From the course: Prometheus and Grafana: Visualizing Application Performance

Unlock this course with a free trial

Join today to access over 24,900 courses taught by industry experts.

The role of context awareness: RAG and MCPs

The role of context awareness: RAG and MCPs

From the course: Prometheus and Grafana: Visualizing Application Performance

Start my 1-month free trial Buy for my team

The role of context awareness: RAG and MCPs

“

- [Instructor] By now, you must be wondering how a machine can possibly have all the relevant information about your unique platform setup, business, or even team. Without context, the only information available to an LLM is the data it was trained on. That information clearly won't be enough to solve your local problems accurately. So how can we bring that context and how do we do it in Grafana? There are currently two main ways to provide context to LLMs. The first is by providing the ability to retrieve external knowledge before generating a response. This is known as RAG, which stands for Retrieval Augmented Generation. It allows the LLM to obtain either domain specific or up to date information. The second way to provide context is by implementing the model context protocol commonly referred to as MCP. This protocol provides a framework for LLMs to interact with external systems and data sources. With either of these two mechanisms, you can easily augment the information…

Contents