Merge pull request #406 from pinecone-io/quickstart-tweak

Quickstart notebook tweaks to align with docs quickstart

Author: jseldess

docs/pinecone-quickstart.ipynb

@@ -56,25 +56,25 @@
       "cell_type": "code",
       "execution_count": 2,
       "metadata": {
-        "id": "89S8G8oP61-t",
         "colab": {
           "base_uri": "https://localhost:8080/",
           "height": 247
         },
+        "id": "89S8G8oP61-t",
         "outputId": "8cf57515-28e1-4953-b86d-d23dad4ea9fe"
       },
       "outputs": [
         {
-          "output_type": "display_data",
           "data": {
-            "text/plain": [
-              "<IPython.core.display.HTML object>"
-            ],
             "text/html": [
               "<script type=\"text/javascript\" src=\"https://connect.pinecone.io/embed.js\"></script>"
+            ],
+            "text/plain": [
+              "<IPython.core.display.HTML object>"
             ]
           },
-          "metadata": {}
+          "metadata": {},
+          "output_type": "display_data"
         }
       ],
       "source": [
@@ -87,14 +87,14 @@
     },
     {
       "cell_type": "markdown",
+      "metadata": {
+        "id": "sbJFp5DO5ryT"
+      },
       "source": [
         "## Initialize a client\n",
         "\n",
         "Use the generated API key to intialize a client connection to Pinecone:"
-      ],
-      "metadata": {
-        "id": "sbJFp5DO5ryT"
-      }
+      ]
     },
     {
       "cell_type": "code",
@@ -113,19 +113,24 @@
     },
     {
       "cell_type": "markdown",
+      "metadata": {
+        "id": "bN9Rl7GP258C"
+      },
       "source": [
         "## Generate vectors\n",
         "\n",
         "A [vector embedding](https://www.pinecone.io/learn/vector-embeddings/) is a numerical representation of data that enables similarity-based search in vector databases like Pinecone. To convert data into this format, you use an embedding model.\n",
         "\n",
-        "For this quickstart, use the [`multilingual-e5-large`](https://docs.pinecone.io/models/multilingual-e5-large) embedding model hosted by Pinecone to [convert](https://docs.pinecone.io/guides/inference/generate-embeddings) four sentences about apples into vectors, three concerning their health benefits, one concerning their cultivation."
-      ],
-      "metadata": {
-        "id": "bN9Rl7GP258C"
-      }
+        "For this quickstart, use the [`multilingual-e5-large`](https://docs.pinecone.io/models/multilingual-e5-large) embedding model hosted by Pinecone to [convert](https://docs.pinecone.io/guides/inference/generate-embeddings) four sentences about apples into vectors, three related to health, one related to cultivation."
+      ]
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "ZIclo2UK3NFE"
+      },
+      "outputs": [],
       "source": [
         "# Define a sample dataset where each item has a unique ID, text, and category\n",
         "data = [\n",
@@ -162,12 +167,7 @@
         ")\n",
         "\n",
         "print(embeddings)"
-      ],
-      "metadata": {
-        "id": "ZIclo2UK3NFE"
-      },
-      "execution_count": null,
-      "outputs": []
+      ]
     },
     {
       "cell_type": "markdown",
@@ -307,7 +307,7 @@
       "source": [
         "## Search the index\n",
         "\n",
-        "Now, let’s say you want to search your index for information about “Disease prevention”.\n",
+        "Now, let’s say you want to search your index for information related to \"health risks\".\n",
         "\n",
         "Use the the `multilingual-e5-large` model hosted by Pinecone *to* convert your query into a vector embedding, and then use the [`query`](https://docs.pinecone.io/guides/data/query-data) operation to search for the three vectors in the index that are most semantically similar to the query vector:"
       ]
@@ -321,7 +321,7 @@
       "outputs": [],
       "source": [
         "# Define your query\n",
-        "query = \"Disease prevention\"\n",
+        "query = \"Health risks\"\n",
         "\n",
         "# Convert the query into a numerical vector that Pinecone can search with\n",
         "query_embedding = pc.inference.embed(\n",
@@ -350,24 +350,29 @@
         "id": "9jAJDjSAjsvA"
       },
       "source": [
-        "Notice that the response includes only records about the health benefits of apples, not the cultivation of apple."
+        "Notice that the response includes only records related to health, not the cultivation of apple."
       ]
     },
     {
       "cell_type": "markdown",
+      "metadata": {
+        "id": "ayZib8aEUYR_"
+      },
       "source": [
         "## Add reranking\n",
         "\n",
         "You can increase the accuracy of your search by reranking results based on their relevance to the query.\n",
         "\n",
-        "Use the `rerank` operation and the `bge-reranker-v2-m3` reranking model hosted by Pinecone to rerank the values of the documents.source_text fields and return only the two most relevant documents:"
-      ],
-      "metadata": {
-        "id": "ayZib8aEUYR_"
-      }
+        "Use the `rerank` operation and the `bge-reranker-v2-m3` reranking model hosted by Pinecone to rerank the values of the documents.source_text fields:"
+      ]
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "SyPG_OmwUjtm"
+      },
+      "outputs": [],
       "source": [
         "# Rerank the search results based on their relevance to the query\n",
         "ranked_results = pc.inference.rerank(\n",
@@ -378,7 +383,7 @@
         "        {\"id\": \"rec1\", \"source_text\": \"Apples are a great source of dietary fiber, which supports digestion and helps maintain a healthy gut.\"},\n",
         "        {\"id\": \"rec4\", \"source_text\": \"The high fiber content in apples can also help regulate blood sugar levels, making them a favorable snack for people with diabetes.\"}\n",
         "    ],\n",
-        "    top_n=2,\n",
+        "    top_n=3,\n",
         "    rank_fields=[\"source_text\"],\n",
         "    return_documents=True,\n",
         "    parameters={\n",
@@ -387,37 +392,37 @@
         ")\n",
         "\n",
         "print(ranked_results)\n"
-      ],
-      "metadata": {
-        "id": "SyPG_OmwUjtm"
-      },
-      "execution_count": null,
-      "outputs": []
+      ]
     },
     {
       "cell_type": "markdown",
-      "source": [
-        "Notice that the two returned records are the most relevant for the query, the first relating to reducing chronic diseases, the second relating to preventing diabetes."
-      ],
       "metadata": {
         "id": "QTkhBFJHUnj0"
-      }
+      },
+      "source": [
+        "Notice that the two records specifically related to \"health risks\" (chronic disease and diabetes) are now ranked highest."
+      ]
     },
     {
       "cell_type": "markdown",
+      "metadata": {
+        "id": "nGjpffT5UrrL"
+      },
       "source": [
         "## Add filtering\n",
         "\n",
         "You can use a [metadata filter](https://docs.pinecone.io/guides/data/understanding-metadata) to limit your search to records matching a filter expression.\n",
         "\n",
         "Your upserted records contain a `category` metadata field. Now use that field as a filter to search for records in the “digestive system” category:"
-      ],
-      "metadata": {
-        "id": "nGjpffT5UrrL"
-      }
+      ]
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "KkH7Wre3Ux5B"
+      },
+      "outputs": [],
       "source": [
         "# Search the index with a metadata filter\n",
         "filtered_results = index.query(\n",
@@ -432,21 +437,16 @@
         ")\n",
         "\n",
         "print(filtered_results)"
-      ],
-      "metadata": {
-        "id": "KkH7Wre3Ux5B"
-      },
-      "execution_count": null,
-      "outputs": []
+      ]
     },
     {
       "cell_type": "markdown",
-      "source": [
-        "Notice that the response includes only the one record in the “digestive system” category."
-      ],
       "metadata": {
         "id": "awumy10tU2Lv"
-      }
+      },
+      "source": [
+        "Notice that the response includes only the one record in the “digestive system” category."
+      ]
     },
     {
       "cell_type": "markdown",
@@ -494,4 +494,4 @@
   },
   "nbformat": 4,
   "nbformat_minor": 0
-}
+}