> ## Documentation Index
> Fetch the complete documentation index at: https://nvd-54.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# MongoDB atlas 集成

> 使用 LangChain Python 与 MongoDB atlas 集成。

> [MongoDB Atlas](https://www.mongodb.com/docs/atlas/) is a fully-managed cloud
> database available in AWS, Azure, and GCP.  It now has support for native
> Vector Search on the MongoDB document data.

## 安装和设置

查看[详细配置说明](/oss/python/integrations/vectorstores/mongodb_atlas).

我们需要安装 `langchain-mongodb` Python 包.

<CodeGroup>
  ```bash pip theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  pip install langchain-mongodb
  ```

  ```bash uv theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  uv add langchain-mongodb
  ```
</CodeGroup>

## 向量存储

查看[使用示例](/oss/python/integrations/vectorstores/mongodb_atlas).

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from langchain_mongodb import MongoDBAtlasVectorSearch
```

## 检索器

### Full text search retriever

> `Hybrid Search Retriever` performs full-text searches using
> Lucene’s standard (`BM25`) analyzer.

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from langchain_mongodb.retrievers import MongoDBAtlasFullTextSearchRetriever
```

### Hybrid search retriever

> `Hybrid Search Retriever` combines vector and full-text searches weighting
> them the via `Reciprocal Rank Fusion` (`RRF`) algorithm.

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from langchain_mongodb.retrievers import MongoDBAtlasHybridSearchRetriever
```

## Model caches

### MongoDBCache

An abstraction to store a simple cache in MongoDB. This does not use Semantic Caching, nor does it require an index to be made on the collection before generation.

要导入此缓存：

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from langchain_mongodb.cache import MongoDBCache
```

要将此缓存与您的大语言模型一起使用：

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from langchain_core.globals import set_llm_cache

# use any embedding provider...
from tests.integration_tests.vectorstores.fake_embeddings import FakeEmbeddings

mongodb_atlas_uri = "<YOUR_CONNECTION_STRING>"
COLLECTION_NAME="<YOUR_CACHE_COLLECTION_NAME>"
DATABASE_NAME="<YOUR_DATABASE_NAME>"

set_llm_cache(MongoDBCache(
    connection_string=mongodb_atlas_uri,
    collection_name=COLLECTION_NAME,
    database_name=DATABASE_NAME,
))
```

### MongoDBAtlasSemanticCache

Semantic caching allows users to retrieve cached prompts based on semantic similarity between the user input and previously cached results. Under the hood it blends MongoDBAtlas as both a cache and a vectorstore.
The MongoDBAtlasSemanticCache inherits from `MongoDBAtlasVectorSearch` and needs an Atlas Vector Search Index defined to work. Please look at the [usage example](/oss/python/integrations/vectorstores/mongodb_atlas) on how to set up the index.

要导入此缓存：

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from langchain_mongodb.cache import MongoDBAtlasSemanticCache
```

要将此缓存与您的大语言模型一起使用：

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from langchain_core.globals import set_llm_cache

# use any embedding provider...
from tests.integration_tests.vectorstores.fake_embeddings import FakeEmbeddings

mongodb_atlas_uri = "<YOUR_CONNECTION_STRING>"
COLLECTION_NAME="<YOUR_CACHE_COLLECTION_NAME>"
DATABASE_NAME="<YOUR_DATABASE_NAME>"

set_llm_cache(MongoDBAtlasSemanticCache(
    embedding=FakeEmbeddings(),
    connection_string=mongodb_atlas_uri,
    collection_name=COLLECTION_NAME,
    database_name=DATABASE_NAME,
))
```

***

<div className="source-links">
  <Callout icon="terminal-2">
    [将这些文档连接](/use-these-docs) 到 Claude、VSCode 等工具，通过 MCP 获取实时答案。
  </Callout>

  <Callout icon="edit">
    [在 GitHub 上编辑此页面](https://github.com/langchain-ai/docs/edit/main/src/oss/python/integrations/providers/mongodb_atlas.mdx)或[提交 issue](https://github.com/langchain-ai/docs/issues/new/choose).
  </Callout>
</div>