Create app.py

app.py

@@ -0,0 +1,85 @@
+import os
+import streamlit as st
+import google.generativeai as genai
+from docx import Document
+import openpyxl
+from pdfminer.high_level import extract_text
+import csv
+from pptx import Presentation
+from io import StringIO  # For handling string-based CSV
+
+# Configure Gemini API
+GOOGLE_API_KEY = os.environ.get("GOOGLE_API_KEY")
+if not GOOGLE_API_KEY:
+    st.error("Please set the GOOGLE_API_KEY environment variable.")
+    st.stop()
+
+genai.configure(api_key=GOOGLE_API_KEY)
+model = genai.GenerativeModel('gemini-1.5-flash')  # Or another Gemini model
+
+
+def load_and_extract_text(file_path):
+    try:
+        file_extension = file_path.split('.')[-1].lower()
+
+        if file_extension == 'docx':
+            doc = Document(file_path)
+            text = '\n'.join([paragraph.text for paragraph in doc.paragraphs])
+        elif file_extension == 'xlsx':
+            workbook = openpyxl.load_workbook(file_path)
+            text = ""
+            for sheet in workbook:
+                for row in sheet.iter_rows():
+                    text += ' '.join([str(cell.value) for cell in row if cell.value is not None]) + '\n'
+        elif file_extension == 'pdf':
+            text = extract_text(file_path)
+        elif file_extension == 'csv':
+            with open(file_path, 'r', encoding='utf-8') as csvfile: # Explicit encoding
+                reader = csv.reader(csvfile)
+                text = '\n'.join([' '.join(row) for row in reader]) # Join rows with spaces
+        elif file_extension == 'txt':
+            with open(file_path, 'r', encoding='utf-8') as txtfile: #Explicit encoding
+                text = txtfile.read()
+        elif file_extension == 'pptx':
+            prs = Presentation(file_path)
+            text = '\n'.join([shape.text for slide in prs.slides for shape in slide.shapes if hasattr(shape, 'text')])
+        else:
+            return "Unsupported file format."
+
+        return text
+    except Exception as e:
+        return f"Error processing file: {e}"
+
+
+def process_document_and_answer(extracted_text, question):
+    if "Error processing file" in extracted_text or "Unsupported file format" in extracted_text:
+        return extracted_text
+
+    prompt = f"Context: {extracted_text}\n\nQuestion: {question}\n\nAnswer:"
+
+    try:
+        response = model.generate_content(prompt)
+        return response.text
+    except Exception as e:
+        return f"Error generating answer: {e}"
+
+
+# Streamlit UI
+st.title("Gemini Document Q&A")
+
+uploaded_file = st.file_uploader("Upload a document", type=["docx", "xlsx", "pdf", "csv", "txt", "pptx"])
+
+question = st.text_input("Ask a question about the document:")
+
+if uploaded_file is not None and question:
+    # Save the uploaded file to a temporary location
+    temp_file_path = "temp." + uploaded_file.name.split('.')[-1].lower()
+    with open(temp_file_path, "wb") as temp_file:
+        temp_file.write(uploaded_file.read())
+
+    extracted_text = load_and_extract_text(temp_file_path)
+
+    os.remove(temp_file_path)  # Clean up the temporary file
+
+    answer = process_document_and_answer(extracted_text, question)
+    st.write("Answer:", answer)