",
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
This strategy uses Elasticsearch's script score query to perform exact vector retrieval (also known as brute force) to retrieve the top-k results. (This strategy was called `ExactRetrievalStrategy` prior to version 0.2.0.)
To use this, specify `DenseVectorScriptScoreStrategy` in `ElasticsearchStore` constructor.
```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
Finally, you can use full-text keyword search.
To use this, specify `BM25Strategy` in `ElasticsearchStore` constructor.
```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
This strategy allows the user to perform searches using pure BM25 without vector search.
To use this, specify `BM25RetrievalStrategy` in `ElasticsearchStore` constructor.
Note that in the example below, the embedding option is not specified, indicating that the search is conducted without using embeddings.
```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)
```
## Customise the query
With `custom_query` parameter at search, you are able to adjust the query that is used to retrieve documents from Elasticsearch. This is useful if you want to use a more complex query, to support linear boosting of fields.
```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
# Example of a custom query that's 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 that's 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])
```
## Customize the document builder
With `doc_builder` parameter at search, you are able to adjust how a Document is being built using data retrieved from Elasticsearch. This is especially useful if you have indices which were not created using LangChain.
```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])
```
## Usage for retrieval-augmented generation
For guides on how to use this vector store for retrieval-augmented generation (RAG), see the following sections:
* [Retrieval docs](/oss/python/langchain/retrieval)
* [Build a RAG app with LangChain](/oss/python/langchain/rag)
* [Agentic RAG](/oss/python/langgraph/agentic-rag)
# FAQ
## Question: Im getting timeout errors when indexing documents into Elasticsearch. how do I fix this?
One possible issue is your documents might take longer to index into Elasticsearch. ElasticsearchStore uses the Elasticsearch bulk API which has a few defaults that you can adjust to reduce the chance of timeout errors.
This is also a good idea when you're using SparseVectorRetrievalStrategy.
The defaults are:
* `chunk_size`: 500
* `max_chunk_bytes`: 100MB
To adjust these, you can pass in the `chunk_size` and `max_chunk_bytes` parameters to the ElasticsearchStore `add_texts` method.
```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
vector_store.add_texts(
texts,
bulk_kwargs={
"chunk_size": 50,
"max_chunk_bytes": 200000000
}
)
```
# Upgrading to ElasticsearchStore
If you're already using Elasticsearch in your langchain based project, you may be using the old implementations: `ElasticVectorSearch` and `ElasticKNNSearch` which are now deprecated. We've introduced a new implementation called `ElasticsearchStore` which is more flexible and easier to use. This notebook will guide you through the process of upgrading to the new implementation.
## What's new?
The new implementation is now one class called `ElasticsearchStore` which can be used for approximate dense vector, exact dense vector, sparse vector (ELSER), BM25 retrieval and hybrid retrieval, via strategies.
## I am using ElasticKNNSearch
```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)
)
```
## I am using ElasticVectorSearch
```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 reference
For detailed documentation of all `ElasticSearchStore` features and configurations head to the [API reference](https://reference.langchain.com/python/langchain-elasticsearch/vectorstores/ElasticsearchStore).
***
[Connect these docs](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers.
[Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/oss/python/integrations/vectorstores/elasticsearch.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).