China Mobile ECloud VectorSearch는 완전 관리형 엔터프라이즈급 분산 검색 및 분석 서비스입니다. China Mobile ECloud VectorSearch는 구조화/비구조화 데이터에 대해 저비용, 고성능, 안정적인 검색 및 분석 플랫폼 수준의 제품 서비스를 제공합니다. vector database로서 다양한 index 유형과 유사도 거리 측정 방법을 지원합니다.
이 integration을 사용하려면 pip install -qU langchain-community로 langchain-community를 설치해야 합니다 이 notebook은 ECloud ElasticSearch VectorStore와 관련된 기능을 사용하는 방법을 보여줍니다. 실행하려면 China Mobile ECloud VectorSearch instance가 실행 중이어야 합니다: 도움말 문서를 읽고 China Mobile ECloud ElasticSearch instance를 빠르게 익히고 구성하세요. instance가 실행되면 다음 단계에 따라 문서를 분할하고, embedding을 가져오고, baidu cloud elasticsearch instance에 연결하고, 문서를 indexing하고, vector 검색을 수행합니다. 
#!pip install elasticsearch == 7.10.1
먼저, OpenAIEmbeddings를 사용하려면 OpenAI API Key를 가져와야 합니다. 
import getpass
import os

if "OPENAI_API_KEY" not in os.environ:
    os.environ["OPENAI_API_KEY"] = getpass.getpass("OpenAI API Key:")
둘째, 문서를 분할하고 embedding을 가져옵니다. 
from langchain_community.document_loaders import TextLoader
from langchain_community.vectorstores import EcloudESVectorStore
from langchain_openai import OpenAIEmbeddings
from langchain_text_splitters import CharacterTextSplitter

loader = TextLoader("../../../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()

ES_URL = "http://localhost:9200"
USER = "your user name"
PASSWORD = "your password"
indexname = "your index name"
그런 다음, 문서를 indexing합니다 
docsearch = EcloudESVectorStore.from_documents(
    docs,
    embeddings,
    es_url=ES_URL,
    user=USER,
    password=PASSWORD,
    index_name=indexname,
    refresh_indices=True,
)
마지막으로, 데이터를 query하고 검색합니다 
query = "What did the president say about Ketanji Brown Jackson"
docs = docsearch.similarity_search(query, k=10)
print(docs[0].page_content)
일반적으로 사용되는 케이스 
def test_dense_float_vectore_lsh_cosine() -> None:
    """
    Test indexing with vectore type knn_dense_float_vector and  model-similarity of lsh-cosine
    this mapping is compatible with model of exact and similarity of l2/cosine
    this mapping is compatible with model of lsh and similarity of cosine
    """
    docsearch = EcloudESVectorStore.from_documents(
        docs,
        embeddings,
        es_url=ES_URL,
        user=USER,
        password=PASSWORD,
        index_name=indexname,
        refresh_indices=True,
        text_field="my_text",
        vector_field="my_vec",
        vector_type="knn_dense_float_vector",
        vector_params={"model": "lsh", "similarity": "cosine", "L": 99, "k": 1},
    )

    docs = docsearch.similarity_search(
        query,
        k=10,
        search_params={
            "model": "exact",
            "vector_field": "my_vec",
            "text_field": "my_text",
        },
    )
    print(docs[0].page_content)

    docs = docsearch.similarity_search(
        query,
        k=10,
        search_params={
            "model": "exact",
            "similarity": "l2",
            "vector_field": "my_vec",
            "text_field": "my_text",
        },
    )
    print(docs[0].page_content)

    docs = docsearch.similarity_search(
        query,
        k=10,
        search_params={
            "model": "exact",
            "similarity": "cosine",
            "vector_field": "my_vec",
            "text_field": "my_text",
        },
    )
    print(docs[0].page_content)

    docs = docsearch.similarity_search(
        query,
        k=10,
        search_params={
            "model": "lsh",
            "similarity": "cosine",
            "candidates": 10,
            "vector_field": "my_vec",
            "text_field": "my_text",
        },
    )
    print(docs[0].page_content)
filter를 사용하는 케이스 
def test_dense_float_vectore_exact_with_filter() -> None:
    """
    Test indexing with vectore type knn_dense_float_vector and default model/similarity
    this mapping is compatible with model of exact and similarity of l2/cosine
    """
    docsearch = EcloudESVectorStore.from_documents(
        docs,
        embeddings,
        es_url=ES_URL,
        user=USER,
        password=PASSWORD,
        index_name=indexname,
        refresh_indices=True,
        text_field="my_text",
        vector_field="my_vec",
        vector_type="knn_dense_float_vector",
    )
    # filter={"match_all": {}} ,default
    docs = docsearch.similarity_search(
        query,
        k=10,
        filter={"match_all": {}},
        search_params={
            "model": "exact",
            "vector_field": "my_vec",
            "text_field": "my_text",
        },
    )
    print(docs[0].page_content)

    # filter={"term": {"my_text": "Jackson"}}
    docs = docsearch.similarity_search(
        query,
        k=10,
        filter={"term": {"my_text": "Jackson"}},
        search_params={
            "model": "exact",
            "vector_field": "my_vec",
            "text_field": "my_text",
        },
    )
    print(docs[0].page_content)

    # filter={"term": {"my_text": "president"}}
    docs = docsearch.similarity_search(
        query,
        k=10,
        filter={"term": {"my_text": "president"}},
        search_params={
            "model": "exact",
            "similarity": "l2",
            "vector_field": "my_vec",
            "text_field": "my_text",
        },
    )
    print(docs[0].page_content)
Edit the source of this page on GitHub.
Connect these docs programmatically to Claude, VSCode, and more via MCP for real-time answers.
⌘I