如果你在 Colab 中打开这个 Notebook，可能需要先安装 LlamaIndex 🦙。

%pip install llama-index-vector-stores-weaviate

!pip install llama-index

import logging
import sys

logging.basicConfig(stream=sys.stdout, level=logging.INFO)
logging.getLogger().addHandler(logging.StreamHandler(stream=sys.stdout))

创建 Weaviate 客户端

import os
import openai

os.environ["OPENAI_API_KEY"] = ""
openai.api_key = os.environ["OPENAI_API_KEY"]

import weaviate

# Connect to cloud instance
cluster_url = ""
api_key = ""

client = weaviate.connect_to_wcs(
    cluster_url=cluster_url,
    auth_credentials=weaviate.auth.AuthApiKey(api_key),
)

# Connect to local instance
# client = weaviate.connect_to_local()

from llama_index.core import VectorStoreIndex, SimpleDirectoryReader
from llama_index.vector_stores.weaviate import WeaviateVectorStore
from llama_index.core.response.notebook_utils import display_response

下载数据

!mkdir -p 'data/paul_graham/'
!wget 'https://raw.githubusercontent.com/run-llama/llama_index/main/docs/examples/data/paul_graham/paul_graham_essay.txt' -O 'data/paul_graham/paul_graham_essay.txt'

加载文档

# load documents
documents = SimpleDirectoryReader("./data/paul_graham/").load_data()

使用 WeaviateVectorStore 构建 VectorStoreIndex

from llama_index.core import StorageContext

vector_store = WeaviateVectorStore(weaviate_client=client)
storage_context = StorageContext.from_defaults(vector_store=vector_store)
index = VectorStoreIndex.from_documents(
    documents, storage_context=storage_context
)

# NOTE: you may also choose to define a index_name manually.
# index_name = "test_prefix"
# vector_store = WeaviateVectorStore(weaviate_client=client, index_name=index_name)

使用默认向量搜索查询索引

# set Logging to DEBUG for more detailed outputs
query_engine = index.as_query_engine(similarity_top_k=2)
response = query_engine.query("What did the author do growing up?")

display_response(response)

使用混合搜索查询索引

将 bm25 与向量结合使用混合搜索。
alpha 参数决定权重（alpha = 0 -> bm25，alpha=1 -> 向量搜索）。

默认使用 alpha=0.75（与向量搜索非常相似）

# set Logging to DEBUG for more detailed outputs
query_engine = index.as_query_engine(
    vector_store_query_mode="hybrid", similarity_top_k=2
)
response = query_engine.query(
    "What did the author do growing up?",
)

display_response(response)

设置 alpha=0. 以偏向 bm25

# set Logging to DEBUG for more detailed outputs
query_engine = index.as_query_engine(
    vector_store_query_mode="hybrid", similarity_top_k=2, alpha=0.0
)
response = query_engine.query(
    "What did the author do growing up?",
)

display_response(response)