Ingest data sources

Train each bot on one or more data sources. You can mix URLs, files, text, and Q&A.

URL sources

Use this to train on existing web pages.

Workflow:

1. Go to Data Sources > URL.
2. Click Add more URLs.
3. Add one or more root URLs (up to 5).
4. Click Parse URLs to discover sub-links.
5. Review the parsed list and remove any unwanted links.
6. Click Train.

Notes:

• Duplicate or already-trained URLs are skipped.

File sources

Use this to train on local files.

Workflow:

1. Go to Data Sources > Files.
2. Click Add more files.
3. Drag and drop files into the upload zone.
4. Click Train bot.

Supported file types:

• TXT
• PDF

Notes:

• Duplicate file names or identical content are skipped.
• Files with unsupported formats will show warnings.

Text sources

Use this for plain text content.

Workflow:

1. Go to Data Sources > Text.
2. Click Add more text.
3. Enter a title and paste content.
4. Click Train bot.

Editing:

• You can edit a text source and save changes.
• After editing, click Retrain to apply the new content.

Limits:

• Max 10,000 characters per text source.

Q&A sources

Use this to train on structured questions and answers.

Workflow:

1. Go to Data Sources > Q&A.
2. Click Add more Q&A.
3. Enter a title and add pairs.
4. Click Train bot.

Editing:

• You can edit Q&A sources and retrain them.

Limits:

• Max 50 pairs per source.
• Max 200 characters per question.
• Max 1,000 characters per answer.

Managing sources

On each data source tab you can:

• Refresh the list.
• Delete sources to remove learned data.
• Retrain when edits are saved.

Training tips:

• Keep content relevant and focused.
• For files and text, use headings and paragraphs when possible.
• Avoid tabular or unformatted text; it can lead to inaccurate responses.

Monthly plan limits

Training counts against two monthly plan allowances:

• Training volume measures the number of source characters processed.
• Tokens measure the estimated embedding usage needed to index the content.

A training request is rejected before embedding work when it would exceed either allowance. Chat requests use the token allowance but do not use the training-volume allowance. You can review current usage on the Profile page.