Skip to content
Prev Previous commit
Next Next commit
minor changes
Signed-off-by: Francisco Javier Arceo <arceofrancisco@gmail.com>
  • Loading branch information
franciscojavierarceo committed Mar 17, 2025
commit 13e433053c584b89bda810bae33ec6ef2a5c3de6
6 changes: 3 additions & 3 deletions infra/website/docs/blog/retrieval-augmentation-with-feast.md
Original file line number Diff line number Diff line change
Expand Up @@ -12,14 +12,14 @@ authors: ["Francisco Javier Arceo"]
# Is a Feature Store a good fit for GenAI use cases?
Comment thread
franciscojavierarceo marked this conversation as resolved.
Outdated
Yes, a Feature Store is a great fit for GenAI use cases!

That's because Feature Stores were developed over the last 10 years to explicitly handle the problems facing AI
practitioners. The Feast maintainers will continue to invest in making the GenAI development experience a first-class
That's because Feature Stores were developed over the last 10 years to explicitly handle the problems AI
practitioners faced when working with data. The Feast maintainers will continue to invest in making the GenAI development experience a first-class
Comment thread
franciscojavierarceo marked this conversation as resolved.
Outdated
citizen so that you can rely on Feast to customize your AI applications. If you have thoughts or ideas
feel free to reach out!
Comment thread
franciscojavierarceo marked this conversation as resolved.
Outdated

# What is Retrieval Augmented Generation (RAG)?
Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This section is fine, but can probably be simplified. We can assume readers know what RAG is and dont need to be educated on it.

[RAG](https://en.wikipedia.org/wiki/Retrieval-augmented_generation) is a technique that combines generative models
(e.g., LLMs) with retrieval systems to produce to generate contextually relevant output for a particular goal (e.g.,
(e.g., LLMs) with retrieval systems to generate contextually relevant output for a particular goal (e.g.,
question and answering).

The typical RAG process involves:
Expand Down