app.py

import openai
import numpy as np
import pandas as pd
import os
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.embeddings.huggingface import HuggingFaceEmbeddings
from langchain import HuggingFaceHub
from langchain.vectorstores import Chroma
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.llms import OpenAI
from langchain.chains import RetrievalQA
from langchain.chains import VectorDBQA
from langchain.document_loaders import TextLoader, WebBaseLoader, SeleniumURLLoader
from langchain.document_loaders import UnstructuredFileLoader
from flask import Flask, jsonify, render_template, request
from werkzeug.utils import secure_filename
from werkzeug.datastructures import  FileStorage
import nltk
nltk.download("punkt")
import warnings
warnings.filterwarnings("ignore")



openai.api_key=os.getenv("OPENAI_API_KEY")


import flask
import os
from dotenv import load_dotenv
load_dotenv()




loader = UnstructuredFileLoader('Jio.txt', mode='elements')
documents= loader.load()

text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
texts = text_splitter.split_documents(documents)
embeddings = OpenAIEmbeddings()
doc_search = Chroma.from_documents(texts,embeddings)
chain = VectorDBQA.from_chain_type(llm=OpenAI(temperature=0.0), chain_type="stuff", vectorstore=doc_search)

app = flask.Flask(__name__, template_folder="./")
# Create a directory in a known location to save files to.
uploads_dir = os.path.join(app.root_path,'static', 'uploads')
os.makedirs(uploads_dir, exist_ok=True)


@app.route('/Home')
def index():
    return flask.render_template('index.html')

@app.route('/post_json', methods=['POST'])
def process_json():
    content_type = request.headers.get('Content-Type')
    if (content_type == 'application/json'):
        requestQuery = request.get_json()
        response= chain.run(requestQuery['query'])
        print("Ques:>>>>"+requestQuery['query']+"\n Ans:>>>"+response)
        return jsonify(botMessage=response); 
    else:
        return 'Content-Type not supported!'


@app.route('/file_upload',methods=['POST'])
def file_Upload():
        
        fileprovided=not request.files.getlist('files[]')[0].filename==''
        urlProvided=not request.form.getlist('weburl')[0]==''
        print("*******")
        print("File Provided:"+str(fileprovided))
        print("URL Provided:"+str(urlProvided))
        print("*******")
            
        documents = []
        if fileprovided:
            #Delete Files
            for filename in os.listdir(uploads_dir):
                file_path = os.path.join(uploads_dir, filename)
                print("Clearing Doc Directory. Trying to delete"+file_path)
                try:
                    if os.path.isfile(file_path) or os.path.islink(file_path):
                        os.unlink(file_path)
                    elif os.path.isdir(file_path):
                        shutil.rmtree(file_path)
                except Exception as e:
                    print('Failed to delete %s. Reason: %s' % (file_path, e))
            #Read and Embed New Files provided        
            for file in request.files.getlist('files[]'):
                print(file.filename)
                file.save(os.path.join(uploads_dir, secure_filename(file.filename)))
                loader = UnstructuredFileLoader(os.path.join(uploads_dir, secure_filename(file.filename)), mode='elements')
                documents.extend(loader.load())
        if urlProvided:
            urlList=request.form.getlist('weburl')
            print(urlList)
            urlLoader=SeleniumURLLoader(urlList)
            documents.extend(urlLoader.load())
        
        print(uploads_dir)
        global chain;

        text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
        texts = text_splitter.split_documents(documents)
        embeddings = OpenAIEmbeddings()
        vectordb = Chroma.from_documents(texts,embeddings)
        chain = RetrievalQA.from_chain_type(llm=OpenAI(temperature=0.0),chain_type="stuff", retriever=vectordb.as_retriever())
        
        return render_template("index.html")

@app.route('/')
def KBUpload():
    return render_template("KBTrain.html")

@app.route('/aiassist')
def aiassist():
    return render_template("index.html")

if __name__ == '__main__':
    app.run(host='0.0.0.0',  port=int(os.environ.get('PORT', 7860)))