PR comments

Author: Amnah199

notebooks/feedback-analysis-agent-with-AzureAISearch.ipynb

@@ -38,7 +38,7 @@
    "metadata": {},
    "source": [
     "## Loading and Preparing the Dataset\n",
-    "We will use an open source dataset consisting of approx. 28000 customer reviews for a clothing store. The dataset is available at [Shopper Sentiments](https://www.kaggle.com/datasets/nelgiriyewithana/shoppersentiments).\n",
+    "We will use an open dataset consisting of approx. 28000 customer reviews for a clothing store. The dataset is available at [Shopper Sentiments](https://www.kaggle.com/datasets/nelgiriyewithana/shoppersentiments).\n",
     "\n",
     "We will load the dataset and convert it into a JSON format that can be used by Haystack.\n"
    ]
@@ -122,7 +122,7 @@
    "source": [
     "## Setting up Azure AI Search and Indexing Pipeline\n",
     "\n",
-    "We set up indexing pipeline with `AzureAISearchDocumentStore` by following these steps:\n",
+    "We set up an indexing pipeline with `AzureAISearchDocumentStore` by following these steps:\n",
     "1. Configure semantic search for the index\n",
     "2. Initialize the document store with custom metadata fields and semantic search configuration\n",
     "3. Create an indexing pipeline that:\n",
@@ -187,7 +187,7 @@
     "\n",
     "# Indexing Pipeline\n",
     "indexing_pipeline = Pipeline()\n",
-    "indexing_pipeline.add_component(\"document_embedder\", AzureOpenAIDocumentEmbedder())\n",
+    "indexing_pipeline.add_component(AzureOpenAIDocumentEmbedder(), name=\"document_embedder\")\n",
     "indexing_pipeline.add_component(instance=DocumentWriter(document_store=document_store), name=\"doc_writer\")\n",
     "indexing_pipeline.connect(\"document_embedder\", \"doc_writer\")\n",
     "\n",
@@ -202,7 +202,7 @@
     "\n",
     "Here we set up the query pipeline that will retrieve relevant reviews based on user queries. The pipeline consists of:\n",
     "\n",
-    "1. A text embedder (`AzureOpenAITextEmbedder`) that converts user queries into vector embeddings\n",
+    "1. A text embedder (`AzureOpenAITextEmbedder`) that converts user queries into embeddings.\n",
     "2. A hybrid retriever (`AzureAISearchHybridRetriever`) that uses vector and semantic search to retrieve the most relevant reviews.\n"
    ]
   },
@@ -303,11 +303,11 @@
     "import numpy as np\n",
     "\n",
     "\n",
-    "def plot_sentiment_distribution(topics):\n",
-    "    # Create DataFrame from topics data\n",
+    "def plot_sentiment_distribution(aspects):\n",
+    "    # Create DataFrame from aspects data\n",
     "    data = [(topic, review['sentiment']['analyzer_rating'], \n",
     "             review['review']['rating'], review['sentiment']['label'])\n",
-    "            for topic, reviews in topics.items()\n",
+    "            for topic, reviews in aspects.items()\n",
     "            for review in reviews]\n",
     "    \n",
     "    df = pd.DataFrame(data, columns=['Topic', 'Normalized Score', 'Original Rating', 'Sentiment'])\n",
@@ -367,8 +367,8 @@
     "\n",
     "Create a tool to perform aspect-based sentiment analysis on customer reviews using the VADER sentiment analyzer. It involves:\n",
     "\n",
-    "- Identifying specific topics within reviews (e.g., product quality, shipping, customer service, pricing) using predefined keywords\n",
-    "- Calculating sentiment scores for each review mentioning these topics\n",
+    "- Identifying specific aspects within reviews (e.g., product quality, shipping, customer service, pricing) using predefined keywords\n",
+    "- Calculating sentiment scores for each review mentioning these aspects\n",
     "- Categorizing sentiment as 'positive', 'negative', or 'neutral' \n",
     "- Normalizing sentiment scores to a scale of 1 to 5 for comparison with customer ratings\n"
    ]
@@ -394,7 +394,7 @@
     "    sentiment scores using VADER and categorizes the sentiment as 'positive', 'negative', or 'neutral'.\n",
     "    \n",
     "    \"\"\"\n",
-    "    topics = {\n",
+    "    aspects = {\n",
     "        \"product_quality\": [],\n",
     "        \"shipping\": [],\n",
     "        \"customer_service\": [],\n",
@@ -432,18 +432,18 @@
     "                    sentiment_label = 'neutral'\n",
     "                \n",
     "                # Append the review along with its sentiment analysis result\n",
-    "                topics[topic].append({\n",
+    "                aspects[topic].append({\n",
     "                    \"review\": review,\n",
     "                    \"sentiment\": {\n",
     "                        \"analyzer_rating\": normalized_score,\n",
     "                        \"label\": sentiment_label\n",
     "                    }\n",
     "                })\n",
-    "    plot_sentiment_distribution(topics)\n",
+    "    plot_sentiment_distribution(aspects)\n",
     "\n",
     "    return {\n",
     "        \"total_reviews\": len(reviews),\n",
-    "        \"sentiment_analysis\": topics,\n",
+    "        \"sentiment_analysis\": aspects,\n",
     "        \"average_rating\": sum(r.get(\"rating\", 3) for r in reviews) / len(reviews)\n",
     "    }\n",
     "\n",