Sources
Upload PDFs, Word docs, and text files. CoachKeeper extracts the content so the AI can search and reference it.
What are sources?
Sources are documents you upload to CoachKeeper, PDFs, Word documents, Markdown, or text files. Once uploaded, CoachKeeper extracts the text and creates vector embeddings, which means the AI assistant can search and reference them when you ask questions.
Think of it as giving your AI assistant a reading list. Everything you upload becomes part of your searchable knowledge base.
Uploading a source
- Go to the Sources tab
- Click Upload and select a file (PDF, DOCX, TXT, or MD)
- The file goes through three stages: Uploaded → Processing → Ready
- Once ready, the content is searchable by the AI
You can also drag and drop files directly onto the Sources tab.
Supported file types
| Type | What gets extracted |
|---|---|
| Full text, page by page | |
| DOCX | Paragraph-level text |
| TXT / MD | Plain text content |
| Images | JPG, PNG, GIF, WebP, viewable in a lightbox (no text extraction) |
How the AI uses sources
When you ask the AI a question, it performs a semantic search across your notes and your sources. This isn’t keyword matching, it searches by meaning.
“What did the research paper say about customer retention?”
…finds relevant passages even if you didn’t use those exact words. The AI retrieves the most relevant chunks from your documents and uses them to generate its response, with context about where the information came from.
This is RAG (Retrieval-Augmented Generation). Your documents become context the AI can draw on, making its answers grounded in your actual materials rather than generic knowledge.
@Mentions in chat
Type @ in the chat input and select a source to pin it to the conversation. The AI gets the full content of that document as context, useful when you want to ask detailed questions about a specific file without the AI having to search for it.
Organizing your library
- Folders, create folders and nest them to organize your documents by project, topic, or category
- Drag and drop, move files between folders by dragging
- Grid and list views, switch between visual grid and compact list layout
- Rename, click a file or folder name to rename it inline
- Multi-select, hold Shift and click to select multiple items for bulk actions
Use cases
- Book reviewers, Upload the book PDF, then ask the AI to help you draft a review based on your highlights and the source material
- Researchers, Upload papers and let the AI cross-reference findings across multiple sources
- Students, Upload lecture slides, then ask the AI to create study todos based on the material
- Knowledge workers, Upload meeting transcripts, contracts, or strategy docs for quick AI-powered lookup
File management
Each source shows its status, filename, file size, and upload date. You can delete sources you no longer need, the embeddings are cleaned up automatically.
For large files, a confirmation dialog appears before upload to let you know the processing may take a moment.
Tips
- Upload early, ask later. The more sources you give the AI, the richer its answers become. Don’t wait until you need something, build your library as you go.
- Use @mentions for focused questions. If you want to ask about a specific document, pin it with
@instead of relying on search. - Organize with folders. A flat list of 50 files is hard to navigate. Group by project or topic for quick access.