Update app.py

app.py

@@ -1,64 +1,68 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+import pdfplumber
+import openai
+import os
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+# Set up OpenAI API Key (Replace with your actual key)
+openai.api_key = "YOUR_OPENAI_API_KEY"
 
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+def clean_text(text):
+    """Cleans extracted text for better processing by the model."""
+    text = unicodedata.normalize("NFKC", text)  # Normalize Unicode characters
+    text = re.sub(r'\s+', ' ', text).strip()  # Remove extra spaces and newlines
+    text = re.sub(r'[^a-zA-Z0-9.,!?;:\'\"()\-]', ' ', text)  # Keep basic punctuation
+    text = re.sub(r'(?i)(page\s*\d+)', '', text)  # Remove page numbers
+    return text
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+def extract_text_from_pdf(pdf_file):
+    """Extract and clean text from the uploaded PDF."""
+    try:
+        with pdfplumber.open(pdf_file) as pdf:
+            text = " ".join(clean_text(text) for page in pdf.pages if (text := page.extract_text()))
+        return text
+    except Exception as e:
+        print(f"Error extracting text: {e}")
+        return None
 
-    messages.append({"role": "user", "content": message})
+def split_text(text, chunk_size=500):
+    """Splits text into smaller chunks for faster processing."""
+    chunks = []
+    for i in range(0, len(text), chunk_size):
+        chunks.append(text[i:i+chunk_size])
+    return chunks
 
-    response = ""
+def chatbot(pdf_file, user_question):
+    """Processes the PDF and answers the user's question."""
+    
+    # Step 1: Extract text from the PDF
+    text = extract_text_from_pdf(pdf_file)
+    
+    # Step 2: Split into chunks
+    chunks = split_text(text)
+    
+    # Step 3: Use only the first chunk for now (to reduce token usage)
+    if not chunks:
+        return "Could not extract any text from the PDF."
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+    prompt = f"Based on this document, answer the question:\n\nDocument:\n{chunks[0]}\n\nQuestion: {user_question}"
 
-        response += token
-        yield response
+    # Step 4: Send to OpenAI's GPT-3.5
+    response = openai.ChatCompletion.create(
+        model="gpt-3.5-turbo",
+        messages=[{"role": "user", "content": prompt}]
+    )
 
+    # Step 5: Return the chatbot's response
+    return response["choices"][0]["message"]["content"]
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
+# Gradio Interface
+iface = gr.Interface(
+    fn=chatbot,
+    inputs=[gr.File(label="Upload PDF"), gr.Textbox(label="Ask a Question")],
+    outputs=gr.Textbox(label="Answer"),
+    title="PDF Q&A Chatbot"
 )
 
-
-if __name__ == "__main__":
-    demo.launch()
+# Launch Gradio app
+iface.launch()