Create app.py

app.py

@@ -0,0 +1,82 @@
+import gradio as gr
+import faiss
+import numpy as np
+from sentence_transformers import SentenceTransformer
+from transformers import pipeline
+from PyPDF2 import PdfReader
+
+# Load AI models
+embedding_model = SentenceTransformer("sentence-transformers/all-MiniLM-L6-v2")  # Converts text to numbers
+llm_pipeline = pipeline("text2text-generation", model="google/flan-t5-small")  # AI that answers questions
+
+# Memory (Database) to store text
+index = None
+chunks = []
+
+# Load and process document
+def load_document(file):
+    global index, chunks
+    text = ""
+    
+    # Determine file path or object
+    # If file is a string, it's a file path
+    if isinstance(file, str):
+        file_path = file
+    else:
+        # If file is not a string, try to use its .name attribute
+        file_path = file.name
+
+    # Read PDF or text file
+    if file_path.endswith(".pdf"):
+        reader = PdfReader(file_path)
+        text = "\n".join(
+            [page.extract_text() for page in reader.pages if page.extract_text()]
+        )
+    else:
+        with open(file_path, "r", encoding="utf-8") as f:
+            text = f.read()
+
+    # Break text into small parts
+    sentences = text.split(". ")
+    chunks = [" ".join(sentences[i:i + 5]) for i in range(0, len(sentences), 5)]
+
+    # Create embeddings and store in FAISS
+    embeddings = np.array([embedding_model.encode(chunk) for chunk in chunks])
+    index = faiss.IndexFlatL2(embeddings.shape[1])
+    index.add(embeddings)
+
+    return "📄 Document is ready! Now ask your question."
+
+# Find and answer questions
+def get_answer(query):
+    if index is None:
+        return "❌ Please upload a document first."
+    
+    # Find best matching text
+    query_embedding = embedding_model.encode(query).reshape(1, -1)
+    distances, indices = index.search(query_embedding, 3)
+    retrieved_text = " ".join([chunks[i] for i in indices[0]])
+
+    # Ask AI to generate an answer
+    input_text = f"Question: {query}\nContext: {retrieved_text}"
+    response = llm_pipeline(input_text, max_length=100)[0]['generated_text']
+    
+    return response
+
+# Webpage design
+with gr.Blocks() as demo:
+    gr.Markdown("# 📚 Smart Study Helper")
+    
+    file_input = gr.File(label="Upload a textbook or notes (PDF/TXT)", file_types=[".pdf", ".txt"])
+    upload_button = gr.Button("Process Document")
+    status_text = gr.Textbox(label="📢 Status", interactive=False)
+
+    query_input = gr.Textbox(label="Ask a question from the document:")
+    query_button = gr.Button("Get Answer")
+    output_text = gr.Textbox(label="🤖 AI Answer", interactive=False)
+
+    upload_button.click(load_document, inputs=file_input, outputs=status_text)
+    query_button.click(get_answer, inputs=query_input, outputs=output_text)
+
+# Run the app
+demo.launch()