Use case 04

Your documents, answering back.

A private AI knowledge base turns your files into something your assistant can search, cite, and reason over — from any AI client, with your data isolated in your own space.

Most of what you know isn't in any AI model. It's in your PDFs, reports, research papers, meeting notes, and manuals. Generic assistants can't see any of it, so they answer your specific questions with general knowledge — confidently, and often wrong.

VeelIQ Context turns those documents into a private knowledge base. Upload once; the content is chunked and indexed. From then on, any connected AI client can search it semantically, quote it, and cite exactly which file an answer came from.

Problem

Solution

Upload documents to your Context workspace at app.context.veeliq.com. Each file is split into chunks and embedded for semantic search. When your assistant needs information, it calls search_knowledge; VeelIQ returns the most relevant chunks with similarity scores and source metadata, and the assistant composes a grounded, cited answer.

The knowledge base lives behind your personal MCP URL, so it works identically in Claude, ChatGPT, Cursor, or any MCP client — one corpus, every tool. Isolation is per-user with row-level security, and your content is never used for model training. For evaluation criteria, see private knowledge bases for AI.

Benefits

Features used

Knowledge upload and semantic search from Context, with workspaces for separation and memory for the facts that emerge from your reading.

Examples

FAQ

How is this different from NotebookLM? # +
NotebookLM is a separate app you visit. A VeelIQ knowledge base plugs into the AI clients you already use — Claude, ChatGPT, your IDE — via MCP. See the full comparison.
What can go into the knowledge base? # +
Documents such as PDFs; supported formats are listed in the app. Content is chunked and embedded for semantic search.
Is the knowledge base really private? # +
Yes: per-user isolation with row-level security, no training on your content, and deletable sources. Only your authenticated endpoint can query it.
Will answers cite my documents? # +
Yes. Retrieval returns chunks with source names and metadata, so the assistant can say which file (and where) an answer came from.
How much can I store? # +
The Beta free plan includes fair-usage limits displayed in the dashboard; larger tiers arrive with general availability.
Can my team query the same knowledge base? # +
A shared context layer across a team's AI tools is a core use case; workspaces keep personal and shared corpora separate.

Related

Make your documents searchable.

Upload your first PDF free and ask your AI about it a minute later.

Try Context free