第一次提交

.idea/.gitignore

@@ -0,0 +1,8 @@
+# 默认忽略的文件
+/shelf/
+/workspace.xml
+# 基于编辑器的 HTTP 客户端请求
+/httpRequests/
+# Datasource local storage ignored files
+/dataSources/
+/dataSources.local.xml

flask_api.py

@@ -0,0 +1,110 @@
+# coding:utf-8
+import os
+import pandas as pd
+
+os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID"
+os.environ["CUDA_VISIBLE_DEVICES"] = "0"
+import torch
+from transformers import (
+    AutoModelForSequenceClassification, AutoTokenizer, DataCollatorWithPadding,
+    Trainer, TrainingArguments
+)
+from flask import Flask, jsonify
+from flask import request
+import uuid
+app = Flask(__name__)
+app.config["JSON_AS_ASCII"] = False
+from threading import Thread
+import redis
+import uuid
+import time
+import json
+import docx2txt
+
+
+pool = redis.ConnectionPool(host='localhost', port=63179, max_connections=100, db=13, password="zhicheng123*")
+redis_ = redis.Redis(connection_pool=pool, decode_responses=True)
+
+db_key_query = 'query'
+db_key_querying = 'querying'
+db_key_queryset = 'queryset'
+batch_size = 32
+
+def ulit_request_file(file):
+    file_name = file.filename
+    file_name_save = "data/request/{}".format(file_name)
+    file.save(file_name_save)
+
+    if file_name.split(".")[-1] == "txt":
+        try:
+            with open(file_name_save, encoding="gbk") as f:
+                content = f.read()
+        except:
+            with open(file_name_save, encoding="utf-8") as f:
+                content = f.read()
+    # elif file_name.split(".")[-1] == "docx":
+    #     content = docx2txt.process(file_name_save)
+
+    content_list = [i.strip("\n") for i in content.split("。")]
+    print(content_list)
+    return content_list
+
+
+@app.route("/predict", methods=["POST"])
+def handle_query_predict():
+    print(request.remote_addr)
+
+    # request.form.get('prompt')
+    dataBases = ""
+    minSimilarity = ""  # txt
+    minWords = ""
+    title = request.form.get("title")
+    author = request.form.get("author")  # txt
+    file = request.files.get('file')
+    token = ""
+    account = ""
+    goodsId = ""
+    callbackUrl = ""
+    content_list = ulit_request_file(file)
+
+    id_ = str(uuid.uuid1())  # 为query生成唯一标识
+    id_ = id_.upper()
+    print("uuid: ", id_)
+    print(id_)
+    d = {
+        'id': id_,
+        'dataBases': dataBases,
+        'minSimilarity': minSimilarity,
+        'minWords': minWords,
+        'title': title,
+        'author': author,
+        'content_list': content_list,
+        'token': token,
+        'account': account,
+        'goodsId': goodsId,
+        'callbackUrl': callbackUrl
+    }
+    print(d)
+    # 绑定文本和query id
+    # recall_10(id_, title, abst_zh, content)
+
+    load_request_path = './request_data_logs/{}.json'.format(id_)
+    with open(load_request_path, 'w', encoding='utf8') as f2: # ensure_ascii=False才能输入中文，否则是Unicode字符 indent=2 JSON数据的缩进，美观
+        json.dump(d, f2, ensure_ascii=False, indent=4)
+    redis_.rpush(db_key_query, json.dumps({"id": id_, "path": load_request_path}))  # 加入redis
+
+    return_text = {
+        'code': 0,
+        'msg': "请求成功",
+        'data': {
+            'balances': "",
+            'orderId': id_,
+            'consumeNum': ""
+        }
+    }
+
+    return jsonify(return_text)  # 返回结果
+
+
+if __name__ == "__main__":
+    app.run(host="0.0.0.0", port=16005, threaded=True, debug=False)

flask_chatgpt-detector_predict_redis_search.py

@@ -0,0 +1,75 @@
+# -*- coding: utf-8 -*-
+
+"""
+@Time    :  2023/3/2 19:31
+@Author  :
+@FileName:
+@Software:
+@Describe:
+"""
+#
+# import redis
+#
+# redis_pool = redis.ConnectionPool(host='127.0.0.1', port=6379, password='', db=0)
+# redis_conn = redis.Redis(connection_pool=redis_pool)
+#
+#
+# name_dict = {
+#     'name_4' : 'Zarten_4',
+#     'name_5' : 'Zarten_5'
+# }
+# redis_conn.mset(name_dict)
+
+import flask
+import redis
+import uuid
+import json
+from threading import Thread
+import time
+
+app = flask.Flask(__name__)
+pool = redis.ConnectionPool(host='localhost', port=63179, max_connections=100, db=13, password="zhicheng123*")
+redis_ = redis.Redis(connection_pool=pool, decode_responses=True)
+
+
+@app.route("/search", methods=["POST"])
+def handle_query():
+    # try:
+    id_ = flask.request.json['orderid']  # 获取用户query中的文本
+    result = redis_.get(id_)  # 获取该query的模型结果
+    if result is not None:
+        # redis_.delete(id_)
+        result_path = result.decode('UTF-8')
+        with open(result_path, encoding='utf8') as f1:
+            # 加载文件的对象
+            result_dict = json.load(f1)
+        resilt = result_dict["resilt"]
+        result_text = {'status': 9,
+                       'resilt': resilt,
+                       'reportId': "",
+                       'downloadurl': "",
+                       'similarity': ""
+                       }
+    else:
+        result_text = {'status': 1,
+                   'resilt': "",
+                   'reportId': "",
+                   'downloadurl': "",
+                   'similarity': ""
+                   }
+
+
+    result = {'code':0,
+              "msg": "请求成功",
+              "data": result_text}
+    # except:
+    #     result = {'code':1,
+    #               "msg": "请求失败"
+    #               }
+
+
+    return flask.jsonify(result)  # 返回结果
+
+
+if __name__ == "__main__":
+    app.run(debug=False, host='0.0.0.0', port=16006)

run_app.sh

@@ -0,0 +1 @@
+nohup python flask_api.py > flask_api.myout.file 2>&1 &

run_app_search.sh

@@ -0,0 +1 @@
+nohup python flask_chatgpt-detector_predict_redis_search.py > flask_chatgpt-detector_predict_redis.myout.file 2>&1 &

run_model.sh

@@ -0,0 +1 @@
+nohup python chatgpt_detector_model_predict.py > chatgpt_detector_model_predict.myout.file 2>&1 &