Update README.md

README.md

@@ -2667,9 +2667,16 @@ Training data to train the models is released in its entirety. For more details,
 
 ## Usage
 
-Note `nomic-embed-text` requires prefixes! We support the prefixes `[search_query, search_document, classification, clustering]`.
+Note `nomic-embed-text` *requires* prefixes! We support the prefixes `[search_query, search_document, classification, clustering]`.
 For retrieval applications, you should prepend `search_document` for all your documents and `search_query` for your queries.
 
+For example, you are building a RAG application over the top of Wikipedia. You would embed all Wikipedia articles with the prefix `search_document`
+and any questions you ask with `search_query`. For example:
+```python
+queries = ["search_query: who is the first president of the united states?", "search_query: when was babe ruth born?"]
+documents = ["search_document: <article about US Presidents>", "search_document: <article about Babe Ruth>"]
+```
+
 ### Sentence Transformers
 ```python
 import torch.nn.functional as F