new changes

app.py

@@ -1,22 +1,38 @@
 import gradio as gr
 import random
-from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
 from datasets import load_dataset
 import requests
 from bs4 import BeautifulSoup
-
-tokenizer = AutoTokenizer.from_pretrained("liamvbetts/bart-large-cnn-v4")
-model = AutoModelForSeq2SeqLM.from_pretrained("liamvbetts/bart-large-cnn-v4")
+import os
 
 dataset = load_dataset("cnn_dailymail", "3.0.0")
 
-NEWS_API_KEY = "da2cc601304341e7a39cb5604d0b076b"  
+NEWS_API_KEY = os.environ['NEWS_API_KEY']
+HF_TOKEN = os.environ['HF_TOKEN']
+
+def summarize(model_name, article):
+    API_URL = f"https://api-inference.huggingface.co/models/{model_name}"
+    headers = {"Authorization": "Bearer {HF_TOKEN}"}
+
+    payload = {"inputs": article}
+    response = requests.post(API_URL, headers=headers, json=payload)
+
+    # Check if the response is successful
+    if response.status_code == 200:
+        # Assuming the response structure has a 'generated_text' field
+        return format(response.json())
+    else:
+        # Handle different types of errors
+        if response.status_code == 401:
+            return "Error: Unauthorized. Check your API token."
+        elif response.status_code == 503:
+            return "Error: Service unavailable or model is currently loading."
+        else:
+            return f"{response} - Error: Encountered an issue (status code: {response.status_code}). Please try again."
+    return format(response.json())
 
-def summarize(article):
-    inputs = tokenizer(article, return_tensors="pt").input_ids
-    outputs = model.generate(inputs, max_new_tokens=128, do_sample=False)
-    summary = tokenizer.decode(outputs[0], skip_special_tokens=True)
-    return summary
+def format(response):
+    return response[0]['generated_text']
 
 def get_random_article():
     random.seed()
@@ -61,28 +77,32 @@ def scrape_article(url):
         
         text = ' '.join([p.get_text() for p in article_content])
         words = text.split()
-        truncated_text = ' '.join(words[:1024])  # Truncate to first 1024 words
+        truncated_text = ' '.join(words[:512])  # Truncate to first 1024 words
 
         return truncated_text, title
     except Exception as e:
         return "Error scraping article: " + str(e), ""
 
-# Using Gradio Blocks
+# Using Gradio Blocks with improved layout and styling
 with gr.Blocks() as demo:
-    gr.Markdown("## News Summary App")
+    gr.Markdown("# News Summary App", elem_id="header")
     gr.Markdown("Enter a news text and get its summary, or load a random article.")
+    
     with gr.Row():
-        article_title = gr.Label()  # Component to display the article title
-        input_text = gr.Textbox(lines=10, label="Input Text")
-        output_text = gr.Textbox(label="Summary")
-
-    load_dataset_article_button = gr.Button("Load Random Article from Dataset")
-    load_news_article_button = gr.Button("Load News Article")
+        with gr.Column():
+            with gr.Row():
+                load_dataset_article_button = gr.Button("Load Random Article from Val Dataset")
+                load_news_article_button = gr.Button("Pull Random News Article from NewsAPI")
+            article_title = gr.Label()  # Component to display the article title
+            input_text = gr.Textbox(lines=10, label="Input Text")
+        with gr.Column():
+            with gr.Row():
+                summarize_button = gr.Button("Summarize")
+            model_name = gr.Dropdown(label="Model Name", choices=["liamvbetts/bart-news-summary-v1", "liamvbetts/bart-base-cnn-v1", "liamvbetts/bart-large-cnn-v2", "liamvbetts/bart-large-cnn-v4"], value="liamvbetts/bart-news-summary-v1")
+            output_text = gr.Textbox(label="Summary")
 
     load_dataset_article_button.click(fn=load_article, inputs=[], outputs=input_text)
     load_news_article_button.click(fn=get_news_article, inputs=[], outputs=[input_text, article_title])
-
-    summarize_button = gr.Button("Summarize")
-    summarize_button.click(fn=summarize, inputs=input_text, outputs=output_text)
+    summarize_button.click(fn=summarize, inputs=[model_name, input_text], outputs=output_text)
 
 demo.launch()

requirements.txt

@@ -1,5 +1,5 @@
 gradio
-transformers
+#transformers
 datasets
 evaluate
 accelerate