Create app.py

app.py

@@ -0,0 +1,94 @@
+import gradio as gr
+import fitz
+import numpy as np
+import requests
+import faiss
+import re
+import json
+import pandas as pd
+from docx import Document
+from pptx import Presentation
+from sentence_transformers import SentenceTransformer
+from concurrent.futures import ThreadPoolExecutor
+import os
+
+# Configuration - Get API key from environment variables
+GEMINI_API_KEY = os.environ.get("GEMINI_API_KEY")
+MODEL_NAME = "all-MiniLM-L6-v2"
+CHUNK_SIZE = 1024
+MAX_TOKENS = 4096
+WORKERS = 8
+
+# Initialize model with error handling
+try:
+    MODEL = SentenceTransformer(MODEL_NAME, device='cpu')
+except Exception as e:
+    raise RuntimeError(f"Failed to initialize model: {str(e)}")
+
+class DocumentProcessor:
+    def __init__(self):
+        self.index = faiss.IndexFlatIP(MODEL.get_sentence_embedding_dimension())
+        self.chunks = []
+        self.processor_pool = ThreadPoolExecutor(max_workers=WORKERS)
+
+    # [Keep all the original document processing methods unchanged]
+    # ... (Include all the document processing methods from previous version) ...
+
+# [Include the complete DocumentProcessor class implementation]
+# ... (Include the full class implementation from previous version) ...
+
+# Initialize processor
+processor = DocumentProcessor()
+
+# Gradio interface with improved error handling
+with gr.Blocks(theme=gr.themes.Soft(), title="Document Chatbot") as app:
+    gr.Markdown("## 📚 Multi-Format Document Chatbot")
+    
+    with gr.Row():
+        with gr.Column(scale=2):
+            files = gr.File(
+                file_count="multiple",
+                file_types=[".pdf", ".docx", ".txt", ".pptx", ".xls", ".xlsx", ".csv"],
+                label="Upload Documents",
+                max_size=500*1024*1024
+            )
+            process_btn = gr.Button("Process Documents", variant="primary")
+            status = gr.Textbox(label="Processing Status")
+            
+        with gr.Column(scale=3):
+            chatbot = gr.Chatbot(height=500, label="Chat History")
+            question = gr.Textbox(
+                label="Ask a question",
+                placeholder="Type your question here...",
+                max_lines=3
+            )
+            with gr.Row():
+                ask_btn = gr.Button("Ask", variant="primary")
+                clear_btn = gr.Button("Clear Chat")
+
+    process_btn.click(
+        fn=processor.process_documents,
+        inputs=files,
+        outputs=status
+    )
+
+    def ask_question(question, chat_history):
+        if not question.strip():
+            return chat_history + [("", "Please enter a valid question")]
+        answer, success = processor.query(question)
+        return chat_history + [(question, answer)]
+
+    ask_btn.click(
+        fn=ask_question,
+        inputs=[question, chatbot],
+        outputs=chatbot
+    ).then(lambda: "", None, question)
+
+    clear_btn.click(
+        fn=lambda: [],
+        inputs=None,
+        outputs=chatbot
+    )
+
+if __name__ == "__main__":
+    app.launch(debug=True)