File size: 3,841 Bytes
eca8f34
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2eabb0b
 
 
 
eca8f34
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2eabb0b
eca8f34
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2eabb0b
 
 
 
 
 
 
 
 
eca8f34
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2eabb0b
 
 
eca8f34
2eabb0b
 
 
 
 
 
 
 
 
eca8f34
2eabb0b
 
 
 
 
eca8f34
 
 
2eabb0b
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
# import firebase_admin
# from firebase_admin import credentials
# from firebase_admin import firestore
import io
from fastapi import FastAPI, File, UploadFile
from werkzeug.utils import secure_filename
# import speech_recognition as sr
import subprocess
import os
import requests
import random
import pandas as pd
from pydub import AudioSegment
from datetime import datetime
from datetime import date
import numpy as np
# from sklearn.ensemble import RandomForestRegressor
import shutil
import json
# from transformers import AutoModelForQuestionAnswering, AutoTokenizer, pipeline
from pydantic import BaseModel
from typing import Annotated
# from transformers import BertTokenizerFast, EncoderDecoderModel
import torch
import re
# from transformers import AutoTokenizer, T5ForConditionalGeneration
from fastapi import Form
# from transformers import AutoModelForSequenceClassification
# from transformers import TFAutoModelForSequenceClassification
# from transformers import AutoTokenizer, AutoConfig
import numpy as np
import threading
import random
import string
import time

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM,pipeline

device = "cpu"

tokenizer = AutoTokenizer.from_pretrained("humarin/chatgpt_paraphraser_on_T5_base")

model = AutoModelForSeq2SeqLM.from_pretrained("humarin/chatgpt_paraphraser_on_T5_base").to(device)

def paraphrase(
    question,
    num_beams=5,
    num_beam_groups=5,
    num_return_sequences=1,
    repetition_penalty=10.0,
    diversity_penalty=3.0,
    no_repeat_ngram_size=2,
    temperature=0.7,
    max_length=10000
):
    input_ids = tokenizer(
        f'paraphrase: {question}',
        return_tensors="pt", padding="longest",
        max_length=max_length,
        truncation=True,
    ).input_ids
    
    outputs = model.generate(
        input_ids, temperature=temperature, repetition_penalty=repetition_penalty,
        num_return_sequences=num_return_sequences, no_repeat_ngram_size=no_repeat_ngram_size,
        num_beams=num_beams, num_beam_groups=num_beam_groups,
        max_length=max_length, diversity_penalty=diversity_penalty
    )

    res = tokenizer.batch_decode(outputs, skip_special_tokens=True)

    return res



class Query(BaseModel):
    text: str

   



class Query2(BaseModel):
    text: str
    host:str

   



from fastapi import FastAPI, Request, Depends, UploadFile, File
from fastapi.exceptions import HTTPException
from fastapi.middleware.cors import CORSMiddleware
from fastapi.responses import JSONResponse


# now = datetime.now()


# UPLOAD_FOLDER = '/files'
# ALLOWED_EXTENSIONS = {'txt', 'pdf', 'png',
#                       'jpg', 'jpeg', 'gif', 'ogg', 'mp3', 'wav'}


app = FastAPI()

app.add_middleware(
    CORSMiddleware,
    allow_origins=['*'],
    allow_credentials=True,
    allow_methods=['*'],
    allow_headers=['*'],
)


# cred = credentials.Certificate('key.json')
# app1 = firebase_admin.initialize_app(cred)
# db = firestore.client()
# data_frame = pd.read_csv('data.csv')



@app.on_event("startup")
async def startup_event():
   print("on startup")

   


@app.post("/")
async def get_answer(q: Query ):
    
    text = q.text
    x= paraphrase(text)
    
    return x[0]



@app.post("/large")
async def get_answer2(q: Query2 ):
    
    text = q.text
    host= q.host

    N = 20
    res = ''.join(random.choices(string.ascii_uppercase +
                             string.digits, k=N))
    res= res+ str(time.time())

    id= res
    
    t = threading.Thread(target=do_ML, args=(id,text,host))  
    t.start()

    return JSONResponse({"id":id})

    



def do_ML(id:str,text:str,host:str):
    try:
        x= paraphrase(text)
        result=x[0]
        data={"id":id,"result":result}
        x=requests.post(host,data= data)
        print(x.text)


    except:
        print("Error occured id="+id)