本指南展示如何在 LlamaIndex 中使用 Weaviate 执行自动检索。

Weaviate 向量数据库除支持用于语义搜索的查询字符串外，还支持一组元数据过滤器。给定自然语言查询后，我们首先使用大语言模型（LLM）推断一组元数据过滤器以及要传给向量数据库的正确查询字符串（两者也可以为空）。随后，将整个查询包针对向量数据库执行。

这允许超越 top-k 语义搜索，实现更动态、更具表现力的检索形式。给定查询的相关上下文可能只需要对元数据标签进行过滤，或者需要在过滤集内进行过滤 + 语义搜索的联合组合，或者只需要原始语义搜索。

设置

我们首先定义导入，并定义一个空的 Weaviate 集合。

如果你在 Colab 中打开此 Notebook，可能需要安装 LlamaIndex 🦙。

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

!pip install llama-index weaviate-client

import logging
import sys

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

我们将使用 GPT-4 的推理能力来推断元数据过滤器。根据你的用例，"gpt-3.5-turbo" 也可以胜任。

# set up OpenAI
import os
import getpass
import openai

os.environ["OPENAI_API_KEY"] = getpass.getpass("OpenAI API Key:")
openai.api_key = os.environ["OPENAI_API_KEY"]

from llama_index.embeddings.openai import OpenAIEmbedding
from llama_index.llms.openai import OpenAI
from llama_index.core.settings import Settings

Settings.llm = OpenAI(model="gpt-4")
Settings.embed_model = OpenAIEmbedding()

本 Notebook 以嵌入式模式使用 Weaviate，该模式支持 Linux 和 macOS。

如果你更想尝试 Weaviate 的全托管服务 Weaviate Cloud Services (WCS)，可以启用注释中的代码。

import weaviate
from weaviate.embedded import EmbeddedOptions

# Connect to Weaviate client in embedded mode
client = weaviate.connect_to_embedded()

# Enable this code if you want to use Weaviate Cloud Services instead of Embedded mode.
"""
import weaviate

# cloud
cluster_url = ""
api_key = ""

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

# local
# client = weaviate.connect_to_local()
"""

定义一些示例数据

我们向向量数据库中插入一些包含文本分块的示例节点。请注意，每个 TextNode 不仅包含文本，还包含元数据，例如 category 和 country。这些元数据字段将按原样转换/存储在底层向量数据库中。

from llama_index.core.schema import TextNode

nodes = [
    TextNode(
        text=(
            "Michael Jordan is a retired professional basketball player,"
            " widely regarded as one of the greatest basketball players of all"
            " time."
        ),
        metadata={
            "category": "Sports",
            "country": "United States",
        },
    ),
    TextNode(
        text=(
            "Angelina Jolie is an American actress, filmmaker, and"
            " humanitarian. She has received numerous awards for her acting"
            " and is known for her philanthropic work."
        ),
        metadata={
            "category": "Entertainment",
            "country": "United States",
        },
    ),
    TextNode(
        text=(
            "Elon Musk is a business magnate, industrial designer, and"
            " engineer. He is the founder, CEO, and lead designer of SpaceX,"
            " Tesla, Inc., Neuralink, and The Boring Company."
        ),
        metadata={
            "category": "Business",
            "country": "United States",
        },
    ),
    TextNode(
        text=(
            "Rihanna is a Barbadian singer, actress, and businesswoman. She"
            " has achieved significant success in the music industry and is"
            " known for her versatile musical style."
        ),
        metadata={
            "category": "Music",
            "country": "Barbados",
        },
    ),
    TextNode(
        text=(
            "Cristiano Ronaldo is a Portuguese professional footballer who is"
            " considered one of the greatest football players of all time. He"
            " has won numerous awards and set multiple records during his"
            " career."
        ),
        metadata={
            "category": "Sports",
            "country": "Portugal",
        },
    ),
]

使用 Weaviate 向量存储构建向量索引

这里我们将数据加载到向量存储中。如上所述，每个节点的文本和元数据都会转换为 Weaviate 中对应的表示形式。现在，我们可以基于 Weaviate 中的这些数据运行语义查询和元数据过滤。

from llama_index.core import VectorStoreIndex, StorageContext
from llama_index.vector_stores.weaviate import WeaviateVectorStore

vector_store = WeaviateVectorStore(
    weaviate_client=client, index_name="LlamaIndex_filter"
)

storage_context = StorageContext.from_defaults(vector_store=vector_store)

index = VectorStoreIndex(nodes, storage_context=storage_context)

定义 VectorIndexAutoRetriever

我们定义核心 VectorIndexAutoRetriever 模块。该模块接收 VectorStoreInfo，其中包含向量存储集合及其支持的元数据过滤器的结构化描述。然后，此信息将用于自动检索提示词中，供 LLM 推断元数据过滤器。

from llama_index.core.retrievers import VectorIndexAutoRetriever
from llama_index.core.vector_stores.types import MetadataInfo, VectorStoreInfo

vector_store_info = VectorStoreInfo(
    content_info="brief biography of celebrities",
    metadata_info=[
        MetadataInfo(
            name="category",
            type="str",
            description=(
                "Category of the celebrity, one of [Sports, Entertainment,"
                " Business, Music]"
            ),
        ),
        MetadataInfo(
            name="country",
            type="str",
            description=(
                "Country of the celebrity, one of [United States, Barbados,"
                " Portugal]"
            ),
        ),
    ],
)

retriever = VectorIndexAutoRetriever(
    index, vector_store_info=vector_store_info
)

在一些示例数据上运行

我们尝试在一些示例数据上运行。注意元数据过滤器是如何被推断出来的——这有助于实现更精确的检索！

response = retriever.retrieve("Tell me about celebrities from United States")

print(response[0])

response = retriever.retrieve(
    "Tell me about Sports celebrities from United States"
)

print(response[0])