update all endpoints

backend/main.py

@@ -1,20 +1,139 @@
-from fastapi import FastAPI
-from backend.news_fetcher import fetch_news
-from backend.recommender import recommend_similar
-from backend.config import Config
+from fastapi import FastAPI, HTTPException
+from fastapi.middleware.cors import CORSMiddleware
+from .news_fetcher import fetch_all_news, save_raw_news, save_processed_news
+from .recommender import recommend_similar, process_articles_for_vector_db
+from .recommender import analyze_article_with_groq
+from .recommender import get_personalized_recommendations, vector_db
+from .vector_store import VectorDB
+from .config import Config
+import os
+
+app = FastAPI(title="DS Task AI News", version="1.0.0")
+
+# Add CORS middleware
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+
+@app.on_event("startup")
+async def startup_event():
+    """Initialize the application"""
+    # Create necessary directories
+    os.makedirs(Config.RAW_NEWS_PATH, exist_ok=True)
+    os.makedirs(Config.PROCESSED_NEWS_PATH, exist_ok=True)
+    os.makedirs("data", exist_ok=True)
+
+    # Load existing vector database if available
+    if os.path.exists(Config.VECTOR_DB_PATH):
+        vector_db.load_index(Config.VECTOR_DB_PATH)
+
+
+@app.get("/")
+async def root():
+    """Root endpoint"""
+    return {"message": "DS Task AI News API", "version": "1.0.0"}
 
-app = FastAPI()
 
 @app.get("/fetch-news")
-async def get_latest_news():
-    all_news = []
-    for feed in Config.RSS_FEEDS:
-        all_news.extend(fetch_news(feed))
-    return {"news": all_news}
+async def fetch_news():
+    """Fetch news from RSS feeds"""
+    try:
+        articles = fetch_all_news()
+
+        if not articles:
+            raise HTTPException(status_code=404, detail="No articles found")
+
+        # Save raw news
+        raw_file = save_raw_news(articles)
+
+        # Process articles for vector database
+        process_articles_for_vector_db(articles)
+
+        # Save processed news
+        processed_file = save_processed_news(articles)
+
+        # Save vector database
+        vector_db.save_index(Config.VECTOR_DB_PATH)
+
+        return {
+            "message": "News fetched successfully",
+            "articles_count": len(articles),
+            "raw_file": raw_file,
+            "processed_file": processed_file,
+            "articles": articles
+        }
+
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"Error fetching news: {str(e)}")
 
 
-@app.get("/recommend")
+@app.get("/recommend-news")
 async def recommend_news(article_id: str):
-    sample_text = "AI breakthroughs in 2024"
-    similar_ids = recommend_similar(sample_text)
-    return {"similar_articles": similar_ids}
+    """Retrieve similar news based on the selected article"""
+    try:
+        recommendations = recommend_similar(article_id)
+
+        if not recommendations:
+            raise HTTPException(status_code=404, detail="No recommendations found")
+
+        return {
+            "article_id": article_id,
+            "recommendations": recommendations,
+            "count": len(recommendations)
+        }
+
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"Error getting recommendations: {str(e)}")
+
+
+@app.get("/analyze-article")
+async def analyze_article(article_id: str):
+    """Analyze article using Groq LLM"""
+    try:
+        article = vector_db.get_article_by_id(article_id)
+
+        if not article:
+            raise HTTPException(status_code=404, detail="Article not found")
+
+        article_text = f"{article['title']} {article['content']}"
+        analysis = analyze_article_with_groq(article_text)
+
+        return {
+            "article_id": article_id,
+            "article": article,
+            "analysis": analysis
+        }
+
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"Error analyzing article: {str(e)}")
+
+
+@app.get("/personalized-recommendations")
+async def personalized_recommendations(interests: str):
+    """Get personalized recommendations based on user interests"""
+    try:
+        recommendations = get_personalized_recommendations(interests)
+
+        return {
+            "interests": interests,
+            "recommendations": recommendations,
+            "count": len(recommendations)
+        }
+
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"Error getting personalized recommendations: {str(e)}")
+
+
+@app.get("/health")
+async def health_check():
+    """Health check endpoint"""
+    return {"status": "healthy", "database_articles": len(vector_db.articles)}
+
+if __name__ == "__main__":
+    import uvicorn
+    uvicorn.run(app, host="0.0.0.0", port=8000)