Crate synaptic_pgvector 

PostgreSQL + pgvector integration for the Synaptic framework.

This crate provides PgVectorStore, an implementation of the VectorStore trait backed by PostgreSQL with the pgvector extension. It stores document content, metadata (as JSONB), and embedding vectors in a single table, using cosine distance (<=>) for similarity search.

Quick start

use sqlx::postgres::PgPoolOptions;
use synaptic_pgvector::{PgVectorConfig, PgVectorStore};

let pool = PgPoolOptions::new()
    .max_connections(5)
    .connect("postgres://user:pass@localhost/mydb")
    .await?;

let config = PgVectorConfig::new("documents", 1536);
let store = PgVectorStore::new(pool, config);
store.initialize().await?;

Structs

Document

A document with content and metadata, used throughout the retrieval pipeline.

PgVectorConfig

Configuration for a PgVectorStore table.

PgVectorStore

A VectorStore backed by PostgreSQL with the pgvector extension.

Traits

Embeddings

Trait for embedding text into vectors.

VectorStore

Trait for vector storage backends.