CITELY / PRIVACY
Privacy,
in plain sight.
Read the privacy policy that applies to your use of Citely.
Overview
Citely lets you upload documents and ask questions about them, with every answer grounded in and cited back to your own document. This policy explains what data we collect to make that work, who else touches it, and how you can remove it.
What we collect
Account data: your email address, and a securely hashed password if you sign up with email — we never store your password itself. If you sign in with GitHub or Google, we store the verified email address that provider gives us. Document content: the files you upload, split into chunks and embedded as vectors for retrieval, plus extracted text and metadata such as filename and page numbers. Conversation history: the questions you ask and the answers returned, scoped to the document you asked about, so you can resume a conversation later. Account activity: when you sign up, sign in and open your workspace, and how many documents and questions you have, with your country (looked up from your internet address, which is not stored) and your browser's timezone. It never includes your password, document names, questions or answers. Only the Citely administrator sees it, to review new accounts and keep the service running. Site visits: Cloudflare Web Analytics counts page views on our public pages (for example the home page, documentation and sign-up) without cookies and without any account information. It is never loaded on pages that carry sign-in or reset links.
How we use it
Solely to run the product: authenticating you, retrieving relevant passages from your documents, generating grounded answers, and letting you resume past conversations. We do not sell your data, and we do not use your documents to train any model.
Where it goes
Citely's server runs on a virtual machine we rent from Oracle Cloud Infrastructure in Frankfurt, Germany. Everything we store is kept there: your account details, conversation history, notes, usage counts and account activity; the files you upload, their extracted text and search indexes; and the vectors used for retrieval, in a Qdrant database we run ourselves on the same machine, filtered so only your account can retrieve them. A temporary in-memory cache on that machine holds recently used document indexes for up to a day, and is cleared when you delete the document. Oracle provides the machine and its storage; the data on it is managed by us. Answers are generated by an Azure-hosted OpenAI deployment (Microsoft), which receives your question and the passages retrieved from your document; if you supply your own OpenAI key instead, that request is sent directly with your key and is never stored on our servers. To make documents searchable, the text of your documents and your questions is sent to Cloudflare Workers AI to compute embeddings. Scanned pages, images and some office files that cannot be read on our server may be sent to Azure AI Document Intelligence (Microsoft) to extract their text. To file each upload under a category (for example Education › Maths), its file name and the first 8,000 characters of its extracted text are sent to TypeSafe, which picks the category; if TypeSafe cannot, the same excerpt goes to the Azure OpenAI deployment above instead. Verification and sign-in codes and account notices are emailed via Azure Communication Services. Cloudflare provides the sign-up spam check (Turnstile) and the cookie-free visit counts. Signing in with GitHub or Google goes through that provider. None of these processors receive more than what is strictly needed to perform their part of the request. Our main website is served by GitHub Pages, and our review and administration sites by Cloudflare Pages; like any website host, they receive your internet address when your browser loads a page. International transfers: your stored data stays in Germany, but some processing happens elsewhere. The one exception for stored data is our separate hackathon demo site, hack.citelyapp.tech: while it runs, the accounts and documents created there are stored on Microsoft Azure in Central India, their search vectors in Qdrant Cloud (on Amazon Web Services in the US East region) and its cache in Upstash (Mumbai); citelyapp.tech itself is not affected. The Azure OpenAI deployment that generates answers is in Microsoft's UAE North region and, as a global deployment, Microsoft may process a request in another of its data centres. Email is sent through Azure Communication Services with its data location in India, document text extraction runs in Microsoft's Central India region, the category of an upload is chosen by TypeSafe in the United States, Cloudflare handles requests on its global network, and your own OpenAI key, if you use one, sends the request to OpenAI.
Data retention & deletion
Your documents, their vectors, and their chat history remain until you delete them. Deleting a document from the workbench removes its database record, its retrieval index, and its vectors from storage — not just a hidden flag. Deleting your account removes everything tied to it; contact us to request that.
Your rights
You can view and delete any document you have uploaded at any time from the workbench. You can request a copy of your account data, or full account deletion, by contacting us.
Security
Every document route is scoped to your authenticated account with a signed token. Passwords are hashed, never stored in plain text. Retrieved document text is treated as untrusted data, never as instructions, when generating answers.
Children's privacy
This service is not directed at children under 13, and we do not knowingly collect data from them.
Changes to this policy
If this policy changes in a way that affects how your data is handled, you will be asked to review and re-accept it the next time you sign in.
Contact
Questions about this policy or your data can be sent via the project repository.