Tue.Nov 19, 2024

article thumbnail

Using Loki and Promtail to Display PostgreSQL Logs From a Kubernetes Cluster in PMM

Percona

This is a follow-up to my colleagues Nickolay and Phong’s Store and Manage Logs of Percona Operator Pods with PMM and Grafana Loki and Agustin’s Turbocharging Percona Monitoring and Management With Loki’s Log-shipping Functionality blog posts.

article thumbnail

Unbundling the Graph in GraphRAG

O'Reilly

One popular term encountered in generative AI practice is retrieval-augmented generation (RAG). Reasons for using RAG are clear: large language models (LLMs), which are effectively syntax engines, tend to “hallucinate” by inventing answers from pieces of their training data. The haphazard results may be entertaining, although not quite based in fact.