components/generators/daily_feed.py

import os
import json
import redis
import numpy as np
from typing import List, Dict
from openai import OpenAI
from components.indexers.news_indexer import get_upstash_vector_store
from llama_index.core.vector_stores.types import VectorStoreQuery, MetadataFilter, MetadataFilters, FilterOperator

# 🔐 Environment variables
REDIS_URL = os.environ.get("UPSTASH_REDIS_URL", "redis://localhost:6379")
REDIS_KEY = os.environ.get("UPSTASH_REDIS_TOKEN")
OPENAI_API_KEY = os.environ.get("OPENAI_API_KEY")

# ✅ Redis client
redis_client = redis.Redis.from_url(REDIS_URL, decode_responses=True)

# 📰 Topics
TOPICS = ["India news", "World news", "Tech news", "Finance news", "Sports news"]
TOPIC_KEYS = [t.lower().replace(" news", "") for t in TOPICS]

# 🧠 Prompt for summarization
BASE_PROMPT = (
    "You are Nuse’s editorial summarizer. Read the excerpts below and extract the most important stories. "
    "Return up to 3 punchy headlines, each under 20 words, and include why the story matters as the second half of the line."
)

# 📥 Load documents by topic and collect references
def load_docs_by_topic_with_refs() -> Dict[str, List[Dict]]:
    topic_docs = {key: [] for key in TOPIC_KEYS}
    try:
        vector_store = get_upstash_vector_store()
        for full_topic, topic_key in zip(TOPICS, TOPIC_KEYS):
            filters = MetadataFilters(
                filters=[MetadataFilter(key="topic", value=topic_key, operator=FilterOperator.EQ)]
            )
            dummy_vector = np.random.rand(384).tolist()
            query = VectorStoreQuery(query_embedding=dummy_vector, similarity_top_k=50, filters=filters)
            result = vector_store.query(query)
            for node in result.nodes:
                content = node.get_content().strip()
                ref_id = node.node_id or node.id_ or ""
                if content and ref_id:
                    topic_docs[topic_key].append({"text": content, "ref": ref_id})
    except Exception as e:
        print("❌ [load_docs_by_topic_with_refs Error]", e)
    return topic_docs

# 🧪 Summarize topic with reference IDs
def summarize_topic(topic_key: str, docs: List[Dict], start_index: int) -> List[Dict]:
    if not docs:
        print(f"⚠️ No docs for topic: {topic_key}")
        return []

    try:
        content = "\n\n---\n\n".join([d["text"] for d in docs])[:12000]
        client = OpenAI(api_key=OPENAI_API_KEY)
        response = client.chat.completions.create(
            model="gpt-4",
            messages=[
                {"role": "system", "content": BASE_PROMPT},
                {"role": "user", "content": content},
            ],
            max_tokens=512,
            temperature=0.7,
        )
        headlines = response.choices[0].message.content.strip().splitlines()
        result = []
        for i, line in enumerate(headlines):
            clean_line = line.strip("-–• ")
            if clean_line:
                ref_id = docs[i]["ref"] if i < len(docs) else ""
                result.append({
                    "summary": f"{start_index + i}. {clean_line}",
                    "ref": ref_id,
                    "image_url": "https://source.unsplash.com/800x600/?news",
                    "article_link": f"https://google.com/search?q={topic_key}+news"
                })
        return result
    except Exception as e:
        print(f"❌ [Summarize topic '{topic_key}' Error]", e)
        return []

# 🚀 Generate and cache full feed
def generate_and_cache_daily_feed():
    print("🆕 Starting daily feed generation with OpenAI...")
    docs_by_topic = load_docs_by_topic_with_refs()
    all_feed = []
    counter = 1
    for topic, topic_key in zip(TOPICS, TOPIC_KEYS):
        try:
            summaries = summarize_topic(topic_key, docs_by_topic[topic_key], start_index=counter)
            counter += len(summaries)
            all_feed.append({"topic": topic, "feed": summaries})
        except Exception as e:
            print(f"❌ [Feed generation error for {topic_key}]", e)
            all_feed.append({"topic": topic, "feed": []})

    try:
        redis_client.set("daily_news_feed_cache", json.dumps(all_feed, ensure_ascii=False))
        redis_client.expire("daily_news_feed_cache", 86400)
        print("✅ Cached final feed.")
    except Exception as e:
        print("❌ [Redis caching error]", e)

    return all_feed

# 🗃️ Fetch from cache
def get_cached_daily_feed():
    try:
        data = redis_client.get("daily_news_feed_cache")
        return json.loads(data) if data else []
    except Exception as e:
        print("❌ [Cache fetch error]", e)
        return []

if __name__ == "__main__":
    feed = generate_and_cache_daily_feed()
    print(json.dumps(feed, indent=2, ensure_ascii=False))