Spaces:
Runtime error
Runtime error
File size: 8,501 Bytes
a7d2416 |
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 |
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Save Markdown text into Vector DB"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Step-1: Config"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"from my_config import MY_CONFIG"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Step-2: Read Markdown"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"import glob\n",
"\n",
"pattern = os.path.join(MY_CONFIG.PROCESSED_DATA_DIR, '*.md')\n",
"md_file_count = len(glob.glob(pattern, recursive=True)) "
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Loaded 96 documents from 96 files\n"
]
}
],
"source": [
"from llama_index.core import SimpleDirectoryReader\n",
"\n",
"reader = SimpleDirectoryReader(input_dir=MY_CONFIG.PROCESSED_DATA_DIR, recursive=False , required_exts=[\".md\"])\n",
"documents = reader.load_data()\n",
"\n",
"print (f\"Loaded {len(documents)} documents from {md_file_count} files\")\n"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Doc ID: 20eef2cd-ee21-4dd4-baf6-eda09d5d793b\n",
"Text: # Building the open future of AI We are technology developers,\n",
"researchers, industry leaders and advocates who collaborate to advance\n",
"safe, responsible AI rooted in open innovation. ![Conference\n",
"Speaker](https://images.prismic.io/ai-alliance/Zy08cq8jQArT0jJI_Imagef\n",
"romNotion.jpeg?auto=format%2Ccompress&fit=max&w=3840) ![Skills &\n",
"Education](htt...\n"
]
}
],
"source": [
"## Inspect a sample doc\n",
"print (documents[0])"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Step-3: Create Chunks"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Created 223 chunks from 96 documents\n"
]
}
],
"source": [
"from llama_index.core import Document\n",
"from llama_index.core.node_parser import SentenceSplitter\n",
"\n",
"parser = SentenceSplitter(chunk_size=MY_CONFIG.CHUNK_SIZE, chunk_overlap=MY_CONFIG.CHUNK_OVERLAP)\n",
"nodes = parser.get_nodes_from_documents(documents)\n",
"print(f\"Created {len(nodes)} chunks from {len(documents)} documents\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Step-4: Setup Embedding Model"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"# If connection to https://huggingface.co/ failed, uncomment the following path\n",
"import os\n",
"os.environ['HF_ENDPOINT'] = 'https://hf-mirror.com'"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/sujee/apps/anaconda3/envs/allycat-6/lib/python3.11/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
" from .autonotebook import tqdm as notebook_tqdm\n"
]
}
],
"source": [
"from llama_index.embeddings.huggingface import HuggingFaceEmbedding\n",
"from llama_index.core import Settings\n",
"\n",
"Settings.embed_model = HuggingFaceEmbedding(\n",
" model_name = MY_CONFIG.EMBEDDING_MODEL\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Step-5: Connect to Milvus"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"✅ Connected to Milvus instance: workspace/rag_website_milvus.db\n"
]
}
],
"source": [
"## Clear up any old data\n",
"\n",
"from pymilvus import MilvusClient\n",
"\n",
"milvus_client = MilvusClient(MY_CONFIG.DB_URI)\n",
"print (\"✅ Connected to Milvus instance: \", MY_CONFIG.DB_URI )\n",
"\n",
"# if we already have a collection, clear it first\n",
"if milvus_client.has_collection(collection_name = MY_CONFIG.COLLECTION_NAME):\n",
" milvus_client.drop_collection(collection_name = MY_CONFIG.COLLECTION_NAME)\n",
" print ('✅ Cleared collection :', MY_CONFIG.COLLECTION_NAME)\n",
" "
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"2025-05-12 23:36:12,218 [DEBUG][_create_connection]: Created new connection using: f81ea0e5320b44f7b5ba8b89f6aa43f7 (async_milvus_client.py:600)\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"✅ Connected Llama-index to Milvus instance: workspace/rag_website_milvus.db\n"
]
}
],
"source": [
"# connect llama-index to vector db\n",
"\n",
"from llama_index.core import StorageContext\n",
"from llama_index.vector_stores.milvus import MilvusVectorStore\n",
"\n",
"vector_store = MilvusVectorStore(\n",
" uri = MY_CONFIG.DB_URI ,\n",
" dim = MY_CONFIG.EMBEDDING_LENGTH , \n",
" collection_name = MY_CONFIG.COLLECTION_NAME,\n",
" overwrite=True\n",
")\n",
"storage_context = StorageContext.from_defaults(vector_store=vector_store)\n",
"\n",
"print (\"✅ Connected Llama-index to Milvus instance: \", MY_CONFIG.DB_URI )"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Step-6: Save to DB"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"CPU times: user 9 μs, sys: 0 ns, total: 9 μs\n",
"Wall time: 18.8 μs\n"
]
}
],
"source": [
"%%time\n",
"\n",
"## We save entire md documents into vector store\n",
"\n",
"# from llama_index.core import VectorStoreIndex\n",
"\n",
"# index = VectorStoreIndex.from_documents(\n",
"# documents, storage_context=storage_context\n",
"# )\n",
"# print (f\"✅ Saved {len(documents)} documents to db: {MY_CONFIG.DB_URI}\" )"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Successfully stored 223 chunks in Milvus collection 'pages'\n",
"CPU times: user 900 ms, sys: 142 ms, total: 1.04 s\n",
"Wall time: 807 ms\n"
]
}
],
"source": [
"%%time \n",
"\n",
"# save chunks into vector db\n",
"\n",
"from llama_index.core import VectorStoreIndex\n",
"\n",
"index = VectorStoreIndex(\n",
" nodes=nodes,\n",
" storage_context=storage_context,\n",
" )\n",
"\n",
"print(f\"Successfully stored {len(nodes)} chunks in Milvus collection '{MY_CONFIG.COLLECTION_NAME}'\")\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"milvus_client.close()"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "allycat-6",
"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": "3.11.11"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|