app.py

# -*- coding: utf-8 -*-
"""Copy of Copy of Chatbot with custom knowledge base

Automatically generated by Colaboratory.

Original file is located at
    https://colab.research.google.com/drive/1VSXUmag_76fzebs16YhW_as4mdhHNdkx
"""

!pip install llama-index
!pip install langchain
!pip install gradio
!pip install pandas 
!pip install openpyxl

import pandas as pd
from llama_index import SimpleDirectoryReader, GPTListIndex, readers, GPTSimpleVectorIndex, LLMPredictor, PromptHelper
from langchain import OpenAI
import sys
import os
from IPython.display import Markdown, display
import pandas as pd
from llama_index import SimpleDirectoryReader, GPTListIndex, readers, GPTSimpleVectorIndex, LLMPredictor, PromptHelper
from langchain import OpenAI
from IPython.display import Markdown, display
import gradio as gr
import gradio
df = pd.read_excel('Shegardi_dataset.xlsx',sheet_name = 'dataset')
os.environ['OPENAI_API_KEY'] = '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'
def construct_index(directory_path):
    # set maximum input size
    max_input_size = 4096
    # set number of output tokens
    num_outputs = 2000
    # set maximum chunk overlap
    max_chunk_overlap = 20
    # set chunk size limit
    chunk_size_limit = 600 

    # define LLM
    llm_predictor = LLMPredictor(llm=OpenAI(temperature=0.5, model_name="text-davinci-003", max_tokens=num_outputs))
    prompt_helper = PromptHelper(max_input_size, num_outputs, max_chunk_overlap, chunk_size_limit=chunk_size_limit)
 
    documents = SimpleDirectoryReader(directory_path).load_data()
    
    index = GPTSimpleVectorIndex(
        documents, llm_predictor=llm_predictor, prompt_helper=prompt_helper
    )

    index.save_to_disk('index.json')

    return index

def ask_ai():
    index = GPTSimpleVectorIndex.load_from_disk('index.json')
    while True: 
        query = input("What do you want to ask? ")
        response = index.query(query, response_mode="compact")
        display(Markdown(f"Response: <b>{response.response}</b>")


construct_index("context_data/data")

def ask_ai(query):
    index = GPTSimpleVectorIndex.load_from_disk('index.json')
    response = index.query(query, response_mode="compact")
    return response.response

iface = gr.Interface(fn=ask_ai, inputs="text", outputs="text", title="The following is a conversation with a human called Shegardi. Shegardi is helpful, precise, truthful, and very friendly.  Also, Shegardi is an employee of Warba Bank, located in Kuwait. Shegardi will only use the information provided to him. ", 
                     description="Enter a question and get an answer from Shegardi.")
iface.launch(share=True)