mirror of
https://github.com/hwchase17/langchain.git
synced 2025-09-05 21:12:48 +00:00
Add dashvector vectorstore (#9163)
## Description Add `Dashvector` vectorstore for langchain - [dashvector quick start](https://help.aliyun.com/document_detail/2510223.html) - [dashvector package description](https://pypi.org/project/dashvector/) ## How to use ```python from langchain.vectorstores.dashvector import DashVector dashvector = DashVector.from_documents(docs, embeddings) ``` --------- Co-authored-by: smallrain.xuxy <smallrain.xuxy@alibaba-inc.com> Co-authored-by: Bagatur <baskaryan@gmail.com>
This commit is contained in:
Xiaoyu Xee
GitHub
24
docs/extras/integrations/providers/dashvector.mdx
Normal file
24
docs/extras/integrations/providers/dashvector.mdx
Normal file
@@ -0,0 +1,24 @@
|
||||
# DashVector
|
||||
|
||||
> [DashVector](https://help.aliyun.com/document_detail/2510225.html) is a fully-managed vectorDB service that supports high-dimension dense and sparse vectors, real-time insertion and filtered search. It is built to scale automatically and can adapt to different application requirements.
|
||||
|
||||
This document demonstrates to leverage DashVector within the LangChain ecosystem. In particular, it shows how to install DashVector, and how to use it as a VectorStore plugin in LangChain.
|
||||
It is broken into two parts: installation and setup, and then references to specific DashVector wrappers.
|
||||
|
||||
## Installation and Setup
|
||||
Install the Python SDK:
|
||||
```bash
|
||||
pip install dashvector
|
||||
```
|
||||
|
||||
## VectorStore
|
||||
|
||||
A DashVector Collection is wrapped as a familiar VectorStore for native usage within LangChain,
|
||||
which allows it to be readily used for various scenarios, such as semantic search or example selection.
|
||||
|
||||
You may import the vectorstore by:
|
||||
```python
|
||||
from langchain.vectorstores import DashVector
|
||||
```
|
||||
|
||||
For a detailed walkthrough of the DashVector wrapper, please refer to [this notebook](/docs/integrations/vectorstores/dashvector.html)
|
||||
236
docs/extras/integrations/vectorstores/dashvector.ipynb
Normal file
236
docs/extras/integrations/vectorstores/dashvector.ipynb
Normal file
@@ -0,0 +1,236 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"pycharm": {
|
||||
"name": "#%% md\n"
|
||||
}
|
||||
},
|
||||
"source": [
|
||||
"# DashVector\n",
|
||||
"\n",
|
||||
"> [DashVector](https://help.aliyun.com/document_detail/2510225.html) is a fully-managed vectorDB service that supports high-dimension dense and sparse vectors, real-time insertion and filtered search. It is built to scale automatically and can adapt to different application requirements.\n",
|
||||
"\n",
|
||||
"This notebook shows how to use functionality related to the `DashVector` vector database.\n",
|
||||
"\n",
|
||||
"To use DashVector, you must have an API key.\n",
|
||||
"Here are the [installation instructions](https://help.aliyun.com/document_detail/2510223.html)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"pycharm": {
|
||||
"name": "#%% md\n"
|
||||
}
|
||||
},
|
||||
"source": [
|
||||
"## Install"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"pycharm": {
|
||||
"name": "#%%\n"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"!pip install dashvector dashscope"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"pycharm": {
|
||||
"name": "#%% md\n"
|
||||
}
|
||||
},
|
||||
"source": [
|
||||
"We want to use `DashScopeEmbeddings` so we also have to get the Dashscope API Key."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"metadata": {
|
||||
"pycharm": {
|
||||
"name": "#%%\n",
|
||||
"is_executing": true
|
||||
},
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-08-11T10:37:15.091585Z",
|
||||
"start_time": "2023-08-11T10:36:51.859753Z"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"import getpass\n",
|
||||
"\n",
|
||||
"os.environ[\"DASHVECTOR_API_KEY\"] = getpass.getpass(\"DashVector API Key:\")\n",
|
||||
"os.environ[\"DASHSCOPE_API_KEY\"] = getpass.getpass(\"DashScope API Key:\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"pycharm": {
|
||||
"name": "#%% md\n"
|
||||
}
|
||||
},
|
||||
"source": [
|
||||
"## Example"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"metadata": {
|
||||
"pycharm": {
|
||||
"name": "#%%\n",
|
||||
"is_executing": true
|
||||
},
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-08-11T10:42:30.243460Z",
|
||||
"start_time": "2023-08-11T10:42:27.783785Z"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.embeddings.dashscope import DashScopeEmbeddings\n",
|
||||
"from langchain.text_splitter import CharacterTextSplitter\n",
|
||||
"from langchain.vectorstores import DashVector"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"metadata": {
|
||||
"pycharm": {
|
||||
"is_executing": true,
|
||||
"name": "#%%\n"
|
||||
},
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-08-11T10:42:30.391580Z",
|
||||
"start_time": "2023-08-11T10:42:30.249021Z"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.document_loaders import TextLoader\n",
|
||||
"\n",
|
||||
"loader = TextLoader(\"../../modules/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 = DashScopeEmbeddings()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"pycharm": {
|
||||
"name": "#%% md\n"
|
||||
}
|
||||
},
|
||||
"source": [
|
||||
"We can create DashVector from documents."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"pycharm": {
|
||||
"name": "#%%\n"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"dashvector = DashVector.from_documents(docs, embeddings)\n",
|
||||
"\n",
|
||||
"query = \"What did the president say about Ketanji Brown Jackson\"\n",
|
||||
"docs = dashvector.similarity_search(query)\n",
|
||||
"print(docs)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"pycharm": {
|
||||
"name": "#%% md\n"
|
||||
}
|
||||
},
|
||||
"source": [
|
||||
"We can add texts with meta datas and ids, and search with meta filter."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"metadata": {
|
||||
"pycharm": {
|
||||
"name": "#%%\n"
|
||||
},
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-08-11T10:42:51.641309Z",
|
||||
"start_time": "2023-08-11T10:42:51.132109Z"
|
||||
}
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"[Document(page_content='baz', metadata={'key': 2})]\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"texts = [\"foo\", \"bar\", \"baz\"]\n",
|
||||
"metadatas = [{\"key\": i} for i in range(len(texts))]\n",
|
||||
"ids = [\"0\", \"1\", \"2\"]\n",
|
||||
"\n",
|
||||
"dashvector.add_texts(texts, metadatas=metadatas, ids=ids)\n",
|
||||
"\n",
|
||||
"docs = dashvector.similarity_search(\"foo\", filter=\"key = 2\")\n",
|
||||
"print(docs)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"outputs": [],
|
||||
"source": [],
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
}
|
||||
}
|
||||
],
|
||||
"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": "3.10.4"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 1
|
||||
}
|
||||
Reference in New Issue
Block a user