app.py

import gradio as gr
from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

# Load the pre-trained model and tokenizer
model_name = "distilbert-base-uncased"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name, num_labels=5)  # Adjust num_labels

# Define the function to get article suggestions
def suggest_articles(case_details):
    inputs = tokenizer(case_details, return_tensors="pt")
    with torch.no_grad():
        outputs = model(**inputs)
    prediction = outputs.logits.argmax(dim=1).item()
    return f"Suggested Article ID: {prediction}"

# Build the Gradio interface
interface = gr.Interface(
    fn=suggest_articles,
    inputs="text",
    outputs="text",
    title="Knowledge Article Suggestion",
    description="Enter case details to get relevant article suggestions."
)

interface.launch()