Spaces:
Running
Running
File size: 3,746 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 |
{
"cells": [
{
"cell_type": "markdown",
"id": "683953b3",
"metadata": {},
"source": [
"# Zilliz\n",
"\n",
">[Zilliz Cloud](https://zilliz.com/doc/quick_start) is a fully managed service on cloud for `LF AI Milvus®`,\n",
"\n",
"This notebook shows how to use functionality related to the Zilliz Cloud managed vector database.\n",
"\n",
"To run, you should have a `Zilliz Cloud` instance up and running. Here are the [installation instructions](https://zilliz.com/cloud)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "c0c50102-e6ac-4475-a930-49c94ed0bd99",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"!pip install pymilvus"
]
},
{
"cell_type": "markdown",
"id": "4b25e246-ffe7-4822-a6bf-85d1a120df00",
"metadata": {},
"source": [
"We want to use `OpenAIEmbeddings` so we have to get the OpenAI API Key."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "d6691489-1ebc-40fa-bc09-b0916903a24d",
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"import getpass\n",
"\n",
"os.environ['OPENAI_API_KEY'] = getpass.getpass('OpenAI API Key:')"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "19a71422",
"metadata": {},
"outputs": [],
"source": [
"# replace \n",
"ZILLIZ_CLOUD_URI = \"\" # example: \"https://in01-17f69c292d4a5sa.aws-us-west-2.vectordb.zillizcloud.com:19536\"\n",
"ZILLIZ_CLOUD_USERNAME = \"\" # example: \"username\"\n",
"ZILLIZ_CLOUD_PASSWORD = \"\" # example: \"*********\""
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "aac9563e",
"metadata": {},
"outputs": [],
"source": [
"from langchain.embeddings.openai import OpenAIEmbeddings\n",
"from langchain.text_splitter import CharacterTextSplitter\n",
"from langchain.vectorstores import Milvus\n",
"from langchain.document_loaders import TextLoader"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a3c3999a",
"metadata": {},
"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": null,
"id": "dcf88bdf",
"metadata": {},
"outputs": [],
"source": [
"vector_db = Milvus.from_documents(\n",
" docs,\n",
" embeddings,\n",
" connection_args={\n",
" \"uri\": ZILLIZ_CLOUD_URI,\n",
" \"username\": ZILLIZ_CLOUD_USERNAME,\n",
" \"password\": ZILLIZ_CLOUD_PASSWORD,\n",
" \"secure\": True\n",
" }\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a8c513ab",
"metadata": {},
"outputs": [],
"source": [
"docs = vector_db.similarity_search(query)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "fc516993",
"metadata": {},
"outputs": [],
"source": [
"docs[0]"
]
}
],
"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": "3.9.6"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|