Skip to main content
POST
Semantic Search

Authentication

Supports both Firebase and API Key authentication.

Request Body

string
required
Natural language search query
integer
default:"10"
Maximum number of results (1-100)

Example Request

Response

Returns matching collections ordered by similarity score.
string
Collection UUID
string
Collection display name
number
Cosine similarity score (0-1, higher is better)

Example Response

How It Works

  1. Query Embedding - Your query is converted to a 768-dimensional vector using Vertex AI
  2. Similarity Search - pgvector performs cosine similarity search against all collection embeddings
  3. Access Filtering - Results are filtered to collections you have access to
  4. Ranking - Results are ordered by similarity score (highest first)

Access Control

  • Admins: Search across all collections
  • Clients: Search only across collections they have access to

Errors