update all endpoints

backend/recommender.py

@@ -1,8 +1,97 @@
-from backend.embeddings import get_embeddings
-from backend.vector_store import VectorDB
+from .embeddings import get_embeddings, get_query_embedding, rerank_results
+from .vector_store import VectorDB
+import groq
+from .config import Config
 
-db = VectorDB()
+# Initialize Groq client
+groq_client = groq.Groq(api_key=Config.GROQ_API_KEY)
 
-def recommend_similar(article_text, top_k=3):
-    query_embed = get_embeddings([article_text])[0]
-    return db.search(query_embed, k=top_k)
+# Vector database instance
+vector_db = VectorDB()
+
+
+def process_articles_for_vector_db(articles):
+    """Process articles and add to vector database"""
+    if not articles:
+        return
+
+    # Extract text content for embedding
+    texts = []
+    for article in articles:
+        text = f"{article['title']} {article['content']}"
+        texts.append(text)
+
+    # Generate embeddings
+    embeddings = get_embeddings(texts)
+    if embeddings:
+        vector_db.add_vectors(embeddings, articles)
+
+
+def recommend_similar(article_id, top_n=3):
+    """Recommend similar articles based on article ID"""
+    article = vector_db.get_article_by_id(article_id)
+    if not article:
+        return []
+
+    # Get embedding for the article
+    article_text = f"{article['title']} {article['content']}"
+    query_embedding = get_query_embedding(article_text)
+
+    if not query_embedding:
+        return []
+
+    # Search for similar articles
+    similar_articles = vector_db.search(query_embedding, k=top_n + 1)
+
+    # Filter out the original article
+    recommendations = [art for art in similar_articles if art.get('slug') != article_id]
+
+    return recommendations[:top_n]
+
+
+def analyze_article_with_groq(article_text):
+    """Analyze article using Groq LLM"""
+    try:
+        response = groq_client.chat.completions.create(
+            model=Config.GROQ_MODEL,
+            messages=[
+                {
+                    "role": "system",
+                    "content": "You are an AI news analyst. Provide insights, key points, and sentiment analysis for the given article."
+                },
+                {
+                    "role": "user",
+                    "content": f"Analyze this news article: {article_text}"
+                }
+            ],
+            max_tokens=500,
+            temperature=0.3
+        )
+        return response.choices[0].message.content
+    except Exception as e:
+        print(f"Error analyzing article with Groq: {str(e)}")
+        return "Analysis unavailable"
+
+
+def get_personalized_recommendations(user_interests, top_n=5):
+    """Get personalized recommendations based on user interests"""
+    query_embedding = get_query_embedding(user_interests)
+    if not query_embedding:
+        return []
+
+    recommendations = vector_db.search(query_embedding, k=top_n)
+
+    # Re-rank results for better relevance
+    if recommendations:
+        documents = [f"{art['title']} {art['content']}" for art in recommendations]
+        reranked = rerank_results(user_interests, documents)
+
+        if reranked:
+            # Reorder recommendations based on reranking
+            reordered = []
+            for result in reranked:
+                if result.index < len(recommendations):
+                    reordered.append(recommendations[result.index])
+            return reordered
+
+    return recommendations