import streamlit as st
from dotenv import load_dotenv
from utils import *
import uuid

#Creating session variables
if 'unique_id' not in st.session_state:
    st.session_state['unique_id'] =''

def main():
    load_dotenv()

    st.set_page_config(page_title="Resume Screening Assistance")
    st.header("ATS • Resume Screening Assistance")
    st.write("Using AI, recruiters save hours to easily find resumes closest matched to job decription.")
    st.write("Chain 1: sentence-transformers/all-MiniLM-L6-v2 for embedding")
    st.write("Chain 2: openAI for doc summarization")
    st.write("Vector DB: pinecone")
    st.write("")

    job_description = st.text_area("Step 1: Paste the JOB DESCRIPTION here.",height=200, key="1")
    document_count = st.text_input("Step 2: Select NUMBER OF RESUMES to return. ",key="2")
    # Upload the Resumes (pdf files)
    pdf = st.file_uploader("Step 3: Upload resumes here. PDF only.", type=["pdf"],accept_multiple_files=True)

    submit=st.button("Find me top resumes")

    if submit:
        with st.spinner('Analyzing...'):

            #Creating a unique ID, so that we can use to query and get only the user uploaded documents from PINECONE vector store
            
            unique_uuid = uuid.uuid4().hex
            # st.session_state['unique_id']=unique_uuid
            # print("st.session_state['unique_id']: ",  unique_uuid) 
            print("unique_uuid: ", unique_uuid) 
            print("job_description: ", job_description) 
            print("document_count: ", document_count) 

            #Create a documents list out of all the user uploaded pdf files
            final_docs_list=create_docs(pdf, unique_uuid)

            #Displaying the count of resumes that have been uploaded
            st.write("• Resumes uploaded :"+str(len(final_docs_list)))

            #Create embeddings instance
            embeddings=create_embeddings_load_data()

            #Push data to PINECONE
            push_to_pinecone("23fd6fd1-744d-4500-a77c-4944591a53f9","gcp-starter","resume-screening",embeddings,final_docs_list)

            #Fecth relavant documents from PINECONE
            relavant_docs=similar_docs(job_description,document_count,"23fd6fd1-744d-4500-a77c-4944591a53f9","gcp-starter","resume-screening",embeddings,unique_uuid)

            #t.write(relavant_docs)

            #Introducing a line separator
            st.write(":heavy_minus_sign:" * 30)

            #For each item in relavant docs - we are displaying some info of it on the UI
            print('>>>> RELEVANT DOCUMENTS: ' + str(len(relavant_docs)))

            for item in range(len(relavant_docs)):
                
                st.subheader("👉 "+str(item+1))

                #Displaying Filepath
                st.write("• File: "+relavant_docs[item][0].metadata['name'])

                #Introducing Expander feature
                with st.expander('Show me summary: 👀'): 
                    st.info("• Match Score: " + str(relavant_docs[item][1]))
                    # print(relavant_docs[item])
                    #st.write("***"+relavant_docs[item][0].page_content)
                    
                    #Gets the summary of the current item using 'get_summary' function that we have created which uses LLM & Langchain chain
                    summary = get_summary(relavant_docs[item][0])
                    st.write("• Summary: "+summary)

        st.success("Analyze Complete. ")


#Invoking main function
if __name__ == '__main__':
    main()