MongoDB Vector Search Tool

MongoDBVectorSearchTool

描述

在 MongoDB Atlas collection 上执行向量相似度查询。支持索引创建辅助功能以及批量插入已嵌入文本。

MongoDB Atlas 原生支持向量搜索。了解更多： https://www.mongodb.com/docs/atlas/atlas-vector-search/vector-search-overview/

安装

使用 MongoDB extra 安装：

pip install crewai-tools[mongodb]

或者

uv add crewai-tools --extra mongodb

参数

初始化

• connection_string (str, required)
• database_name (str, required)
• collection_name (str, required)
• vector_index_name (str, default vector_index)
• text_key (str, default text)
• embedding_key (str, default embedding)
• dimensions (int, default 1536)

运行参数

• query (str, required): 要嵌入并搜索的自然语言查询。

快速开始

from crewai_tools import MongoDBVectorSearchTool

tool = MongoDBVectorSearchTool(
  connection_string="mongodb+srv://...",
  database_name="mydb",
  collection_name="docs",
)

print(tool.run(query="how to create vector index"))

索引创建辅助

使用 create_vector_search_index(...) 可以创建具有正确维度和相似度设置的 Atlas Vector Search 索引。

常见问题

• 认证失败：请确保你的 Atlas IP Access List 允许运行环境访问，并且连接字符串中包含凭据。
• 找不到索引：先创建 vector index；名称必须与 vector_index_name 一致。
• 维度不匹配：确保 embedding 模型维度与 dimensions 对齐。

更多示例

基本初始化

from crewai_tools import MongoDBVectorSearchTool

tool = MongoDBVectorSearchTool(
    database_name="example_database",
    collection_name="example_collection",
    connection_string="<your_mongodb_connection_string>",
)

自定义查询配置

from crewai_tools import MongoDBVectorSearchConfig, MongoDBVectorSearchTool

query_config = MongoDBVectorSearchConfig(limit=10, oversampling_factor=2)
tool = MongoDBVectorSearchTool(
    database_name="example_database",
    collection_name="example_collection",
    connection_string="<your_mongodb_connection_string>",
    query_config=query_config,
    vector_index_name="my_vector_index",
)

rag_agent = Agent(
    name="rag_agent",
    role="You are a helpful assistant that can answer questions with the help of the MongoDBVectorSearchTool.",
    goal="...",
    backstory="...",
    tools=[tool],
)

预加载数据库并创建索引

import os
from crewai_tools import MongoDBVectorSearchTool

tool = MongoDBVectorSearchTool(
    database_name="example_database",
    collection_name="example_collection",
    connection_string="<your_mongodb_connection_string>",
)

# Load text content from a local folder and add to MongoDB
texts = []
for fname in os.listdir("knowledge"):
    path = os.path.join("knowledge", fname)
    if os.path.isfile(path):
        with open(path, "r", encoding="utf-8") as f:
            texts.append(f.read())

tool.add_texts(texts)

# Create the Atlas Vector Search index (e.g., 3072 dims for text-embedding-3-large)
tool.create_vector_search_index(dimensions=3072)

示例

from crewai import Agent, Task, Crew
from crewai_tools import MongoDBVectorSearchTool

tool = MongoDBVectorSearchTool(
    connection_string="mongodb+srv://...",
    database_name="mydb",
    collection_name="docs",
)

agent = Agent(
    role="RAG Agent",
    goal="Answer using MongoDB vector search",
    backstory="Knowledge retrieval specialist",
    tools=[tool],
    verbose=True,
)

task = Task(
    description="Find relevant content for 'indexing guidance'",
    expected_output="A concise answer citing the most relevant matches",
    agent=agent,
)

crew = Crew(
    agents=[agent],
    tasks=[task],
    verbose=True,
)

result = crew.kickoff()