Update app.py

app.py

@@ -1,22 +1,14 @@
 import os
 import gradio as gr
-import tempfile
-from dotenv import load_dotenv
-
 from langchain_community.document_loaders import PyPDFLoader
 from langchain_text_splitters import RecursiveCharacterTextSplitter
 from langchain_huggingface import HuggingFaceEmbeddings
 from langchain_community.vectorstores import FAISS
-
 from groq import Groq
 
 # ================= ENVIRONMENT =================
-load_dotenv()
-GROQ_API_KEY = os.getenv("GROQ_API_KEY")  # Use HF secret
-
-client = None
-if GROQ_API_KEY:
-    client = Groq(api_key=GROQ_API_KEY)
+GROQ_API_KEY = os.getenv("GROQ_API_KEY")  # Set in Hugging Face Secrets
+client = Groq(api_key=GROQ_API_KEY) if GROQ_API_KEY else None
 
 vector_db = None
 
@@ -24,7 +16,6 @@ vector_db = None
 def groq_llm(prompt):
     if client is None:
         return "❌ GROQ API key not set. Set it in Hugging Face Secrets."
-
     response = client.chat.completions.create(
         model="llama-3.3-70b-versatile",
         messages=[{"role": "user", "content": prompt}],
@@ -34,27 +25,19 @@ def groq_llm(prompt):
 # ================= PROCESS PDF =================
 def process_pdf(file):
     global vector_db
-
     if file is None:
         return "❌ Please upload a PDF."
 
-    with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as tmp:
-        tmp.write(file)
-        pdf_path = tmp.name
+    # Use the file path from Gradio File component
+    pdf_path = file.name
 
     loader = PyPDFLoader(pdf_path)
     documents = loader.load()
 
-    splitter = RecursiveCharacterTextSplitter(
-        chunk_size=500,
-        chunk_overlap=100
-    )
+    splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=100)
     docs = splitter.split_documents(documents)
 
-    embeddings = HuggingFaceEmbeddings(
-        model_name="sentence-transformers/all-MiniLM-L6-v2"
-    )
-
+    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
     vector_db = FAISS.from_documents(docs, embeddings)
 
     return f"✅ PDF processed successfully! {len(docs)} chunks created."
@@ -62,16 +45,16 @@ def process_pdf(file):
 # ================= ASK QUESTION =================
 def ask_question(question, chat_history):
     global vector_db
-
     if vector_db is None:
-        return chat_history + [["System", "❌ Please upload and process a PDF first."]]
+        chat_history.append(["System", "❌ Please upload and process a PDF first."])
+        return chat_history, chat_history
 
     retriever = vector_db.as_retriever(search_kwargs={"k": 3})
     docs = retriever.get_relevant_documents(question)
     context = "\n\n".join([doc.page_content for doc in docs])
 
     prompt = f"""
-You are a smart assistant.
+You are an intelligent assistant.
 Answer ONLY using the provided context.
 
 Context:
@@ -82,7 +65,6 @@ Question:
 
 Answer:
 """
-
     answer = groq_llm(prompt)
     chat_history.append(["User", question])
     chat_history.append(["Assistant", answer])
@@ -91,14 +73,11 @@ Answer:
 # ================= GRADIO UI =================
 with gr.Blocks(css="""
     body {background-color: #f5f5f5;}
-    .gradio-container {max-width: 900px; margin:auto; padding:20px; border-radius:12px; box-shadow: 0 4px 15px rgba(0,0,0,0.1);}
-    .chat-message {border-radius:12px; padding:10px; margin:5px 0;}
-    .user {background-color:#4f46e5; color:white;}
-    .assistant {background-color:#e0e7ff; color:black;}
+    .gradio-container {max-width: 900px; margin:auto; padding:20px; border-radius:12px; box-shadow:0 4px 15px rgba(0,0,0,0.1);}
 """) as demo:
 
-    gr.Markdown("<h1 style='text-align:center; color:#4f46e5;'>📄 RAG PDF Question Answering</h1>", elem_id="title")
-    gr.Markdown("<p style='text-align:center; color:#333;'>Upload a PDF and chat with it like a smart assistant!</p>")
+    gr.Markdown("<h1 style='text-align:center; color:#4f46e5;'>📄 RAG PDF QA</h1>", elem_id="title")
+    gr.Markdown("<p style='text-align:center; color:#333;'>Upload a PDF and chat with it!</p>")
 
     if client is None:
         gr.Markdown("⚠️ GROQ_API_KEY not set. Set it in Hugging Face Secrets to enable answering.")
@@ -106,13 +85,14 @@ with gr.Blocks(css="""
     with gr.Row():
         with gr.Column(scale=1):
             pdf_upload = gr.File(label="Upload PDF", file_types=[".pdf"])
-            process_btn = gr.Button("Process PDF", elem_id="process_btn")
+            process_btn = gr.Button("Process PDF")
             status = gr.Textbox(label="Status", interactive=False)
         with gr.Column(scale=2):
             chatbot = gr.Chatbot(label="Chat with PDF")
             question = gr.Textbox(placeholder="Type your question here and press Enter")
-    
-    process_btn.click(process_pdf, inputs=pdf_upload, outputs=status)
-    question.submit(ask_question, inputs=[question, chatbot], outputs=[chatbot, chatbot])
+
+    process_btn.click(fn=process_pdf, inputs=pdf_upload, outputs=status)
+    question.submit(fn=ask_question, inputs=[question, chatbot], outputs=[chatbot, chatbot])
 
 demo.launch()
+