File size: 2,181 Bytes
f4c8d5e
 
 
 
 
 
 
 
6351d67
f4c8d5e
6024be4
 
 
 
 
 
 
aa05778
 
 
 
f4c8d5e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
aa05778
 
 
 
f4c8d5e
aa05778
f4c8d5e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
43a47b5
f4c8d5e
43a47b5
 
a032a3b
 
aec9d8a
f4c8d5e
5189e82
a032a3b
 
5189e82
43a47b5
 
aec9d8a
 
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
from fastapi import FastAPI, File, UploadFile
from pydantic import BaseModel
from pathlib import Path
from fastapi import Form
from fastapi.responses import JSONResponse
from langchain.text_splitter import RecursiveCharacterTextSplitter
from PyPDF2 import PdfReader
from fastapi import Depends
#在FastAPI中,Depends()函数用于声明依赖项

import random
import string
import sys
import timeit
import datetime
import io

import os
from dotenv import load_dotenv
load_dotenv()

def generate_random_string(length):
    letters = string.ascii_lowercase
    return ''.join(random.choice(letters) for i in range(length))  

app = FastAPI()

class FileToProcess(BaseModel):
    uploaded_file: UploadFile = File(...)

@app.get("/")
async def home():
    return "API Working!"

@app.post("/file/upload")
async def upload_file(username: str, file_to_process: FileToProcess = Depends()):
    uploaded_file = file_to_process.uploaded_file
    
    random_string = generate_random_string(20)
    file_path = Path.cwd() / random_string
    file_path.mkdir(parents=True, exist_ok=True)
    file_saved_in_api = file_path / uploaded_file.filename
    with open(file_saved_in_api, "wb+") as file_object:
        file_object.write(uploaded_file.file.read())   

    text_splitter = RecursiveCharacterTextSplitter(        
        #separator = "\n",
        chunk_size = 500,
        chunk_overlap  = 100, #striding over the text
        length_function = len,
    )        

    doc_reader = PdfReader(file_saved_in_api)
    raw_text = ''
    for i, page in enumerate(doc_reader.pages):
        text = page.extract_text()
        if text:
            raw_text += text
    temp_texts = text_splitter.split_text(raw_text)
    
    print(temp_texts)
    print()
    
    #api_call_msg={"INFO": f"File '{uploaded_file.filename}' saved to your profile."}
    api_call_msg={"INFO": f"File '{file_saved_in_api}' saved to your profile."}    
    print(api_call_msg)

    print(api_call_msg["INFO"])
    #File 'uploaded_file' saved to your profile.
    print()

    print("API call finished...")

    #return {"INFO": f"File '{uploaded_file.filename}' saved to your profile."}
    return api_call_msg