# pgvector-crystal

> Crystal SDK/client for pgvector PostgreSQL extension, providing idiomatic bindings for vector storage and similarity search. Supports embeddings workflows (OpenAI/Cohere), hybrid/sparse search via crystal-pg driver. For integrating Postgres vector ops into Crystal apps; official community client vs. direct SQL or other lang bindings.

- **URL:** https://github.com/pgvector/pgvector-crystal
- **Category:** Postgres Vector Extensions
- **Tags:** Crystal, Pgvector, Async Client, Postgres Client
- **Updated:** 2026-04-28 11:38
- **Canonical page:** https://vectordb.ever.works/nl/items/pgvector-crystal

## Details

## Overview

pgvector-crystal offers Crystal language bindings for pgvector, enabling vector operations in PostgreSQL from Crystal applications.

## SDK Features

- Integration with crystal-pg PostgreSQL driver
- Vector embeddings support (OpenAI, Cohere binary)
- Hybrid search with RRF (Ollama)
- Sparse vector search
- Similarity queries (cosine, L2, etc.)

## Use Cases

- App integration for Crystal/Phoenix stacks
- RAG and semantic search
- Embeddings storage/querying

## Comparisons

- Community Crystal client vs. official Python/JS/.NET or raw SQL

## Pricing

Free open-source (MIT).

---

_This Markdown mirror is generated by Ever Works for AI agents. The canonical HTML page is at https://vectordb.ever.works/nl/items/pgvector-crystal._