Update app.py

app.py

@@ -6,8 +6,6 @@ from langchain.vectorstores import FAISS
 from langchain.embeddings import HuggingFaceEmbeddings
 from langchain.chains import RetrievalQA
 from langchain.llms import HuggingFacePipeline
-
-# 1. Load Granite 2B model
 model_id = "ibm-granite/granite-3.3-2b-instruct"
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(
@@ -24,8 +22,6 @@ def extract_text(pdf_file):
         if page.extract_text():
             text += page.extract_text() + "\n"
     return text
-
-# 3. Build retrieval-based QA chain
 def build_qa_chain(pdf_text):
     splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
     chunks = splitter.split_text(pdf_text)
@@ -52,8 +48,7 @@ def process_pdf(file):
     global qa_chain
     text = extract_text(file)
     qa_chain = build_qa_chain(text)
-    return "✅ PDF processed. You can now ask questions."
-
+    return
 def answer_question(question):
     if qa_chain is None:
         return "❌ Please upload a PDF first."
@@ -73,5 +68,4 @@ with gr.Blocks() as demo:
         answer_output = gr.Textbox(label="Answer")
         ask_btn = gr.Button("Ask")
     ask_btn.click(answer_question, question_input, answer_output)
-
-demo.launch()
+demo.launch()