report generator added

Modules/data_QA.py

@@ -6,7 +6,7 @@ from dotenv import load_dotenv
 import os
 from Modules.code_runner import run_script
 from Modules.code_debugger import code_debugger
-from Modules.output_interpreter import output_interpreter
+from Modules.output_interpreter import output_interpreter,display_pdf,create_combined_pdf
 from Modules.data_code_gen import DataCodeGen
 from Modules.python_interpreter import PythonInterpreter, run_interpreter
 import subprocess
@@ -91,7 +91,27 @@ class DataQA:
                 # Process final output
                 answer = output_interpreter(query)
                 st.write(answer)
+                display_pdf("file.pdf")
+                # Specify the file paths
+                text_file = "data.txt"
+                code_file = "code.py"
+                figure_file = "file.pdf"
+                output_file = "report.pdf"
 
+                # Create the combined PDF
+                create_combined_pdf(text_file, code_file, figure_file, output_file)
+
+                pdf_file_path = "report.pdf"
+
+                # Read the PDF file content
+                with open(pdf_file_path, "rb") as pdf_file:
+                    pdf_content = pdf_file.read()
+                st.download_button(
+                    label="Download Report PDF",
+                    data=pdf_content,
+                    file_name="report.pdf",
+                    mime="application/pdf"
+                )
                 # Clean up by removing the code file
                 os.remove("code.py")
 

Modules/llm_summary.py

@@ -8,7 +8,7 @@ load_dotenv()  # take environment variables from .env.
 os.environ['GEMINI_API_KEY'] = os.getenv("GOOGLE_API_KEY")
 
 @st.cache_data(experimental_allow_widgets=True)
-def LLM_summary():
+def LLM_summary(data):
     file_path = './data.csv'
     df = pd.read_csv(file_path)
 

Modules/output_interpreter.py

@@ -1,6 +1,14 @@
 from litellm import completion
 from dotenv import load_dotenv
 import os
+import streamlit as st
+import base64
+
+from reportlab.lib.pagesizes import letter
+from reportlab.pdfgen import canvas
+from reportlab.lib.utils import ImageReader
+import PyPDF2
+import io
 
 load_dotenv()  # take environment variables from .env.
 
@@ -24,4 +32,70 @@ def output_interpreter(query):
     )
 
     response = output.choices[0].message.content
-    return response
+    return response
+
+def display_pdf(file_path):
+    with open(file_path, "rb") as f:
+        base64_pdf = base64.b64encode(f.read()).decode('utf-8')
+    pdf_display = f'<iframe src="data:application/pdf;base64,{base64_pdf}" width="700" height="1000" type="application/pdf"></iframe>'
+    st.markdown(pdf_display, unsafe_allow_html=True)
+
+
+
+
+def create_combined_pdf(text_file, code_file, figure_file, output_file):
+    # Create a canvas object
+    packet = io.BytesIO()
+    can = canvas.Canvas(packet, pagesize=letter)
+    
+    # Add text content from data.txt
+    with open(text_file, 'r') as file:
+        text = file.read()
+    can.drawString(72, 750, "Text Content from data.txt:")
+    text_lines = text.split('\n')
+    y = 730
+    for line in text_lines:
+        can.drawString(72, y, line)
+        y -= 15
+
+    # Add some space between sections
+    y -= 30
+
+    # Add code content from code.py
+    with open(code_file, 'r') as file:
+        code = file.read()
+    can.drawString(72, y, "Code Content from code.py:")
+    y -= 20
+    code_lines = code.split('\n')
+    for line in code_lines:
+        if y < 50:  # Prevent printing beyond the page
+            can.showPage()
+            y = 750
+        can.drawString(72, y, line)
+        y -= 15
+
+    # Save the canvas content to the packet
+    can.save()
+
+    # Move to the beginning of the StringIO buffer
+    packet.seek(0)
+    new_pdf = PyPDF2.PdfReader(packet)
+
+    # Read the existing PDF (figure)
+    existing_pdf = PyPDF2.PdfReader(open(figure_file, "rb"))
+
+    # Create a PdfFileWriter object to combine the PDFs
+    output = PyPDF2.PdfWriter()
+
+    # Add the new PDF (text and code)
+    output.add_page(new_pdf.pages[0])
+
+    # Add the existing PDF (figure)
+    for page_num in range(len(existing_pdf.pages)):
+        output.add_page(existing_pdf.pages[page_num])
+
+    # Write the combined PDF to a file
+    with open(output_file, "wb") as outputStream:
+        output.write(outputStream)
+
+

app.py

@@ -46,7 +46,7 @@ def main():
             data = pd.read_csv("data.csv")
             data_analyzer = DataAnalyzer(data)
             data_analyzer.show_eda()
-            LLM_summary()
+            LLM_summary(data)
             
             data_analyzer.show_count_plots()
 

requirements.txt

@@ -11,4 +11,6 @@ litellm
 streamlit_option_menu
 scikit-learn
 pytest
-streamlit-modal
+streamlit-modal
+reportlab
+PyPDF2