跳转到内容

Weaviate 向量搜索

WeaviateVectorSearchTool 专为在存储于 Weaviate 向量数据库中的文档上执行语义搜索而设计。此工具可以帮助你找到与给定查询在语义上相似的文档,结合向量搜索与关键字搜索的能力,获得更准确且更贴近上下文的搜索结果。

Weaviate 是一个存储和查询向量嵌入的向量数据库,支持语义搜索能力。

要将此工具集成到项目中,你需要安装 Weaviate 客户端:

Terminal window
uv add weaviate-client

要有效使用 WeaviateVectorSearchTool,请按以下步骤操作:

  1. 安装包:确认你的 Python 环境中已安装 crewai[tools]weaviate-client
  2. 设置 Weaviate:配置一个 Weaviate 集群。你可以参考 Weaviate 文档 获取说明。
  3. API Keys:获取你的 Weaviate 集群 URL 和 API key。
  4. OpenAI API Key:确保你已将 OpenAI API key 设为环境变量 OPENAI_API_KEY

下面的示例演示如何初始化工具并执行搜索:

from crewai_tools import WeaviateVectorSearchTool
# Initialize the tool
tool = WeaviateVectorSearchTool(
collection_name='example_collections',
limit=3,
alpha=0.75,
weaviate_cluster_url="https://your-weaviate-cluster-url.com",
weaviate_api_key="your-weaviate-api-key",
)
@agent
def search_agent(self) -> Agent:
'''
This agent uses the WeaviateVectorSearchTool to search for
semantically similar documents in a Weaviate vector database.
'''
return Agent(
config=self.agents_config["search_agent"],
tools=[tool]
)

WeaviateVectorSearchTool 接受以下参数:

  • collection_name:必需。要搜索的集合名称。
  • weaviate_cluster_url:必需。Weaviate 集群的 URL。
  • weaviate_api_key:必需。Weaviate 集群的 API key。
  • limit:可选。返回结果数量。默认值为 3
  • alpha:可选。控制向量搜索与关键字(BM25)搜索之间的权重。alpha = 0 表示仅 BM25,alpha = 1 表示仅向量搜索。默认值为 0.75
  • vectorizer:可选。要使用的向量化器。如果未提供,则使用带有 nomic-embed-text 模型的 text2vec_openai
  • generative_model:可选。要使用的生成模型。如果未提供,则使用 OpenAI 的 gpt-4o

你可以自定义工具所使用的 vectorizer 和生成模型:

from crewai_tools import WeaviateVectorSearchTool
from weaviate.classes.config import Configure
# Setup custom model for vectorizer and generative model
tool = WeaviateVectorSearchTool(
collection_name='example_collections',
limit=3,
alpha=0.75,
vectorizer=Configure.Vectorizer.text2vec_openai(model="nomic-embed-text"),
generative_model=Configure.Generative.openai(model="gpt-4o-mini"),
weaviate_cluster_url="https://your-weaviate-cluster-url.com",
weaviate_api_key="your-weaviate-api-key",
)

在使用该工具之前,你可以先向 Weaviate 数据库预加载文档:

import os
from crewai_tools import WeaviateVectorSearchTool
import weaviate
from weaviate.classes.init import Auth
# Connect to Weaviate
client = weaviate.connect_to_weaviate_cloud(
cluster_url="https://your-weaviate-cluster-url.com",
auth_credentials=Auth.api_key("your-weaviate-api-key"),
headers={"X-OpenAI-Api-Key": "your-openai-api-key"}
)
# Get or create collection
test_docs = client.collections.get("example_collections")
if not test_docs:
test_docs = client.collections.create(
name="example_collections",
vectorizer_config=Configure.Vectorizer.text2vec_openai(model="nomic-embed-text"),
generative_config=Configure.Generative.openai(model="gpt-4o"),
)
# Load documents
docs_to_load = os.listdir("knowledge")
with test_docs.batch.dynamic() as batch:
for d in docs_to_load:
with open(os.path.join("knowledge", d), "r") as f:
content = f.read()
batch.add_object(
{
"content": content,
"year": d.split("_")[0],
}
)
# Initialize the tool
tool = WeaviateVectorSearchTool(
collection_name='example_collections',
limit=3,
alpha=0.75,
weaviate_cluster_url="https://your-weaviate-cluster-url.com",
weaviate_api_key="your-weaviate-api-key",
)

以下示例展示了如何将 WeaviateVectorSearchTool 与 CrewAI 代理集成:

from crewai import Agent
from crewai_tools import WeaviateVectorSearchTool
# Initialize the tool
weaviate_tool = WeaviateVectorSearchTool(
collection_name='example_collections',
limit=3,
alpha=0.75,
weaviate_cluster_url="https://your-weaviate-cluster-url.com",
weaviate_api_key="your-weaviate-api-key",
)
# Create an agent with the tool
rag_agent = Agent(
name="rag_agent",
role="You are a helpful assistant that can answer questions with the help of the WeaviateVectorSearchTool.",
llm="gpt-4o-mini",
tools=[weaviate_tool],
)

WeaviateVectorSearchTool 提供了一种强大的方式,可在 Weaviate 向量数据库中搜索语义相似文档。通过利用向量嵌入,它比传统基于关键字的搜索更准确,也更贴近上下文。对于需要基于含义而非精确匹配来查找信息的应用,这个工具尤其有用。