Data Sources¶

14 data sources for ingesting documents — cloud storage, enterprise repositories, and web sources.

Sub-sections:

• Overview — all 14 sources + supported file formats
• Configuration — credentials and settings
• S3 Setup · Azure Blob · GCS · Alfresco · Nuxeo · CMIS
• Sign-In and Permission-Aware Search — per-user sign-in so search and chat use only documents the user may read; setup for Microsoft 365 · Box · Google · Azure Storage · Amazon S3 · CMIS vendors
• Incremental Auto-Sync — real-time and near-real-time change detection
• Document Processing — Docling and LlamaParse, supported formats