Create app.py

app.py

@@ -0,0 +1,77 @@
+import gradio as gr
+from langchain.chains import LLMChain
+from langchain.prompts import PromptTemplate
+from langchain.llms import HuggingFacePipeline
+from transformers import pipeline
+from gtts import gTTS
+from bs4 import BeautifulSoup
+import tempfile
+import os
+import requests
+from moviepy.editor import *
+
+# CPU-friendly summarization model
+summary_pipe = pipeline("text2text-generation", model="google/flan-t5-base", device=-1)
+llm = HuggingFacePipeline(pipeline=summary_pipe)
+
+# LangChain summarization prompt
+summary_prompt = PromptTemplate.from_template("""
+Summarize the following article content in a clear, concise way:
+
+{text}
+
+Summary:
+""")
+summary_chain = LLMChain(llm=llm, prompt=summary_prompt)
+
+def extract_main_content(url):
+    try:
+        response = requests.get(url, timeout=10)
+        soup = BeautifulSoup(response.content, "html.parser")
+        for tag in soup(["nav", "header", "footer", "aside", "script", "style", "noscript"]):
+            tag.decompose()
+        paragraphs = soup.find_all("p")
+        content = "\n".join([p.get_text() for p in paragraphs if len(p.get_text()) > 60])
+        return content.strip()
+    except Exception as e:
+        return f"Error extracting article content: {str(e)}"
+
+def url_to_av_summary(url):
+    try:
+        article_text = extract_main_content(url)
+        if article_text.startswith("Error"):
+            return article_text, None
+
+        summary = summary_chain.run(text=article_text)
+
+        # Generate speech using gTTS
+        tts = gTTS(text=summary)
+        audio_path = tempfile.NamedTemporaryFile(delete=False, suffix=".mp3").name
+        tts.save(audio_path)
+
+        # Create video clip (text overlay + audio)
+        video_clip = TextClip(summary, fontsize=32, color='white', bg_color='black', size=(1280, 720), method='caption')
+        video_clip = video_clip.set_duration(AudioFileClip(audio_path).duration)
+        video_clip = video_clip.set_audio(AudioFileClip(audio_path))
+
+        video_path = tempfile.NamedTemporaryFile(delete=False, suffix=".mp4").name
+        video_clip.write_videofile(video_path, fps=24, codec='libx264')
+
+        return summary, video_path
+
+    except Exception as e:
+        return f"Error: {str(e)}", None
+
+iface = gr.Interface(
+    fn=url_to_av_summary,
+    inputs=gr.Textbox(label="Article URL", placeholder="Paste a news/blog URL here..."),
+    outputs=[
+        gr.Textbox(label="Summary"),
+        gr.Video(label="Video Summary")
+    ],
+    title="URL to AV Summary Agent",
+    description="Summarizes only article content from a URL and creates a narrated video. CPU-only."
+)
+
+if __name__ == "__main__":
+    iface.launch()