DS_Task_AI_News/backend/recommender.py

from .embeddings import get_embeddings, get_query_embedding, rerank_results
from .vector_store import VectorDB
import groq
from .config import Config

# Initialize Groq client
groq_client = groq.Groq(api_key=Config.GROQ_API_KEY)

# 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