Supported Sources
Learn about the different content sources you can add to your knowledge base.
Document Types
Upload files directly to your knowledge base.
Supported Formats
| Format | Extension | Description |
|---|---|---|
.pdf | PDF documents with text extraction | |
| Word | .docx | Microsoft Word documents |
| Excel | .xlsx | Excel spreadsheets |
| CSV | .csv | Comma-separated values |
| Text | .txt | Plain text files |
| Markdown | .md | Markdown documents |
| JSON | .json | JSON data files |
Document Tips
- Use searchable PDFs when possible (faster processing)
- Break large documents into smaller files
- Ensure good text quality for scanned documents
- Keep content well-structured with headings
Web URLs
Automatically crawl and index web pages.
Adding a Website
Enter your website’s domain URL:
https://example.comPage Selection
When you add a website:
- Enter the domain URL
- We discover crawlable pages (up to 10)
- Select which pages to include
- Optionally add specific page URLs manually
Best Practices
- Start with your main documentation or FAQ pages
- Select only relevant pages (skip login pages, admin areas)
- Re-crawl periodically to capture updates
Data Source Connectors
Sync data from external sources automatically.
Available Connectors
| Connector | Description |
|---|---|
| Google Sheets | Sync rows from Google Spreadsheets |
| Airtable | Import records from Airtable bases |
| Notion | Pull content from Notion databases |
| REST API | Fetch data from any REST endpoint |
| Excel/CSV | Upload and parse spreadsheet files |
Sync Features
- Configurable sync intervals
- Manual sync trigger
- Sync history tracking
Source Management
Viewing Sources
The Knowledge tab shows all sources with:
- Source type and name
- Status (processing, ready, error)
- Last updated date
Updating Sources
- URLs: Click “Recrawl” to fetch latest content
- Files: Upload a new version to replace
- Connectors: Trigger manual sync or adjust schedule
Deleting Sources
Removing a source immediately removes its content from the knowledge base. This action cannot be undone.
Processing Pipeline
When you add content, it goes through these steps:
- Uploading — Content is received
- Extracting — Text is extracted from the source
- Chunking — Content is split into smaller pieces
- Embedding — Chunks are converted to vectors
- Indexing — Vectors are stored for search
Processing Status
| Status | Description |
|---|---|
| Pending | Waiting to be processed |
| Processing | Currently being indexed |
| Completed | Successfully processed |
| Failed | Processing failed (see error message) |
Last updated on