database at all. A guest’s conversation lives in their browser and is gone on reload.

The application runs in Frankfurt (Vercel fra1) and the database is a Neon Postgres instance in the same region. Both are pinned in configuration rather than left to a default.

• Google (Gemini API) — receives the text of retrieved passages and your question in order to generate an answer, and receives document text in order to produce embeddings. See the warning below.
• Vercel — hosts the application and terminates requests.
• Neon — hosts the database.
• GitHub — only if you sign in with it, and only to confirm who you are.

This deployment uses Google’s free tier. Under the standard free-tier terms, Google may use submitted content to improve its services. A paid tier, or written data-processing terms, changes that — and until this deployment has one and this page says so, you should treat anything you upload as content you would be willing to share with a third party.

That is why the demo workspace is read-only and seeded with a fictional document, and why this warning appears beside the upload control rather than only here.

Deleting a document removes its text, its passages and their embeddings. Deleting your account removes the account, its workspaces, every document in them, every conversation, and every usage record — in one operation, with no soft-delete and no recovery window. You can do it yourself from the account page.

• Document contents and message bodies are never written to logs.
• There is no analytics, advertising or third-party tracking.
• Nothing is sold or shared beyond the processors listed above.

This is a portfolio project rather than a company. Questions and erasure requests go through the repository, which is linked in the footer of every page. You can also delete everything yourself from the account page without asking anyone.