app.py

import streamlit as st
from utils import *
import constants

# Creating Session State Variables

if 'Website_URL' not in st.session_state:
    st.session_state['Website_URL'] =''
if 'HuggingFace_API_Key' not in st.session_state:
    st.session_state['HuggingFace_API_Key'] =''
if 'Pinecone_Index' not in st.session_state:
    st.session_state['Pinecone_Index'] =''
if 'Pinecone_EBV' not in st.session_state:
    st.session_state['Pinecone_ENV'] =''
if 'Pinecone_API_Key' not in st.session_state:
    st.session_state['Pinecone_API_Key'] =''
if 'API_Key' not in st.session_state:
    st.session_state['API_Key'] = ''
if 'history' not in st.session_state:
    st.session_state['history'] = ''



# clear the chat history from streamlit session state
def clear_history():
    if 'history' in st.session_state:
        del st.session_state['history']



#
st.title('Query a Sitemap') 

st.video("https://youtu.be/a6tZd-niM1o")

#********SIDE BAR Funtionality started*******

# Sidebar to capture the API keys
st.sidebar.title("🗝️")
st.session_state['Website_URL']= st.sidebar.text_input('Input the Sitemap you want to Query against','https://jobs.excelcult.com/wp-sitemap-posts-post-1.xml')
st.session_state['HuggingFace_API_Key']= st.sidebar.text_input('Input Your HuggingFace API key',type="password")
st.session_state['Pinecone_Index']= st.sidebar.text_input('Input Your Pinecone Index','chatbot')
st.session_state['Pinecone_ENV']= st.sidebar.text_input('Input Your Pinecone Environment','gcp-starter')
st.session_state['Pinecone_API_Key']= st.sidebar.text_input('Input your Pinecone API key?',type="password")

load_button = st.sidebar.button("Load data to Pinecone", key="load_button")

#If the bove button is clicked, pushing the data to Pinecone...
if load_button:
    #Proceed only if API keys are provided
    if st.session_state['Website_URL'] !="" and st.session_state['HuggingFace_API_Key'] !="" and st.session_state['Pinecone_ENV'] !="" and st.session_state['Pinecone_API_Key']!="" :

        #Fetch data from site
        site_data=get_website_data(st.session_state['Website_URL'])
        st.write("Data pull done...")

        #Split data into chunks
        chunks_data=split_data(site_data)
        st.write("Spliting data done...")

        #Creating embeddings instance
        embeddings=create_embeddings()
        # st.session_state.vs=embeddings
        st.write("Embeddings instance creation done...")

        #Push data to Pinecone
        push_to_pinecone(st.session_state['Pinecone_API_Key'],st.session_state['Pinecone_ENV'],st.session_state['Pinecone_Index'],embeddings,chunks_data)
        st.write("Pushing data to Pinecone done...")

        st.sidebar.success("Data pushed to Pinecone successfully!")
    else:
        st.sidebar.error("Ooopssss!!! Please provide API keys and webstie URL.....")

#********SIDE BAR Funtionality ended*******

#Captures User Inputs
prompt = st.text_input('Ask a question about your uploaded website: ❓',key="prompt")  # The box for the text prompt
document_count = st.slider('No.Of links to return 🔗 - (0 LOW || 5 HIGH)', 0, 5, 2,step=1)

submit = st.button("Search") 


if submit:
    #Proceed only if API keys are provided
    if st.session_state['Website_URL'] !="" and st.session_state['HuggingFace_API_Key'] !="" and st.session_state['Pinecone_ENV'] !="" and st.session_state['Pinecone_API_Key']!="":

        
       #Creating embeddings instance
        embeddings=create_embeddings()
        st.write("Embeddings instance creation done...")

        #Pull index data from Pinecone
        index=pull_from_pinecone(st.session_state['Pinecone_API_Key'],st.session_state['Pinecone_ENV'],st.session_state['Pinecone_Index'],embeddings)
        st.write("Pinecone index retrieval done...")

        #Fetch relavant documents from Pinecone index
        relavant_docs=get_similar_docs(index,prompt,document_count)
        #st.write(relavant_docs)

        #Displaying search results
        st.success("Please find the search results :")
         #Displaying search results
        st.write("search results list....")
        for document in relavant_docs:
            
            st.write("👉**Result : "+ str(relavant_docs.index(document)+1)+"**")
            st.write("**Info**: "+document.page_content)
            st.write("**Link**: "+ document.metadata['source'])
        
    

    else:
        st.sidebar.error("Ooopssss!!! Please provide API keys.....")