app.py

import gradio as gr
from transformers import pipeline
theme = gr.themes.ThemeClass.from_hub("mkill33/master_chief")
image_classifier = pipeline(
    "image-classification",
    model="google/vit-base-patch16-224"
) 
""""
(Tried UI design code from google)
import customtkinter as ctk

# Set UX theme preferences
ctk.set_appearance_mode("dark")  # Modes: "System", "Dark", "Light"
ctk.set_default_color_theme("blue") 

# Create the main window
app = ctk.CTk()
app.geometry("400x200")
app.title("Modern Python UI")

# Add a text label (UI element)
label = ctk.CTkLabel(app, text="Hello, User!", font=("Arial", 20))
label.pack(pady=20)

# Add an interactive button (UX element)
def on_click():
    label.configure(text="Button Clicked!")

button = ctk.CTkButton(app, text="Click Me", command=on_click)
button.pack(pady=10)

# Run the application loop
app.mainloop()
import torch
model = torch.hub.load('pytorch/vision:v0.6.0', 'resnet18', pretrained=True).eval()

import requests
from PIL import Image
from torchvision import transforms

# Download human-readable labels for ImageNet.
response = requests.get("https://git.io/JJkYN")
labels = response.text.split("\n")

def predict(inp):
  inp = transforms.ToTensor()(inp).unsqueeze(0)
  with torch.no_grad():
    prediction = torch.nn.functional.softmax(model(inp)[0], dim=0)
    confidences = {labels[i]: float(prediction[i]) for i in range(1000)}
  return confidences

gr.Interface(fn=predict,
             inputs=gr.Image(type="pil"),
             outputs=gr.Label(num_top_classes=3),
             examples=["lion.jpg", "cheetah.jpg"]).launch()
"""

from huggingface_hub import InferenceClient
from sentence_transformers import SentenceTransformer
client = InferenceClient("Qwen/Qwen2.5-7B-Instruct")

with open("recycling_text.txt", "r", encoding="utf-8") as file:
  # Read the entire contents of the file and store it in a variable
  recycling_text = file.read()

with open("aqi_text.txt", "r", encoding="utf-8") as file:
  # Read the entire contents of the file and store it in a variable
  aqi_text = file.read()

#image_classifier = pipeline("image-classification", model="google/vit-base-patch16-224")

def preprocess_text(text):
    # Strip extra whitespace from the beginning and the end of the text
    cleaned_text = text.strip()
    
    # Split the cleaned_text by every newline character (\n)
    chunks = cleaned_text.split("\n")
    
    # Create an empty list to store cleaned chunks
    cleaned_chunks = []

# Write your for-in loop below to clean each chunk and add it to the cleaned_chunks list
    for chunk in chunks:
        stripped_chunk = chunk.strip()
        if len(stripped_chunk) > 0:
          cleaned_chunks.append(stripped_chunk)
    return cleaned_chunks
combined_text = recycling_text + "\n" + aqi_text
cleaned_chunks = preprocess_text(combined_text)


model = SentenceTransformer('all-MiniLM-L6-v2')

def create_embeddings(text_chunks):
    chunk_embeddings = model.encode(text_chunks, convert_to_tensor=True)
    
    print(chunk_embeddings)
    
    # Print the shape of chunk_embeddings
    print(chunk_embeddings.shape)
    # Return the chunk_embeddings
    
    return chunk_embeddings

# Call the create_embeddings function and store the result in a new chunk_embeddings variable
chunk_embeddings = create_embeddings(cleaned_chunks)

def get_top_chunks(query, chunk_embeddings, text_chunks):
  # Convert the query text into a vector embedding
  query_embedding = model.encode(query, convert_to_tensor=True) # Complete this line

  # Normalize the query embedding to unit length for accurate similarity comparison
  query_embedding_normalized = query_embedding / query_embedding.norm()

  # Normalize all chunk embeddings to unit length for consistent comparison
  chunk_embeddings_normalized = chunk_embeddings / chunk_embeddings.norm(dim=1, keepdim=True)

  # Calculate cosine similarity between query and all chunks using matrix multiplication
  similarities = torch.matmul(chunk_embeddings_normalized,query_embedding_normalized) # Complete this line

  # Print the similarities
  print(similarities)

  # Find the indices of the 3 chunks with highest similarity scores
  top_indices = torch.topk(similarities, k=3).indices

  # Print the top indices
  print(top_indices)

  # Create an empty list to store the most relevant chunks
  top_chunks = []

  # Loop through the top indices and retrieve the corresponding text chunks
  for i in top_indices:
    chunk=text_chunks[i]
    top_chunks.append(chunk)
  # Return the list of most relevant chunks
  return top_chunks



def respond(message, history):
    messages = [{"role": "system", "content": "You are a friendly chatbot."}]

    if history:
        messages.extend(history)

    messages.append({"role": "user", "content": message})
    
    response = client.chat_completion(
        messages,
        max_tokens=1000
    )
    return response.choices[0].message.content.strip()

    chatbot = gr.ChatInterface(respond, type="messages")      
def classify_image(image):
    if image is None:
        return "Upload an image"
    results=image_classifier(image)
    output=""
    for result in results[:3]:
        label=result["label"]
        score=round(result["score"]*100,2)
        output += f"{label}: {score}%\n"
    return output
with gr.Blocks(theme=theme) as chatbot:
    gr.Image(value="enviff.png", show_label=False, interactive=False)
    with gr.Tab("Chatbot"):
        gr.ChatInterface(respond, title="From Waste To Wisdom, From Air To Action.")
    with gr.Tab("Image Classifier"):
        image_input = gr.Image(type="pil")
        image_output = gr.Textbox()
        classify_button = gr.Button("Classify Image")
        classify_button.click(
            fn=classify_image,
            inputs=image_input,
            outputs=image_output
        )

chatbot.launch()