Skip to main content
OpenSearch 是一个可扩展、灵活且可拓展的开源软件套件，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，您应该有一个正在运行的 OpenSearch 实例：查看简单的 Docker 安装指南。 similarity_search 默认执行近似 k-NN 搜索，该搜索使用多种算法中的一种，如 lucene、nmslib、faiss，适用于大型数据集。为了执行暴力搜索，我们有其他称为脚本评分和 Painless 脚本的搜索方法。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
我们要使用 OpenAIEmbeddings，因此需要获取 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()
使用自定义参数进行 Approximate k-NN 搜索的 similarity_search 
docsearch = OpenSearchVectorSearch.from_documents(
    docs, embeddings, opensearch_url="http://localhost:9200"
)

# If using the default Docker installation, use this instantiation instead:
# 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)
使用自定义参数进行 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)
使用自定义参数进行 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，但也希望获得多样化的结果，那么 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度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)

​
使用现有的 OpenSearch 实例

也可以使用具有现成向量的现有 OpenSearch 实例。 
# this is just an example, you would need to change these values to point to another opensearch instance
docsearch = OpenSearchVectorSearch(
    index_name="index-*",
    embedding_function=embeddings,
    opensearch_url="http://localhost:9200",
)

# you can specify custom field names to match the fields you're using to store your embedding, document text value, and metadata
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"  # must set the service as '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

# This is just an example to show how to use Amazon OpenSearch Service, you need to set proper values.
import boto3
from opensearchpy import RequestsHttpConnection

service = "es"  # must set the service as '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,
)
Edit this page on GitHub or file an issue.
Connect these docs to Claude, VSCode, and more via MCP for real-time answers.