Delete app.py

app.py

@@ -1,120 +0,0 @@
-import gradio as gr
-from huggingface_hub import InferenceClient
-from sentence_transformers import SentenceTransformer
-import faiss
-import numpy as np
-import pdfplumber
-
-# Initialize the InferenceClient
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-# Function to extract text from PDFs
-def extract_text_from_pdf(pdf_path):
-    text = ""
-    with pdfplumber.open(pdf_path) as pdf:
-        for page in pdf.pages:
-            page_text = page.extract_text()
-            if page_text:
-                text += page_text
-    return text
-
-# Load and preprocess book PDFs
-pdf_files = ["Diagnostic and statistical manual of mental disorders _ DSM-5 ( PDFDrive.com ).pdf"]
-all_texts = [extract_text_from_pdf(pdf) for pdf in pdf_files]
-
-# Split text into chunks
-def chunk_text(text, chunk_size=300):
-    sentences = text.split('. ')
-    chunks, current_chunk = [], ""
-    for sentence in sentences:
-        if len(current_chunk) + len(sentence) <= chunk_size:
-            current_chunk += sentence + ". "
-        else:
-            chunks.append(current_chunk.strip())
-            current_chunk = sentence + ". "
-    if current_chunk:
-        chunks.append(current_chunk.strip())
-    return chunks
-
-# Prepare embeddings for each book
-model = SentenceTransformer("all-MiniLM-L6-v2")
-index = faiss.IndexFlatL2(model.get_sentence_embedding_dimension())
-chunked_texts = [chunk_text(text) for text in all_texts]
-all_chunks = [chunk for chunks in chunked_texts for chunk in chunks]
-embeddings = model.encode(all_chunks, convert_to_tensor=True).detach().cpu().numpy()
-index.add(embeddings)
-
-# Function to generate response
-def respond(message, history, system_message, max_tokens, temperature, top_p):
-    # Step 1: Retrieve relevant chunks based on user message
-    query_embedding = model.encode([message], convert_to_tensor=True).detach().cpu().numpy()
-    k = 5
-    _, indices = index.search(query_embedding, k)
-    relevant_chunks = " ".join([all_chunks[idx] for idx in indices[0]])
-    
-    # Step 2: Create prompt for the model
-    prompt = f"{system_message}\n\nUser Query: {message}\n\nRelevant Information: {relevant_chunks}"
-    response = ""
-
-    # Step 3: Generate response
-    for message in client.chat_completion(
-        [{"role": "system", "content": system_message}, {"role": "user", "content": message}],
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-        response += token
-        yield response
-
-# HTML for navigation bar
-navbar_html = """
-<div style="background-color: #f1f1f1; padding: 10px; text-align: center;">
-    <a href="#about" style="margin-right: 20px; text-decoration: none; font-weight: bold;">About Us</a>
-    <a href="#team" style="text-decoration: none; font-weight: bold;">Team</a>
-</div>
-"""
-
-# About Us section
-about_us = """
-# About Us
-*Personal Psychologist AI* is an AI-driven mental health assistant designed to provide users with mental health support and guidance. The application leverages state-of-the-art natural language processing (NLP) techniques to analyze user input and provide insightful, empathetic, and actionable responses. The AI is powered by models fine-tuned with mental health-related data, including the DSM-5, to assist in diagnosing and offering mental health advice based on text input.
-
-### Key Features:
-- **AI-Powered Mental Health Support**: Uses advanced NLP models like GPT-2 and fine-tuned models for mental health sentiment analysis.
-- **DSM-5 Integration**: The app uses DSM-5 (Diagnostic and Statistical Manual of Mental Disorders) to guide responses related to various mental health conditions.
-- **Personalized Recommendations**: Based on user input, the AI provides personalized advice, coping strategies, and insights.
-- **Fast Information Retrieval**: Embedding techniques (like Sentence-BERT) and FAISS (Fast Approximate Nearest Neighbors) are used for efficient information retrieval from mental health books and other resources.
-- **User Interaction**: Users can input their mental health concerns or queries, and the AI generates helpful and empathetic responses.
-
-### Project Team:
-- **Hamaad Ayub Khan**: hakgs1234@gmail.com | [LinkedIn](https://linkedin.com/in/hamaadayubkhan)
-- **Muhammad Zeeshan Burki**: zeshanburki42@gmail.com | [LinkedIn](https://linkedin.com/in/muhammad-zeeshan-burki)
-- **Izhan Sajid**: izhansajid847@gmail.com | [LinkedIn](https://linkedin.com/in/izhan-sajid-70a6bb302)
-- **Izza Shahzad**: izzashahzad2003@gmail.com | [LinkedIn](https://linkedin.com/in/izza-shahzad-b43273267)
-- **Salar Tariq**: msalartariq05@gmail.com | [LinkedIn](https://linkedin.com/in/msalaartariq)
-"""
-
-# Gradio ChatInterface with additional inputs
-demo = gr.ChatInterface(
-    respond,
-    title="Personal Psychologist",
-    description="AI-driven mental health assistant based on DSM-5.",
-    additional_inputs=[
-        gr.Textbox(value="You are a helpful and empathetic mental health assistant.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"),
-    ],
-    layout="vertical",
-)
-
-# Combine Navbar and About Us section with the interface
-with demo:
-    gr.HTML(navbar_html)
-    gr.HTML(about_us)
-
-# Launch the Gradio interface
-if __name__ == "__main__":
-    demo.launch()