Delete app.py

app.py

@@ -1,69 +0,0 @@
-import gradio as gr
-import faiss
-import numpy as np
-import torch
-from sentence_transformers import SentenceTransformer
-from transformers import pipeline
-from PyPDF2 import PdfReader
-
-# Load embedding model & LLM
-embedding_model = SentenceTransformer("sentence-transformers/all-MiniLM-L6-v2")
-llm_pipeline = pipeline("text2text-generation", model="google/flan-t5-small")
-
-# Initialize FAISS index
-index = None
-chunks = []
-
-# Load and process document
-def load_document(file):
-    global index, chunks
-    text = ""
-
-    if file.name.endswith(".pdf"):
-        reader = PdfReader(file.name)
-        text = "\n".join([page.extract_text() for page in reader.pages if page.extract_text()])
-    else:
-        text = file.read().decode("utf-8")
-
-    # Split text into chunks
-    sentences = text.split(". ")
-    chunks = [" ".join(sentences[i:i + 5]) for i in range(0, len(sentences), 5)]
-
-    # Create embeddings and FAISS index
-    embeddings = np.array([embedding_model.encode(chunk) for chunk in chunks])
-    index = faiss.IndexFlatL2(embeddings.shape[1])
-    index.add(embeddings)
-
-    return "Document uploaded and indexed!"
-
-# Retrieve and generate response
-def get_answer(query):
-    if index is None:
-        return "Please upload a document first."
-    
-    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]])
-
-    input_text = f"Answer the question: {query}\nContext: {retrieved_text}"
-    response = llm_pipeline(input_text, max_length=100)[0]['generated_text']
-    
-    return response
-
-# Gradio Interface
-with gr.Blocks() as demo:
-    gr.Markdown("# 📄 Simple RAG App")
-    
-    file_input = gr.File(label="Upload a PDF or Text File")
-    upload_button = gr.Button("Process Document")
-    status_text = gr.Textbox(label="Status", interactive=False)
-
-    query_input = gr.Textbox(label="Enter your question:")
-    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)
-
-# Launch App
-demo.launch()