Initial commit 🚀

agent.py

@@ -0,0 +1,19 @@
+from transformers import pipeline
+
+summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
+classifier = pipeline("zero-shot-classification")
+
+def analyze_article(text, title, link):
+    summary = summarizer(text[:1024], max_length=200, min_length=50, do_sample=False)[0]['summary_text']
+    relevance = classifier(
+        summary,
+        candidate_labels=["Useful for data analytics team", "Not useful"],
+        multi_label=False
+    )
+    is_useful = relevance["labels"][0] == "Useful for data analytics team"
+    return {
+        "title": title,
+        "summary": summary,
+        "link": link,
+        "useful": is_useful
+    }

app.py

@@ -0,0 +1,24 @@
+import gradio as gr
+from rss_reader import fetch_articles
+from agent import analyze_article
+from renderer import render_html
+
+def process_rss(rss_input):
+    rss_urls = [url.strip() for url in rss_input.strip().splitlines() if url.strip()]
+    raw_articles = fetch_articles(rss_urls)
+    analyzed = [analyze_article(a['text'], a['title'], a['link']) for a in raw_articles]
+    return render_html(analyzed)
+
+default_rss = """https://rss.nytimes.com/services/xml/rss/nyt/Technology.xml
+https://www.reutersagency.com/feed/?best-sectors=technology"""
+
+iface = gr.Interface(
+    fn=process_rss,
+    inputs=gr.Textbox(label="Enter RSS URLs (one per line)", value=default_rss, lines=4),
+    outputs=gr.HTML(label="📊 GenAI RSS Digest"),
+    title="GenAI RSS Summarizer",
+    description="Summarizes articles and detects what’s useful to analytics teams"
+)
+
+if __name__ == "__main__":
+    iface.launch()

readme.MD

@@ -0,0 +1,9 @@
+# 🤖 GenAI RSS Summarizer
+
+Summarizes RSS feeds using Hugging Face models and renders as a digest with relevance checks for data teams.
+
+## To Run Locally
+
+```bash
+pip install -r requirements.txt
+python app.py

renderer.py

@@ -0,0 +1,6 @@
+from jinja2 import Template
+
+def render_html(summaries):
+    with open("templates/summary.html") as f:
+        template = Template(f.read())
+    return template.render(summaries=summaries)

requirements.txt

@@ -0,0 +1,6 @@
+gradio
+transformers
+feedparser
+newspaper3k
+jinja2
+torch

rss_reader.py

@@ -0,0 +1,21 @@
+import feedparser
+from newspaper import Article
+
+def fetch_articles(rss_urls, limit=3):
+    articles = []
+    for url in rss_urls:
+        feed = feedparser.parse(url)
+        for entry in feed.entries[:limit]:
+            try:
+                article = Article(entry.link)
+                article.download()
+                article.parse()
+                articles.append({
+                    "title": entry.title,
+                    "link": entry.link,
+                    "text": article.text,
+                    "published": entry.published
+                })
+            except:
+                continue
+    return articles