Create app.py

app.py

@@ -0,0 +1,235 @@
+import gradio as gr 
+import PyPDF2
+import io
+import os
+import time
+from together import Together 
+import textwrap 
+import tempfile
+
+# 1st work is to extract the pdf file 
+def extract_pdf(pdf_file):
+    text= ""
+    try:
+        if hasattr(pdf_file, "read"):  #convert pf into bytes format (data byte bit type)
+            pdf_content= pdf_file.read()
+            if hasattr(pdf_file,"seek"):
+                pdf_file.seek(0)
+
+        else:
+            #if it already in bites and read
+            pdf_content= pdf_file
+
+        pdf_reader= PyPDF2.PdfReader(io.BytesIO(pdf_content)) #START reading and need to extract the pdf
+
+        for page_num in range(len(pdf_reader.pages)):
+            page_text= pdf_reader.pages[page_num].extract_text()
+            if page_text: # check the extract is working or not
+                print("okay")
+                text= text + page_text + "\n"
+            else:
+                print("no extractable text is found there")
+                text += f"[Page{page_num+1}]" 
+        if not text.strip():
+            return "no text extracted from PDF it a scanned file or image"
+
+        return text
+    except Exception as e:
+        return f"Error when extracting text from pdf : {str(e)}"
+
+
+## create a function to chat with the pdf
+def chat_with_pdf(api_key, pdf_text, user_question, history):
+    if not api_key.strip():
+        return history + [(user_question,"Error: plase enter your own api key")], history
+    if not pdf_text.strip() or pdf_text.startswith("Error") or pdf_text.startswith("No text"):
+        return history + [(user_question,"Error: plase upload a valid pdf file with extractable text format")], history
+    if not user_question.strip():
+        return history + [(user_question,"Error: please  enter a valid question")], history
+
+    try:
+        # model connections all for same
+        client= Together(api_key=api_key) # server e giye hi dibe and server response korbe vhul hole server response korbe na 
+        max_content_len= 150000 # check for the number of word 
+
+        if len(pdf_text) > max_content_len:
+            half_len = max_content_len//2
+            pdf_context= pdf_text[: half_len]+ "\n\n[....Content truncated due to length ....]\n\n" + pdf_text[-half_len:]
+        else:
+            pdf_content= pdf_text
+
+        system_message= f"""You are an intelligent assistant designed to read, understand, and extract information from PDF documents. 
+Based on any question or query the user asks—whether it's about content, summaries, data extraction, definitions, insights, or interpretation—you will 
+analyze the following PDF content and provide an accurate, helpful response grounded in the document. Always respond with clear, concise, and context-aware information.
+PDF CONTENT:
+{pdf_context}
+Answer the user's questions only based on the PDF content above. If the answer cannot be found in the PDF, politely state that the information is not available in the provided document."""
+
+        messages= [
+            {"role": "system", "content": system_message}
+        ]
+        for h_user , h_bot in history:
+            messages.append({"role": "user", "content": h_user})
+            messages.append({"role": "assistant", "content": h_bot})
+
+        #add the current user question into history
+        messages.append(["role": "user", "content": user_question])
+
+        #connect the model with the app
+        reponse = client.chat.completions.create(
+            model= "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
+            messages= messages,
+            max_tokens= 5000 #5000
+            temperature= .7
+        )
+        assistance_reponse = response.choices[0].message.content
+
+        # update the chat history
+        new_history= history + [(user_question, assistance_reponse)] #history update purono conversation + current conver= new history
+
+        return new_history, new_history
+    except Exception as e:
+        error_message= f"Error:{str(e)}"
+        return history + [(user_question, error_message)], history
+
+# now process the pdf before the chat
+def process_pdf(pdf_file, api_key_input):
+    if pdf_file is None:
+        return "please upload a PDF file.","",[]
+    try:
+        file_name= os.path.basename(pdf_file.name) if hasattr(pdf_file,"name") else "please Upload"
+        pdf_text= extract_pdf(pdf_file)
+
+        if pdf_text.startswith("Error extracting text from PDF"):
+             return f"❌ {pdf_text}", "", []
+        if not pdf_text.strip() or pdf_text.startswith("No text could be extracted"):
+            return f"⚠️ {pdf_text}", "", []
+
+        word_count= len(pdf_text.split())
+        # Return a message with the file name and text content
+        status_message = f"✅ Successfully processed PDF: {file_name} ({word_count} words extracted)"
+
+        return status_message, pdf_text,[]
+    except Exception as e:
+        return f"❌ Error processing PDF: {str(e)}", "", []
+
+# 
+def validate_api_key(api_key):
+    """Simple validation for API key format"""
+    if not api_key or not api_key.strip():
+        return "❌ API Key is required"
+    
+    if len(api_key.strip()) < 10:
+        return "❌ API Key appears to be too short"
+    
+    return "✓ API Key format looks valid (not verified with server)"
+
+
+with gr.Blocks(title="chatsPDFsupport", theme=gr.themes.Ocean()) as app:
+    gr.Markdown("# 📄 ChatPDF with Together AI")
+    gr.Markdown("Upload a PDF and chat with it using the Llama-3.3-70B model.")
+
+    with gr.Row():
+        with gr.Column(scale=1)
+        api_key_input = gr.Textbox(
+                label="Together API Key",
+                placeholder="Enter your Together API key here...",
+                type="password")
+        # API key validation
+            api_key_status = gr.Textbox(
+                label="API Key Status",
+                interactive=False
+            )
+        # PDF upload
+            pdf_file = gr.File(
+                label="Upload PDF",
+                file_types=[".pdf"],
+                type="binary"  # Ensure we get binary data
+            )
+        # Process PDF button
+            process_button = gr.Button("Process PDF")
+            
+        # Status message
+        status_message = gr.Textbox(
+            label="Status",
+            interactive=False
+        )
+        # Hidden field to store the PDF text
+        pdf_text = gr.Textbox(visible=False)
+
+        # Optional: Show PDF preview
+        with gr.Accordion("PDF Content Preview", open=False):
+            pdf_preview = gr.Textbox(
+                label="Extracted Text Preview",
+                interactive=False,
+                max_lines=10,
+                show_copy_button=True
+            )
+
+    with gr.Column(scale=2): #right side column row
+        # Chat interface
+        chatbot = gr.Chatbot(
+        label="Chat with PDF",
+        height=500,
+        show_copy_button=True
+        )
+    # Question input
+        question = gr.Textbox(
+            label="Ask a question about the PDF",
+            placeholder="What is the main topic of this document?",
+            lines=2
+            )
+
+        #submit button 
+        sumbit_button= gr.Button("Submit Question")
+ 
+       # Event handlers
+    def update_preview(text):
+        """Update the preview with the first few lines of the PDF text"""
+        if not text or text.startswith("Error") or text.startswith("No text"):
+            return text
+        
+        # Get the first ~500 characters for preview
+        preview = text[:500]
+        if len(text) > 500:
+            preview += "...\n[Text truncated for preview. Full text will be used for chat.]"
+        return preview
+
+    # API key validation event
+    api_key_input.change(
+        fn=validate_api_key,
+        inputs=[api_key_input],
+        outputs=[api_key_status]
+    )
+    
+    process_button.click(
+        fn=process_pdf,
+        inputs=[pdf_file, api_key_input],
+        outputs=[status_message, pdf_text, chatbot]
+    ).then(
+        fn=update_preview,
+        inputs=[pdf_text],
+        outputs=[pdf_preview]
+    )
+    
+    submit_button.click(
+        fn=chat_with_pdf,
+        inputs=[api_key_input, pdf_text, question, chatbot],
+        outputs=[chatbot, chatbot]
+    ).then(
+        fn=lambda: "",
+        outputs=question
+    )
+    
+    question.submit(
+        fn=chat_with_pdf,
+        inputs=[api_key_input, pdf_text, question, chatbot],
+        outputs=[chatbot, chatbot]
+    ).then(
+        fn=lambda: "",
+        outputs=question
+    )
+
+# Launch the app
+if __name__ == "__main__":
+    app.launch(share=True)