> ## Documentation Index > Fetch the complete documentation index at: https://langchain-zh.cn/llms.txt > Use this file to discover all available pages before exploring further. # MongoDB Atlas 集成 > 使用 LangChain Python 与 MongoDB Atlas 向量存储进行集成。 本笔记本介绍如何使用 `langchain-mongodb` 包在 LangChain 中进行 MongoDB Atlas 向量搜索。 > [MongoDB Atlas](https://www.mongodb.com/docs/atlas/) 是一个完全托管的云端数据库，可在 AWS、Azure 和 GCP 上使用。它支持原生向量搜索、全文搜索（BM25）以及 MongoDB 文档数据上的混合搜索。 > [MongoDB Atlas Vector Search](https://www.mongodb.com/products/platform/atlas-vector-search) 允许将嵌入存储在 MongoDB 文档中，创建向量搜索索引，并使用近似最近邻算法（`Hierarchical Navigable Small Worlds`）执行 KNN 搜索。它使用 [\$vectorSearch MQL Stage](https://www.mongodb.com/docs/atlas/atlas-vector-search/vector-search-overview/)。 ## 设置 > \*运行 MongoDB 版本 6.0.11、7.0.2 或更高版本（包括 RC 版）的 Atlas 集群。 要使用 MongoDB Atlas，您必须先部署一个集群。我们提供在您选择的云上的永久免费集群层级。要开始使用，请访问此处：[快速开始](https://www.mongodb.com/docs/atlas/getting-started/)。 您需要安装 `langchain-mongodb` 和 `pymongo` 才能使用此集成。 ```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} pip install -qU langchain-mongodb pymongo ``` ### 凭据 对于此笔记本，您需要找到 MongoDB 集群 URI。 有关查找集群 URI 的信息，请阅读 [此指南](https://www.mongodb.com/docs/manual/reference/connection-string/)。 ```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} import getpass MONGODB_ATLAS_CLUSTER_URI = getpass.getpass("MongoDB Atlas Cluster URI:") ``` 如果您希望获得模型调用的最佳类自动化跟踪，也可以通过取消注释以下内容来设置您的 [LangSmith](/langsmith/home) API 密钥： ```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} os.environ["LANGSMITH_API_KEY"] = getpass.getpass("Enter your LangSmith API key: ") os.environ["LANGSMITH_TRACING"] = "true" ``` ## 初始化 ```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} # | output: false # | echo: false from langchain_openai import OpenAIEmbeddings embeddings = OpenAIEmbeddings() ``` ```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} from langchain_mongodb import MongoDBAtlasVectorSearch from pymongo import MongoClient # initialize MongoDB python client client = MongoClient(MONGODB_ATLAS_CLUSTER_URI) DB_NAME = "langchain_test_db" COLLECTION_NAME = "langchain_test_vectorstores" ATLAS_VECTOR_SEARCH_INDEX_NAME = "langchain-test-index-vectorstores" MONGODB_COLLECTION = client[DB_NAME][COLLECTION_NAME] vector_store = MongoDBAtlasVectorSearch( collection=MONGODB_COLLECTION, embedding=embeddings, index_name=ATLAS_VECTOR_SEARCH_INDEX_NAME, relevance_score_fn="cosine", ) # Create vector search index on the collection # Since we are using the default OpenAI embedding model (ada-v2) we need to specify the dimensions as 1536 vector_store.create_vector_search_index(dimensions=1536) ``` \[可选] 作为上述 `vector_store.create_vector_search_index` 命令的替代方案，您也可以使用以下索引定义通过 Atlas UI 创建向量搜索索引： ```json theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} { "fields":[ { "type": "vector", "path": "embedding", "numDimensions": 1536, "similarity": "cosine" } ] } ``` ## 管理向量存储 创建向量存储后，我们可以通过添加和删除不同项目与其交互。 ### 向向量存储添加项目 我们可以使用 `add_documents` 函数向向量存储添加项目。 ```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} from uuid import uuid4 from langchain_core.documents import Document document_1 = Document( page_content="I had chocolate chip pancakes and scrambled eggs for breakfast this morning.", metadata={"source": "tweet"}, ) document_2 = Document( page_content="The weather forecast for tomorrow is cloudy and overcast, with a high of 62 degrees.", metadata={"source": "news"}, ) document_3 = Document( page_content="Building an exciting new project with LangChain - come check it out!", metadata={"source": "tweet"}, ) document_4 = Document( page_content="Robbers broke into the city bank and stole $1 million in cash.", metadata={"source": "news"}, ) document_5 = Document( page_content="Wow! That was an amazing movie. I can't wait to see it again.", metadata={"source": "tweet"}, ) document_6 = Document( page_content="Is the new iPhone worth the price? Read this review to find out.", metadata={"source": "website"}, ) document_7 = Document( page_content="The top 10 soccer players in the world right now.", metadata={"source": "website"}, ) document_8 = Document( page_content="LangGraph is the best framework for building stateful, agentic applications!", metadata={"source": "tweet"}, ) document_9 = Document( page_content="The stock market is down 500 points today due to fears of a recession.", metadata={"source": "news"}, ) document_10 = Document( page_content="I have a bad feeling I am going to get deleted :(", metadata={"source": "tweet"}, ) documents = [ document_1, document_2, document_3, document_4, document_5, document_6, document_7, document_8, document_9, document_10, ] uuids = [str(uuid4()) for _ in range(len(documents))] vector_store.add_documents(documents=documents, ids=uuids) ``` ```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} ['03ad81e8-32a0-46f0-b7d8-f5b977a6b52a', '8396a68d-f4a3-4176-a581-a1a8c303eea4', 'e7d95150-67f6-499f-b611-84367c50fa60', '8c31b84e-2636-48b6-8b99-9fccb47f7051', 'aa02e8a2-a811-446a-9785-8cea0faba7a9', '19bd72ff-9766-4c3b-b1fd-195c732c562b', '642d6f2f-3e34-4efa-a1ed-c4ba4ef0da8d', '7614bb54-4eb5-4b3b-990c-00e35cb31f99', '69e18c67-bf1b-43e5-8a6e-64fb3f240e52', '30d599a7-4a1a-47a9-bbf8-6ed393e2e33c'] ``` ### 从向量存储删除项目 ```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} vector_store.delete(ids=[uuids[-1]]) ``` ```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} True ``` ## 查询向量存储 一旦创建了向量存储并添加了相关文档，您很可能希望在运行链或代理期间对其进行查询。 ### 直接查询 #### 相似性搜索 执行简单的相似性搜索可以如下所示： ```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} results = vector_store.similarity_search( "LangChain provides abstractions to make working with LLMs easy", k=2 ) for res in results: print(f"* {res.page_content} [{res.metadata}]") ``` ```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} * Building an exciting new project with LangChain - come check it out! [{'_id': 'e7d95150-67f6-499f-b611-84367c50fa60', 'source': 'tweet'}] * LangGraph is the best framework for building stateful, agentic applications! [{'_id': '7614bb54-4eb5-4b3b-990c-00e35cb31f99', 'source': 'tweet'}] ``` #### 带分数的相似性搜索 您也可以带分数进行搜索： ```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} results = vector_store.similarity_search_with_score("Will it be hot tomorrow?", k=1) for res, score in results: print(f"* [SIM={score:3f}] {res.page_content} [{res.metadata}]") ``` ```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} * [SIM=0.784560] The weather forecast for tomorrow is cloudy and overcast, with a high of 62 degrees. [{'_id': '8396a68d-f4a3-4176-a581-a1a8c303eea4', 'source': 'news'}] ``` ### 使用相似性搜索进行预过滤 Atlas Vector Search 支持使用 MQL 运算符进行过滤的预过滤。下面是上面加载的相同数据和查询的一个示例索引，允许您对 "page" 字段进行元数据过滤。您可以更新现有索引以包含定义的过滤器，并对向量搜索进行预过滤。 要启用预过滤，需要更新索引定义以包含过滤器字段。在此示例中，我们将使用 `source` 字段作为过滤器字段。 这可以使用 `MongoDBAtlasVectorSearch.create_vector_search_index` 方法以编程方式完成。 ```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} vectorstore.create_vector_search_index( dimensions=1536, filters=[{"type":"filter", "path":"source"}], update=True ) ``` 或者，您也可以使用以下索引定义通过 Atlas UI 更新索引： ```json theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} { "fields":[ { "type": "vector", "path": "embedding", "numDimensions": 1536, "similarity": "cosine" }, { "type": "filter", "path": "source" } ] } ``` 然后您可以按如下方式运行带有过滤器的查询： ```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} results = vector_store.similarity_search(query="foo", k=1, pre_filter={"source": {"$eq": "https://example.com"}}) for doc in results: print(f"* {doc.page_content} [{doc.metadata}]") ``` #### 其他搜索方法 本笔记本未涵盖各种其他搜索方法，例如 MMR 搜索或通过向量搜索。有关 `MongoDBAtlasVectorStore` 可用的搜索能力的完整列表，请查看 [API 参考](https://reference.langchain.com/python/langchain-mongodb/vectorstores/MongoDBAtlasVectorSearch)。 ### 转换为检索器进行查询 您还可以将向量存储转换为检索器，以便在链中更轻松地使用。 以下是如何将向量存储转换为检索器，然后使用简单查询和过滤器调用检索器。 ```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} retriever = vector_store.as_retriever( search_type="similarity_score_threshold", search_kwargs={"k": 1, "score_threshold": 0.2}, ) retriever.invoke("Stealing from the bank is a crime") ``` ```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} [Document(metadata={'_id': '8c31b84e-2636-48b6-8b99-9fccb47f7051', 'source': 'news'}, page_content='Robbers broke into the city bank and stole $1 million in cash.')] ``` ## 用于检索增强生成的用法 有关如何使用此向量存储进行检索增强生成 (RAG) 的指南，请参阅以下部分： * [教程](/oss/python/langchain/rag) * [操作指南：使用 RAG 进行问答](https://python.langchain.com/docs/how_to/#qa-with-rag) * [检索概念文档](https://python.langchain.com/docs/concepts/retrieval) # 其他说明 > * 更多文档可在 [MongoDB 的 LangChain 文档](https://www.mongodb.com/docs/atlas/atlas-vector-search/ai-integrations/langchain/) 站点找到 > * 此功能已正式发布，可用于生产部署。 > * langchain 版本 0.0.305 ([发布说明](https://github.com/langchain-ai/langchain/releases/tag/v0.0.305)) 引入了对 \$vectorSearch MQL stage 的支持，该功能在 MongoDB Atlas 6.0.11 和 7.0.2 上可用。使用早期版本 MongoDB Atlas 的用户需要将 LangChain 版本锁定为 \<=0.0.304 *** ## API 参考 有关所有 `MongoDBAtlasVectorSearch` 功能和配置的详细文档，请前往 [API 参考](https://reference.langchain.com/python/langchain-mongodb)。 ***
[Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/i18n\zh-CN\oss\python\integrations\vectorstores\mongodb_atlas.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose). [Connect these docs](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers.