>ZeusDB 是一款由 Rust 提供支持的高性能向量数据库，提供产品量化、持久存储和企业级日志记录等高级功能。

本文档展示了如何使用 ZeusDB 为您的 LangChain 应用程序带来企业级向量搜索能力。

快速开始

安装

pip install langchain-zeusdb

uv add langchain-zeusdb

开始使用

此示例使用 *OpenAIEmbeddings*，需要 OpenAI API 密钥 - 在此获取您的 OpenAI API 密钥

如果您愿意，也可以将此包与任何其他嵌入提供程序（Hugging Face、Cohere、自定义函数等）配合使用。

pip install langchain-openai

os.environ['OPENAI_API_KEY'] = getpass.getpass('OpenAI API Key:')

基本用法

from langchain_zeusdb import ZeusDBVectorStore
from langchain_openai import OpenAIEmbeddings
from zeusdb import VectorDatabase

# 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
)

# Add documents
from langchain_core.documents import Document

docs = [
    Document(page_content="ZeusDB is fast", metadata={"source": "docs"}),
    Document(page_content="LangChain is powerful", metadata={"source": "docs"}),
]

vector_store.add_documents(docs)

# Search
results = vector_store.similarity_search("fast database", k=2)
print(f"Found the following {len(results)} results:")
print(results)

预期结果：

Found the following 2 results:
[Document(id='ea2b4f13-b0b7-4cef-bb91-0fc4f4c41295', metadata={'source': 'docs'}, page_content='ZeusDB is fast'), Document(id='33dc1e87-a18a-4827-a0df-6ee47eabc7b2', metadata={'source': 'docs'}, page_content='LangChain is powerful')]

工厂方法

为方便起见，您可以一步创建并填充向量存储：

示例 1：从文本创建（一步创建索引并添加文本）

vector_store_texts = ZeusDBVectorStore.from_texts(
    texts=["Hello world", "Goodbye world"],
    embedding=embeddings,
    metadatas=[{"source": "text1"}, {"source": "text2"}]
)

print("texts store count:", vector_store_texts.get_vector_count())         # -> 2
print("texts store peek:", vector_store_texts.zeusdb_index.list(2))        # [('id1', {...}), ('id2', {...})]

# Search the texts-based store
results = vector_store_texts.similarity_search("Hello", k=1)
print(f"Found in texts store: {results[0].page_content}")                  # -> "Hello world"

预期结果：

texts store count: 2
texts store peek: [('e9c39b44-b610-4e00-91f3-bf652e9989ac', {'source': 'text1', 'text': 'Hello world'}), ('d33f210c-ed53-4006-a64a-a9eee397fec9', {'source': 'text2', 'text': 'Goodbye world'})]
Found in texts store: Hello world

示例 2：从文档创建（一步创建索引并添加文档）

new_docs = [
    Document(page_content="Python is great", metadata={"source": "python"}),
    Document(page_content="JavaScript is flexible", metadata={"source": "js"}),
]

vector_store_docs = ZeusDBVectorStore.from_documents(
    documents=new_docs,
    embedding=embeddings
)

print("docs store count:", vector_store_docs.get_vector_count())           # -> 2
print("docs store peek:", vector_store_docs.zeusdb_index.list(2))          # [('id3', {...}), ('id4', {...})]

# Search the documents-based store
results = vector_store_docs.similarity_search("Python", k=1)
print(f"Found in docs store: {results[0].page_content}")                   # -> "Python is great"

预期结果：

docs store count: 2
docs store peek: [('aab2d1c1-7e02-4817-8dd8-6fb03570bb6f', {'text': 'Python is great', 'source': 'python'}), ('9a8a82cb-0e70-456c-9db2-556e464de14e', {'text': 'JavaScript is flexible', 'source': 'js'})]
Found in docs store: Python is great

高级功能

ZeusDB 的企业级功能已完全集成到 LangChain 生态系统中，提供量化、持久化、高级搜索功能以及许多其他企业级能力。

使用量化的内存高效设置

对于大型数据集，使用产品量化来减少内存使用：

# Create quantized index for memory efficiency
quantization_config = {
    'type': 'pq',
    'subvectors': 8,
    'bits': 8,
    'training_size': 10000
}

vdb = VectorDatabase()
index = vdb.create(
    index_type="hnsw",
    dim=1536,
    space="cosine",
    quantization_config=quantization_config
)

vector_store = ZeusDBVectorStore(
    zeusdb_index=index,
    embedding=embeddings
)

请参阅我们的 文档 获取有关设置量化的有用配置指南和建议。

持久化

ZeusDB 持久化功能让您能够将完全填充的索引保存到磁盘，并在之后加载它并完整恢复状态。这包括向量、元数据、HNSW 图，以及（如果启用了）产品量化模型。

保存的内容：

• - 向量和 ID
• - 元数据
• - HNSW 图结构
• - 量化配置、质心和训练状态（如果启用了 PQ）

如何保存向量存储

# Save index
vector_store.save_index("my_index.zdb")

如何加载向量存储

# Load index
loaded_store = ZeusDBVectorStore.load_index(
    path="my_index.zdb",
    embedding=embeddings
)

# Verify after load
print("vector count:", loaded_store.get_vector_count())
print("index info:", loaded_store.info())
print("store peek:", loaded_store.zeusdb_index.list(2))

注意事项

• - 路径是目录，不是单个文件。确保目标可写。
• - Saved indexes are cross-platform and include format/version info for compatibility checks.
• - 如果您使用了 PQ，压缩模型和状态都会被保留——加载后无需重新训练。
• - 您可以继续使用所有向量存储 API（相似度_搜索、检索器等）在加载的_store.

有关更多详细信息（包括文件结构和更多综合示例），请参阅 文档.

高级搜索选项

使用这些选项来控制搜索的评分、多样性、元数据过滤和检索器集成。

带分数的相似性搜索

返回 (Document, raw_distance) 来自 ZeusDB 的配对（距离越小 = 越相似）。 如果您偏好归一化的相关性 [0, 1]，请使用 similarity_search_with_relevance_scores.

# Similarity search with scores
results_with_scores = vector_store.similarity_search_with_score(
    query="machine learning",
    k=5
)

print(results_with_scores)

预期结果：

[
  (Document(id='ac0eaf5b-9f02-4ce2-8957-c369a7262c61', metadata={'source': 'docs'}, page_content='LangChain is powerful'), 0.8218843340873718),
  (Document(id='faae3adf-7cf3-463c-b282-3790b096fa23', metadata={'source': 'docs'}, page_content='ZeusDB is fast'), 0.9140053391456604)
]

用于多样性的 MMR 搜索

MMR（最大边际相关性）在两个力量之间取得平衡：对查询的相关性和所选结果之间的多样性，减少近乎重复的答案。使用 lambda 参数控制权衡_（1.0 = 全部相关性，0.0 = 全部多样性）。

# MMR search for diversity
mmr_results = vector_store.max_marginal_relevance_search(
    query="AI applications",
    k=5,
    fetch_k=20,
    lambda_mult=0.7  # Balance relevance vs diversity
)

print(mmr_results)

使用元数据过滤进行搜索

使用添加文档时存储的文档元数据来过滤结果

# Search with metadata filtering
results = vector_store.similarity_search(
    query="database performance",
    k=3,
    filter={"source": "documentation"}
)

有关支持的元数据查询类型和运算符，请参阅 文档.

作为检索器

将向量存储转换为检索器可为您提供标准 LangChain 接口，链（如 RetrievalQA）可以调用它来获取上下文。在底层它使用您选择的搜索类型（相似性或 MMR）和搜索_kwargs.

# Convert to retriever for use in chains
retriever = vector_store.as_retriever(
    search_type="mmr",
    search_kwargs={"k": 3, "lambda_mult": 0.8}
)

# Use with LangChain Expression Language (LCEL) - requires only langchain-core
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.output_parsers import StrOutputParser
from langchain_core.runnables import RunnablePassthrough
from langchain_openai import ChatOpenAI

def format_docs(docs):
    return "\n\n".join([d.page_content for d in docs])

template = """Answer the question based only on the following context:
{context}

Question: {question}
"""

prompt = ChatPromptTemplate.from_template(template)
llm = ChatOpenAI()

# Create a chain using LCEL
chain = (
    {"context": retriever | format_docs, "question": RunnablePassthrough()}
    | prompt
    | llm
    | StrOutputParser()
)

# Use the chain
answer = chain.invoke("What is ZeusDB?")
print(answer)

预期结果：

ZeusDB is a fast database management system.

异步支持

ZeusDB 支持异步操作，用于非阻塞、并发向量操作。

何时使用异步： web servers (FastAPI/Starlette), agents/pipelines doing parallel searches, or notebooks where you want non-blocking/concurrent retrieval. If you're writing simple scripts, the sync methods are fine.

这些是 **异步操作** - the async/await versions of the regular synchronous methods. Here's what each one does:

1. await vector_store.aadd_documents(documents) - 异步向向量存储添加文档（ add_documents())
2. await vector_store.asimilarity_search("query", k=5) - 异步执行相似性搜索（ similarity_search())
3. await vector_store.adelete(ids=["doc1", "doc2"]) - 异步按 ID 删除文档（ delete())

异步版本在以下情况下很有用：

• - 您正在构建异步应用程序（使用 asyncio、FastAPI 等）
• - 您需要可以并发运行的无阻塞操作
• - 您正在同时处理多个请求
• - You want better performance in I/O-bound applications

例如，不在添加文档时阻塞：

# Synchronous (blocking)
vector_store.add_documents(docs)  # Blocks until complete

# Asynchronous (non-blocking)
await vector_store.aadd_documents(docs)  # Can do other work while this runs

All operations support async/await:

**脚本版本（python my_script.py):**

from langchain_zeusdb import ZeusDBVectorStore
from langchain_openai import OpenAIEmbeddings
from langchain_core.documents import Document
from zeusdb import VectorDatabase

# Setup
embeddings = OpenAIEmbeddings(model="text-embedding-3-small")
vdb = VectorDatabase()
index = vdb.create(index_type="hnsw", dim=1536, space="cosine")
vector_store = ZeusDBVectorStore(zeusdb_index=index, embedding=embeddings)

docs = [
    Document(page_content="ZeusDB is fast", metadata={"source": "docs"}),
    Document(page_content="LangChain is powerful", metadata={"source": "docs"}),
]

async def main():
    # Add documents asynchronously
    ids = await vector_store.aadd_documents(docs)
    print("Added IDs:", ids)

    # Run multiple searches concurrently
    results_fast, results_powerful = await asyncio.gather(
        vector_store.asimilarity_search("fast", k=2),
        vector_store.asimilarity_search("powerful", k=2),
    )
    print("Fast results:", [d.page_content for d in results_fast])
    print("Powerful results:", [d.page_content for d in results_powerful])

    # Delete documents asynchronously
    deleted = await vector_store.adelete(ids=ids[:1])
    print("Deleted first doc:", deleted)

if __name__ == "__main__":
    asyncio.run(main())

**Colab/Notebook/Jupyter version (top-level await):**

from langchain_zeusdb import ZeusDBVectorStore
from langchain_openai import OpenAIEmbeddings
from langchain_core.documents import Document
from zeusdb import VectorDatabase


# Setup
embeddings = OpenAIEmbeddings(model="text-embedding-3-small")
vdb = VectorDatabase()
index = vdb.create(index_type="hnsw", dim=1536, space="cosine")
vector_store = ZeusDBVectorStore(zeusdb_index=index, embedding=embeddings)

docs = [
    Document(page_content="ZeusDB is fast", metadata={"source": "docs"}),
    Document(page_content="LangChain is powerful", metadata={"source": "docs"}),
]

# Add documents asynchronously
ids = await vector_store.aadd_documents(docs)
print("Added IDs:", ids)

# Run multiple searches concurrently
results_fast, results_powerful = await asyncio.gather(
    vector_store.asimilarity_search("fast", k=2),
    vector_store.asimilarity_search("powerful", k=2),
)
print("Fast results:", [d.page_content for d in results_fast])
print("Powerful results:", [d.page_content for d in results_powerful])

# Delete documents asynchronously
deleted = await vector_store.adelete(ids=ids[:1])
print("Deleted first doc:", deleted)

预期结果：

Added IDs: ['9c440918-715f-49ba-9b97-0d991d29e997', 'ad59c645-d3ba-4a4a-a016-49ed39514123']
Fast results: ['ZeusDB is fast', 'LangChain is powerful']
Powerful results: ['LangChain is powerful', 'ZeusDB is fast']
Deleted first doc: True

监控与可观测性

性能监控

# Get index statistics
stats = vector_store.get_zeusdb_stats()
print(f"Index size: {stats.get('total_vectors', '0')} vectors")
print(f"Dimension: {stats.get('dimension')} | Space: {stats.get('space')} | Index type: {stats.get('index_type')}")

# Benchmark search performance
performance = vector_store.benchmark_search_performance(
    query_count=100,
    max_threads=4
)
print(f"Search QPS: {performance.get('parallel_qps', 0):.0f}")

# Check quantization status
if vector_store.is_quantized():
    progress = vector_store.get_training_progress()
    print(f"Quantization training: {progress:.1f}% complete")
else:
    print("Index is not quantized")

预期结果：

Index size: 2 vectors
Dimension: 1536 | Space: cosine | Index type: HNSW
Search QPS: 53807
Index is not quantized

企业级日志

ZeusDB 包含企业级结构化日志，可通过智能环境检测自动工作：

# ZeusDB automatically detects your environment and applies appropriate logging:
# - Development: Human-readable logs, WARNING level
# - Production: JSON structured logs, ERROR level
# - Testing: Minimal output, CRITICAL level
# - Jupyter: Clean readable logs, INFO level

# Operations are automatically logged with performance metrics
vector_store.add_documents(docs)
# Logs: {"operation":"vector_addition","total_inserted":2,"duration_ms":45}

# Control logging with environment variables if needed
# ZEUSDB_LOG_LEVEL=debug ZEUSDB_LOG_FORMAT=json python your_app.py

要了解更多关于 ZeusDB 企业级日志功能的完整特性，请阅读以下 文档.

配置选项

索引参数

vdb = VectorDatabase()
index = vdb.create(
    index_type="hnsw",           # Index algorithm
    dim=1536,                    # Vector dimension
    space="cosine",              # Distance metric: cosine, l2, l1
    m=16,                        # HNSW connectivity
    ef_construction=200,         # Build-time search width
    expected_size=100000,        # Expected number of vectors
    quantization_config=None     # Optional quantization
)

搜索参数

results = vector_store.similarity_search(
    query="search query",
    k=5,                         # Number of results
    ef_search=None,              # Runtime search width (auto if None)
    filter={"key": "value"}      # Metadata filter
)

错误处理

该集成包含全面的错误处理：

try:
    results = vector_store.similarity_search("query")
    print(results)
except Exception as e:
    # Graceful degradation with logging
    print(f"Search failed: {e}")
    # Fallback logic here

要求

• Python：3.10 或更高版本
• ZeusDB：0.0.8 或更高版本
• LangChain Core: 0.3.74 或更高版本

源码安装

git clone https://github.com/zeusdb/langchain-zeusdb.git
cd langchain-zeusdb/libs/zeusdb
pip install -e .

使用场景

• RAG 应用: 用于问答的高性能检索
• 语义搜索: 在大型文档集合中快速进行相似性搜索
• 推荐系统: 基于向量的内容过滤和协同过滤
• 嵌入分析: 高维嵌入空间分析
• 实时应用: 生产系统的低延迟向量搜索

兼容性

LangChain 版本

• LangChain Core: 0.3.74+

距离度量

• 余弦: 默认值，归一化相似度
• 欧几里得 (L2): 几何距离
• 曼哈顿 (L1): 城市街区距离

嵌入模型

兼容任何嵌入提供者：

• - OpenAI (text-embedding-3-small, text-embedding-3-large)
• - Hugging Face Transformers
• - Cohere Embeddings
• - 自定义嵌入函数

支持

• 文档: docs.zeusdb.com
• 问题反馈: GitHub Issues
• 电子邮件: contact@zeusdb.com

*让向量搜索快速、可扩展且对开发者友好。*