> ## 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.

# Astra DB 集成

> 使用 LangChain Python 与 Astra DB 集成。

> [DataStax Astra DB](https://docs.datastax.com/en/astra-db-serverless/index.html) 是一个基于 `Apache Cassandra®` 构建的无服务器 AI 就绪数据库，并通过易于使用的 JSON API 方便地提供。

查看 [DataStax 提供的教程](https://docs.datastax.com/en/astra/astra-db-vector/tutorials/chatbot.html)。

## 安装和设置

安装以下 Python 包：

<CodeGroup>
  ```bash pip theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  pip install "langchain-astradb>=0.6,<0.7"
  ```

  ```bash uv theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  uv add langchain-astradb>=0.6,<0.7
  ```
</CodeGroup>

创建数据库（如果需要）并获取 [连接密钥](https://docs.datastax.com/en/astra-db-serverless/get-started/quickstart.html#create-a-database-and-store-your-credentials)。
设置以下变量：

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
ASTRA_DB_API_ENDPOINT="API_ENDPOINT"
ASTRA_DB_APPLICATION_TOKEN="TOKEN"
```

## 向量存储

此处展示了一些典型的初始化模式：

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

vector_store = AstraDBVectorStore(
    embedding=my_embedding,
    collection_name="my_store",
    api_endpoint=ASTRA_DB_API_ENDPOINT,
    token=ASTRA_DB_APPLICATION_TOKEN,
)


from astrapy.info import VectorServiceOptions

vector_store_vectorize = AstraDBVectorStore(
    collection_name="my_vectorize_store",
    api_endpoint=ASTRA_DB_API_ENDPOINT,
    token=ASTRA_DB_APPLICATION_TOKEN,
    collection_vector_service_options=VectorServiceOptions(
        provider="nvidia",
        model_name="NV-Embed-QA",
    ),
)


from astrapy.info import (
    CollectionLexicalOptions,
    CollectionRerankOptions,
    RerankServiceOptions,
    VectorServiceOptions,
)

vector_store_hybrid = AstraDBVectorStore(
    collection_name="my_hybrid_store",
    api_endpoint=ASTRA_DB_API_ENDPOINT,
    token=ASTRA_DB_APPLICATION_TOKEN,
    collection_vector_service_options=VectorServiceOptions(
        provider="nvidia",
        model_name="NV-Embed-QA",
    ),
    collection_lexical=CollectionLexicalOptions(analyzer="standard"),
    collection_rerank=CollectionRerankOptions(
        service=RerankServiceOptions(
            provider="nvidia",
            model_name="nvidia/llama-3.2-nv-rerankqa-1b-v2",
        ),
    ),
)
```

`AstraDBVectorStore` 类的显著功能：

* 原生异步 API；
* 搜索中的元数据过滤；
* MMR（最大边际相关性）搜索；
* 服务端嵌入计算（在 Astra DB 术语中称为 ["vectorize"](https://docs.datastax.com/en/astra-db-serverless/databases/embedding-generation.html)）；
* 从现有的、已预填充的 Astra DB 集合自动检测其设置；
* [混合搜索](https://docs.datastax.com/en/astra-db-serverless/databases/hybrid-search.html#the-hybrid-search-process)（向量 + BM25，然后是重排序步骤）；
* 支持非 Astra Data API（例如自托管的 [HCD](https://docs.datastax.com/en/hyper-converged-database/1.1/get-started/get-started-hcd.html) 部署）；

在 [示例笔记本](/oss/python/integrations/vectorstores/astradb) 中了解更多。

查看 [DataStax 提供的示例](https://docs.datastax.com/en/astra/astra-db-vector/integrations/langchain.html)。

## LLM 缓存

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

set_llm_cache(AstraDBCache(
    api_endpoint=ASTRA_DB_API_ENDPOINT,
    token=ASTRA_DB_APPLICATION_TOKEN,
))
```

## 语义 LLM 缓存

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

set_llm_cache(AstraDBSemanticCache(
    embedding=my_embedding,
    api_endpoint=ASTRA_DB_API_ENDPOINT,
    token=ASTRA_DB_APPLICATION_TOKEN,
))
```

## 文档加载器

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

loader = AstraDBLoader(
    collection_name="my_collection",
    api_endpoint=ASTRA_DB_API_ENDPOINT,
    token=ASTRA_DB_APPLICATION_TOKEN,
)
```

在 [示例笔记本](/oss/python/integrations/document_loaders/astradb) 中了解更多。

## 自查询检索器

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from langchain_astradb import AstraDBVectorStore
from langchain_classic.retrievers.self_query.base import SelfQueryRetriever

vector_store = AstraDBVectorStore(
    embedding=my_embedding,
    collection_name="my_store",
    api_endpoint=ASTRA_DB_API_ENDPOINT,
    token=ASTRA_DB_APPLICATION_TOKEN,
)

retriever = SelfQueryRetriever.from_llm(
    my_llm,
    vector_store,
    document_content_description,
    metadata_field_info
)
```

## 存储

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

store = AstraDBStore(
    collection_name="my_kv_store",
    api_endpoint=ASTRA_DB_API_ENDPOINT,
    token=ASTRA_DB_APPLICATION_TOKEN,
)
```

查看 [AstraDBStore](https://reference.langchain.com/python/langchain-astradb/storage/AstraDBStore) 的 API 参考。

## 字节存储

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

store = AstraDBByteStore(
    collection_name="my_kv_store",
    api_endpoint=ASTRA_DB_API_ENDPOINT,
    token=ASTRA_DB_APPLICATION_TOKEN,
)
```

查看 [AstraDBByteStore](https://reference.langchain.com/python/langchain-astradb/storage/AstraDBByteStore) 的 API 参考。

***

<div className="source-links">
  <Callout icon="edit">
    [Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/i18n\zh-CN\oss\python\integrations\providers\astradb.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).
  </Callout>

  <Callout icon="terminal-2">
    [Connect these docs](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers.
  </Callout>
</div>