mirror of
https://github.com/hwchase17/langchain
synced 2024-10-29 17:07:25 +00:00
113 lines
2.6 KiB
Plaintext
113 lines
2.6 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "683953b3",
|
|
"metadata": {},
|
|
"source": [
|
|
"# Zilliz\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: https://zilliz.com/cloud"
|
|
]
|
|
},
|
|
{
|
|
"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": "19a71422",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# replace \n",
|
|
"ZILLIZ_CLOUD_HOSTNAME = \"\" # example: \"in01-17f69c292d4a50a.aws-us-west-2.vectordb.zillizcloud.com\"\n",
|
|
"ZILLIZ_CLOUD_PORT = \"\" #example: \"19532\""
|
|
]
|
|
},
|
|
{
|
|
"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={\"host\": ZILLIZ_CLOUD_HOSTNAME, \"port\": ZILLIZ_CLOUD_PORT},\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": "3.8.9"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 5
|
|
}
|