Spaces:
Runtime error
Runtime error
File size: 13,060 Bytes
0685af6 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 |
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# ETL to get the text data from the playlist\n",
"\n",
"This notebook shows the process of building the corpus of transcripts from the YouTube playlist.\n",
"\n",
"**Extract**: Pull data (transcripts) from each video. \n",
"**Transform**: \n",
"**Load**: Load data into our database where it will be retrieved from. "
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"from models import etl\n",
"import json"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"First we load the video information. This includes the video IDs and titles."
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"with open('data/single_video.json') as f:\n",
" video_info = json.load(f)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Then we must extract the transcripts using the YouTube Transcript API. This is done over all of the videos. \n",
"This produces a list of video segments with timestamps. \n",
"Next, we format the transcript by adding metadata so that the segments are easily identified for retreival later. \n",
"Since the original segments are small, they are batched with overlap to preserve semantic meaning."
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"get_video_transcript took 0.84 seconds.\n",
"Transcript for video 5sLYAQS9sWQ fetched.\n"
]
}
],
"source": [
"videos = []\n",
"for video in video_info:\n",
" video_id = video[\"id\"]\n",
" video_title = video[\"title\"]\n",
" transcript = etl.get_video_transcript(video_id)\n",
" print(f\"Transcript for video {video_id} fetched.\")\n",
" if transcript:\n",
" formatted_transcript = etl.format_transcript(transcript, video_id, video_title, batch_size=5, overlap=2)\n",
" \n",
" videos.extend(formatted_transcript)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"The last step is to load the data into a database. We will use a Chromadb database. \n",
"The embedding function is the ____ model from HuggingFace."
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Database created at data/single_video.db\n"
]
}
],
"source": [
"# Initialize the database\n",
"from utils.embedding_utils import MyEmbeddingFunction\n",
"import chromadb\n",
"\n",
"embed_text = MyEmbeddingFunction()\n",
"\n",
"db_path = \"data/single_video.db\"\n",
"client = chromadb.PersistentClient(path=db_path)\n",
"\n",
"client.create_collection(\n",
" name=\"huberman_videos\",\n",
" embedding_function=embed_text,\n",
" metadata={\"hnsw:space\": \"cosine\"}\n",
")\n",
"\n",
"print(f\"Database created at {db_path}\")"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Data loaded to database at data/single_video.db.\n"
]
}
],
"source": [
"# Add the data to the database\n",
"client = chromadb.PersistentClient(path=db_path)\n",
" \n",
"collection = client.get_collection(\"huberman_videos\")\n",
"\n",
"documents = [segment['text'] for segment in videos]\n",
"metadata = [segment['metadata'] for segment in videos]\n",
"ids = [segment['metadata']['segment_id'] for segment in videos]\n",
"\n",
"collection.add(\n",
" documents=documents,\n",
" metadatas=metadata,\n",
" ids=ids\n",
")\n",
"\n",
"print(f\"Data loaded to database at {db_path}.\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Here is some of the data:"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Number of segments: 26\n"
]
},
{
"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>ids</th>\n",
" <th>embeddings</th>\n",
" <th>metadatas</th>\n",
" <th>documents</th>\n",
" <th>uris</th>\n",
" <th>data</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>5sLYAQS9sWQ__0</td>\n",
" <td>[-0.11489544063806534, -0.03262839838862419, -...</td>\n",
" <td>{'segment_id': '5sLYAQS9sWQ__0', 'source': 'ht...</td>\n",
" <td>GPT, or Generative Pre-trained Transformer, is...</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>5sLYAQS9sWQ__12</td>\n",
" <td>[0.094169981777668, -0.10430295020341873, 0.02...</td>\n",
" <td>{'segment_id': '5sLYAQS9sWQ__12', 'source': 'h...</td>\n",
" <td>Now foundation models are pre-trained on large...</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>5sLYAQS9sWQ__15</td>\n",
" <td>[0.042587604373693466, -0.061460819095373154, ...</td>\n",
" <td>{'segment_id': '5sLYAQS9sWQ__15', 'source': 'h...</td>\n",
" <td>I'm talking about things like code. Now, large...</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>5sLYAQS9sWQ__18</td>\n",
" <td>[-0.0245895367115736, -0.058405470103025436, -...</td>\n",
" <td>{'segment_id': '5sLYAQS9sWQ__18', 'source': 'h...</td>\n",
" <td>these models can be tens of gigabytes in size ...</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>5sLYAQS9sWQ__21</td>\n",
" <td>[0.05348338559269905, -0.016104578971862793, -...</td>\n",
" <td>{'segment_id': '5sLYAQS9sWQ__21', 'source': 'h...</td>\n",
" <td>So to put that into perspective, a text file t...</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>5sLYAQS9sWQ__24</td>\n",
" <td>[0.07004527002573013, -0.08996045589447021, -0...</td>\n",
" <td>{'segment_id': '5sLYAQS9sWQ__24', 'source': 'h...</td>\n",
" <td>A lot of words just in one Gb. And how many gi...</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>5sLYAQS9sWQ__27</td>\n",
" <td>[0.0283487681299448, -0.11020224541425705, -0....</td>\n",
" <td>{'segment_id': '5sLYAQS9sWQ__27', 'source': 'h...</td>\n",
" <td>Yeah, that's truly a lot of text. And LLMs are...</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>5sLYAQS9sWQ__3</td>\n",
" <td>[-0.0700172707438469, -0.061202701181173325, -...</td>\n",
" <td>{'segment_id': '5sLYAQS9sWQ__3', 'source': 'ht...</td>\n",
" <td>And I've been using GPT in its various forms f...</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>5sLYAQS9sWQ__30</td>\n",
" <td>[-0.04904637485742569, -0.1277533322572708, -0...</td>\n",
" <td>{'segment_id': '5sLYAQS9sWQ__30', 'source': 'h...</td>\n",
" <td>and the more parameters a model has, the more ...</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>5sLYAQS9sWQ__33</td>\n",
" <td>[0.03286760300397873, -0.041724931448698044, 0...</td>\n",
" <td>{'segment_id': '5sLYAQS9sWQ__33', 'source': 'h...</td>\n",
" <td>All right, so how do they work? Well, we can t...</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" ids embeddings \\\n",
"0 5sLYAQS9sWQ__0 [-0.11489544063806534, -0.03262839838862419, -... \n",
"1 5sLYAQS9sWQ__12 [0.094169981777668, -0.10430295020341873, 0.02... \n",
"2 5sLYAQS9sWQ__15 [0.042587604373693466, -0.061460819095373154, ... \n",
"3 5sLYAQS9sWQ__18 [-0.0245895367115736, -0.058405470103025436, -... \n",
"4 5sLYAQS9sWQ__21 [0.05348338559269905, -0.016104578971862793, -... \n",
"5 5sLYAQS9sWQ__24 [0.07004527002573013, -0.08996045589447021, -0... \n",
"6 5sLYAQS9sWQ__27 [0.0283487681299448, -0.11020224541425705, -0.... \n",
"7 5sLYAQS9sWQ__3 [-0.0700172707438469, -0.061202701181173325, -... \n",
"8 5sLYAQS9sWQ__30 [-0.04904637485742569, -0.1277533322572708, -0... \n",
"9 5sLYAQS9sWQ__33 [0.03286760300397873, -0.041724931448698044, 0... \n",
"\n",
" metadatas \\\n",
"0 {'segment_id': '5sLYAQS9sWQ__0', 'source': 'ht... \n",
"1 {'segment_id': '5sLYAQS9sWQ__12', 'source': 'h... \n",
"2 {'segment_id': '5sLYAQS9sWQ__15', 'source': 'h... \n",
"3 {'segment_id': '5sLYAQS9sWQ__18', 'source': 'h... \n",
"4 {'segment_id': '5sLYAQS9sWQ__21', 'source': 'h... \n",
"5 {'segment_id': '5sLYAQS9sWQ__24', 'source': 'h... \n",
"6 {'segment_id': '5sLYAQS9sWQ__27', 'source': 'h... \n",
"7 {'segment_id': '5sLYAQS9sWQ__3', 'source': 'ht... \n",
"8 {'segment_id': '5sLYAQS9sWQ__30', 'source': 'h... \n",
"9 {'segment_id': '5sLYAQS9sWQ__33', 'source': 'h... \n",
"\n",
" documents uris data \n",
"0 GPT, or Generative Pre-trained Transformer, is... None None \n",
"1 Now foundation models are pre-trained on large... None None \n",
"2 I'm talking about things like code. Now, large... None None \n",
"3 these models can be tens of gigabytes in size ... None None \n",
"4 So to put that into perspective, a text file t... None None \n",
"5 A lot of words just in one Gb. And how many gi... None None \n",
"6 Yeah, that's truly a lot of text. And LLMs are... None None \n",
"7 And I've been using GPT in its various forms f... None None \n",
"8 and the more parameters a model has, the more ... None None \n",
"9 All right, so how do they work? Well, we can t... None None "
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import pandas as pd\n",
"\n",
"client = chromadb.PersistentClient('data/single_video.db')\n",
"collection= client.get_collection('huberman_videos')\n",
"\n",
"num_segments = collection.count()\n",
"sample_data = collection.peek()\n",
"\n",
"transcript_df = pd.DataFrame(sample_data)\n",
"\n",
"print(f\"Number of segments: {num_segments}\")\n",
"transcript_df"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.1"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|