Create app.py

app.py

@@ -0,0 +1,91 @@
+import gradio as gr
+from langchain.document_loaders import PyPDFLoader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.vectorstores import FAISS
+from langchain.chains import RetrievalQA
+from langchain.llms import HuggingFacePipeline
+
+from transformers import pipeline
+import os
+
+# Global variables
+vectorstore = None
+qa_chain = None
+
+# Load embedding model once
+embeddings = HuggingFaceEmbeddings(
+    model_name="sentence-transformers/all-MiniLM-L6-v2"
+)
+
+# Load LLM once
+pipe = pipeline(
+    "text2text-generation",
+    model="google/flan-t5-base",
+    max_length=512
+)
+
+llm = HuggingFacePipeline(pipeline=pipe)
+
+def process_pdf(pdf_file):
+    global vectorstore, qa_chain
+    
+    if pdf_file is None:
+        return "Please upload a PDF first."
+    
+    # Load PDF
+    loader = PyPDFLoader(pdf_file.name)
+    documents = loader.load()
+    
+    # Split text
+    splitter = RecursiveCharacterTextSplitter(
+        chunk_size=1000,
+        chunk_overlap=200
+    )
+    texts = splitter.split_documents(documents)
+    
+    # Create vector DB
+    vectorstore = FAISS.from_documents(texts, embeddings)
+    
+    # Create QA chain
+    qa_chain = RetrievalQA.from_chain_type(
+        llm=llm,
+        retriever=vectorstore.as_retriever(),
+        return_source_documents=True
+    )
+    
+    return "PDF processed successfully! You can now ask questions."
+
+def ask_question(question):
+    global qa_chain
+    
+    if qa_chain is None:
+        return "Upload and process a PDF first."
+    
+    result = qa_chain(question)
+    
+    answer = result["result"]
+    sources = "\n\n".join(
+        [doc.page_content[:300] for doc in result["source_documents"]]
+    )
+    
+    return f"Answer:\n{answer}\n\nSources:\n{sources}"
+
+# Gradio UI
+with gr.Blocks() as demo:
+    gr.Markdown("# 📄 PDF Question Answering System")
+    gr.Markdown("Upload a PDF and ask questions about it.")
+    
+    pdf_input = gr.File(file_types=[".pdf"])
+    process_btn = gr.Button("Process PDF")
+    status = gr.Textbox(label="Status")
+    
+    question = gr.Textbox(label="Ask a question")
+    ask_btn = gr.Button("Get Answer")
+    
+    output = gr.Textbox(label="Response", lines=15)
+    
+    process_btn.click(process_pdf, inputs=pdf_input, outputs=status)
+    ask_btn.click(ask_question, inputs=question, outputs=output)
+
+demo.launch()