ZeusDB 集成

pip install -qU langchain-zeusdb

pip install -qU langchain-zeusdb

pip install -qU langchain-openai

# 如果在 Jupyter Notebooks 中，请使用此命令
#pip install -qU langchain-openai

import os
import getpass

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

from dotenv import load_dotenv

load_dotenv()  # 读取 .env 并设置 OPENAI_API_KEY

# 导入所需的包和类
from langchain_zeusdb import ZeusDBVectorStore
from langchain_openai import OpenAIEmbeddings
from zeusdb import VectorDatabase

# 初始化嵌入
embeddings = OpenAIEmbeddings(model="text-embedding-3-small")

# 创建 ZeusDB 索引
vdb = VectorDatabase()
index = vdb.create(index_type="hnsw", dim=1536, space="cosine")

# 创建向量存储
vector_store = ZeusDBVectorStore(zeusdb_index=index, embedding=embeddings)

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"])

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"])

vector_store.delete(ids=["3"])

results = vector_store.similarity_search(query="high performance database", k=2)

for doc in results:
    print(f"* {doc.page_content} [{doc.metadata}]")

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}]")

retriever = vector_store.as_retriever(search_type="mmr", search_kwargs={"k": 2})

retriever.invoke("vector database features")

# 创建内存优化的向量存储
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()}")

# 保存向量存储
vector_store.save_index("my_zeusdb_index.zdb")

# 加载向量存储
loaded_store = ZeusDBVectorStore.load_index(
    path="my_zeusdb_index.zdb", embedding=embeddings
)

print(f"Loaded store with {loaded_store.get_vector_count()} vectors")