Skip to main content

Introduction

Vector Data Loader is a powerful document management platform designed to help you load, organize, and synchronize documents from multiple sources into vector stores. This enables advanced semantic search and retrieval-augmented generation (RAG) applications.

What is a Vector Store?​

A vector store is a specialized database that stores documents as numerical representations called "embeddings." These embeddings capture the semantic meaning of your content, allowing for intelligent similarity searches. Instead of traditional keyword matching, vector stores find documents based on conceptual similarity—understanding that "automobile" and "car" mean the same thing.

Key Features​

  • Multi-Source Ingestion: Connect to Confluence, Google Drive, websites, or upload files directly
  • Automatic Chunking: Documents are intelligently split into optimal-sized chunks for vector storage
  • Multiple Vector Store Support: Choose from Supabase pgvector, Pinecone, Qdrant, or Milvus (coming soon)
  • Flexible Embedding Models: Support for OpenAI, Cohere, Google Gemini, and Ollama
  • Project Organization: Organize documents into projects for better management
  • Real-time Sync: Keep your vector store up-to-date with source changes
  • Team Collaboration: Multi-tenant architecture with organization support

Next Steps​

Ready to get started? Check out our Getting Started guide to create your account and begin loading documents into your vector store.

Documentation last verified: February 2026