Spaces:

shukdevdatta123
/

Smart-AI-Tutor-APP

Running

App Files Files Community

shukdevdatta123 commited on Jan 7

Commit

291f44e

verified ·

1 Parent(s): dcebc1a

Update app.py

Browse files

Files changed (1) hide show

app.py +73 -36

app.py CHANGED Viewed

@@ -6,9 +6,6 @@ import os
 import numpy as np
 from sklearn.feature_extraction.text import TfidfVectorizer
 from sklearn.metrics.pairwise import cosine_similarity
-from reportlab.lib.pagesizes import letter
-from reportlab.pdfgen import canvas
-from io import BytesIO
 # Function to extract text from a PDF file
 def extract_text_from_pdf(pdf_file):
@@ -29,29 +26,67 @@ def search_similar(query_embedding, index, stored_texts, top_k=3):
     results = [(stored_texts[i], distances[0][idx]) for idx, i in enumerate(indices[0])]
     return results
-# Function to create a PDF from the response
-def create_pdf(response_text):
-    buffer = BytesIO()
-    c = canvas.Canvas(buffer, pagesize=letter)
-    width, height = letter
-    # Add the response text to the PDF
-    c.drawString(30, height - 30, "Intelligent Reply:")
-    text_object = c.beginText(30, height - 50)
-    text_object.setFont("Helvetica", 10)
-    text_object.setTextOrigin(30, height - 50)
-    # Add the response text, line by line
-    lines = response_text.split("\n")
-    for line in lines:
-        text_object.textLine(line)
-    c.drawText(text_object)
-    c.showPage()
-    c.save()
-    buffer.seek(0)
-    return buffer
 # Streamlit app starts here
 st.title("Course Query Assistant")
@@ -112,18 +147,20 @@ if openai_api_key:
                 messages=[{"role": "user", "content": modified_prompt}]
             )
-            # Extract the response text
-            response_text = response['choices'][0]['message']['content']
-            # Display the response
             st.write("### Intelligent Reply:")
-            st.write(response_text)
-            # Button to download the response as PDF
-            pdf_buffer = create_pdf(response_text)
             st.download_button(
-                label="Download Intelligent Reply as PDF",
-                data=pdf_buffer,
-                file_name="intelligent_reply.pdf",
-                mime="application/pdf"
             )

 import numpy as np
 from sklearn.feature_extraction.text import TfidfVectorizer
 from sklearn.metrics.pairwise import cosine_similarity
 # Function to extract text from a PDF file
 def extract_text_from_pdf(pdf_file):
     results = [(stored_texts[i], distances[0][idx]) for idx, i in enumerate(indices[0])]
     return results
+# Function to generate HTML with nice styling
+def generate_html(response_content):
+    html_template = f"""
+    <!DOCTYPE html>
+    <html lang="en">
+    <head>
+        <meta charset="UTF-8">
+        <meta name="viewport" content="width=device-width, initial-scale=1.0">
+        <title>Course Query Response</title>
+        <style>
+            body {{
+                font-family: Arial, sans-serif;
+                margin: 0;
+                padding: 0;
+                background-color: #f4f4f9;
+                color: #333;
+            }}
+            .container {{
+                width: 80%;
+                margin: 30px auto;
+                background-color: white;
+                padding: 20px;
+                border-radius: 8px;
+                box-shadow: 0 4px 6px rgba(0, 0, 0, 0.1);
+            }}
+            h1 {{
+                color: #2C3E50;
+                font-size: 2em;
+                text-align: center;
+            }}
+            .response {{
+                background-color: #ecf0f1;
+                border-left: 5px solid #3498db;
+                padding: 20px;
+                font-size: 1.2em;
+                margin-top: 20px;
+                border-radius: 5px;
+            }}
+            footer {{
+                text-align: center;
+                margin-top: 30px;
+                font-size: 0.9em;
+                color: #7f8c8d;
+            }}
+        </style>
+    </head>
+    <body>
+        <div class="container">
+            <h1>Course Query Response</h1>
+            <div class="response">
+                <h3>Answer:</h3>
+                <p>{response_content}</p>
+            </div>
+            <footer>
+                <p>Generated by Course Query Assistant</p>
+            </footer>
+        </div>
+    </body>
+    </html>
+    """
+    return html_template
 # Streamlit app starts here
 st.title("Course Query Assistant")
                 messages=[{"role": "user", "content": modified_prompt}]
             )
+            # Get the response content
+            response_content = response['choices'][0]['message']['content']
+            # Display the response in Streamlit
             st.write("### Intelligent Reply:")
+            st.write(response_content)
+            # Generate HTML content
+            html_content = generate_html(response_content)
+            # Provide the download button for the HTML file
             st.download_button(
+                label="Download Response as HTML",
+                data=html_content,
+                file_name="course_query_response.html",
+                mime="text/html"
             )