Skip to main content

Getting Started with Embedd.to

Embedd.to is a provider-agnostic vectorized table management API. It connects to your existing databases, automatically generates and maintains vector embeddings, and provides a unified query interface for semantic search.

What Embedd.to Does​

  • Connects to your data — Snowflake, PostgreSQL, with more providers coming
  • Generates embeddings — Automatically embeds your text data using OpenAI, Google Gemini, or Snowflake Cortex
  • Keeps vectors in sync — CDC and batch sync modes detect changes and re-embed automatically
  • Unified query API — One API for semantic search across any provider, any embedding model

Key Concepts​

Environments​

Environments isolate resources (connections, vector tables) within your organization. Use them to separate dev, staging, and production.

Connections​

A connection stores credentials to a source database. Connections are scoped to an environment and support Snowflake and PostgreSQL.

Embedding Providers​

An embedding provider stores API credentials for an embedding service (OpenAI, Google Gemini). Required for managed mode and PostgreSQL platform mode.

Vector Tables​

A vector table links a source table to its vector representation. It defines which columns to embed, which embedding model to use, and where to store the vectors.

Modes​

  • Managed mode — Embedd.to stores vectors in its own Qdrant instance. Best for getting started quickly.
  • Platform mode — Vectors are stored in your own database (Snowflake or PostgreSQL with pgvector). Best for keeping data in your infrastructure.

Sync Modes​

  • Batch — Periodic full-table comparison to detect changes
  • CDC — Polling-based change data capture for near-real-time sync

Next Steps​

  1. Set up authentication to get your API key
  2. Follow the Quick Start guide to create your first vector table
  3. Read the Provider Guides for provider-specific setup