added video.py file

src/video.py

@@ -0,0 +1,115 @@
+"""
+Video processing module for Study Companion
+Handles video upload, audio extraction, transcription, and chat functionality
+"""
+
+import streamlit as st
+import tempfile
+import os
+from moviepy.editor import VideoFileClip
+from openai import OpenAI
+
+# Initialize OpenAI client
+api_key = os.getenv("OPENAI_API_KEY")
+client = OpenAI(api_key=api_key)
+
+
+# ---------------------------
+# Core Video Processing Functions
+# ---------------------------
+
+def extract_audio(video_path: str) -> str:
+    """Extract audio from the video file and save as MP3."""
+    try:
+        clip = VideoFileClip(video_path)
+        audio_path = video_path.replace(".mp4", ".mp3").replace(".mkv", ".mp3").replace(".webm", ".mp3").replace(".mov", ".mp3").replace(".avi", ".mp3")
+        clip.audio.write_audiofile(audio_path, codec='mp3', logger=None)
+        clip.close()
+        return audio_path
+    except Exception as e:
+        st.error(f"Error extracting audio: {e}")
+        return None
+
+
+def transcribe_audio(audio_path: str) -> str:
+    """Transcribe the audio to text using OpenAI's Whisper API."""
+    try:
+        with open(audio_path, "rb") as audio_file:
+            transcript = client.audio.transcriptions.create(
+                model="whisper-1", 
+                file=audio_file
+            )
+        return transcript.text
+    except Exception as e:
+        st.error(f"Error transcribing audio: {e}")
+        return ""
+
+
+def generate_video_summary(transcript_text: str) -> str:
+    """Generate a concise summary of the video transcript using OpenAI."""
+    prompt = (
+        f"Summarize the following video transcript in a concise manner, "
+        "highlighting the key points that a student should know.\n\n"
+        "Feel free to use bullet points, bold, italics and headers to emphasize key points where necessary.\n\n"
+        f"Transcript:\n\n{transcript_text}"
+    )
+    messages = [
+        {"role": "system", "content": "You are an educational assistant that creates clear, structured summaries."},
+        {"role": "user", "content": prompt}
+    ]
+    completion = client.chat.completions.create(
+        model="gpt-4o-mini", 
+        messages=messages
+    )
+    return completion.choices[0].message.content.strip()
+
+
+def chat_with_video(transcript_text: str, conversation_history: list, user_query: str) -> str:
+    """Generate a chat response using the video transcript as context."""
+    messages = conversation_history + [
+        {"role": "user", "content": f"Based on the following video transcript:\n\n{transcript_text}\n\nQuestion: {user_query}"}
+    ]
+    completion = client.chat.completions.create(
+        model="gpt-4o-mini", 
+        messages=messages
+    )
+    return completion.choices[0].message.content.strip()
+
+
+def process_uploaded_video(uploaded_video) -> tuple:
+    """
+    Process an uploaded video file: extract audio and transcribe.
+    Returns: (transcript_text, video_path) or (None, None) on error
+    """
+    # Check file size (200MB limit)
+    if uploaded_video.size > 200 * 1024 * 1024:
+        st.error("File size exceeds 200MB. Please upload a smaller video.")
+        return None, None
+    
+    # Save uploaded video to temporary file
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".mp4") as tmp:
+        tmp.write(uploaded_video.read())
+        video_path = tmp.name
+    
+    # Extract audio
+    with st.spinner("🎵 Extracting audio from video..."):
+        audio_path = extract_audio(video_path)
+    
+    if not audio_path:
+        return None, None
+    
+    # Transcribe audio
+    with st.spinner("📝 Transcribing audio... This may take a few minutes."):
+        transcript_text = transcribe_audio(audio_path)
+    
+    # Clean up audio file
+    try:
+        os.unlink(audio_path)
+    except:
+        pass
+    
+    if not transcript_text:
+        st.error("Failed to transcribe audio.")
+        return None, None
+    
+    return transcript_text, video_path