Skip to main content
OpenSearch 是一个可扩展、灵活且可扩展的开源软件套件，用于搜索、分析和可观测性应用程序，采用 Apache 2.0 许可。OpenSearch 是一个基于 Apache Lucene 的分布式搜索和分析引擎。
本笔记本展示了如何使用与 OpenSearch 数据库相关的功能。 要运行，您需要有一个正在运行的 OpenSearch 实例：请参阅此处了解简单的 Docker 安装。 默认情况下，similarity_search 执行近似 k-NN 搜索，该搜索使用几种算法之一，如 lucene、nmslib、faiss，推荐用于大型数据集。要执行暴力搜索，我们有其他搜索方法，称为脚本评分和无痛脚本。请查看此链接 了解更多详情。

​
安装

安装 Python 客户端。 
pip install -qU  opensearch-py langchain-community
我们想使用 OpenAIEmbeddings，因此我们需要获取 OpenAI API 密钥。 
import getpass
import os

if "OPENAI_API_KEY" not in os.environ:
    os.environ["OPENAI_API_KEY"] = getpass.getpass("OpenAI API Key:")

from langchain_community.document_loaders import TextLoader
from langchain_community.vectorstores import OpenSearchVectorSearch
from langchain_openai import OpenAIEmbeddings
from langchain_text_splitters import CharacterTextSplitter

from langchain_community.document_loaders import TextLoader

loader = TextLoader("../../how_to/state_of_the_union.txt")
documents = loader.load()
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
docs = text_splitter.split_documents(documents)

embeddings = OpenAIEmbeddings()
使用自定义参数的 Approximate k-NN 搜索的 similarity_search 
docsearch = OpenSearchVectorSearch.from_documents(
    docs, embeddings, opensearch_url="http://localhost:9200"
)

# 如果使用默认的 Docker 安装，请改用此实例化：
# docsearch = OpenSearchVectorSearch.from_documents(
#     docs,
#     embeddings,
#     opensearch_url="https://localhost:9200",
#     http_auth=("admin", "admin"),
#     use_ssl = False,
#     verify_certs = False,
#     ssl_assert_hostname = False,
#     ssl_show_warn = False,
# )

query = "What did the president say about Ketanji Brown Jackson"
docs = docsearch.similarity_search(query, k=10)

print(docs[0].page_content)

docsearch = OpenSearchVectorSearch.from_documents(
    docs,
    embeddings,
    opensearch_url="http://localhost:9200",
    engine="faiss",
    space_type="innerproduct",
    ef_construction=256,
    m=48,
)

query = "What did the president say about Ketanji Brown Jackson"
docs = docsearch.similarity_search(query)

print(docs[0].page_content)
使用自定义参数的 Script Scoring 的 similarity_search 
docsearch = OpenSearchVectorSearch.from_documents(
    docs, embeddings, opensearch_url="http://localhost:9200", is_appx_search=False
)

query = "What did the president say about Ketanji Brown Jackson"
docs = docsearch.similarity_search(
    "What did the president say about Ketanji Brown Jackson",
    k=1,
    search_type="script_scoring",
)

print(docs[0].page_content)
使用自定义参数的 Painless Scripting 的 similarity_search 
docsearch = OpenSearchVectorSearch.from_documents(
    docs, embeddings, opensearch_url="http://localhost:9200", is_appx_search=False
)
filter = {"bool": {"filter": {"term": {"text": "smuggling"}}}}
query = "What did the president say about Ketanji Brown Jackson"
docs = docsearch.similarity_search(
    "What did the president say about Ketanji Brown Jackson",
    search_type="painless_scripting",
    space_type="cosineSimilarity",
    pre_filter=filter,
)

print(docs[0].page_content)

​
最大边际相关性搜索 (MMR)

如果您想查找一些相似文档，但又希望获得多样化的结果，MMR 是您应该考虑的方法。最大边际相关性优化了与查询的相似性以及所选文档之间的多样性。 
query = "What did the president say about Ketanji Brown Jackson"
docs = docsearch.max_marginal_relevance_search(query, k=2, fetch_k=10, lambda_param=0.5)

​
使用预先存在的 OpenSearch 实例

也可以使用预先存在的 OpenSearch 实例，其中已包含向量的文档。 
# 这只是一个示例，您需要更改这些值以指向另一个 opensearch 实例
docsearch = OpenSearchVectorSearch(
    index_name="index-*",
    embedding_function=embeddings,
    opensearch_url="http://localhost:9200",
)

# 您可以指定自定义字段名称以匹配您用于存储嵌入、文档文本值和元数据的字段
docs = docsearch.similarity_search(
    "Who was asking about getting lunch today?",
    search_type="script_scoring",
    space_type="cosinesimil",
    vector_field="message_embedding",
    text_field="message",
    metadata_field="message_metadata",
)

​
使用 AOSS (Amazon OpenSearch Service serverless)

这是使用 faiss 引擎和 efficient_filter 的 AOSS 示例。 我们需要安装几个 python 包。 
pip install -qU  boto3 requests requests-aws4auth

import boto3
from opensearchpy import RequestsHttpConnection
from requests_aws4auth import AWS4Auth

service = "aoss"  # 必须将服务设置为 'aoss'
region = "us-east-2"
credentials = boto3.Session(
    aws_access_key_id="xxxxxx", aws_secret_access_key="xxxxx"
).get_credentials()
awsauth = AWS4Auth("xxxxx", "xxxxxx", region, service, session_token=credentials.token)

docsearch = OpenSearchVectorSearch.from_documents(
    docs,
    embeddings,
    opensearch_url="host url",
    http_auth=awsauth,
    timeout=300,
    use_ssl=True,
    verify_certs=True,
    connection_class=RequestsHttpConnection,
    index_name="test-index-using-aoss",
    engine="faiss",
)

docs = docsearch.similarity_search(
    "What is feature selection",
    efficient_filter=filter,
    k=200,
)

​
使用 AOS (Amazon OpenSearch Service)

pip install -qU  boto3

# 这只是一个示例，展示如何使用 Amazon OpenSearch Service，您需要设置适当的值。
import boto3
from opensearchpy import RequestsHttpConnection

service = "es"  # 必须将服务设置为 'es'
region = "us-east-2"
credentials = boto3.Session(
    aws_access_key_id="xxxxxx", aws_secret_access_key="xxxxx"
).get_credentials()
awsauth = AWS4Auth("xxxxx", "xxxxxx", region, service, session_token=credentials.token)

docsearch = OpenSearchVectorSearch.from_documents(
    docs,
    embeddings,
    opensearch_url="host url",
    http_auth=awsauth,
    timeout=300,
    use_ssl=True,
    verify_certs=True,
    connection_class=RequestsHttpConnection,
    index_name="test-index",
)

docs = docsearch.similarity_search(
    "What is feature selection",
    k=200,
)
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，以获取实时答案。