Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,40 +1,410 @@
-import altair as alt
-import numpy as np
-import pandas as pd
 import streamlit as st
+import requests
+import pandas as pd
+from together import Together
+import os
+
+# =============================================================================
+# CONFIGURATION - Using Secrets Management
+# =============================================================================
+NOCODB_URL = "https://app.nocodb.com"  # Base URL
+
+# Get sensitive data from Streamlit secrets or environment variables
+def get_api_credentials():
+    """Get API credentials from secrets or environment"""
+    try:
+        # Try Streamlit secrets first (for Hugging Face Spaces)
+        api_token = st.secrets.get("NOCODB_API_TOKEN", os.environ.get("NOCODB_API_TOKEN", ""))
+        together_key = st.secrets.get("TOGETHER_API_KEY", os.environ.get("TOGETHER_API_KEY", ""))
+        endpoint_path = st.secrets.get("NOCODB_ENDPOINT_PATH", os.environ.get("NOCODB_ENDPOINT_PATH", ""))
+        
+        return api_token, together_key, endpoint_path
+    except:
+        # Fallback to environment variables
+        api_token = os.environ.get("NOCODB_API_TOKEN", "")
+        together_key = os.environ.get("TOGETHER_API_KEY", "")
+        endpoint_path = os.environ.get("NOCODB_ENDPOINT_PATH", "")
+        
+        return api_token, together_key, endpoint_path
+
+# Initialize Together AI client
+@st.cache_resource
+def get_ai_client():
+    """Initialize Together AI client"""
+    _, together_key, _ = get_api_credentials()
+    if not together_key:
+        st.error("Together AI API key not found. Please configure it in the secrets.")
+        return None
+    return Together(api_key=together_key)
+
+# =============================================================================
+# HELPER FUNCTIONS
+# =============================================================================
+@st.cache_data(ttl=300)  # Cache for 5 minutes
+def get_netflix_content():
+    """Fetch Netflix content from NocoDB"""
+    api_token, _, endpoint_path = get_api_credentials()
+    
+    if not api_token or not endpoint_path:
+        st.error("NocoDB credentials not configured. Please set up your secrets.")
+        return []
+    
+    headers = {"xc-token": api_token}
+    
+    try:
+        response = requests.get(
+            f"{NOCODB_URL}{endpoint_path}?limit=1000",
+            headers=headers
+        )
+        
+        if response.status_code == 200:
+            data = response.json()
+            return data.get('list', [])
+        else:
+            st.error(f"Failed to fetch data: {response.status_code}")
+            return []
+            
+    except Exception as e:
+        st.error(f"Error connecting to database: {e}")
+        return []
+
+def filter_content(content_list, filters):
+    """Apply filters to Netflix content list"""
+    filtered = []
+    
+    for content in content_list:
+        # Type filter
+        if filters['content_type'] and content.get('type') != filters['content_type']:
+            continue
+            
+        # Rating filter
+        if filters['ratings'] and content.get('rating') not in filters['ratings']:
+            continue
+            
+        # Genre filter
+        if filters['genres'] and not any(genre in content.get('listed_in', '') for genre in filters['genres']):
+            continue
+            
+        # Release year filter
+        try:
+            release_year = int(content.get('release_year', 0))
+            if release_year < filters['year_range'][0] or release_year > filters['year_range'][1]:
+                continue
+        except (ValueError, TypeError):
+            continue
+            
+        # Duration filter (different handling for movies and shows)
+        duration = content.get('duration', '')
+        if filters['content_type'] == 'Movie' and 'min' in duration:
+            try:
+                minutes = int(duration.split()[0])
+                if minutes < filters['duration_range'][0] or minutes > filters['duration_range'][1]:
+                    continue
+            except (ValueError, IndexError):
+                continue
+        
+        filtered.append(content)
+    
+    return filtered
+
+def create_content_context(content_list):
+    """Create context string about current content for AI"""
+    if not content_list:
+        return "No content matches the current filters."
+    
+    total = len(content_list)
+    movies = sum(1 for c in content_list if c.get('type') == 'Movie')
+    shows = sum(1 for c in content_list if c.get('type') == 'TV Show')
+    
+    context = f"""Currently showing {total} Netflix titles ({movies} movies and {shows} TV shows). """
+    
+    # Add some genre info
+    all_genres = []
+    for content in content_list[:20]:  # Sample from first 20 items
+        genres = content.get('listed_in', '').split(', ')
+        all_genres.extend(genres)
+    
+    if all_genres:
+        genre_counts = pd.Series(all_genres).value_counts()
+        top_genres = genre_counts.head(5).index.tolist()
+        context += f"Top genres include: {', '.join(top_genres)}. "
+    
+    # Add year range
+    years = [int(c.get('release_year', 0)) for c in content_list if c.get('release_year')]
+    if years:
+        context += f"Release years range from {min(years)} to {max(years)}."
+    
+    return context
+
+def get_ai_response(client, question, context, model_name):
+    """Get response from Together AI"""
+    try:
+        prompt = f"""You are a helpful Netflix content expert. Based on the current content data, please answer the user's question accurately and helpfully.
+
+Current Content Data Context:
+{context}
+
+User Question: {question}
+
+Please provide a helpful, accurate response based on the data provided. Keep your answer concise but informative."""
+
+        response = client.chat.completions.create(
+            model=model_name,
+            messages=[
+                {"role": "system", "content": "You are a helpful Netflix content expert with deep knowledge of movies and TV shows."},
+                {"role": "user", "content": prompt}
+            ],
+            max_tokens=300,
+            temperature=0.7,
+        )
+        
+        return response.choices[0].message.content
+        
+    except Exception as e:
+        raise Exception(f"Together AI Error: {str(e)}")
+
+# =============================================================================
+# MAIN APP
+# =============================================================================
+def main():
+    # Page config
+    st.set_page_config(
+        page_title="Netflix Content Explorer",
+        page_icon="🎬",
+        layout="wide"
+    )
+    
+    # Header
+    st.title("🎬 Netflix Content Explorer")
+    st.write("Explore Netflix movies and TV shows with AI-powered insights!")
+    
+    # Check API credentials
+    api_token, together_key, endpoint_path = get_api_credentials()
+    
+    if not together_key:
+        st.error("⚠️ Together AI API key not configured!")
+        st.info("Please set your TOGETHER_API_KEY in the Hugging Face Spaces secrets.")
+        st.stop()
+    
+    if not api_token or not endpoint_path:
+        st.error("⚠️ NocoDB credentials not configured!")
+        st.info("Please set NOCODB_API_TOKEN and NOCODB_ENDPOINT_PATH in the Hugging Face Spaces secrets.")
+        st.stop()
+    
+    # Initialize AI client
+    try:
+        client = get_ai_client()
+        if not client:
+            st.stop()
+    except Exception as e:
+        st.error(f"Failed to initialize Together AI client: {e}")
+        st.stop()
+    
+    # Load all content first
+    with st.spinner("Loading Netflix content..."):
+        all_content = get_netflix_content()
+    
+    if not all_content:
+        st.error("Could not load Netflix content. Please check your NocoDB connection.")
+        st.stop()
+    
+    # Extract unique values for filters
+    all_ratings = sorted(list(set([c.get('rating') for c in all_content if c.get('rating')])))
+    all_genres = sorted(list(set(
+        genre.strip()
+        for c in all_content
+        for genre in c.get('listed_in', '').split(',')
+        if genre.strip()
+    )))
+    
+    # Sidebar filters
+    st.sidebar.header("🔍 Filter Content")
+    
+    content_type = st.sidebar.selectbox(
+        "Content Type",
+        options=["All", "Movie", "TV Show"],
+        index=0
+    )
+    
+    selected_ratings = st.sidebar.multiselect(
+        "Ratings",
+        options=all_ratings,
+        default=[]
+    )
+    
+    selected_genres = st.sidebar.multiselect(
+        "Genres",
+        options=all_genres,
+        default=[]
+    )
+    
+    # Year range slider
+    years = [int(c.get('release_year', 0)) for c in all_content if c.get('release_year')]
+    min_year, max_year = min(years), max(years)
+    year_range = st.sidebar.slider(
+        "Release Year",
+        min_value=min_year,
+        max_value=max_year,
+        value=(min_year, max_year)
+    )
+    
+    # Duration range slider (for movies only)
+    movie_durations = [
+        int(c.get('duration', '0 min').split()[0])
+        for c in all_content
+        if c.get('type') == 'Movie' and 'min' in c.get('duration', '')
+    ]
+    if movie_durations:
+        min_duration, max_duration = min(movie_durations), max(movie_durations)
+        duration_range = st.sidebar.slider(
+            "Movie Duration (minutes)",
+            min_value=min_duration,
+            max_value=max_duration,
+            value=(min_duration, max_duration),
+            help="This filter only applies to movies"
+        )
+    else:
+        duration_range = (0, 1000)  # Fallback values
+    
+    # Create filter dictionary
+    filters = {
+        'content_type': content_type if content_type != "All" else None,
+        'ratings': selected_ratings,
+        'genres': selected_genres,
+        'year_range': year_range,
+        'duration_range': duration_range
+    }
+    
+    # Apply filters
+    filtered_content = filter_content(all_content, filters)
+    
+    # Main content area
+    col1, col2 = st.columns([2, 1])
+    
+    with col1:
+        # Content listings
+        st.subheader(f"📋 Found {len(filtered_content)} Titles")
+        
+        if filtered_content:
+            # Show first 10 items
+            for i, content in enumerate(filtered_content[:10]):
+                with st.expander(f"{content.get('title', 'N/A')} ({content.get('release_year', 'N/A')})"):
+                    # Content details in columns
+                    detail_col1, detail_col2 = st.columns(2)
+                    
+                    with detail_col1:
+                        st.write(f"**🎭 Type:** {content.get('type', 'N/A')}")
+                        st.write(f"**⭐ Rating:** {content.get('rating', 'N/A')}")
+                        st.write(f"**⏱️ Duration:** {content.get('duration', 'N/A')}")
+                    
+                    with detail_col2:
+                        st.write(f"**🎬 Genre:** {content.get('listed_in', 'N/A')}")
+                        st.write(f"**👥 Cast:** {content.get('cast', 'N/A')[:100]}...")
+                        st.write(f"**📝 Director:** {content.get('director', 'N/A')}")
+                    
+                    # Description
+                    st.write(f"**📖 Description:**")
+                    st.write(content.get('description', 'N/A'))
+            
+            if len(filtered_content) > 10:
+                st.info(f"Showing first 10 of {len(filtered_content)} titles. Adjust filters to narrow results.")
+        else:
+            st.info("No content matches your current filters. Try adjusting the criteria.")
+    
+    with col2:
+        # AI Chat Section
+        st.subheader("🤖 Ask AI Assistant")
+        st.write("Ask questions about the Netflix content!")
+        
+        # Model selection for Together AI
+        model_choice = st.selectbox(
+            "Select AI Model:",
+            [
+                "google/gemma-2b-it",
+                "google/gemma-2-27b-it",
+                "mistralai/Mistral-7B-Instruct-v0.1",
+                "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO",
+                "mistralai/Mixtral-8x7B-Instruct-v0.1"
+            ],
+            help="Select an AI model to answer your questions"
+        )
+        
+        # Example questions
+        with st.expander("💡 Example Questions"):
+            st.write("• What are the most common genres?")
+            st.write("• What's the average movie duration?")
+            st.write("• Which directors have the most content?")
+            st.write("• What are the trends in content ratings?")
+            st.write("• Tell me about the release year distribution")
+        
+        user_question = st.text_area(
+            "Your Question:",
+            placeholder="Ask about genres, ratings, directors, trends...",
+            height=100
+        )
+        
+        if st.button("🔍 Ask AI", type="primary"):
+            if user_question:
+                with st.spinner("AI is analyzing the content..."):
+                    # Create context from current filtered data
+                    context = create_content_context(filtered_content)
+                    
+                    try:
+                        # Get AI response
+                        ai_response = get_ai_response(client, user_question, context, model_choice)
+                        
+                        st.success("**AI Assistant Response:**")
+                        st.write(ai_response)
+                        
+                        # Show debug info
+                        with st.expander("Debug Info"):
+                            st.write(f"Model used: {model_choice}")
+                            st.write(f"Content items analyzed: {len(filtered_content)}")
+                            st.write(f"Context: {context[:150]}...")
+                        
+                    except Exception as e:
+                        st.error(f"AI Error: {str(e)}")
+                        
+                        # Fallback response with data analysis
+                        st.info("**Fallback Analysis:**")
+                        if filtered_content:
+                            movies = sum(1 for c in filtered_content if c.get('type') == 'Movie')
+                            shows = sum(1 for c in filtered_content if c.get('type') == 'TV Show')
+                            st.write(f"• Found {len(filtered_content)} titles ({movies} movies, {shows} TV shows)")
+                            
+                            # Show top genres
+                            genres = [g.strip() for c in filtered_content for g in c.get('listed_in', '').split(',')]
+                            genre_counts = pd.Series(genres).value_counts()
+                            st.write(f"• Top genres: {', '.join(genre_counts.head(3).index)}")
+                            
+                            # Show year range
+                            years = [int(c.get('release_year', 0)) for c in filtered_content if c.get('release_year')]
+                            if years:
+                                st.write(f"• Release years: {min(years)} - {max(years)}")
+            else:
+                st.warning("Please enter a question first!")
+    
+    # Footer stats
+    st.markdown("---")
+    if all_content:
+        total_items = len(all_content)
+        filtered_items = len(filtered_content)
+        
+        stat_col1, stat_col2, stat_col3, stat_col4 = st.columns(4)
+        
+        with stat_col1:
+            st.metric("Total Titles", total_items)
+        
+        with stat_col2:
+            st.metric("Filtered Results", filtered_items)
+        
+        with stat_col3:
+            movies = sum(1 for c in filtered_content if c.get('type') == 'Movie')
+            st.metric("Movies", movies)
+        
+        with stat_col4:
+            shows = sum(1 for c in filtered_content if c.get('type') == 'TV Show')
+            st.metric("TV Shows", shows)
 
-"""
-# Welcome to Streamlit!
-
-Edit `/streamlit_app.py` to customize this app to your heart's desire :heart:.
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
-
-In the meantime, below is an example of what you can do with just a few lines of code:
-"""
-
-num_points = st.slider("Number of points in spiral", 1, 10000, 1100)
-num_turns = st.slider("Number of turns in spiral", 1, 300, 31)
-
-indices = np.linspace(0, 1, num_points)
-theta = 2 * np.pi * num_turns * indices
-radius = indices
-
-x = radius * np.cos(theta)
-y = radius * np.sin(theta)
-
-df = pd.DataFrame({
-    "x": x,
-    "y": y,
-    "idx": indices,
-    "rand": np.random.randn(num_points),
-})
-
-st.altair_chart(alt.Chart(df, height=700, width=700)
-    .mark_point(filled=True)
-    .encode(
-        x=alt.X("x", axis=None),
-        y=alt.Y("y", axis=None),
-        color=alt.Color("idx", legend=None, scale=alt.Scale()),
-        size=alt.Size("rand", legend=None, scale=alt.Scale(range=[1, 150])),
-    ))
+if __name__ == "__main__":
+    main()