Apply suggestions from code review

Co-authored-by: Katarina Supe <61758502+katarinasupe@users.noreply.github.com>

Author: antejavor

memgraph-graphRAG/graphRAG.ipynb

@@ -100,7 +100,7 @@
    "source": [
     "## Enrich knowledge graph with the embeddings \n",
     "\n",
-    "Since in GraphRAG you are not writing actual Cypher queries, rather you are\n",
+    "In GraphRAG, you are not writing actual Cypher queries, but you are\n",
     "asking the questions about your domain knowledge graph in plain English. To\n",
     "retrieve relevant parts of the knowledge graph, you'll need a way to encode\n",
     "semantic meaning into the graph.  \n",
@@ -167,7 +167,7 @@
     "\n",
     "Asking the question `Who is Viserys Targaryen?` will yield a very similar\n",
     "embedding, allowing you to locate that node in the graph. However, if you ask a\n",
-    "longer question like, `To whom was Viserys Targaryen Loyal in seasone 1 of Game\n",
+    "longer question like, `To whom was Viserys Targaryen Loyal in season 1 of Game\n",
     "of Thrones?`, there is a chance that this question might not locate the `Viserys\n",
     "Targaryen` node in the graph due to its length and complexity. \n",
     "\n",
@@ -360,7 +360,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Running the graph RAG\n",
+    "## Running the graphRAG\n",
     "\n",
     "Now, it all comes together in the `main` function: \n",
     "\n",
@@ -379,7 +379,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "## Getting a Graph RAG answer \n",
+    "## Getting a GraphRAG answer \n",
     "\n",
     "def main():\n",
     "\n",
@@ -541,8 +541,8 @@
    "source": [
     "The goal of extracting entities from the text is to preprocess the data before\n",
     "sending it to the GPT model, ensuring more accurate and relevant results. By\n",
-    "using SpaCy, we can identify key entities such as characters, locations and\n",
-    "other entities for better understanding of the context of the text.\n",
+    "using SpaCy, we can identify key entities such as characters and locations\n",
+    "for a better understanding of the context of the text.\n",
     "\n",
     "This is particularly useful because SpaCy is specifically trained to recognize\n",
     "linguistic patterns and relationships in text, which helps to isolate and\n",
@@ -613,7 +613,7 @@
     "prompt, along with clear instructions on how to extract nodes and relationships\n",
     "from those entities. These instructions will guide the model in identifying key\n",
     "connections between the entities, which can then be used to build a knowledge\n",
-    "graph. In this example, we will be using a gpt-4 model. "
+    "graph. In this example, we will be using the GPT-4 model. "
    ]
   },
   {