The best vector database is the database you already have.
Vector Store and Embeddings Support
Utilize Postgres and pgvector to store and index vector embeddings.
Python Client for Unstructured Embeddings
Easily manage unstructured embeddings with a dedicated Python client.
Embedding Generation Process
Generate embeddings using open source models directly in Edge Functions.
Integrations with Popular AI Providers
Seamlessly integrate with AI tools like OpenAI, Hugging Face, and LangChain.
Supabase AI & Vectors provides an open-source toolkit for developing AI applications, leveraging PostgreSQL and the pgvector extension. This toolkit allows developers to efficiently store, index, and query vector embeddings at scale. With features such as a dedicated Python client and automatic embedding generation, Supabase simplifies the integration of AI capabilities into applications. Additionally, it offers various search functionalities, including semantic, keyword, and hybrid search, making it versatile for different use cases.
Supabase AI & Vectors operates using PostgreSQL with pgvector, facilitating database migrations for structured embeddings and supporting a range of AI models from popular providers.
Building AI-powered search features in applications.
Managing and querying vector embeddings at scale.
Integrating machine learning models for enhanced application functionality.
It is an open-source toolkit for developing AI applications using PostgreSQL and pgvector.
It allows storage, indexing, and querying of vector embeddings efficiently.
Supabase integrates with popular AI providers such as OpenAI, Hugging Face, and LangChain.
%20(1).png)
