Elasticsearch 集成 - AI 开发中文文档

Elasticsearch 是一个分布式、RESTful 搜索与分析引擎。它提供分布式、多租户支持的全文本搜索引擎，具有HTTP Web界面和 schema-free JSON文档。支持关键词搜索、向量搜索、混合搜索和复杂过滤。

The ElasticsearchRetriever 是一个通用包装器，通过 Query DSL 实现对所有 Elasticsearch 功能的灵活访问。对于大多数用例，其他类（ElasticsearchStore, ElasticsearchEmbeddings 等）已足够，但若需要可使用 ElasticsearchRetriever。本指南将帮助您入门 Elasticsearch retriever。如需了解所有 ElasticsearchRetriever 功能和配置的详细文档，请访问 API reference。

集成细节

配置

设置 Elasticsearch 实例主要有两种方式：

Elastic Cloud: Elastic Cloud 是托管型Elasticsearch服务。注册免费试用。若连接无需登录凭证的Elasticsearch实例（如安全启用的Docker实例），请将Elasticsearch URL、索引名称与嵌入对象一起传递给构造函数。
本地安装Elasticsearch: 通过运行本地Elasticsearch开始。最便捷的方式是使用官方Elasticsearch Docker镜像。更多详情请参考 Elasticsearch Docker文档。

若需启用单个查询的自动化追踪，可设置 LangSmith API密钥（取消注释下方代码）：

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

安装

本检索器位于 langchain-elasticsearch 包中。为演示目的，我们将同时安装 langchain-community 以生成文本 embeddings。

langchain-community包已不再维护。从langchain_community导入的示例可能过时或无法使用。请谨慎使用。

pip install -qU langchain-community langchain-elasticsearch

from typing import Any, Dict, Iterable

from elasticsearch import Elasticsearch
from elasticsearch.helpers import bulk
from langchain_community.embeddings import DeterministicFakeEmbedding
from langchain_core.documents import Document
from langchain.embeddings import Embeddings
from langchain_elasticsearch import ElasticsearchRetriever

配置

此处定义与Elasticsearch的连接。本例使用本地运行实例，也可注册 Elastic Cloud 并启动免费试用。

es_url = "http://localhost:9200"
es_client = Elasticsearch(hosts=[es_url])
es_client.info()

向量搜索示例使用随机嵌入进行演示。实际应用中请选择LangChain提供的 Embeddings 类。

embeddings = DeterministicFakeEmbedding(size=3)

定义示例数据

index_name = "test-langchain-retriever"
text_field = "text"
dense_vector_field = "fake_embedding"
num_characters_field = "num_characters"
texts = [
    "foo",
    "bar",
    "world",
    "hello world",
    "hello",
    "foo bar",
    "bla bla foo",
]

索引数据

通常用户会在已有Elasticsearch索引时使用 ElasticsearchRetriever。此处索引示例文本文档。若已通过 ElasticsearchStore.from_documents 创建索引也可使用。

def create_index(
    es_client: Elasticsearch,
    index_name: str,
    text_field: str,
    dense_vector_field: str,
    num_characters_field: str,
):
    es_client.indices.create(
        index=index_name,
        mappings={
            "properties": {
                text_field: {"type": "text"},
                dense_vector_field: {"type": "dense_vector"},
                num_characters_field: {"type": "integer"},
            }
        },
    )


def index_data(
    es_client: Elasticsearch,
    index_name: str,
    text_field: str,
    dense_vector_field: str,
    embeddings: Embeddings,
    texts: Iterable[str],
    refresh: bool = True,
) -> None:
    create_index(
        es_client, index_name, text_field, dense_vector_field, num_characters_field
    )

    vectors = embeddings.embed_documents(list(texts))
    requests = [
        {
            "_op_type": "index",
            "_index": index_name,
            "_id": i,
            text_field: text,
            dense_vector_field: vector,
            num_characters_field: len(text),
        }
        for i, (text, vector) in enumerate(zip(texts, vectors))
    ]

    bulk(es_client, requests)

    if refresh:
        es_client.indices.refresh(index=index_name)

    return len(requests)

index_data(es_client, index_name, text_field, dense_vector_field, embeddings, texts)

初始化

向量搜索

使用假嵌入进行密集向量检索。

def vector_query(search_query: str) -> Dict:
    vector = embeddings.embed_query(search_query)  # same embeddings as for indexing
    return {
        "knn": {
            "field": dense_vector_field,
            "query_vector": vector,
            "k": 5,
            "num_candidates": 10,
        }
    }


vector_retriever = ElasticsearchRetriever.from_es_params(
    index_name=index_name,
    body_func=vector_query,
    content_field=text_field,
    url=es_url,
)

vector_retriever.invoke("foo")

[Document(page_content='foo', metadata={'_index': 'test-langchain-index', '_id': '0', '_score': 1.0, '_source': {'fake_embedding': [-2.336764233933763, 0.27510289545940503, -0.7957597268194339], 'num_characters': 3}}),
 Document(page_content='world', metadata={'_index': 'test-langchain-index', '_id': '2', '_score': 0.6770179, '_source': {'fake_embedding': [-0.7041151202179595, -1.4652961969276497, -0.25786766898672847], 'num_characters': 5}}),
 Document(page_content='hello world', metadata={'_index': 'test-langchain-index', '_id': '3', '_score': 0.4816144, '_source': {'fake_embedding': [0.42728413221815387, -1.1889908285425348, -1.445433230084671], 'num_characters': 11}}),
 Document(page_content='hello', metadata={'_index': 'test-langchain-index', '_id': '4', '_score': 0.46853775, '_source': {'fake_embedding': [-0.28560441330564046, 0.9958894823084921, 1.5489829880195058], 'num_characters': 5}}),
 Document(page_content='foo bar', metadata={'_index': 'test-langchain-index', '_id': '5', '_score': 0.2086992, '_source': {'fake_embedding': [0.2533670476638539, 0.08100381646160418, 0.7763644080870179], 'num_characters': 7}})]

BM25

传统关键词匹配。

def bm25_query(search_query: str) -> Dict:
    return {
        "query": {
            "match": {
                text_field: search_query,
            },
        },
    }


bm25_retriever = ElasticsearchRetriever.from_es_params(
    index_name=index_name,
    body_func=bm25_query,
    content_field=text_field,
    url=es_url,
)

bm25_retriever.invoke("foo")

[Document(page_content='foo', metadata={'_index': 'test-langchain-index', '_id': '0', '_score': 0.9711467, '_source': {'fake_embedding': [-2.336764233933763, 0.27510289545940503, -0.7957597268194339], 'num_characters': 3}}),
 Document(page_content='foo bar', metadata={'_index': 'test-langchain-index', '_id': '5', '_score': 0.7437035, '_source': {'fake_embedding': [0.2533670476638539, 0.08100381646160418, 0.7763644080870179], 'num_characters': 7}}),
 Document(page_content='bla bla foo', metadata={'_index': 'test-langchain-index', '_id': '6', '_score': 0.6025789, '_source': {'fake_embedding': [1.7365927060137358, -0.5230400847844948, 0.7978339724186192], 'num_characters': 11}})]

混合搜索

通过 Reciprocal Rank Fusion（RRF）组合向量搜索与BM25搜索的结果集。

def hybrid_query(search_query: str) -> Dict:
    vector = embeddings.embed_query(search_query)  # same embeddings as for indexing
    return {
        "retriever": {
            "rrf": {
                "retrievers": [
                    {
                        "standard": {
                            "query": {
                                "match": {
                                    text_field: search_query,
                                }
                            }
                        }
                    },
                    {
                        "knn": {
                            "field": dense_vector_field,
                            "query_vector": vector,
                            "k": 5,
                            "num_candidates": 10,
                        }
                    },
                ]
            }
        }
    }


hybrid_retriever = ElasticsearchRetriever.from_es_params(
    index_name=index_name,
    body_func=hybrid_query,
    content_field=text_field,
    url=es_url,
)

hybrid_retriever.invoke("foo")

[Document(page_content='foo', metadata={'_index': 'test-langchain-index', '_id': '0', '_score': 0.9711467, '_source': {'fake_embedding': [-2.336764233933763, 0.27510289545940503, -0.7957597268194339], 'num_characters': 3}}),
 Document(page_content='foo bar', metadata={'_index': 'test-langchain-index', '_id': '5', '_score': 0.7437035, '_source': {'fake_embedding': [0.2533670476638539, 0.08100381646160418, 0.7763644080870179], 'num_characters': 7}}),
 Document(page_content='bla bla foo', metadata={'_index': 'test-langchain-index', '_id': '6', '_score': 0.6025789, '_source': {'fake_embedding': [1.7365927060137358, -0.5230400847844948, 0.7978339724186192], 'num_characters': 11}})]

模糊匹配

支持拼写错误的词匹配。

def fuzzy_query(search_query: str) -> Dict:
    return {
        "query": {
            "match": {
                text_field: {
                    "query": search_query,
                    "fuzziness": "AUTO",
                }
            },
        },
    }


fuzzy_retriever = ElasticsearchRetriever.from_es_params(
    index_name=index_name,
    body_func=fuzzy_query,
    content_field=text_field,
    url=es_url,
)

fuzzy_retriever.invoke("fox")  # note the character tolerance

[Document(page_content='foo', metadata={'_index': 'test-langchain-index', '_id': '0', '_score': 0.6474311, '_source': {'fake_embedding': [-2.336764233933763, 0.27510289545940503, -0.7957597268194339], 'num_characters': 3}}),
 Document(page_content='foo bar', metadata={'_index': 'test-langchain-index', '_id': '5', '_score': 0.49580228, '_source': {'fake_embedding': [0.2533670476638539, 0.08100381646160418, 0.7763644080870179], 'num_characters': 7}}),
 Document(page_content='bla bla foo', metadata={'_index': 'test-langchain-index', '_id': '6', '_score': 0.40171927, '_source': {'fake_embedding': [1.7365927060137358, -0.5230400847844948, 0.7978339724186192], 'num_characters': 11}})]

复杂过滤

组合不同字段的过滤条件。

def filter_query_func(search_query: str) -> Dict:
    return {
        "query": {
            "bool": {
                "must": [
                    {"range": {num_characters_field: {"gte": 5}}},
                ],
                "must_not": [
                    {"prefix": {text_field: "bla"}},
                ],
                "should": [
                    {"match": {text_field: search_query}},
                ],
            }
        }
    }


filtering_retriever = ElasticsearchRetriever.from_es_params(
    index_name=index_name,
    body_func=filter_query_func,
    content_field=text_field,
    url=es_url,
)

filtering_retriever.invoke("foo")

[Document(page_content='foo bar', metadata={'_index': 'test-langchain-index', '_id': '5', '_score': 1.7437035, '_source': {'fake_embedding': [0.2533670476638539, 0.08100381646160418, 0.7763644080870179], 'num_characters': 7}}),
 Document(page_content='world', metadata={'_index': 'test-langchain-index', '_id': '2', '_score': 1.0, '_source': {'fake_embedding': [-0.7041151202179595, -1.4652961969276497, -0.25786766898672847], 'num_characters': 5}}),
 Document(page_content='hello world', metadata={'_index': 'test-langchain-index', '_id': '3', '_score': 1.0, '_source': {'fake_embedding': [0.42728413221815387, -1.1889908285425348, -1.445433230084671], 'num_characters': 11}}),
 Document(page_content='hello', metadata={'_index': 'test-langchain-index', '_id': '4', '_score': 1.0, '_source': {'fake_embedding': [-0.28560441330564046, 0.9958894823084921, 1.5489829880195058], 'num_characters': 5}})]

注意查询匹配位于最上方。其他通过过滤条件筛选的文档也包含在结果集中，但它们得分相同。

自定义文档映射

可自定义将Elasticsearch结果（hit）转换为LangChain文档的函数。

def num_characters_mapper(hit: Dict[str, Any]) -> Document:
    num_chars = hit["_source"][num_characters_field]
    content = hit["_source"][text_field]
    return Document(
        page_content=f"This document has {num_chars} characters",
        metadata={"text_content": content},
    )


custom_mapped_retriever = ElasticsearchRetriever.from_es_params(
    index_name=index_name,
    body_func=filter_query_func,
    document_mapper=num_characters_mapper,
    url=es_url,
)

custom_mapped_retriever.invoke("foo")

[Document(page_content='This document has 7 characters', metadata={'text_content': 'foo bar'}),
 Document(page_content='This document has 5 characters', metadata={'text_content': 'world'}),
 Document(page_content='This document has 11 characters', metadata={'text_content': 'hello world'}),
 Document(page_content='This document has 5 characters', metadata={'text_content': 'hello'})]

使用

基于上述示例，使用 invoke 发起单次查询。

API参考

如需了解所有 ElasticsearchRetriever 功能和配置的详细文档，请访问 API reference。

官方原文：src/oss/python/integrations/retrievers/elasticsearch_retriever.mdx · 非官方翻译，译文由 AI 生成，以英文原文为准。

​集成细节

​配置

​安装

​配置

​定义示例数据

​索引数据

​初始化

​向量搜索

​BM25

​混合搜索

​模糊匹配

​复杂过滤

​自定义文档映射

​使用

​API参考

集成细节

配置

安装

配置

定义示例数据

索引数据

初始化

向量搜索

BM25

混合搜索

模糊匹配

复杂过滤

自定义文档映射

使用

API参考