A data source contains data that has been ingested (pre-processed for an LLM model to use) to form a knowledge base.
Each data source contains either uploaded files with metadata, current published chatbot content, or crawled web pages, and is configured to ingest the data a specific way. The storage type and ingestion configurations can't be changed once the data source has been created.
Changes to data sources must be published before they take effect in your chatbot. You should sync your data source to test your changes thoroughly in TestBot before you publish them.
Data source data is not stored in versions
Changes to data sources must be published so that you have control over when your chatbot uses an updated data source, but the data is not stored in your chatbot version. If you delete a data source or knowledge base, it is deleted immediately from your live chatbot and can't be recovered.
You can:
- Create a data source
- Manage data in a file storage data source:
- Connect the published content of the current chatbot:
- Manage data in a web crawler data source:
- Sync a data source
- View the sync and publishing history of a data source
- Delete a data source