> ## Documentation Index
> Fetch the complete documentation index at: https://langchain-zh.cn/llms.txt
> Use this file to discover all available pages before exploring further.
# ZeusDB 集成
> 使用 LangChain Python 与 ZeusDB 向量存储进行集成。
> [ZeusDB](https://www.zeusdb.com) 是一个由 Rust 驱动的高性能向量数据库，提供产品量化、持久化存储和企业级日志等高级功能。
本文档展示了如何使用 ZeusDB 为您的 LangChain 应用带来企业级向量搜索能力。
***
## 设置
从 PyPI 安装 ZeusDB LangChain 集成包：
```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
pip install -qU langchain-zeusdb
```
在 Jupyter Notebook 中设置
```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
pip install -qU langchain-zeusdb
```
***
## 入门指南
此示例使用 OpenAIEmbeddings，需要 OpenAI API 密钥：[在此获取您的 OpenAI API 密钥](https://platform.openai.com/api-keys)
如果您愿意，也可以使用此包配合任何其他嵌入提供商（Hugging Face、Cohere、自定义函数等）。
从 PyPI 安装 LangChain OpenAI 集成包：
```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
pip install -qU langchain-openai
# Use this command if inside Jupyter Notebooks
#pip install -qU langchain-openai
```
#### 请选择以下选项以集成您的 OpenAI 密钥
*选项 1: 🔑 每次输入您的 API 密钥*
在 Jupyter 中使用 getpass 安全地输入当前会话的密钥：
```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
import os
import getpass
os.environ["OPENAI_API_KEY"] = getpass.getpass("OpenAI API Key:")
```
*选项 2: 🗂️ 使用 .env 文件*
将密钥保存在本地 .env 文件中，并使用 python-dotenv 自动加载它
```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from dotenv import load_dotenv
load_dotenv() # reads .env and sets OPENAI_API_KEY
```
🎉 做得好！您已准备就绪。
***
## 初始化
```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
# Import required Packages and Classes
from langchain_zeusdb import ZeusDBVectorStore
from langchain_openai import OpenAIEmbeddings
from zeusdb import VectorDatabase
```
```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
# Initialize embeddings
embeddings = OpenAIEmbeddings(model="text-embedding-3-small")
# Create ZeusDB index
vdb = VectorDatabase()
index = vdb.create(index_type="hnsw", dim=1536, space="cosine")
# Create vector store
vector_store = ZeusDBVectorStore(zeusdb_index=index, embedding=embeddings)
```
***
## 管理向量存储
### 2.1 向向量存储添加项目
```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from langchain_core.documents import Document
document_1 = Document(
page_content="ZeusDB is a high-performance vector database",
metadata={"source": "https://docs.zeusdb.com"},
)
document_2 = Document(
page_content="Product Quantization reduces memory usage significantly",
metadata={"source": "https://docs.zeusdb.com"},
)
document_3 = Document(
page_content="ZeusDB integrates seamlessly with LangChain",
metadata={"source": "https://docs.zeusdb.com"},
)
documents = [document_1, document_2, document_3]
vector_store.add_documents(documents=documents, ids=["1", "2", "3"])
```
### 2.2 更新向量存储中的项目
```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
updated_document = Document(
page_content="ZeusDB now supports advanced Product Quantization with 4x-256x compression",
metadata={"source": "https://docs.zeusdb.com", "updated": True},
)
vector_store.add_documents([updated_document], ids=["1"])
```
### 2.3 从向量存储删除项目
```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
vector_store.delete(ids=["3"])
```
***
## 查询向量存储
### 3.1 直接查询
执行简单的相似度搜索：
```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
results = vector_store.similarity_search(query="high performance database", k=2)
for doc in results:
print(f"* {doc.page_content} [{doc.metadata}]")
```
如果您想执行相似度搜索并接收相应的分数：
```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
results = vector_store.similarity_search_with_score(query="memory optimization", k=2)
for doc, score in results:
print(f"* [SIM={score:.3f}] {doc.page_content} [{doc.metadata}]")
```
### 3.2 转换为检索器进行查询
您还可以将向量存储转换为检索器，以便在链中更轻松地使用：
```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
retriever = vector_store.as_retriever(search_type="mmr", search_kwargs={"k": 2})
retriever.invoke("vector database features")
```
***
## ZeusDB 特定功能
### 4.1 使用产品量化的内存高效设置
对于大型数据集，请使用产品量化来减少内存使用：
```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
# Create memory-optimized vector store
quantization_config = {"type": "pq", "subvectors": 8, "bits": 8, "training_size": 10000}
vdb_quantized = VectorDatabase()
quantized_index = vdb_quantized.create(
index_type="hnsw", dim=1536, quantization_config=quantization_config
)
quantized_vector_store = ZeusDBVectorStore(
zeusdb_index=quantized_index, embedding=embeddings
)
print(f"Created quantized store: {quantized_index.info()}")
```
### 4.2 持久性
将向量存储保存到磁盘并加载：
如何保存您的向量存储
```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
# Save the vector store
vector_store.save_index("my_zeusdb_index.zdb")
```
如何加载您的向量存储
```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
# Load the vector store
loaded_store = ZeusDBVectorStore.load_index(
path="my_zeusdb_index.zdb", embedding=embeddings
)
print(f"Loaded store with {loaded_store.get_vector_count()} vectors")
```
***
## 检索增强生成 (RAG) 的使用
关于如何使用此向量存储进行检索增强生成 (RAG) 的指南，请参阅以下部分：
* [操作指南：使用 RAG 进行问答](https://python.langchain.com/docs/how_to/#qa-with-rag)
* [检索概念文档](https://python.langchain.com/docs/concepts/retrieval/)
***
## API 参考
有关所有 `ZeusDBVectorStore` 功能和配置的详细文档，请前往 [ZeusDB 文档](https://docs.zeusdb.com/en/latest/vector_database/integrations/langchain.html)。
***
[Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/i18n\zh-CN\oss\python\integrations\vectorstores\zeusdb.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).
[Connect these docs](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers.