这是继上一篇文章 “Elasticsearch：使用 Open AI 和 Langchain 的 RAG - Retrieval Augmented Generation （一）” 的续篇。在这篇文章中，我主要来讲述 ElasticVectorSearch 的使用。

我们的设置和之前的那篇文章是一样的，只不过，在这里我们使用 ElasticVectorSearch 而不是 ElasticKnnSearch。

创建应用并展示

安装包

#!pip3 install langchain

导入包

from dotenv import load_dotenv
from langchain.embeddings import OpenAIEmbeddings
from langchain.vectorstores import ElasticKnnSearch
from langchain.text_splitter import CharacterTextSplitter
from urllib.request import urlopen
import os, jsonload_dotenv()openai_api_key=os.getenv('OPENAI_API_KEY')
elastic_user=os.getenv('ES_USER')
elastic_password=os.getenv('ES_PASSWORD')
elastic_endpoint=os.getenv("ES_ENDPOINT")
elastic_index_name='elastic-vector-search'

将文档分成段落

import json# Load data into a JSON object
with open('workplace-docs.json') as f:workplace_docs = json.load(f)print(f"Successfully loaded {len(workplace_docs)} documents")metadata = []
content = []for doc in workplace_docs:content.append(doc["content"])metadata.append({"name": doc["name"],"summary": doc["summary"],"rolePermissions":doc["rolePermissions"]})text_splitter = CharacterTextSplitter(chunk_size=100, chunk_overlap=0)
docs = text_splitter.create_documents(content, metadatas=metadata)

把数据写入到 Elasticsearch

embeddings = OpenAIEmbeddings(openai_api_key=openai_api_key)url = f"https://{elastic_user}:{elastic_password}@{elastic_endpoint}:9200"ssl_verify = {"verify_certs": True,"basic_auth": (elastic_user, elastic_password),"ca_certs": "./http_ca.crt"
}es = ElasticVectorSearch.from_documents( docs,embedding = embeddings, elasticsearch_url = url, index_name = elastic_index_name, ssl_verify = ssl_verify)

如上所示，ElasticVectorSearch 在未来的发布中将被移除。

运行完上面的代码后，我们可以到 Kibana 中进行查看：

展示结果

def showResults(output):print("Total results: ", len(output))for index in range(len(output)):print(output[index])

Similarity / Vector Search (KNN Search)

query = "work from home policy"
result = es.similarity_search(query=query)showResults(result)

我们上面实现的代码可以在地址  https://github.com/liu-xiao-guo/semantic_search_es/blob/main/ElasticVectorSearch.ipynb 进行下载。