fix docs: typo (#161)

docs/guides/use_cases.md

@@ -12,7 +12,6 @@ are a simple and effective tool that allows you to answer a query over a large c
 When you define a Vector Store Index over a collection of documents, it embeds each text chunk and stores the 
 embedding in an underlying vector store. To answer a query, the vector store index embedds the query, 
 fetches the top-k text chunks by embedding similarity, and runs the LLM over these chunks in order to synthesize the answer.
-to obtain
 [The starter example](/getting_started/starter_example.md) shows how to get started using a Vector Store Index
 (`GPTSimpleVectorIndex`). See [Embedding Support How-To](/how_to/embeddings.md) for a more detailed treatment of all vector
 store indices (e.g. using Faiss, Weaviate).