Create app.py

app.py

@@ -0,0 +1,118 @@
+# -*- coding: utf-8 -*-
+"""Customer_Care_ChatbotV1.ipynb
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/1ICE_-Hl23GdbEO6Tt5VjvJ8XMyYC3Z3b
+"""
+
+
+
+
+
+import torch
+import fitz  # PyMuPDF for PDF text extraction
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
+from sentence_transformers import SentenceTransformer
+import faiss
+import gradio as gr
+import os
+from huggingface_hub import login
+
+# Authenticate with Hugging Face Hub
+pdf_path1 ='/content/Chrono 1.pdf'
+pdf_path2 ='/content/Chrono 2.pdf'
+pdf_path3 ='/content/Chrono 3.pdf'
+
+# Load the Mistral 7B model and tokenizer
+model_name = 'mistralai/Mistral-7B-Instruct-v0.3'
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto", torch_dtype=torch.float16)
+
+# Load sentence transformer for embedding and similarity search
+embedder = SentenceTransformer('sentence-transformers/all-MiniLM-L6-v2')
+
+# Function to extract text from PDFs
+def extract_text_from_pdf(pdf_file_path):
+    doc = fitz.open(pdf_file_path)
+    text = ""
+    for page in doc:
+        text += page.get_text("text")
+    return text
+
+# Placeholder PDF knowledge base (Extracted content from PDFs)
+pdf_knowledge_base = []
+pdf_files = [pdf_path1, pdf_path2,pdf_path3]  # Add the actual paths to your PDF files
+
+for pdf_file in pdf_files:
+    pdf_text = extract_text_from_pdf(pdf_file)
+    pdf_knowledge_base.append({"document": pdf_file, "content": pdf_text})
+
+# Combine extracted text with specific company information
+knowledge_base = [
+    {"question": "How does DiabeTrek ensure data privacy and security?",
+     "answer": ("DiabeTrek ensures data privacy through multiple layers of protection, including data encryption during "
+                "transit and at rest. We comply with regulations like HIPAA and GDPR to safeguard your personal data.")},
+    {"question": "What are DiabeTrek's emergency guidelines?",
+     "answer": "DiabeTrek advises users to seek immediate medical attention in case of diabetes-related emergencies. This chatbot is not for emergency use."},
+    {"question": "What are DiabeTrek's mission, vision, and values?",
+     "answer": "DiabeTrek's mission is to improve the lives of people with diabetes through innovative AI-driven solutions. Our vision is a world where diabetes care is seamless, proactive, and accessible."},
+    # Additional items can be added here following the CEO's instructions
+]
+
+# Create a FAISS index for efficient retrieval
+embedding_dim = 384  # Output dimension of the MiniLM model
+index = faiss.IndexFlatL2(embedding_dim)
+
+# Create a list of embeddings and index them
+knowledge_embeddings = []
+for entry in knowledge_base:
+    embedding = embedder.encode(entry['question'], convert_to_tensor=False)
+    knowledge_embeddings.append(embedding)
+    index.add(embedding.reshape(1, -1))
+
+# Create embeddings for PDF content and index them
+for pdf_entry in pdf_knowledge_base:
+    embedding = embedder.encode(pdf_entry['content'], convert_to_tensor=False)
+    knowledge_embeddings.append(embedding)
+    index.add(embedding.reshape(1, -1))
+
+# RAG Retrieval function
+def retrieve_knowledge(question, top_k=1):
+    question_embedding = embedder.encode(question, convert_to_tensor=False)
+    D, I = index.search(question_embedding.reshape(1, -1), top_k)
+    results = [knowledge_base[idx] for idx in I[0]]
+    return results
+
+# Chatbot function combining retrieval and generation
+def customer_support_chatbot(user_input):
+    # Retrieve relevant knowledge
+    retrieved_knowledge = retrieve_knowledge(user_input)
+
+    # Prepare context for the generative model
+    context = " ".join([f"Q: {entry['question']} A: {entry['answer']}" for entry in retrieved_knowledge])
+
+    # Generate response using Mistral
+    prompt = f"Customer Question: {user_input}\n\n{context}\n\nResponse:"
+    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+    outputs = model.generate(**inputs, max_length=150, do_sample=True, temperature=0.7)
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+    return response
+
+# Gradio UI
+def gradio_interface(user_input):
+    response = customer_support_chatbot(user_input)
+    return response
+
+# Build Gradio interface
+interface = gr.Interface(fn=gradio_interface,
+                         inputs="text",
+                         outputs="text",
+                         title="DiabeTrek Customer Support Chatbot",
+                         description="Ask any question about DiabeTrek, its services, and policies.")
+
+# Launch the Gradio app
+interface.launch()
+