",
index_name="test-elser",
strategy=SparseVectorStrategy(model_id=".elser_model_2"),
)
db.client.indices.refresh(index="test-elser")
results = db.similarity_search(
"What did the president say about Ketanji Brown Jackson", k=4
)
print(results[0])
```
### DenseVectorScriptScoreStrategy
此策略使用 Elasticsearch 的脚本评分查询来执行精确向量检索（也称为暴力搜索）以获取前 k 个结果。（此策略在 0.2.0 版本之前称为 `ExactRetrievalStrategy`。）
要使用此功能，请在 `ElasticsearchStore` 构造函数中指定 `DenseVectorScriptScoreStrategy`。
```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from langchain_elasticsearch import SparseVectorStrategy
db = ElasticsearchStore.from_documents(
docs,
embeddings,
es_url="http://localhost:9200",
index_name="test",
strategy=DenseVectorScriptScoreStrategy(),
)
```
### BM25Strategy
最后，您可以使用全文关键词搜索。
要使用此功能，请在 `ElasticsearchStore` 构造函数中指定 `BM25Strategy`。
```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from langchain_elasticsearch import BM25Strategy
db = ElasticsearchStore.from_documents(
docs,
es_url="http://localhost:9200",
index_name="test",
strategy=BM25Strategy(),
)
```
### BM25RetrievalStrategy
此策略允许用户执行纯 BM25 搜索，无需向量搜索。
要使用此功能，请在 `ElasticsearchStore` 构造函数中指定 `BM25RetrievalStrategy`。
请注意，在下例中，未指定嵌入选项，表示搜索是在不使用嵌入的情况下进行的。
```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from langchain_elasticsearch import ElasticsearchStore
db = ElasticsearchStore(
es_url="http://localhost:9200",
index_name="test_index",
strategy=ElasticsearchStore.BM25RetrievalStrategy(),
)
db.add_texts(
["foo", "foo bar", "foo bar baz", "bar", "bar baz", "baz"],
)
results = db.similarity_search(query="foo", k=10)
print(results)
```
## 自定义查询
通过搜索时的 `custom_query` 参数，您可以调整用于从 Elasticsearch 检索文档的查询。如果您想使用更复杂的查询以支持字段的线性提升，这很有用。
```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
# Example of a custom query thats just doing a BM25 search on the text field.
def custom_query(query_body: dict, query: str):
"""Custom query to be used in Elasticsearch.
Args:
query_body (dict): Elasticsearch query body.
query (str): Query string.
Returns:
dict: Elasticsearch query body.
"""
print("Query Retriever created by the retrieval strategy:")
print(query_body)
print()
new_query_body = {"query": {"match": {"text": query}}}
print("Query thats actually used in Elasticsearch:")
print(new_query_body)
print()
return new_query_body
results = db.similarity_search(
"What did the president say about Ketanji Brown Jackson",
k=4,
custom_query=custom_query,
)
print("Results:")
print(results[0])
```
## 自定义文档构建器
通过搜索时的 `doc_builder` 参数，您可以调整如何使用从 Elasticsearch 检索的数据构建文档。如果您有不是使用 LangChain 创建的索引，这特别有用。
```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from typing import Dict
from langchain_core.documents import Document
def custom_document_builder(hit: Dict) -> Document:
src = hit.get("_source", {})
return Document(
page_content=src.get("content", "Missing content!"),
metadata={
"page_number": src.get("page_number", -1),
"original_filename": src.get("original_filename", "Missing filename!"),
},
)
results = db.similarity_search(
"What did the president say about Ketanji Brown Jackson",
k=4,
doc_builder=custom_document_builder,
)
print("Results:")
print(results[0])
```
## 检索增强生成 (RAG) 用法
关于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 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)
# 常见问题解答
## 问题：在向 Elasticsearch 索引文档时我收到超时错误。我该如何修复？
一个可能的问题是您的文档可能需要更长时间才能索引到 Elasticsearch 中。ElasticsearchStore 使用 Elasticsearch bulk API，其中有一些默认值可以调整以减少超时错误的几率。
当您使用 SparseVectorRetrievalStrategy 时，这也是一个好主意。
默认值是：
* `chunk_size`: 500
* `max_chunk_bytes`: 100MB
要调整这些，您可以将 `chunk_size` 和 `max_chunk_bytes` 参数传递给 ElasticsearchStore `add_texts` 方法。
```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
vector_store.add_texts(
texts,
bulk_kwargs={
"chunk_size": 50,
"max_chunk_bytes": 200000000
}
)
```
# 升级到 ElasticsearchStore
如果您已经在基于 langchain 的项目中使用 Elasticsearch，您可能正在使用旧的实现：`ElasticVectorSearch` 和 `ElasticKNNSearch`，它们现已弃用。我们引入了一个新的实现 `ElasticsearchStore`，它更灵活且易于使用。本笔记本将指导您完成升级到新实现的过程。
## 新功能？
新的实现现在是一个名为 `ElasticsearchStore` 的类，可以通过策略用于近似密集向量、精确密集向量、稀疏向量 (ELSER)、BM25 检索和混合检索。
## 我正在使用 ElasticKNNSearch
旧实现：
```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from langchain_community.vectorstores.elastic_vector_search import ElasticKNNSearch
db = ElasticKNNSearch(
elasticsearch_url="http://localhost:9200",
index_name="test_index",
embedding=embedding
)
```
新实现：
```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from langchain_elasticsearch import ElasticsearchStore, DenseVectorStrategy
db = ElasticsearchStore(
es_url="http://localhost:9200",
index_name="test_index",
embedding=embedding,
# if you use the model_id
# strategy=DenseVectorStrategy(model_id="test_model")
# if you use hybrid search
# strategy=DenseVectorStrategy(hybrid=True)
)
```
## 我正在使用 ElasticVectorSearch
旧实现：
```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from langchain_community.vectorstores.elastic_vector_search import ElasticVectorSearch
db = ElasticVectorSearch(
elasticsearch_url="http://localhost:9200",
index_name="test_index",
embedding=embedding
)
```
新实现：
```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from langchain_elasticsearch import ElasticsearchStore, DenseVectorScriptScoreStrategy
db = ElasticsearchStore(
es_url="http://localhost:9200",
index_name="test_index",
embedding=embedding,
strategy=DenseVectorScriptScoreStrategy()
)
```
```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
db.client.indices.delete(
index="test-metadata, test-elser, test-basic",
ignore_unavailable=True,
allow_no_indices=True,
)
```
***
## API 参考
有关所有 `ElasticSearchStore` 功能和配置的详细文档，请前往 [API 参考](https://reference.langchain.com/python/langchain-elasticsearch/vectorstores/ElasticsearchStore)
***
[Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/i18n\zh-CN\oss\python\integrations\vectorstores\elasticsearch.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.