> ## 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.

# Elasticsearch 集成

> 使用 LangChain Python 与 Elasticsearch 嵌入模型进行集成。

通过托管在 Elasticsearch 中的嵌入模型生成嵌入向量的操作指南

实例化 `ElasticsearchEmbeddings` 类最简单的方式是：

* 如果使用 Elastic Cloud，则使用 `from_credentials` 构造函数
* 或者使用 `from_es_connection` 构造函数连接任意 Elasticsearch 集群

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
!pip -q install langchain-elasticsearch
```

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

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
# 定义模型 ID
model_id = "your_model_id"
```

## 使用 `from_credentials` 进行测试

这需要 Elastic Cloud 的 `cloud_id`

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
# 使用凭据实例化 ElasticsearchEmbeddings
embeddings = ElasticsearchEmbeddings.from_credentials(
    model_id,
    es_cloud_id="your_cloud_id",
    es_user="your_user",
    es_password="your_password",
)
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
# 为多个文档创建嵌入向量
documents = [
    "这是一个示例文档。",
    "另一个用于生成嵌入向量的示例文档。",
]
document_embeddings = embeddings.embed_documents(documents)
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
# 打印文档嵌入向量
for i, embedding in enumerate(document_embeddings):
    print(f"文档 {i + 1} 的嵌入向量: {embedding}")
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
# 为单个查询创建嵌入向量
query = "这是一个单独的查询。"
query_embedding = embeddings.embed_query(query)
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
# 打印查询嵌入向量
print(f"查询的嵌入向量: {query_embedding}")
```

## 使用现有的 Elasticsearch 客户端连接进行测试

这可用于任何 Elasticsearch 部署

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
# 创建 Elasticsearch 连接
from elasticsearch import Elasticsearch

es_connection = Elasticsearch(
    hosts=["https://es_cluster_url:port"], basic_auth=("user", "password")
)
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
# 使用 es_connection 实例化 ElasticsearchEmbeddings
embeddings = ElasticsearchEmbeddings.from_es_connection(
    model_id,
    es_connection,
)
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
# 为多个文档创建嵌入向量
documents = [
    "这是一个示例文档。",
    "另一个用于生成嵌入向量的示例文档。",
]
document_embeddings = embeddings.embed_documents(documents)
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
# 打印文档嵌入向量
for i, embedding in enumerate(document_embeddings):
    print(f"文档 {i + 1} 的嵌入向量: {embedding}")
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
# 为单个查询创建嵌入向量
query = "这是一个单独的查询。"
query_embedding = embeddings.embed_query(query)
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
# 打印查询嵌入向量
print(f"查询的嵌入向量: {query_embedding}")
```

***

<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\embeddings\elasticsearch.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>