Spaces:
Sleeping
Sleeping
File size: 8,796 Bytes
cfd3735 |
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 |
{
"cells": [
{
"cell_type": "markdown",
"id": "683953b3",
"metadata": {},
"source": [
"# MyScale\n",
"\n",
">[MyScale](https://docs.myscale.com/en/overview/) is a cloud-based database optimized for AI applications and solutions, built on the open-source [ClickHouse](https://github.com/ClickHouse/ClickHouse). \n",
"\n",
"This notebook shows how to use functionality related to the `MyScale` vector database."
]
},
{
"cell_type": "markdown",
"id": "43ead5d5-2c1f-4dce-a69a-cb00e4f9d6f0",
"metadata": {},
"source": [
"## Setting up envrionments"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "7dccc580-8270-4714-ad61-f79783dd6eea",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"!pip install clickhouse-connect"
]
},
{
"cell_type": "markdown",
"id": "15a1d477-9cdb-4d82-b019-96951ecb2b72",
"metadata": {},
"source": [
"We want to use OpenAIEmbeddings so we have to get the OpenAI API Key."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "91003ea5-0c8c-436c-a5de-aaeaeef2f458",
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"import getpass\n",
"\n",
"os.environ['OPENAI_API_KEY'] = getpass.getpass('OpenAI API Key:')"
]
},
{
"cell_type": "markdown",
"id": "a9d16fa3",
"metadata": {},
"source": [
"There are two ways to set up parameters for myscale index.\n",
"\n",
"1. Environment Variables\n",
"\n",
" Before you run the app, please set the environment variable with `export`:\n",
" `export MYSCALE_URL='<your-endpoints-url>' MYSCALE_PORT=<your-endpoints-port> MYSCALE_USERNAME=<your-username> MYSCALE_PASSWORD=<your-password> ...`\n",
"\n",
" You can easily find your account, password and other info on our SaaS. For details please refer to [this document](https://docs.myscale.com/en/cluster-management/)\n",
"\n",
" Every attributes under `MyScaleSettings` can be set with prefix `MYSCALE_` and is case insensitive.\n",
"\n",
"2. Create `MyScaleSettings` object with parameters\n",
"\n",
"\n",
" ```python\n",
" from langchain.vectorstores import MyScale, MyScaleSettings\n",
" config = MyScaleSetting(host=\"<your-backend-url>\", port=8443, ...)\n",
" index = MyScale(embedding_function, config)\n",
" index.add_documents(...)\n",
" ```"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "aac9563e",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"from langchain.embeddings.openai import OpenAIEmbeddings\n",
"from langchain.text_splitter import CharacterTextSplitter\n",
"from langchain.vectorstores import MyScale\n",
"from langchain.document_loaders import TextLoader"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a3c3999a",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"from langchain.document_loaders import TextLoader\n",
"loader = TextLoader('../../../state_of_the_union.txt')\n",
"documents = loader.load()\n",
"text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
"docs = text_splitter.split_documents(documents)\n",
"\n",
"embeddings = OpenAIEmbeddings()"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "6e104aee",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Inserting data...: 100%|██████████| 42/42 [00:18<00:00, 2.21it/s]\n"
]
}
],
"source": [
"for d in docs:\n",
" d.metadata = {'some': 'metadata'}\n",
"docsearch = MyScale.from_documents(docs, embeddings)\n",
"\n",
"query = \"What did the president say about Ketanji Brown Jackson\"\n",
"docs = docsearch.similarity_search(query)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "9c608226",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"As Frances Haugen, who is here with us tonight, has shown, we must hold social media platforms accountable for the national experiment they’re conducting on our children for profit. \n",
"\n",
"It’s time to strengthen privacy protections, ban targeted advertising to children, demand tech companies stop collecting personal data on our children. \n",
"\n",
"And let’s get all Americans the mental health services they need. More people they can turn to for help, and full parity between physical and mental health care. \n",
"\n",
"Third, support our veterans. \n",
"\n",
"Veterans are the best of us. \n",
"\n",
"I’ve always believed that we have a sacred obligation to equip all those we send to war and care for them and their families when they come home. \n",
"\n",
"My administration is providing assistance with job training and housing, and now helping lower-income veterans get VA care debt-free. \n",
"\n",
"Our troops in Iraq and Afghanistan faced many dangers.\n"
]
}
],
"source": [
"print(docs[0].page_content)"
]
},
{
"cell_type": "markdown",
"id": "e3a8b105",
"metadata": {},
"source": [
"## Get connection info and data schema"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "69996818",
"metadata": {},
"outputs": [],
"source": [
"print(str(docsearch))"
]
},
{
"cell_type": "markdown",
"id": "f59360c0",
"metadata": {},
"source": [
"## Filtering\n",
"\n",
"You can have direct access to myscale SQL where statement. You can write `WHERE` clause following standard SQL.\n",
"\n",
"**NOTE**: Please be aware of SQL injection, this interface must not be directly called by end-user.\n",
"\n",
"If you custimized your `column_map` under your setting, you search with filter like this:"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "232055f6",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Inserting data...: 100%|██████████| 42/42 [00:15<00:00, 2.69it/s]\n"
]
}
],
"source": [
"from langchain.vectorstores import MyScale, MyScaleSettings\n",
"from langchain.document_loaders import TextLoader\n",
"\n",
"loader = TextLoader('../../../state_of_the_union.txt')\n",
"documents = loader.load()\n",
"text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
"docs = text_splitter.split_documents(documents)\n",
"\n",
"embeddings = OpenAIEmbeddings()\n",
"\n",
"for i, d in enumerate(docs):\n",
" d.metadata = {'doc_id': i}\n",
"\n",
"docsearch = MyScale.from_documents(docs, embeddings)"
]
},
{
"cell_type": "code",
"execution_count": 16,
"id": "ddbcee77",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"0.252379834651947 {'doc_id': 6, 'some': ''} And I’m taking robus...\n",
"0.25022566318511963 {'doc_id': 1, 'some': ''} Groups of citizens b...\n",
"0.2469480037689209 {'doc_id': 8, 'some': ''} And so many families...\n",
"0.2428302764892578 {'doc_id': 0, 'some': 'metadata'} As Frances Haugen, w...\n"
]
}
],
"source": [
"meta = docsearch.metadata_column\n",
"output = docsearch.similarity_search_with_relevance_scores('What did the president say about Ketanji Brown Jackson?', \n",
" k=4, where_str=f\"{meta}.doc_id<10\")\n",
"for d, dist in output:\n",
" print(dist, d.metadata, d.page_content[:20] + '...')"
]
},
{
"cell_type": "markdown",
"id": "a359ed74",
"metadata": {},
"source": [
"## Deleting your data"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "fb6a9d36",
"metadata": {},
"outputs": [],
"source": [
"docsearch.drop()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "48dbd8e0",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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": "3.10.6"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|