Skip to main content
Open In ColabOpen on GitHub

OpenSearch

OpenSearch is a scalable, flexible, and extensible open-source software suite for search, analytics, and observability applications licensed under Apache 2.0. OpenSearch is a distributed search and analytics engine based on Apache Lucene.

This notebook shows how to use functionality related to the OpenSearch database.

To run, you should have an OpenSearch instance up and running: see here for an easy Docker installation.

similarity_search by default performs the Approximate k-NN Search which uses one of the several algorithms like lucene, nmslib, faiss recommended for large datasets. To perform brute force search we have other search methods known as Script Scoring and Painless Scripting. Check this for more details.

安装​

安装 Python 客户端。

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

我们想使用 OpenAIEmbeddings，所以必须获取 OpenAI API Key。

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()
API Reference:TextLoader

similarity_search 使用近似 k-NN​

使用自定义参数的近似 k-NN 搜索进行 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)

similarity_search 使用 Script Scoring​

使用自定义参数的 similarity_search 和 Script Scoring

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 Painless 脚本进行相似性搜索​

使用自定义参数的 Painless Scripting 进行 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的文档，但又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)

使用已存在的 OpenSearch 实例​

您也可以使用已存在的 OpenSearch 实例，其中包含已存在向量的文档。

# 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）​

这是一个使用 faiss 引擎和 efficient_filter 的 AOSS 示例。

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)​

AOS, a fully managed service, makes it easy to

%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,
)