mirror of
https://github.com/hwchase17/langchain.git
synced 2025-09-14 05:56:40 +00:00
community[minor]: add vikingdb vecstore (#15155)
--------- Co-authored-by: gaoyuan <gaoyuan.20001218@bytedance.com>
This commit is contained in:
高远
GitHub
248
docs/docs/integrations/vectorstores/vikingdb.ipynb
Normal file
248
docs/docs/integrations/vectorstores/vikingdb.ipynb
Normal file
@@ -0,0 +1,248 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "96ff9e912bfe9d8",
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"source": [
|
||||
"# viking DB\n",
|
||||
"\n",
|
||||
">[viking DB](https://www.volcengine.com/docs/6459/1163946) is a database that stores, indexes, and manages massive embedding vectors generated by deep neural networks and other machine learning (ML) models.\n",
|
||||
"\n",
|
||||
"This notebook shows how to use functionality related to the VikingDB vector database.\n",
|
||||
"\n",
|
||||
"To run, you should have a [viking DB instance up and running](https://www.volcengine.com/docs/6459/1165058).\n",
|
||||
"\n",
|
||||
"\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "dd771e02d8a93a0",
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"!pip install --upgrade volcengine"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "12719205caed0d18",
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"source": [
|
||||
"We want to use VikingDBEmbeddings so we have to get the VikingDB API Key."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "fbfb32665b4a3640",
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-12-21T09:53:24.186916Z",
|
||||
"start_time": "2023-12-21T09:53:24.179524Z"
|
||||
},
|
||||
"collapsed": false
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import getpass\n",
|
||||
"import os\n",
|
||||
"\n",
|
||||
"os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "d8c983d329237fa4",
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.document_loaders import TextLoader\n",
|
||||
"from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
|
||||
"from langchain.vectorstores.vikingdb import VikingDB, VikingDBConfig\n",
|
||||
"from langchain_openai import OpenAIEmbeddings"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "1a4aea2eaeb2261",
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"loader = TextLoader(\"./test.txt\")\n",
|
||||
"documents = loader.load()\n",
|
||||
"text_splitter = RecursiveCharacterTextSplitter(chunk_size=10, chunk_overlap=0)\n",
|
||||
"docs = text_splitter.split_documents(documents)\n",
|
||||
"\n",
|
||||
"embeddings = OpenAIEmbeddings()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "bfd593f3deabfaf8",
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"db = VikingDB.from_documents(\n",
|
||||
" docs,\n",
|
||||
" embeddings,\n",
|
||||
" connection_args=VikingDBConfig(\n",
|
||||
" host=\"host\", region=\"region\", ak=\"ak\", sk=\"sk\", scheme=\"http\"\n",
|
||||
" ),\n",
|
||||
" drop_old=True,\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "50e6ee12ca7eec39",
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-12-21T10:01:47.355894Z",
|
||||
"start_time": "2023-12-21T10:01:47.334789Z"
|
||||
},
|
||||
"collapsed": false
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"query = \"What did the president say about Ketanji Brown Jackson\"\n",
|
||||
"docs = db.similarity_search(query)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "b6b81f5995c79ef0",
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-12-21T10:01:47.771478Z",
|
||||
"start_time": "2023-12-21T10:01:47.731485Z"
|
||||
},
|
||||
"collapsed": false
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"docs[0].page_content"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "a2d932c1290478ee",
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"source": [
|
||||
"### Compartmentalize the data with viking DB Collections\n",
|
||||
"\n",
|
||||
"You can store different unrelated documents in different collections within same viking DB instance to maintain the context"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "907de4eb10626d2a",
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"source": [
|
||||
"Here's how you can create a new collection"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "4f5a59ba40f7985f",
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"db = VikingDB.from_documents(\n",
|
||||
" docs,\n",
|
||||
" embeddings,\n",
|
||||
" connection_args=VikingDBConfig(\n",
|
||||
" host=\"host\", region=\"region\", ak=\"ak\", sk=\"sk\", scheme=\"http\"\n",
|
||||
" ),\n",
|
||||
" collection_name=\"collection_1\",\n",
|
||||
" drop_old=True,\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "7c8eada37b17d992",
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"source": [
|
||||
"And here is how you retrieve that stored collection"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "883ec678d47c9adc",
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"db = VikingDB.from_documents(\n",
|
||||
" embeddings,\n",
|
||||
" connection_args=VikingDBConfig(\n",
|
||||
" host=\"host\", region=\"region\", ak=\"ak\", sk=\"sk\", scheme=\"http\"\n",
|
||||
" ),\n",
|
||||
" collection_name=\"collection_1\",\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "2f0be30cfe70083d",
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"source": [
|
||||
"After retreival you can go on querying it as usual."
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 2
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython2",
|
||||
"version": "2.7.6"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
Reference in New Issue
Block a user