Spaces:
Running
Running
| from transformers import pipeline | |
| import gradio as gr | |
| import requests | |
| # Initialize the summarization pipeline (global initialization for efficiency) | |
| summarizer = pipeline("summarization", model="facebook/bart-large-cnn") | |
| # Function to fetch content from Wikipedia with a limit on length | |
| def fetch_wikipedia_content(search_term, max_chars=10000): | |
| url = "https://en.wikipedia.org/w/api.php" | |
| params = { | |
| "action": "query", | |
| "format": "json", | |
| "prop": "extracts", | |
| "explaintext": True, | |
| "titles": search_term, | |
| "redirects": 1 # Follow redirects | |
| } | |
| try: | |
| response = requests.get(url, headers=headers, params=params) | |
| response.raise_for_status() | |
| data = response.json() | |
| page = next(iter(data["query"]["pages"].values())) | |
| content = page.get("extract", "") | |
| return content[:max_chars] if content else "⚠️ No content found for this topic." | |
| except requests.RequestException as e: | |
| return f"⚠️ Error fetching article: {e}" | |
| # Function to split text into manageable chunks | |
| def split_text_into_chunks(text, max_words=500): | |
| words = text.split() | |
| return [" ".join(words[i:i + max_words]) for i in range(0, len(words), max_words)] | |
| # Function to summarize text in chunks | |
| def summarize_text(text): | |
| chunks = split_text_into_chunks(text) | |
| summaries = [] | |
| for i, chunk in enumerate(chunks): | |
| try: | |
| chunk_word_count = len(chunk.split()) | |
| max_summary_length = min(120, max(40, chunk_word_count // 2)) # Optimized for smaller summaries | |
| summary = summarizer(chunk, max_length=max_summary_length, min_length=30, do_sample=False)[0]['summary_text'] | |
| summaries.append(summary) | |
| except Exception as e: | |
| summaries.append(f"⚠️ Error summarizing chunk {i + 1}: {str(e)}") | |
| return "\n\n".join(summaries) | |
| # Main function for Gradio | |
| def fetch_and_summarize(search_term): | |
| content = fetch_wikipedia_content(search_term) | |
| if content.startswith("⚠️"): | |
| return content | |
| return summarize_text(content) | |
| # Gradio Interface | |
| iface = gr.Interface( | |
| fn=fetch_and_summarize, | |
| inputs=gr.Textbox(lines=1, placeholder="Enter a Wikipedia topic", label="Wikipedia Topic"), | |
| outputs=gr.Textbox(label="Summarized Content"), | |
| title="Optimized Wikipedia Article Summarizer", | |
| description="Fetch and summarize Wikipedia articles efficiently. Optimized for lightweight summarization.", | |
| allow_flagging="never" # Disable flagging for a lightweight deployment | |
| ) | |
| # Launch Gradio with queuing for handling concurrent requests | |
| if __name__ == "__main__": | |
| iface.queue(concurrency_count=4).launch(debug=False) |