app_proper_align.py

import streamlit as st
import tempfile
import os
import shutil
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.text_splitter import CharacterTextSplitter
from langchain.vectorstores import FAISS
from langchain_community.document_loaders import WebBaseLoader
from langchain.chains.question_answering import load_qa_chain
from langchain_openai import ChatOpenAI
from reportlab.lib.pagesizes import letter
from reportlab.pdfgen import canvas
from reportlab.pdfbase.pdfmetrics import stringWidth

# Hardcoded OpenAI API Key
os.environ['OPENAI_API_KEY'] = os.getenv('OPENAI_API_KEY')

# Streamlit UI
st.title("🔍 AI Benefits Analysis for Any Company")

# User input: Only Website URL (with placeholder)
website_url = st.text_input("Enter Website URL", placeholder="e.g., https://www.companywebsite.com")

# Fixed question for AI analysis
fixed_question = (
    "Analyze how Artificial Intelligence (AI) can benefit this company based on its industry, "
    "key operations, and challenges. Provide insights on AI-driven improvements in customer experience, "
    "automation, sales, risk management, decision-making, and innovation. Include an AI implementation roadmap, "
    "challenges, solutions, and future opportunities with real-world examples."
)

# Temporary directory to store FAISS index
temp_dir = tempfile.gettempdir()
faiss_db_path = os.path.join(temp_dir, "faiss_index_dir")

# Function to fetch and process website data
def build_embeddings(url):
    st.info("Fetching and processing website data...")

    # Load website data
    loader = WebBaseLoader(url)
    raw_text = loader.load()

    # Chunking the fetched text
    text_splitter = CharacterTextSplitter(separator='\n', chunk_size=500, chunk_overlap=50)
    docs = text_splitter.split_documents(raw_text)

    # Creating embeddings
    embeddings = OpenAIEmbeddings()
    docsearch = FAISS.from_documents(docs, embeddings)

    # Save FAISS index
    if os.path.exists(faiss_db_path):
        shutil.rmtree(faiss_db_path)
    os.makedirs(faiss_db_path)
    docsearch.save_local(faiss_db_path)

    return docsearch

# Function to save text to a PDF file
def save_text_to_pdf(text, file_path):
    c = canvas.Canvas(file_path, pagesize=letter)
    width, height = letter
    
    # Define margins
    margin_x = 50
    margin_y = 50
    max_width = width - 2 * margin_x  # Usable text width
    
    # Title
    c.setFont("Helvetica-Bold", 16)
    c.drawString(margin_x, height - margin_y, "AI Benefits Analysis Report")
    
    # Move cursor down
    y_position = height - margin_y - 30
    c.setFont("Helvetica", 12)
    
    # Function to wrap text within max_width
    def wrap_text(text, font_name, font_size, max_width):
        words = text.split()
        lines = []
        current_line = ""
        
        for word in words:
            test_line = current_line + " " + word if current_line else word
            if stringWidth(test_line, font_name, font_size) <= max_width:
                current_line = test_line
            else:
                lines.append(current_line)
                current_line = word
        
        if current_line:
            lines.append(current_line)
        
        return lines
    
    # Process text
    lines = text.split("\n")
    wrapped_lines = []
    for line in lines:
        wrapped_lines.extend(wrap_text(line, "Helvetica", 12, max_width))
    
    # Write text line by line with proper spacing
    for line in wrapped_lines:
        if y_position < margin_y:  # If at bottom of page, create a new page
            c.showPage()
            c.setFont("Helvetica", 12)
            y_position = height - margin_y
        c.drawString(margin_x, y_position, line)
        y_position -= 16  # Line spacing
    
    c.save()
    
# Run everything in one click
if st.button("Get AI Insights") and website_url:
    docsearch = build_embeddings(website_url)

    # AI Benefits Analysis
    st.subheader("💬 AI Benefits Analysis")

    chain = load_qa_chain(ChatOpenAI(model="gpt-4o"), chain_type="stuff")
    docs = docsearch.similarity_search(fixed_question)
    response = chain.run(input_documents=docs, question=fixed_question)

    st.write("**AI Insights:**", response)

    # Save the AI insights as a PDF
    pdf_file = tempfile.NamedTemporaryFile(delete=False, suffix=".pdf")
    save_text_to_pdf(response, pdf_file.name)

    # Provide download link for the generated PDF file
    with open(pdf_file.name, "rb") as f:
        st.download_button(
            label="Download AI Insights as PDF File",
            data=f,
            file_name="ai_benefits_analysis_report.pdf",
            mime="application/pdf"
        )