import streamlit as st
from gpt_researcher import GPTResearcher
import asyncio
import nest_asyncio
import os

# Access secrets
openai_api_key = st.secrets["OPENAI_API_KEY"]
tavily_api_key = st.secrets["TAVILY_API_KEY"]

# Apply the asyncio patch from nest_asyncio if required
nest_asyncio.apply()

# Set the document path environment variable
os.environ['DOC_PATH'] = './'  # Path to the folder with documents

# Constants
REPORT_TYPE = "research_report"
DOCUMENT_FILE = 'removed_code.txt'  # Name of the document file

# Function to handle asynchronous calls
def run_async(coroutine):
    loop = asyncio.get_event_loop()
    return loop.run_until_complete(coroutine)

# Define the asynchronous function to fetch the report
async def fetch_report(query, report_type):
    """
    Fetch a research report based on the provided query and report type.
    Research is conducted on a local document specified by DOCUMENT_FILE.
    """
    researcher = GPTResearcher(query=query, report_type=report_type, report_source='local')
    await researcher.conduct_research()
    report = await researcher.write_report()
    return report

# Streamlit interface
st.title("Google Leak Reporting Tool")

# User input for the query
query = st.text_input(
    "Enter your research query:",
    "Extract all the information about how the ranking for internal links works."
)

# Button to generate report
if st.button("Generate Report"):
    if not query:
        st.warning("Please enter a query to generate a report.")
    else:
        with st.spinner("Generating report..."):
            # Fetch the report asynchronously using the local document
            fetch_report_coroutine = fetch_report(query, REPORT_TYPE)
            report = run_async(fetch_report_coroutine)
            st.success("Report generated successfully!")
            st.write(report)