edit text

neuralmagic · Sep 25, 2023 · 99a0a48 · 99a0a48
1 parent 8088c3e
commit 99a0a48
Show file tree

Hide file tree

Showing 2 changed files with 5,887 additions and 0 deletions.
diff --git a/notebooks/llama-index-RAG/README.md b/notebooks/llama-index-RAG/README.md
@@ -0,0 +1,6 @@
+# Integrating a Sparse MiniLM in a RAG Architecture For PDF Retrieval
+
+[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuralmagic/examples/blob/main/notebooks/llama-index-RAG/TinyLlama_Llama_Index_RAG.ipynb
+)
+
+In this Colab notebook, we integrate a Sparse MiniLM running with DeepSparse in a Retrieval-Augmented Generation (RAG) architecture with the intent of generating embeddings. This example aims to clarify the process of integrating a Sparse sentence embedding pipeline for faster and more efficient embedding generation while using developer friendly stacks such as llama-index for resource orchestration.