Our great sponsors
-
WorkOS
The modern identity platform for B2B SaaS. The APIs are flexible and easy-to-use, supporting authentication, user identity, and complex enterprise features like SSO and SCIM provisioning.
A RAG implementation's quality and performance highly depend on the similarity-based search of embeddings. The challenge arises from the fact that embeddings are usually high-dimensional vectors, and the knowledge base may have many documents. It's not surprising that the popularity of LLM catalyzed the development of specialized vector databases like Pinecone and Weaviate. However, SQL databases are also evolving to meet the new challenge.
PostgreSQL's pgvector extension is probably the most widely used SQL solution for storing and searching vector data today. The extension introduces a "vector" type specialized for storing high-dimensional vector data. It allows you to create vector indices (in "IVFFlat" or "HNSW" format for different indexing/searching performance tradeoffs) and leverage them to do various types of similarity searches.
Mindsdb is a good example. It abstracts everything related to an AI workflow as "virtual tables". For example, you can import OpenAI API as a "virtual table":