Skip to main content
Open In ColabOpen on GitHub

Elasticsearch

Elasticsearch 是一个分布式的、RESTful 风格的搜索和分析引擎,能够执行向量和词汇搜索。它构建在 Apache Lucene 库之上。

本笔记本展示了如何使用与Elasticsearch向量存储相关的功能。

设置

为了使用Elasticsearch向量搜索,您必须安装langchain-elasticsearch包。

%pip install -qU langchain-elasticsearch

凭证

有两种主要方式可以设置一个Elasticsearch实例以供使用:

  1. Elastic Cloud: Elastic Cloud 是一个托管的 Elasticsearch 服务。注册免费试用

要连接到不需要登录凭据的Elasticsearch实例(启动启用了安全性的docker实例),请将Elasticsearch URL和索引名称以及嵌入对象传递给构造函数。

  1. 本地安装 Elasticsearch:通过在本地运行 Elasticsearch 来开始使用。最简单的方法是使用官方的 Elasticsearch Docker 镜像。有关更多信息,请参阅 Elasticsearch Docker 文档

通过 Docker 运行 Elasticsearch

示例:运行一个禁用安全性的单节点Elasticsearch实例。不建议在生产环境中使用。

%docker run -p 9200:9200 -e "discovery.type=single-node" -e "xpack.security.enabled=false" -e "xpack.security.http.ssl.enabled=false" docker.elastic.co/elasticsearch/elasticsearch:8.12.1

使用认证运行

对于生产环境,我们建议您在启用安全性的情况下运行。要使用登录凭据连接,您可以使用参数 es_api_keyes_useres_password

pip install -qU langchain-openai
import getpass
import os

if not os.environ.get("OPENAI_API_KEY"):
os.environ["OPENAI_API_KEY"] = getpass.getpass("Enter API key for OpenAI: ")

from langchain_openai import OpenAIEmbeddings

embeddings = OpenAIEmbeddings(model="text-embedding-3-large")
from langchain_elasticsearch import ElasticsearchStore

elastic_vector_search = ElasticsearchStore(
es_url="http://localhost:9200",
index_name="langchain_index",
embedding=embeddings,
es_user="elastic",
es_password="changeme",
)
API Reference:ElasticsearchStore

如何获取默认“elastic”用户的密码?

获取默认“elastic”用户的Elastic Cloud密码:

  1. 登录Elastic Cloud控制台,网址为 https://cloud.elastic.co
  2. 转到“安全” > “用户”
  3. 找到 "elastic" 用户并点击 "编辑"
  4. 点击“重置密码”
  5. 按照提示重置密码

如何获取API密钥?

获取API密钥:

  1. 登录Elastic Cloud控制台,网址为 https://cloud.elastic.co
  2. 打开 Kibana 并转到 堆栈管理 > API 密钥
  3. 点击“创建API密钥”
  4. 输入API密钥的名称并点击“创建”
  5. 复制API密钥并将其粘贴到api_key参数中

Elastic 云

要连接到Elastic Cloud上的Elasticsearch实例,您可以使用es_cloud_id参数或es_url

elastic_vector_search = ElasticsearchStore(
es_cloud_id="<cloud_id>",
index_name="test_index",
embedding=embeddings,
es_user="elastic",
es_password="changeme",
)

如果你想获得最佳的模型调用自动追踪功能,你也可以通过取消下面的注释来设置你的LangSmith API密钥:

# os.environ["LANGSMITH_API_KEY"] = getpass.getpass("Enter your LangSmith API key: ")
# os.environ["LANGSMITH_TRACING"] = "true"

初始化

Elasticsearch 正在本地运行在 localhost:9200 上,使用 docker。有关如何从 Elastic Cloud 连接到 Elasticsearch 的更多详细信息,请参阅上面的 使用身份验证连接

from langchain_elasticsearch import ElasticsearchStore

vector_store = ElasticsearchStore(
"langchain-demo", embedding=embeddings, es_url="http://localhost:9201"
)
API Reference:ElasticsearchStore

管理向量存储

添加项目到向量存储

from uuid import uuid4

from langchain_core.documents import Document

document_1 = Document(
page_content="I had chocalate chip pancakes and scrambled eggs for breakfast this morning.",
metadata={"source": "tweet"},
)

document_2 = Document(
page_content="The weather forecast for tomorrow is cloudy and overcast, with a high of 62 degrees.",
metadata={"source": "news"},
)

document_3 = Document(
page_content="Building an exciting new project with LangChain - come check it out!",
metadata={"source": "tweet"},
)

document_4 = Document(
page_content="Robbers broke into the city bank and stole $1 million in cash.",
metadata={"source": "news"},
)

document_5 = Document(
page_content="Wow! That was an amazing movie. I can't wait to see it again.",
metadata={"source": "tweet"},
)

document_6 = Document(
page_content="Is the new iPhone worth the price? Read this review to find out.",
metadata={"source": "website"},
)

document_7 = Document(
page_content="The top 10 soccer players in the world right now.",
metadata={"source": "website"},
)

document_8 = Document(
page_content="LangGraph is the best framework for building stateful, agentic applications!",
metadata={"source": "tweet"},
)

document_9 = Document(
page_content="The stock market is down 500 points today due to fears of a recession.",
metadata={"source": "news"},
)

document_10 = Document(
page_content="I have a bad feeling I am going to get deleted :(",
metadata={"source": "tweet"},
)

documents = [
document_1,
document_2,
document_3,
document_4,
document_5,
document_6,
document_7,
document_8,
document_9,
document_10,
]
uuids = [str(uuid4()) for _ in range(len(documents))]

vector_store.add_documents(documents=documents, ids=uuids)
API Reference:Document
['21cca03c-9089-42d2-b41c-3d156be2b519',
'a6ceb967-b552-4802-bb06-c0e95fce386e',
'3a35fac4-e5f0-493b-bee0-9143b41aedae',
'176da099-66b1-4d6a-811b-dfdfe0808d30',
'ecfa1a30-3c97-408b-80c0-5c43d68bf5ff',
'c0f08baa-e70b-4f83-b387-c6e0a0f36f73',
'489b2c9c-1925-43e1-bcf0-0fa94cf1cbc4',
'408c6503-9ba4-49fd-b1cc-95584cd914c5',
'5248c899-16d5-4377-a9e9-736ca443ad4f',
'ca182769-c4fc-4e25-8f0a-8dd0a525955c']

从向量存储中删除项目

vector_store.delete(ids=[uuids[-1]])
True

查询向量存储

一旦您的向量存储被创建并且相关文档已被添加,您很可能希望在链或代理运行期间查询它。这些示例还展示了在搜索时如何使用过滤。

直接查询

执行一个简单的相似性搜索并过滤元数据可以如下进行:

results = vector_store.similarity_search(
query="LangChain provides abstractions to make working with LLMs easy",
k=2,
filter=[{"term": {"metadata.source.keyword": "tweet"}}],
)
for res in results:
print(f"* {res.page_content} [{res.metadata}]")
* Building an exciting new project with LangChain - come check it out! [{'source': 'tweet'}]
* LangGraph is the best framework for building stateful, agentic applications! [{'source': 'tweet'}]

带分数的相似性搜索

如果你想执行相似性搜索并接收相应的分数,你可以运行:

results = vector_store.similarity_search_with_score(
query="Will it be hot tomorrow",
k=1,
filter=[{"term": {"metadata.source.keyword": "news"}}],
)
for doc, score in results:
print(f"* [SIM={score:3f}] {doc.page_content} [{doc.metadata}]")
* [SIM=0.765887] The weather forecast for tomorrow is cloudy and overcast, with a high of 62 degrees. [{'source': 'news'}]

通过转换为检索器进行查询

你也可以将向量存储转换为检索器,以便在你的链中更轻松地使用。

retriever = vector_store.as_retriever(
search_type="similarity_score_threshold", search_kwargs={"score_threshold": 0.2}
)
retriever.invoke("Stealing from the bank is a crime")
[Document(metadata={'source': 'news'}, page_content='Robbers broke into the city bank and stole $1 million in cash.'),
Document(metadata={'source': 'news'}, page_content='The stock market is down 500 points today due to fears of a recession.'),
Document(metadata={'source': 'website'}, page_content='Is the new iPhone worth the price? Read this review to find out.'),
Document(metadata={'source': 'tweet'}, page_content='Building an exciting new project with LangChain - come check it out!')]

检索增强生成的使用

有关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:

常见问题解答

问题:在将文档索引到Elasticsearch时,我遇到了超时错误。我该如何解决这个问题?

一个可能的问题是,您的文档可能需要更长的时间才能索引到Elasticsearch中。ElasticsearchStore使用了Elasticsearch的批量API,该API有一些默认设置,您可以调整这些设置以减少超时错误的发生。

当您使用SparseVectorRetrievalStrategy时,这也是一个好主意。

默认值为:

  • chunk_size: 500
  • max_chunk_bytes: 100MB

要调整这些,你可以将chunk_sizemax_chunk_bytes参数传递给ElasticsearchStore的add_texts方法。

    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:ElasticVectorSearchElasticKNNSearch,这些实现现在已被弃用。我们引入了一个名为ElasticsearchStore的新实现,它更加灵活且易于使用。本笔记本将指导您完成升级到新实现的过程。

有什么新内容?

新的实现现在是一个名为ElasticsearchStore的类,它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:


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:


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:


from langchain_community.vectorstores.elastic_vector_search import ElasticVectorSearch

db = ElasticVectorSearch(
elasticsearch_url="http://localhost:9200",
index_name="test_index",
embedding=embedding
)

API Reference:ElasticVectorSearch

新实现:


from langchain_elasticsearch import ElasticsearchStore, DenseVectorScriptScoreStrategy

db = ElasticsearchStore(
es_url="http://localhost:9200",
index_name="test_index",
embedding=embedding,
strategy=DenseVectorScriptScoreStrategy()
)

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,请访问API参考:https://python.langchain.com/api_reference/elasticsearch/vectorstores/langchain_elasticsearch.vectorstores.ElasticsearchStore.html


这个页面有帮助吗?