Skip to main content
  1. 它是一个分布式向量数据库
  2. JaguarDB 的”ZeroMove”特性支持即时水平扩展
  3. 多模态：嵌入、文本、图像、视频、PDF、音频、时间序列和地理空间数据
  4. 全主节点：同时支持并行读写
  5. 异常检测能力
  6. RAG 支持：将 LLM 与专有数据及实时数据相结合
  7. 共享元数据：在多个向量索引之间共享元数据
  8. 距离度量：欧氏距离、余弦距离、内积、曼哈顿距离、切比雪夫距离、汉明距离、杰卡德距离、闵可夫斯基距离

​
前提条件

运行本文件中的示例需满足以下两个条件。
  1. 您必须安装并配置 JaguarDB 服务器及其 HTTP 网关服务器。 请参阅以下说明： www.jaguardb.com 在 Docker 环境中快速部署： 
    docker pull jaguardb/jaguardb
docker run -d -p 8888:8888 -p 8080:8080 --name jaguardb  jaguardb/jaguardb
    不使用 Docker 时，执行： 
    curl -fsSL http://jaguardb.com/install.sh | sh
    此命令会同时安装 Jaguar 向量数据库和 HTTP 网关，安装完成后服务器将自动启动。
  2. 您必须安装 JaguarDB 的 HTTP 客户端包： 
        pip install -U jaguardb-http-client
  3. 使用此集成需要通过 pip install -qU langchain-community 安装 langchain-community

​
与 LangChain 结合使用 RAG

本节演示如何在 LangChain 软件栈中将 LLM 与 Jaguar 结合使用进行对话。 
from langchain_classic.chains import RetrievalQAWithSourcesChain
from langchain_community.document_loaders import TextLoader
from langchain_community.vectorstores.jaguar import Jaguar
from langchain_core.output_parsers import StrOutputParser
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.runnables import RunnablePassthrough
from langchain_openai import ChatOpenAI, OpenAI, OpenAIEmbeddings
from langchain_text_splitters import CharacterTextSplitter

"""
Load a text file into a set of documents
"""
loader = TextLoader("../../how_to/state_of_the_union.txt")
documents = loader.load()
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=300)
docs = text_splitter.split_documents(documents)

"""
Instantiate a Jaguar vector store
"""
### Jaguar HTTP endpoint
url = "http://192.168.5.88:8080/fwww/"

### Use OpenAI embedding model
embeddings = OpenAIEmbeddings()

### Pod is a database for vectors
pod = "vdb"

### Vector store name
store = "langchain_rag_store"

### Vector index name
vector_index = "v"

### Type of the vector index
# cosine: distance metric
# fraction: embedding vectors are decimal numbers
# float: values stored with floating-point numbers
vector_type = "cosine_fraction_float"

### Dimension of each embedding vector
vector_dimension = 1536

### Instantiate a Jaguar store object
vectorstore = Jaguar(
    pod, store, vector_index, vector_type, vector_dimension, url, embeddings
)

"""
Login must be performed to authorize the client.
The environment variable JAGUAR_API_KEY or file $HOME/.jagrc
should contain the API key for accessing JaguarDB servers.
"""
vectorstore.login()


"""
Create vector store on the JaguarDB database server.
This should be done only once.
"""
# Extra metadata fields for the vector store
metadata = "category char(16)"

# Number of characters for the text field of the store
text_size = 4096

#  Create a vector store on the server
vectorstore.create(metadata, text_size)

"""
Add the texts from the text splitter to our vectorstore
"""
vectorstore.add_documents(docs)
# or tag the documents:
# vectorstore.add_documents(more_docs, text_tag="tags to these documents")

""" Get the retriever object """
retriever = vectorstore.as_retriever()
# retriever = vectorstore.as_retriever(search_kwargs={"where": "m1='123' and m2='abc'"})

template = """You are an assistant for question-answering tasks. Use the following pieces of retrieved context to answer the question. If you don't know the answer, just say that you don't know. Use three sentences maximum and keep the answer concise.
Question: {question}
Context: {context}
Answer:
"""
prompt = ChatPromptTemplate.from_template(template)

""" Obtain a Large Language Model """
LLM = ChatOpenAI(model="gpt-3.5-turbo", temperature=0)

""" Create a chain for the RAG flow """
rag_chain = (
    {"context": retriever, "question": RunnablePassthrough()}
    | prompt
    | LLM
    | StrOutputParser()
)

resp = rag_chain.invoke("What did the president say about Justice Breyer?")
print(resp)

​
与 Jaguar 向量存储交互

用户可以直接与 Jaguar 向量存储交互，进行相似度搜索和异常检测。 
from langchain_community.vectorstores.jaguar import Jaguar
from langchain_openai import OpenAIEmbeddings

# Instantiate a Jaguar vector store object
url = "http://192.168.3.88:8080/fwww/"
pod = "vdb"
store = "langchain_test_store"
vector_index = "v"
vector_type = "cosine_fraction_float"
vector_dimension = 10
embeddings = OpenAIEmbeddings()
vectorstore = Jaguar(
    pod, store, vector_index, vector_type, vector_dimension, url, embeddings
)

# Login for authorization
vectorstore.login()

# Create the vector store with two metadata fields
# This needs to be run only once.
metadata_str = "author char(32), category char(16)"
vectorstore.create(metadata_str, 1024)

# Add a list of texts
texts = ["foo", "bar", "baz"]
metadatas = [
    {"author": "Adam", "category": "Music"},
    {"author": "Eve", "category": "Music"},
    {"author": "John", "category": "History"},
]
ids = vectorstore.add_texts(texts=texts, metadatas=metadatas)

#  Search similar text
output = vectorstore.similarity_search(
    query="foo",
    k=1,
    metadatas=["author", "category"],
)
assert output[0].page_content == "foo"
assert output[0].metadata["author"] == "Adam"
assert output[0].metadata["category"] == "Music"
assert len(output) == 1

# Search with filtering (where)
where = "author='Eve'"
output = vectorstore.similarity_search(
    query="foo",
    k=3,
    fetch_k=9,
    where=where,
    metadatas=["author", "category"],
)
assert output[0].page_content == "bar"
assert output[0].metadata["author"] == "Eve"
assert output[0].metadata["category"] == "Music"
assert len(output) == 1

# Anomaly detection
result = vectorstore.is_anomalous(
    query="dogs can jump high",
)
assert result is False

# Remove all data in the store
vectorstore.clear()
assert vectorstore.count() == 0

# Remove the store completely
vectorstore.drop()

# Logout
vectorstore.logout()
在 GitHub 上编辑此页面 或 提交问题。
通过 MCP 将这些文档连接 到 Claude、VSCode 等，获取实时答案。