Create app.py

app.py

@@ -0,0 +1,118 @@
+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)
+
+vector_db = None
+
+# ================= LLM FUNCTION =================
+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}],
+    )
+    return response.choices[0].message.content
+
+# ================= 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
+
+    loader = PyPDFLoader(pdf_path)
+    documents = loader.load()
+
+    splitter = RecursiveCharacterTextSplitter(
+        chunk_size=500,
+        chunk_overlap=100
+    )
+    docs = splitter.split_documents(documents)
+
+    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."
+
+# ================= 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."]]
+
+    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.
+Answer ONLY using the provided context.
+
+Context:
+{context}
+
+Question:
+{question}
+
+Answer:
+"""
+
+    answer = groq_llm(prompt)
+    chat_history.append(["User", question])
+    chat_history.append(["Assistant", answer])
+    return chat_history, chat_history
+
+# ================= 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;}
+""") 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>")
+
+    if client is None:
+        gr.Markdown("⚠️ GROQ_API_KEY not set. Set it in Hugging Face Secrets to enable answering.")
+
+    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")
+            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])
+
+demo.launch()