File size: 2,607 Bytes
de1c898
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
408cbf0
de1c898
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 langchain_openai import OpenAI

from PyPDF2 import PdfReader
import pandas as pd
import re
import replicate
from langchain.prompts import PromptTemplate

def get_pdf_text(pdf_doc):
    text = ""
    pdf_reader = PdfReader(pdf_doc)
    for page in pdf_reader.pages:
        text += page.extract_text()
    return text

def extracted_data(pages_data):

    template = """Please Extract all the following values : invoice no., Description, Quantity, date, 
        Unit price , Amount, Total, email, phone number and address from this data: {pages}

        Expected output: remove any dollar symbols {{'Invoice no.': '1001329','Description': 'Office Chair','Quantity': '2','Date': '5/4/2023','Unit price': '1100.00$','Amount': '2200.00$','Total': '2200.00$','Email': 'sam@gmail.com','Phone number': '9999999999','Address': 'Hyderabad , India'}}
        """
    prompt_template = PromptTemplate(input_variables=["pages"], template=template)

    llm = OpenAI(temperature=.7)
    full_response=llm(prompt_template.format(pages=pages_data))

    return full_response

def create_docs(user_pdf_list):
    
    df = pd.DataFrame({'Invoice no.': pd.Series(dtype='str'),
                   'Description': pd.Series(dtype='str'),
                   'Quantity': pd.Series(dtype='str'),
                   'Date': pd.Series(dtype='str'),
	                'Unit price': pd.Series(dtype='str'),
                   'Amount': pd.Series(dtype='int'),
                   'Total': pd.Series(dtype='str'),
                   'Email': pd.Series(dtype='str'),
	                'Phone number': pd.Series(dtype='str'),
                   'Address': pd.Series(dtype='str')
                    })

    for filename in user_pdf_list:
        
        print(filename)
        raw_data=get_pdf_text(filename)
        print("extracted raw data")

        llm_extracted_data=extracted_data(raw_data)
        #print(llm_extracted_data)
        #print("llm extracted data")
        #Adding items to our list - Adding data & its metadata

        pattern = r'{(.+)}'
        match = re.search(pattern, llm_extracted_data, re.DOTALL)

       

        if match:
            extracted_text = match.group(1)
            # Converting the extracted text to a dictionary
            data_dict = eval('{' + extracted_text + '}')
            print(data_dict)
        else:
            print("No match found.")
            # Initialize data_dict
            data_dict = {}

        
        df=df._append([data_dict], ignore_index=True)
        #df=df.append(save_to_dataframe(llm_extracted_data), ignore_index=True)

    df.head()
    return df