Add explanation to OptimizerDemo.ipynb

Added an explanation at the beginning of the notebook describing what the Sentence Embedding Optimizer does.

docs/docs/examples/node_postprocessor/OptimizerDemo.ipynb

@@ -15,7 +15,9 @@
    "id": "7ff2c269",
    "metadata": {},
    "source": [
-    "# Sentence Embedding Optimizer"
+    "# Sentence Embedding Optimizer",
+    "This postprocessor optimizes token usage by removing sentences that are not relevant to the query (this is done using embeddings).",
+     "The percentile cutoff is a measure for using the top percentage of relevant sentences. The threshold cutoff can be specified instead, which uses a raw similarity cutoff for picking which sentences to keep."
    ]
   },
   {