开放搜索

OpenSearch 是一个可扩展、灵活且可扩展的开源软件套件，适用于根据 Apache 2.0 许可的搜索、分析和可观测性应用程序。OpenSearch是一个分布式搜索和分析引擎，基于Apache Lucene.

此笔记本展示了如何使用与OpenSearch数据库。

要运行，您应该启动并运行一个 OpenSearch 实例：请参阅此处以了解如何轻松安装 Docker。

similarity_search默认情况下，执行近似 k-NN 搜索，该搜索使用多种算法之一，如 lucene、nmslib、faiss，推荐用于大型数据集。为了执行暴力搜索，我们还有其他搜索方法，称为脚本评分和无痛脚本。查看此处了解更多详情。

安装

安装 Python 客户端。

%pip install --upgrade --quiet  opensearch-py langchain-community

我们想要使用 OpenAIEmbeddings，所以我们必须获取 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

API 参考：TextLoader | OpenSearch矢量搜索 | OpenAI 嵌入 | CharacterTextSplitter（字符文本拆分器）

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()

API 参考：TextLoader

使用近似 k-NN 进行similarity_search

similarity_search用Approximate k-NN使用自定义参数搜索

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)

similarity_search 使用脚本评分

similarity_search用Script Scoring使用自定义参数

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)

similarity_search 使用 Painless Scripting

similarity_search用Painless Scripting使用自定义参数

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）

如果您想查找一些类似的文档，但您也希望收到不同的结果，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

也可以将预先存在的 OpenSearch 实例与已经存在向量的文档一起使用。

# 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AOSS跟faissengine 和efficient_filter.

我们需要安装几个python包。

%pip install --upgrade --quiet  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 --upgrade --quiet  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,
)

矢量存储概念指南
Vector store 操作指南

安装