Update app.py

app.py

@@ -1,95 +1,23 @@
 
 
-# import nest_asyncio
-# from youtube_transcript_api import YouTubeTranscriptApi
-# import streamlit as st
-# import os
-# from groq import Groq
-
-# nest_asyncio.apply()
-
-# # --- CONFIGURATION ---
-# YOUTUBE_API_KEY = os.environ.get("YOUTUBE_API_KEY")  # Set in your HuggingFace Secrets
-# channel_id = "UCsv3kmQ5k1eIRG2R9mWN"  # @icodeguru0
-
-# # Initialize Groq client once
-# groq_client = Groq(api_key=os.environ.get("GROQ_API_KEY"))
-
-# # --- FUNCTION: Fetch recent video IDs from YouTube channel ---
-# def get_latest_video_ids(channel_id, max_results=5):
-#     import requests
-#     url = f"https://www.googleapis.com/youtube/v3/search?key={YOUTUBE_API_KEY}&channelId={channel_id}&part=snippet,id&order=date&maxResults={max_results}"
-#     response = requests.get(url)
-#     videos = response.json().get('items', [])
-#     return [v['id']['videoId'] for v in videos if v['id']['kind'] == 'youtube#video']
-
-# # --- FUNCTION: Get video transcripts ---
-# def get_video_transcripts(video_ids):
-#     all_transcripts = []
-#     for vid in video_ids:
-#         try:
-#             transcript = YouTubeTranscriptApi.get_transcript(vid)
-#             text = " ".join([t['text'] for t in transcript])
-#             all_transcripts.append(text)
-#         except:
-#             continue
-#     return all_transcripts
-
-# # --- FUNCTION: Ask Groq API using official client ---
-# def ask_groq(context, question):
-#     messages = [
-#         {"role": "system", "content": "You are a helpful assistant."},
-#         {"role": "user", "content": f"Context: {context}\n\nQuestion: {question}\nAnswer:"}
-#     ]
-#     chat_completion = groq_client.chat.completions.create(
-#         model="llama-3.3-70b-versatile",  # Or the model you have access to
-#         messages=messages,
-#     )
-#     return chat_completion.choices[0].message.content.strip()
-
-# # --- STREAMLIT APP ---
-# def main():
-#     st.set_page_config(page_title="EduBot - YouTube Channel QA", layout="wide")
-#     st.title("🎓 EduBot for @icodeguru0")
-#     st.markdown("Ask anything based on the channel’s recent videos.")
-
-#     question = st.text_input("💬 Ask your question here:")
-#     if question:
-#         with st.spinner("🔍 Fetching videos and transcripts..."):
-#             video_ids = get_latest_video_ids(channel_id)
-#             transcripts = get_video_transcripts(video_ids)
-#             full_context = "\n\n".join(transcripts)
-#         with st.spinner("🧠 Thinking..."):
-#             answer = ask_groq(full_context, question)
-#         st.success(answer)
-
-#     st.markdown("---")
-#     st.caption("Powered by YouTube + Groq | Built for @icodeguru0")
-
-# if __name__ == "__main__":
-#     main()
-
-
 import nest_asyncio
 from youtube_transcript_api import YouTubeTranscriptApi
 import streamlit as st
 import os
 from groq import Groq
-import requests
-from bs4 import BeautifulSoup
 
 nest_asyncio.apply()
 
 # --- CONFIGURATION ---
 YOUTUBE_API_KEY = os.environ.get("YOUTUBE_API_KEY")  # Set in your HuggingFace Secrets
 channel_id = "UCsv3kmQ5k1eIRG2R9mWN"  # @icodeguru0
-website_url = "https://icode.guru/"  # Automatically included website
 
 # Initialize Groq client once
 groq_client = Groq(api_key=os.environ.get("GROQ_API_KEY"))
 
 # --- FUNCTION: Fetch recent video IDs from YouTube channel ---
 def get_latest_video_ids(channel_id, max_results=5):
+    import requests
     url = f"https://www.googleapis.com/youtube/v3/search?key={YOUTUBE_API_KEY}&channelId={channel_id}&part=snippet,id&order=date&maxResults={max_results}"
     response = requests.get(url)
     videos = response.json().get('items', [])
@@ -107,62 +35,36 @@ def get_video_transcripts(video_ids):
             continue
     return all_transcripts
 
-# --- FUNCTION: Fetch and parse website text content ---
-def fetch_website_text(url):
-    try:
-        resp = requests.get(url, timeout=10)
-        resp.raise_for_status()
-        soup = BeautifulSoup(resp.text, "html.parser")
-
-        # Remove scripts, styles, and nav/footer tags for cleaner text
-        for tag in soup(["script", "style", "nav", "footer", "header", "form", "noscript"]):
-            tag.decompose()
-
-        # Get visible text and clean up spaces
-        text = soup.get_text(separator=" ", strip=True)
-        return text
-    except Exception as e:
-        print(f"Error fetching website: {e}")
-        return ""
-
 # --- FUNCTION: Ask Groq API using official client ---
 def ask_groq(context, question):
     messages = [
-        "role": "system", "content": f"You are a helpful assistant. Always include full clickable URLs in your answers. The base website is {website_url}."
-
+        {"role": "system", "content": "You are a helpful assistant."},
         {"role": "user", "content": f"Context: {context}\n\nQuestion: {question}\nAnswer:"}
     ]
     chat_completion = groq_client.chat.completions.create(
-        model="llama-3.3-70b-versatile",  # Or your accessible model
+        model="llama-3.3-70b-versatile",  # Or the model you have access to
         messages=messages,
     )
     return chat_completion.choices[0].message.content.strip()
 
 # --- STREAMLIT APP ---
 def main():
-    st.set_page_config(page_title="EduBot - YouTube Channel & Website QA", layout="wide")
+    st.set_page_config(page_title="EduBot - YouTube Channel QA", layout="wide")
     st.title("🎓 EduBot for @icodeguru0")
-    st.markdown(f"**Including content from website:** {website_url}")
-    st.markdown("Ask anything based on the channel’s recent videos and the included website content.")
+    st.markdown("Ask anything based on the channel’s recent videos.")
 
     question = st.text_input("💬 Ask your question here:")
-
     if question:
-        with st.spinner("🔍 Fetching data..."):
+        with st.spinner("🔍 Fetching videos and transcripts..."):
             video_ids = get_latest_video_ids(channel_id)
             transcripts = get_video_transcripts(video_ids)
             full_context = "\n\n".join(transcripts)
-
-            website_text = fetch_website_text(website_url)
-            if website_text:
-                full_context += "\n\nWebsite Content:\n" + website_text
-
         with st.spinner("🧠 Thinking..."):
             answer = ask_groq(full_context, question)
         st.success(answer)
 
     st.markdown("---")
-    st.caption("Powered by YouTube + Website + Groq | Built for @icodeguru0")
+    st.caption("Powered by YouTube + Groq | Built for @icodeguru0")
 
 if __name__ == "__main__":
     main()