Skip to main content

Quick Start

This guide walks you through creating your first vector table and running a semantic search query in under 5 minutes.

Prerequisites​

  • An Embedd.to API key
  • A source database (Snowflake or PostgreSQL) with a table containing text data
  • An embedding provider API key (OpenAI or Google Gemini)

Step 1: Create an Environment​

curl -X POST https://api.embedd.to/v1/environments \
  -H "Authorization: Bearer sk_your_key" \
  -H "Content-Type: application/json" \
  -d '{"name": "production"}'
{
  "id": "env_abc123",
  "org_id": "org_xyz",
  "name": "production",
  "created_at": "2025-01-15T10:00:00Z"
}

Step 2: Create a Connection​

curl -X POST https://api.embedd.to/v1/providers/snowflake/connections \
  -H "Authorization: Bearer sk_your_key" \
  -H "X-Environment-Id: env_abc123" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "my-snowflake",
    "mode": "managed",
    "credentials": {
      "auth_method": "password",
      "account": "myorg-account",
      "user": "EMBEDD_USER",
      "password": "secure_password",
      "warehouse": "COMPUTE_WH",
      "database": "ANALYTICS",
      "schema": "PUBLIC",
      "role": "EMBEDD_ROLE"
    }
  }'

Step 3: Test the Connection​

curl -X POST https://api.embedd.to/v1/connections/{connection_id}/test \
  -H "Authorization: Bearer sk_your_key" \
  -H "X-Environment-Id: env_abc123"
{
  "status": "connected",
  "details": {"latency_ms": 245}
}

Step 4: Register an Embedding Provider​

curl -X POST https://api.embedd.to/v1/embedding-providers \
  -H "Authorization: Bearer sk_your_key" \
  -H "X-Environment-Id: env_abc123" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "my-openai",
    "provider": "openai",
    "api_key": "sk-proj-...",
    "default_model": "text-embedding-3-small"
  }'

Step 5: Create a Vector Table​

curl -X POST https://api.embedd.to/v1/vector-tables \
  -H "Authorization: Bearer sk_your_key" \
  -H "X-Environment-Id: env_abc123" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "product-search",
    "connection_id": "conn_abc123",
    "embedding_provider_id": "ep_abc123",
    "source_table": "PRODUCTS",
    "primary_key_column": "ID",
    "columns": [
      {"name": "DESCRIPTION", "role": "embedding", "ordinal": 1},
      {"name": "CATEGORY", "role": "metadata", "filter_type": "keyword"},
      {"name": "PRICE", "role": "metadata", "filter_type": "float"}
    ],
    "embedding_model": "text-embedding-3-small",
    "embedding_dimensions": 1536,
    "mode": "managed",
    "sync_mode": "cdc"
  }'

Step 6: Trigger a Backfill​

curl -X POST https://api.embedd.to/v1/vector-tables/{vector_table_id}/backfill \
  -H "Authorization: Bearer sk_your_key" \
  -H "X-Environment-Id: env_abc123"

The backfill runs asynchronously, reading all rows from the source table, generating embeddings, and storing the vectors.

Step 7: Query​

curl -X POST https://api.embedd.to/v1/vector-tables/{vector_table_id}/query \
  -H "Authorization: Bearer sk_your_key" \
  -H "X-Environment-Id: env_abc123" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "comfortable running shoes",
    "limit": 5,
    "filters": {
      "CATEGORY": {"$eq": "footwear"},
      "PRICE": {"$lte": 150}
    }
  }'
{
  "results": [
    {
      "id": 42,
      "similarity_score": 0.92,
      "metadata": {"CATEGORY": "footwear", "PRICE": 129.99},
      "embedded_text": "Lightweight running shoe with cushioned sole..."
    }
  ],
  "query": "comfortable running shoes",
  "model": "text-embedding-3-small",
  "total_results": 1
}

Next Steps​