Update app.py

app.py

@@ -50,65 +50,8 @@ def extract_files_from_folder(folder_path):
     print("Files found:", extracted_files)  # Debugging log
     return extracted_files
 
-def read_text_from_files(file_paths):
-    """Reads text content from a list of files."""
-    text = ""
-    for file_path in file_paths:
-        print(f"Reading text file: {file_path}")  # Debugging log
-        with open(file_path, "r", encoding="utf-8", errors="ignore") as file:
-            file_text = file.read()
-            text += file_text + "\n"
-    print("Extracted text from TXT files:", text[:500])  # Debugging log (First 500 chars)
-    return text
-
-def get_text_from_pdf(pdf_files):
-    text = ""
-    for pdf_path in pdf_files:
-        print(f"Reading PDF file: {pdf_path}")  # Debugging log
-        with open(pdf_path, "rb") as pdf_file:
-            reader = PyPDF2.PdfReader(pdf_file)
-            for page in reader.pages:
-                page_text = page.extract_text()
-                if page_text:
-                    text += page_text + "\n"
-    print("Extracted text from PDF files:", text[:500])  # Debugging log (First 500 chars)
-    return text
-
-def get_text_from_csv(csv_files):
-    text = ""
-    for csv_path in csv_files:
-        print(f"Reading CSV file: {csv_path}")  # Debugging log
-        df = pd.read_csv(csv_path)
-        text += df.to_string() + "\n"
-    print("Extracted text from CSV files:", text[:500])  # Debugging log (First 500 chars)
-    return text
-
-def get_text_from_docx(docx_files):
-    text = ""
-    for docx_path in docx_files:
-        print(f"Reading DOCX file: {docx_path}")  # Debugging log
-        doc = Document(docx_path)
-        for para in doc.paragraphs:
-            text += para.text + "\n"
-    print("Extracted text from DOCX files:", text[:500])  # Debugging log (First 500 chars)
-    return text
-
-def get_text_from_ipynb(ipynb_files):
-    text = ""
-    for ipynb_path in ipynb_files:
-        print(f"Reading IPYNB file: {ipynb_path}")  # Debugging log
-        with open(ipynb_path, "r", encoding="utf-8") as file:
-            notebook = json.load(file)
-            for cell in notebook.get("cells", []):
-                if cell.get("cell_type") == "markdown":
-                    text += "\n".join(cell.get("source", [])) + "\n"
-    print("Extracted text from IPYNB files:", text[:500])  # Debugging log (First 500 chars)
-    return text
-
-def chatbot_interface(question):
-    folder_path = "New_Data_Analytics/"
-    extracted_files = extract_files_from_folder(folder_path)
-    
+def combine_text_from_files(extracted_files):
+    """Combines text from all extracted files."""
     text = (
         get_text_from_pdf(extracted_files["pdf"]) +
         read_text_from_files(extracted_files["txt"]) +
@@ -116,13 +59,31 @@ def chatbot_interface(question):
         get_text_from_docx(extracted_files["docx"]) +
         get_text_from_ipynb(extracted_files["ipynb"])
     )
+    return text
+
+def generate_response(question, text):
+    """Uses OpenAI to answer a question based on extracted text."""
+    response = openai.ChatCompletion.create(
+        model="gpt-3.5-turbo",
+        messages=[
+            {"role": "system", "content": "You are a data analytics assistant. Answer the question based on the provided document content."},
+            {"role": "user", "content": f"{question}\n\nBased on the following document content:\n{text[:3000]}"}  # Limit to 3000 characters to avoid excessive token usage
+        ]
+    )
+    return response["choices"][0]["message"]["content"].strip()
+
+def chatbot_interface(question):
+    folder_path = "New_Data_Analytics/"
+    extracted_files = extract_files_from_folder(folder_path)
+    
+    text = combine_text_from_files(extracted_files)
     
     print("Final extracted text for chatbot processing:", text[:500])  # Debugging log (First 500 chars)
     
     if not text.strip():
         return "The folder does not contain valid PDF, TXT, CSV, DOCX, or IPYNB files. Please upload supported file types."
     
-    return "Files successfully read. Processing question..."
+    return generate_response(question, text)
 
 # Gradio interface
 demo = gr.Interface(
@@ -131,4 +92,4 @@ demo = gr.Interface(
     outputs=gr.Textbox(label="Answer")
 )
 
-demo.launch()
+demo.launch()