app.py

import gradio as gr
from transformers import TapexTokenizer, BartForConditionalGeneration
import pandas as pd
import pkg_resources

# Get a list of installed packages and their versions
installed_packages = {pkg.key: pkg.version for pkg in pkg_resources.working_set}

# Print the list of packages
for package, version in installed_packages.items():
    print(f"{package}=={version}")

#wikisql take longer to process
#model_name = "microsoft/tapex-large-finetuned-wikisql"  # You can change this to any other model from the list above
#model_name = "microsoft/tapex-base-finetuned-wikisql"

model_name = "microsoft/tapex-large-finetuned-wtq"
#model_name = "microsoft/tapex-base-finetuned-wtq"

tokenizer = TapexTokenizer.from_pretrained(model_name)
model = BartForConditionalGeneration.from_pretrained(model_name)

data = {
    "year": [1896, 1900, 1904, 2004, 2008, 2012],
    "city": ["athens", "paris", "st. louis", "athens", "beijing", "london"]
}
table = pd.DataFrame.from_dict(data)

def chatbot_response(user_message):
    
    #inputs = tokenizer.encode("User: " + user_message, return_tensors="pt")
    inputs = user_message
    encoding = tokenizer(table=table, query=inputs, return_tensors="pt")
    outputs = model.generate(**encoding)
    response = tokenizer.batch_decode(outputs, skip_special_tokens=True)
    
    return response

# Define the chatbot interface using Gradio
iface = gr.Interface(
    fn=chatbot_response,
    inputs=gr.Textbox(prompt="You:"),
    outputs=gr.Textbox(),
    live=True,
    capture_session=True,
    title="ST SQL Chatbot",
    description="Type your message in the box above, and the chatbot will respond.",
)

# Launch the Gradio interface
if __name__ == "__main__":
    iface.launch()