Large language models (LLMs) have evolved beyond generating text responses to interpreting text prompts. Discover how you can use a multimodal LLM to search your AI applications with PostgreSQL pgvector. This blog examines the architecture, database schema, and code required to build an application that searches recipes by both text and image.
Developers can now store, index and query vectors in PostgreSQL using pgvector, eliminating the need for a dedicated vector database. This blog deep dives into pgvector, and explains how to store text embeddings as vectors, execute similarity search, choose between indexes, and scale with distributed SQL.
Postgres is increasingly being used for Gen AI workloads, but users have reported scalability and performance issues, data privacy challenges and high availability concerns. Before you choose a scalable, HA, vector database instead, try running distributed PostgreSQL. Read our new blog to discover when and how to use distributed PostgreSQL for Gen AI workloads.
In this blog, we examine how to create a fully autonomous AI travel agent, capable of finding listings and managing bookings using LangChain, OpenAI, PostgreSQL and pgvector, with YugabyteDB as the underlying database. Learn how to build your own AI agent backed by PostgreSQL using components available in today’s ecosystem.
Adopting AI to automate release note creation, the software development teams at YugabyteDB have significantly streamlined their processes. By harnessing OpenAI’s GPT-4, they now generate precise, user-friendly documentation from extensive code changes, enhancing both efficiency and readability for end users.
