Creating app.py

app.py

@@ -0,0 +1,142 @@
+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
+import re
+
+# 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:
+        # Convert markdown to readable format
+        line = re.sub(r'###\s*(.*)', r'\n\n\1\n\n', line)  # Convert ### headings
+        line = re.sub(r'\*\*(.*?)\*\*', r'\1', line)  # Remove bold **text**
+        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"
+        )