目標(biāo)記錄

["你好，我的愛人","你好，我的愛妻","你好，我的病人","世界真美麗"]

搜索詞

愛人

預(yù)期返回

["你好，我的愛人","你好，我的愛妻"]

示例代碼：

代碼連接 es8以及bge-large-zh模型，

bge-large-zh用來(lái)將文本轉(zhuǎn)換為向量數(shù)據(jù)

es用來(lái)存儲(chǔ)向量數(shù)據(jù)，并根據(jù)向量來(lái)搜索相似度最高的文本(相似度可以用閾值調(diào)整)

from flask import Flask, request  # 導(dǎo)入Flask類
from FlagEmbedding import FlagModel
from elasticsearch import Elasticsearch
from elasticsearch.helpers import bulkapp = Flask(__name__)  # 實(shí)例化并命名為app實(shí)例
model = FlagModel('./models/bge/bge-large-zh', query_instruction_for_retrieval="為這個(gè)句子生成表示以用于檢索相關(guān)文章：")
# 創(chuàng)建Elasticsearch客戶端對(duì)象
es = Elasticsearch(hosts="http://localhost:9200")
es.ping()@app.route('/ins', methods=['POST'])
def index():    data = request.get_json()print(data)strs = data["strs"]documents = []for str in strs:            print(str)tmp = model.encode(str)documents.append({"general_text": str,"general_text_vector": tmp,# "domain":"001"})documentsbulk(es, documents, index="demo")return success(1)@app.route('/search', methods=['POST'])
def search():data = request.get_json()doc_vector = model.encode(data["name"])results = es.search(index="demo",source=["general_text",            ],min_score= 1.83,query={"script_score": {"query": { "match_all": {} },"script": {"source": "cosineSimilarity(params.queryVector, 'general_text_vector') + 1.0","params": {"queryVector": doc_vector.tolist()}}}},size=1000)# return resultsreturn results['hits']['hits']def success(data):return {"status": "success","result": data}def fail(data):return {"status": "fail","result": data}if __name__ == "__main__":# Runport = 5000app.run(host='127.0.0.1', port=port, debug=False, use_reloader=False)

es存儲(chǔ)數(shù)據(jù)

搜索結(jié)果