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

# Elasticsearch 集成

> 集成Elasticsearch嵌入模型，使用LangChain Python。

使用 Elasticsearch 中的托管嵌入模型生成嵌入的步骤说明

实例化 `ElasticsearchEmbeddings` 类最简单的方法是

* 如果您使用 Elastic Cloud，则使用 `from_credentials` 构造函数
* 或者使用 `from_es_connection` 构造函数与任何 Elasticsearch 集群

```python theme={null}
!pip -q install langchain-elasticsearch
```

```python theme={null}
from langchain_elasticsearch import ElasticsearchEmbeddings
```

```python theme={null}
# Define the model ID
model_id = "your_model_id"
```

## 使用 `from_credentials` 进行测试

这需要一个 Elastic Cloud `cloud_id`

```python theme={null}
# Instantiate ElasticsearchEmbeddings using credentials
embeddings = ElasticsearchEmbeddings.from_credentials(
    model_id,
    es_cloud_id="your_cloud_id",
    es_user="your_user",
    es_password="your_password",
)
```

```python theme={null}
# Create embeddings for multiple documents
documents = [
    "This is an example document.",
    "Another example document to generate embeddings for.",
]
document_embeddings = embeddings.embed_documents(documents)
```

```python theme={null}
# Print document embeddings
for i, embedding in enumerate(document_embeddings):
    print(f"Embedding for document {i + 1}: {embedding}")
```

```python theme={null}
# Create an embedding for a single query
query = "This is a single query."
query_embedding = embeddings.embed_query(query)
```

```python theme={null}
# Print query embedding
print(f"Embedding for query: {query_embedding}")
```

## 使用现有的 Elasticsearch 客户端连接进行测试

这可以用于任何 Elasticsearch 部署

```python theme={null}
# Create Elasticsearch connection
from elasticsearch import Elasticsearch

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

```python theme={null}
# Instantiate ElasticsearchEmbeddings using es_connection
embeddings = ElasticsearchEmbeddings.from_es_connection(
    model_id,
    es_connection,
)
```

```python theme={null}
# Create embeddings for multiple documents
documents = [
    "This is an example document.",
    "Another example document to generate embeddings for.",
]
document_embeddings = embeddings.embed_documents(documents)
```

```python theme={null}
# Print document embeddings
for i, embedding in enumerate(document_embeddings):
    print(f"Embedding for document {i + 1}: {embedding}")
```

```python theme={null}
# Create an embedding for a single query
query = "This is a single query."
query_embedding = embeddings.embed_query(query)
```

```python theme={null}
# Print query embedding
print(f"Embedding for query: {query_embedding}")
```

***

> 官方原文：[src/oss/python/integrations/embeddings/elasticsearch.mdx](https://github.com/langchain-ai/docs/blob/main/src/oss/python/integrations/embeddings/elasticsearch.mdx) · 非官方翻译，译文由 AI 生成，以英文原文为准。


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.