Llama-index 如何针对 OpenSearch Elasticsearch 索引执行搜索查询？

Question

我有这段代码，可以在 Opensearch Elasticsearch 中创建索引：

def openes_initiate(file):
    

    endpoint = getenv("OPENSEARCH_ENDPOINT", "http://localhost:9200")
    # index to demonstrate the VectorStore impl
    idx = getenv("OPENSEARCH_INDEX", "llama-osindex-demo")
    
    UnstructuredReader = download_loader("UnstructuredReader")

    loader = UnstructuredReader()
    documents = loader.load_data(file=Path(file))

    # OpensearchVectorClient stores text in this field by default
    text_field = "content"
    # OpensearchVectorClient stores embeddings in this field by default
    embedding_field = "embedding"
    # OpensearchVectorClient encapsulates logic for a
    # single opensearch index with vector search enabled
    client = OpensearchVectorClient(endpoint, idx, 1536, embedding_field=embedding_field, text_field=text_field)
    # initialize vector store
    vector_store = OpensearchVectorStore(client)
    storage_context = StorageContext.from_defaults(vector_store=vector_store)
    # initialize an index using our sample data and the client we just created
    index = GPTVectorStoreIndex.from_documents(documents=documents,storage_context=storage_context)

我遇到的问题是，一旦我对数据建立了索引，我就无法重新加载它并对其进行查询。我尝试这样做：

def query(index,question):
    query_engine = index.as_query_engine()
    res = query_engine.query(question)
    print(res.response)

其中

index

是我在第一段代码中创建的，但它返回

None

Answer 1

您需要创建开放搜索客户端并使用 VectorStoreIndex.from_vector_store() 加载索引，然后才能对其运行查询，

index 对象为 null，不会生成 null 结果。

Answer 2

数据嵌入后，要检索它，您需要从

OpensearchVectorClient

获取矢量存储。这是一个可以帮助您的片段：

鉴于：

client = OpensearchVectorClient(endpoint, idx, 1536, 
                                embedding_field=embedding_field, 
                                text_field=text_field)
vector_store = OpensearchVectorStore(client)

从

VectorStoreIndex

获取

vector_store

：

service_context = ServiceContext.from_defaults(
        llm=None,   # or use your LLM   
        embed_model= your_embedding_model
)
vsi = VectorStoreIndex.from_vector_store(vector_store,                                       
                                         service_context=service_context)
query_engine = vsi.as_query_engine()
res = query_engine.query("your question")
print(res)

这应该可以帮助您检索和查询嵌入的数据。