pgai is a suite of PostgreSQL extensions developed by Timescale to empower developers in building AI applications directly within their databases. It integrates tools for vector storage, advanced indexing, and AI model interactions, facilitating the development of applications like semantic search and Retrieval-Augmented Generation (RAG) without leaving the SQL environment.
Features
- Includes pgvector for storing and querying vector embeddings
- Provides pgvectorscale for enhanced indexing using StreamingDiskANN
- Offers pgai extension to call AI models directly from SQL
- Supports building semantic search and RAG applications within PostgreSQL
- Enables storage of vector embeddings alongside relational and time-series data
- Designed for seamless integration with Timescale Cloud
Follow pgai
Other Useful Business Software
Stop Storing Third-Party Tokens in Your Database
Rolling your own OAuth token storage can be a security liability. Token Vault securely stores access and refresh tokens from federated providers and handles exchange and renewal automatically. Connected accounts, refresh exchange, and privileged worker flows included.
Rate This Project
Login To Rate This Project
User Reviews
Be the first to post a review of pgai!