From dd95f4215df0790d42b45e4c3d5d6feea4807a00 Mon Sep 17 00:00:00 2001
From: Hoang Viet Khoa <khoahv92@gmail.com>
Date: Thu, 28 Sep 2023 05:32:04 +0900
Subject: [PATCH] [web-q-and-a] remove unnecessary cell (#309)

---
 apps/web-crawl-q-and-a/web-qa.ipynb | 96 -----------------------------
 1 file changed, 96 deletions(-)

diff --git a/apps/web-crawl-q-and-a/web-qa.ipynb b/apps/web-crawl-q-and-a/web-qa.ipynb
index 87c530de..f7f969df 100644
--- a/apps/web-crawl-q-and-a/web-qa.ipynb
+++ b/apps/web-crawl-q-and-a/web-qa.ipynb
@@ -932,102 +932,6 @@
     "df.head()"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": 30,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>text</th>\n",
-       "      <th>n_tokens</th>\n",
-       "      <th>embeddings</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>blog authors maddie.   Maddie Hall - OpenAI   ...</td>\n",
-       "      <td>175</td>\n",
-       "      <td>[-0.012958061881363392, -0.006103983614593744,...</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1</th>\n",
-       "      <td>blog authors tom.   Tom Brown - OpenAI        ...</td>\n",
-       "      <td>228</td>\n",
-       "      <td>[-0.0053874170407652855, -0.009962032549083233...</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2</th>\n",
-       "      <td>blog openai scholars 2019 final projects.   Op...</td>\n",
-       "      <td>492</td>\n",
-       "      <td>[0.0019150723237544298, -0.0070442273281514645...</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3</th>\n",
-       "      <td>In this project, I used curiosity-driven explo...</td>\n",
-       "      <td>478</td>\n",
-       "      <td>[-0.0067560747265815735, 0.0004431474662851542...</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4</th>\n",
-       "      <td>Results revealed that the optimal RL policies ...</td>\n",
-       "      <td>499</td>\n",
-       "      <td>[-0.012868616729974747, 0.0029640409629791975,...</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "                                                text  n_tokens  \\\n",
-       "0  blog authors maddie.   Maddie Hall - OpenAI   ...       175   \n",
-       "1  blog authors tom.   Tom Brown - OpenAI        ...       228   \n",
-       "2  blog openai scholars 2019 final projects.   Op...       492   \n",
-       "3  In this project, I used curiosity-driven explo...       478   \n",
-       "4  Results revealed that the optimal RL policies ...       499   \n",
-       "\n",
-       "                                          embeddings  \n",
-       "0  [-0.012958061881363392, -0.006103983614593744,...  \n",
-       "1  [-0.0053874170407652855, -0.009962032549083233...  \n",
-       "2  [0.0019150723237544298, -0.0070442273281514645...  \n",
-       "3  [-0.0067560747265815735, 0.0004431474662851542...  \n",
-       "4  [-0.012868616729974747, 0.0029640409629791975,...  "
-      ]
-     },
-     "execution_count": 30,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from openai.embeddings_utils import distances_from_embeddings\n",
-    "\n",
-    "df['embeddings'] = df.text.apply(lambda x: openai.Embedding.create(input=x, engine='text-embedding-ada-002')['data'][0]['embedding'])\n",
-    "\n",
-    "df.to_csv('processed/embeddings.csv')\n",
-    "df.head()"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": 31,