utils.py

from openai import OpenAI
#from langchain_openai import OpenAI
from pypdf import PdfReader
import PyPDF2
import pandas as pd
import re
import replicate
from langchain.prompts import PromptTemplate

#Extract Information from PDF file
def get_pdf_text(pdf_doc):
    text = ""
    pdf_reader = PyPDF2.PdfReader(pdf_doc)
    for page in pdf_reader.pages:
        text += page.extract_text()
    return text



#Function to extract data from text
def extracted_data(pages_data):

    template = """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 and the object must be in JSON format between curly brackets. this is the format {{'Invoice no.': '1001329','Description': 'Office Chair','Quantity': '2','Date': '5/4/2023','Unit price': '1100.00','Amount': '2200.00','Total': '2200.00','Email': 'Santoshvarma0988@gmail.com','Phone number': '9999999999','Address': 'Mumbai, India'}}
            """
    prompt_template = PromptTemplate(input_variables=["pages"], template=template)

    #llm = OpenAI(temperature=0.7)
    #full_response= llm.invoke(prompt_template.format(pages=pages_data))
    

    #The below code will be used when we want to use LLAMA 2 model,  we will use Replicate for hosting our model....
    
    output = replicate.run('meta/llama-2-7b-chat:13c3cdee13ee059ab779f0291d29054dab00a47dad8261375654de5540165fb0', 
                            input={"prompt":prompt_template.format(pages=pages_data) ,"temperature":0.1, "top_p":0.9, "max_new_tokens": 250,"max_length":500, "repetition_penalty":1})
    
    full_response = ''
    for item in output: #Uncomment this if you want to use LLAMA 2 model
        full_response += item
    

    print(full_response)
    return full_response


# iterate over files in
# that user uploaded PDF files, one by one
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(raw_data)
        print("extracted raw data")

        llm_extracted_data=extracted_data(raw_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)
        # = re.compile(r'{(.+)}', re.DOTALL)
        #match = pattern.search(llm_extracted_data)
        data_dict = {} 
        #data_dict = {'text':llm_extracted_data}  # Initialize data_dict with an empty dictionary

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

        
        #df = pd.concat([df, pd.DataFrame(data_dict, index=[0])], ignore_index=True)
        df=df._append(data_dict, ignore_index=True)
        print("********************DONE***************")
        #df = pd.concat([df, save_to_dataframe(llm_extracted_data)], ignore_index=True)


    df.head()
    return df