Update app.py

app.py

@@ -1,58 +1,85 @@
 import gradio as gr
-from transformers import pipeline
-import PyPDF2
-
-summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
-
-def summarize_pdf(pdf_file):
-    if pdf_file is None:
-        return "❌ Please upload a PDF file first."
-    
-    try:
-        reader = PyPDF2.PdfReader(pdf_file)
-        text = ""
-        for page in reader.pages:
-            text += page.extract_text() or ""
-        
-        text = text[:2000]  # limit to avoid too long input
-        summary = summarizer(text, max_length=150, min_length=30, do_sample=False)[0]['summary_text']
-        return summary
-    except Exception as e:
-        return f"❌ Error reading PDF: {str(e)}"
-
-with gr.Blocks(css="""
-    body {background: #f0f4f8; font-family: 'Segoe UI', Tahoma, Geneva, Verdana, sans-serif;}
-    #main_container { max-width: 720px; margin: auto; padding: 2rem; background: white; 
-                     box-shadow: 0 8px 24px rgba(149, 157, 165, 0.2); border-radius: 12px; }
-    .btn-primary {background: #3b82f6; color: white; font-weight: 600; padding: 0.8rem 1.6rem;
-                  border-radius: 8px; border: none; transition: background 0.3s;}
-    .btn-primary:hover {background: #2563eb;}
-    .scroll-box {max-height: 220px; overflow-y: auto; padding: 1rem; border: 1px solid #ddd; border-radius: 8px; background: #fafafa;}
-""") as demo:
-
-    with gr.Column(elem_id="main_container"):
-        gr.Markdown(
-            """
-            <h1 style="text-align:center; color:#1e40af;">📄 PDF Summarizer</h1>
-            <p style="text-align:center; color:#475569;">
-            Upload your PDF and get a crisp summary generated by Hugging Face's BART model.
-            </p>
-            """
-        )
-        
-        pdf_input = gr.File(label="Upload PDF file", file_types=[".pdf"], interactive=True)
-        summary_output = gr.Textbox(label="Summary", interactive=False, elem_classes="scroll-box", lines=8)
-        summarize_btn = gr.Button("Generate Summary", elem_classes="btn-primary")
-
-        summarize_btn.click(fn=summarize_pdf, inputs=pdf_input, outputs=summary_output)
-
-        gr.Markdown(
-            """
-            <footer style="text-align:center; margin-top:2rem; font-size:0.9rem; color:#94a3b8;">
-            Made with ❤️ by YourName | Powered by Hugging Face & Gradio
-            </footer>
-            """
-        )
+from langchain_community.document_loaders import PyPDFLoader
+from langchain_community.embeddings import HuggingFaceEmbeddings
+from langchain_community.vectorstores import Chroma
+from langchain_community.llms import HuggingFaceEndpoint
+from langchain.chains import RetrievalQA
+import os
+import shutil
+
+# Hugging Face API key (store in your Space's secrets for security)
+HUGGINGFACEHUB_API_TOKEN = os.environ.get("HUGGINGFACEHUB_API_TOKEN")
+
+# Load HF Inference Endpoint (like mistralai/Mistral-7B-Instruct)
+llm = HuggingFaceEndpoint(
+    repo_id="mistralai/Mistral-7B-Instruct-v0.2",
+    temperature=0.2,
+    huggingfacehub_api_token=HUGGINGFACEHUB_API_TOKEN
+)
+
+# Embeddings (Hugging Face miniLM for fast processing)
+embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
+
+# Temporary folder to store PDFs
+UPLOAD_DIR = "pdf_uploads"
+if not os.path.exists(UPLOAD_DIR):
+    os.makedirs(UPLOAD_DIR)
+
+def process_pdf(file):
+    # Save PDF file
+    file_path = os.path.join(UPLOAD_DIR, file.name)
+    with open(file_path, "wb") as f:
+        f.write(file.read())
+    
+    # Load PDF text using langchain
+    loader = PyPDFLoader(file_path)
+    pages = loader.load_and_split()
+    
+    # Create Chroma vector store (in-memory)
+    vectordb = Chroma.from_documents(pages, embedding=embeddings)
+    retriever = vectordb.as_retriever()
+    
+    # Create RetrievalQA chain
+    qa_chain = RetrievalQA.from_chain_type(
+        llm=llm,
+        chain_type="stuff",
+        retriever=retriever,
+        return_source_documents=True
+    )
+    
+    # Return the QA chain to use in the chat
+    return qa_chain
+
+# Global variable to hold QA chain for the session
+qa_chain = None
+
+def upload_pdf(file):
+    global qa_chain
+    qa_chain = process_pdf(file)
+    return "✅ PDF uploaded and processed! Ask me anything about it."
+
+def chatbot(user_message, history):
+    if qa_chain is None:
+        return "❌ Please upload a PDF first.", history
+    
+    response = qa_chain.run(user_message)
+    history.append((user_message, response))
+    return "", history
+
+with gr.Blocks(theme=gr.themes.Soft()) as demo:
+    gr.Markdown("<h1 style='text-align:center;'>📚 PDF Chatbot Assistant</h1>")
+    
+    with gr.Row():
+        pdf_upload = gr.File(label="Upload your PDF", file_types=[".pdf"])
+        upload_btn = gr.Button("Process PDF")
+    
+    chatbot_ui = gr.Chatbot(height=400)
+    user_input = gr.Textbox(label="Ask something about the PDF...", placeholder="Type your question here and hit Enter")
+
+    upload_btn.click(upload_pdf, inputs=pdf_upload, outputs=chatbot_ui)
+    user_input.submit(chatbot, [user_input, chatbot_ui], [user_input, chatbot_ui])
+    
+    gr.Markdown("<footer style='text-align:center; font-size:0.85rem; color:#64748b;'>Created by YourName - Powered by Hugging Face</footer>")
 
 if __name__ == "__main__":
     demo.launch()