Full-featured data pipeline
Everything you need topower your RAG pipeline
Connect any data source, embed with any model, and store in any vector database. All without writing a single line of ETL code.
0
Data Sources
Confluence, Drive, S3 & more
0
Vector Stores
Pinecone, pgvector & more
0
Embedding Models
OpenAI, Cohere, Gemini, Ollama
0
Platform
Unified management
Connect your data sources
Pull documents from where your team already works. All connectors support browsing and selective sync.
Confluence
Sync pages from Atlassian Confluence with OAuth authentication.
- OAuth authentication
- Tree browsing
- Space filtering
- Page content extraction
Google Drive
Import documents, PDFs, and sheets from Google Drive.
- OAuth authentication
- Folder browsing
- PDF extraction
- Multiple file types
Amazon S3
Connect any S3-compatible storage for document ingestion.
- Access key auth
- Bucket browsing
- Prefix filtering
- Any S3-compatible
Supabase Storage
Sync documents directly from Supabase Storage buckets.
- API key auth
- Bucket selection
- File browsing
- Direct integration
Notion
Import pages and databases from Notion workspaces.
- OAuth authentication
- Page selection
- Database support
- Rich content
Website Crawler
Crawl and index web pages and documentation sites.
- URL-based
- Depth control
- Link following
- SSRF protection
File Upload
Direct upload of PDF, DOCX, TXT, CSV, and JSON files.
- Drag & drop
- Multiple formats
- Bulk upload
- Progress tracking
Ready to build your RAG pipeline?
Get 250 free credits every month. Start syncing documents in minutes.