Delete app.py

app.py

@@ -1,116 +0,0 @@
-import gradio as gr
-from langchain.document_loaders import PyPDFLoader
-from langchain.text_splitter import CharacterTextSplitter
-from langchain.embeddings import SentenceTransformerEmbeddings
-from langchain.vectorstores import FAISS
-from langchain.memory import ConversationBufferMemory
-from groq import Groq
-import requests
-from bs4 import BeautifulSoup
-import time  # To simulate progress updates
-
-client = Groq(api_key="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")
-embedding_model = SentenceTransformerEmbeddings(model_name="sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2")
-
-memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)
-
-def process_pdf_with_langchain(pdf_path, progress_callback):
-    # progress_callback("Initializing PDF processing... 0%")
-    time.sleep(0.5)
-    loader = PyPDFLoader(pdf_path)
-    # progress_callback("Loading PDF... 20%")
-    documents = loader.load()
-    time.sleep(0.5)
-    # progress_callback("Splitting documents... 50%")
-    text_splitter = CharacterTextSplitter(chunk_size=500, chunk_overlap=50)
-    split_documents = text_splitter.split_documents(documents)
-    time.sleep(0.5)
-    # progress_callback("Creating vector store... 80%")
-    vectorstore = FAISS.from_documents(split_documents, embedding_model)
-    retriever = vectorstore.as_retriever(search_kwargs={"k": 3})
-    progress_callback("Processing complete! 100%")
-    return retriever
-
-
-def generate_response(query, retriever=None, use_web_search=False):
-
-    knowledge = ""
-
-    if retriever:
-        relevant_docs = retriever.get_relevant_documents(query)
-        knowledge += "\n".join([doc.page_content for doc in relevant_docs])
-
-    if use_web_search:
-        web_results = scrape_google_search(query)
-        knowledge += f"\n\nWeb Search Results:\n{web_results}"
-
-    chat_history = memory.load_memory_variables({}).get("chat_history", "")
-    context = (
-        f"This is a conversation with ParvizGPT, an AI model designed by Amir Mahdi Parviz from Kermanshah University of Technology (KUT), "
-        f"to help with tasks like answering questions in Persian, providing recommendations, and decision-making."
-    )
-    if knowledge:
-        context += f"\n\nRelevant Knowledge:\n{knowledge}"
-    if chat_history:
-        context += f"\n\nChat History:\n{chat_history}"
-
-    context += f"\n\nYou: {query}\nParvizGPT:"
-
-    chat_completion = client.chat.completions.create(
-        messages=[{"role": "user", "content": context}],
-        model="llama-3.3-70b-versatile",
-    )
-    response = chat_completion.choices[0].message.content.strip()
-
-    memory.save_context({"input": query}, {"output": response})
-    return response
-
-def upload_and_process(file, progress_display):
-    try:
-        global retriever
-        progress_updates = []
-        
-        retriever = process_pdf_with_langchain(file.name, lambda msg: progress_updates.append(msg))
-
-        return "\n".join(progress_updates), "File uploaded and processed successfully."
-    except Exception as e:
-        return "", f"Error processing file: {e}"
-
-def gradio_interface(user_message, chat_box, enable_web_search=False):
-    global retriever
-    response = generate_response(user_message, retriever=retriever, use_web_search=enable_web_search)
-    chat_box.append(("You", user_message))
-    chat_box.append(("ParvizGPT", response))
-    return chat_box
-
-def clear_memory():
-    memory.clear()
-    return []
-
-retriever = None
-with gr.Blocks() as interface:
-    gr.Markdown("## ParvizGPT")
-    with gr.Row():
-        chat_box = gr.Chatbot(label="Chat History", value=[])
-    with gr.Row():
-        user_message = gr.Textbox(
-            label="Your Message",
-            placeholder="Type your message here and press Enter...",
-            lines=1,
-            interactive=True,
-        )
-    with gr.Row():
-        clear_memory_btn = gr.Button("Clear Memory", interactive=True)
-        enable_web_search = gr.Checkbox(label="🌐Enable Web Search", value=False, interactive=True)
-    with gr.Row():
-        pdf_upload = gr.UploadButton(label="📄 Upload Your PDF", file_types=[".pdf"])
-        progress_display = gr.Textbox(label="Progress", placeholder="Progress updates will appear here", interactive=True)
-    with gr.Row():
-        submit_btn = gr.Button("Submit")
-    pdf_upload.upload(upload_and_process, inputs=[pdf_upload, progress_display], outputs=[progress_display])
-
-    submit_btn.click(gradio_interface, inputs=[user_message, chat_box, enable_web_search], outputs=chat_box)
-    user_message.submit(gradio_interface, inputs=[user_message, chat_box, enable_web_search], outputs=chat_box)
-    clear_memory_btn.click(clear_memory, inputs=[], outputs=chat_box)
-
-interface.launch()