OpenSearch 集成

pip install -qU  opensearch-py langchain-community

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()

docsearch = OpenSearchVectorSearch.from_documents(
    docs, embeddings, opensearch_url="http://localhost:9200"
)

# 如果使用默认的 Docker 安装，请改用此实例化方式：
# 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)

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)

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)

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)

# 这只是一个示例，你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",
)

# 你可以指定自定义字段名称，以匹配你用于存储嵌入、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",
)

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,
)

pip install -qU  boto3

# 这只是一个示例，展示如何使用 Amazon OpenSearch Service，你需要设置适当的值。
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,
)