diff --git a/topics/rag/index.md b/topics/rag/index.md
new file mode 100644
index 00000000000..97a32ca67db
--- /dev/null
+++ b/topics/rag/index.md
@@ -0,0 +1,13 @@
+---
+aliases: retrieval-augmented-generation, rag-pipeline
+display_name: Retrieval-Augmented Generation
+short_description: Retrieval-augmented generation connects Large Language Models to external knowledge bases to provide accurate responses.
+topic: rag
+logo: rag.png
+wikipedia_url: https://en.wikipedia.org/wiki/Retrieval-augmented_generation
+related: artificial-intelligence, generative-ai, llms, embeddings
+---
+
+Retrieval-augmented generation (RAG) is a technique that improves large language models by retrieving relevant information from external sources and using it to generate more accurate and context-aware responses.
+
+A RAG system combines information retrieval with a language model. It is commonly used in AI assistants, search systems, document question answering, and applications that need access to private or frequently updated information.
diff --git a/topics/rag/rag.png b/topics/rag/rag.png
new file mode 100644
index 00000000000..06f61705b72
Binary files /dev/null and b/topics/rag/rag.png differ