feat: Implement complete RSS news fetching system with multi-source support
This commit is contained in:
Aherobo Ovie Victor
+234
@@ -0,0 +1,234 @@
|
||||
"""FastAPI backend for DS Task AI News"""
|
||||
from fastapi import FastAPI, HTTPException, Query
|
||||
from fastapi.middleware.cors import CORSMiddleware
|
||||
from pydantic import BaseModel
|
||||
from typing import List, Dict, Any, Optional
|
||||
import uvicorn
|
||||
|
||||
from config import settings
|
||||
from news_fetcher import NewsFetcher
|
||||
from recommender import NewsRecommender
|
||||
|
||||
# Initialize FastAPI app
|
||||
app = FastAPI(
|
||||
title="DS Task AI News API",
|
||||
description="AI-powered news retrieval and recommendation system",
|
||||
version="1.0.0"
|
||||
)
|
||||
|
||||
# Add CORS middleware
|
||||
app.add_middleware(
|
||||
CORSMiddleware,
|
||||
allow_origins=["*"], # In production, specify actual origins
|
||||
allow_credentials=True,
|
||||
allow_methods=["*"],
|
||||
allow_headers=["*"],
|
||||
)
|
||||
|
||||
# Initialize components
|
||||
news_fetcher = NewsFetcher()
|
||||
recommender = NewsRecommender()
|
||||
|
||||
# Pydantic models
|
||||
class NewsQuery(BaseModel):
|
||||
query: str
|
||||
top_k: int = 5
|
||||
|
||||
class InterestsQuery(BaseModel):
|
||||
interests: List[str]
|
||||
top_k: int = 10
|
||||
|
||||
class SearchQuery(BaseModel):
|
||||
query: str
|
||||
source: Optional[str] = None
|
||||
top_k: int = 10
|
||||
|
||||
# API Endpoints
|
||||
|
||||
@app.get("/")
|
||||
async def root():
|
||||
"""Health check endpoint"""
|
||||
return {
|
||||
"message": "DS Task AI News API is running!",
|
||||
"version": "1.0.0",
|
||||
"status": "healthy"
|
||||
}
|
||||
|
||||
@app.get("/health")
|
||||
async def health_check():
|
||||
"""Detailed health check"""
|
||||
stats = recommender.get_store_stats()
|
||||
return {
|
||||
"status": "healthy",
|
||||
"vector_store": stats,
|
||||
"settings": {
|
||||
"embedding_model": settings.embedding_model,
|
||||
"vector_db_type": settings.vector_db_type,
|
||||
"rss_feeds_count": len(settings.rss_feeds)
|
||||
}
|
||||
}
|
||||
|
||||
@app.post("/fetch-news")
|
||||
async def fetch_news():
|
||||
"""Fetch news from RSS feeds and add to vector store"""
|
||||
try:
|
||||
# Fetch news articles
|
||||
result = news_fetcher.fetch_and_save_news()
|
||||
|
||||
if not result["success"]:
|
||||
raise HTTPException(status_code=500, detail=result.get("message", "Failed to fetch news"))
|
||||
|
||||
# Add articles to vector store
|
||||
articles = result["articles"]
|
||||
store_result = recommender.add_articles_to_store(articles)
|
||||
|
||||
if not store_result["success"]:
|
||||
raise HTTPException(status_code=500, detail=store_result.get("message", "Failed to add articles to store"))
|
||||
|
||||
return {
|
||||
"success": True,
|
||||
"message": "News fetched and processed successfully",
|
||||
"articles_fetched": result["articles_count"],
|
||||
"articles_stored": store_result["articles_added"],
|
||||
"total_articles": store_result["total_articles"]
|
||||
}
|
||||
|
||||
except Exception as e:
|
||||
raise HTTPException(status_code=500, detail=f"Error fetching news: {str(e)}")
|
||||
|
||||
@app.get("/recommend-news")
|
||||
async def recommend_news(
|
||||
article_id: str = Query(..., description="ID of the article to find similar articles for"),
|
||||
top_k: int = Query(5, description="Number of recommendations to return")
|
||||
):
|
||||
"""Get news recommendations based on article ID"""
|
||||
try:
|
||||
recommendations = recommender.recommend_by_article_id(article_id, top_k)
|
||||
|
||||
return {
|
||||
"success": True,
|
||||
"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.post("/recommend-by-query")
|
||||
async def recommend_by_query(query_data: NewsQuery):
|
||||
"""Get news recommendations based on text query"""
|
||||
try:
|
||||
recommendations = recommender.recommend_by_query(query_data.query, query_data.top_k)
|
||||
|
||||
return {
|
||||
"success": True,
|
||||
"query": query_data.query,
|
||||
"recommendations": recommendations,
|
||||
"count": len(recommendations)
|
||||
}
|
||||
|
||||
except Exception as e:
|
||||
raise HTTPException(status_code=500, detail=f"Error getting recommendations: {str(e)}")
|
||||
|
||||
@app.post("/recommend-by-interests")
|
||||
async def recommend_by_interests(interests_data: InterestsQuery):
|
||||
"""Get news recommendations based on user interests"""
|
||||
try:
|
||||
recommendations = recommender.recommend_by_interests(interests_data.interests, interests_data.top_k)
|
||||
|
||||
return {
|
||||
"success": True,
|
||||
"interests": interests_data.interests,
|
||||
"recommendations": recommendations,
|
||||
"count": len(recommendations)
|
||||
}
|
||||
|
||||
except Exception as e:
|
||||
raise HTTPException(status_code=500, detail=f"Error getting recommendations: {str(e)}")
|
||||
|
||||
@app.get("/trending")
|
||||
async def get_trending_news(top_k: int = Query(10, description="Number of trending articles to return")):
|
||||
"""Get trending news articles"""
|
||||
try:
|
||||
trending = recommender.get_trending_articles(top_k)
|
||||
|
||||
return {
|
||||
"success": True,
|
||||
"trending_articles": trending,
|
||||
"count": len(trending)
|
||||
}
|
||||
|
||||
except Exception as e:
|
||||
raise HTTPException(status_code=500, detail=f"Error getting trending news: {str(e)}")
|
||||
|
||||
@app.get("/articles")
|
||||
async def get_all_articles(
|
||||
source: Optional[str] = Query(None, description="Filter by news source"),
|
||||
limit: int = Query(50, description="Maximum number of articles to return")
|
||||
):
|
||||
"""Get all articles with optional filtering"""
|
||||
try:
|
||||
if source:
|
||||
articles = recommender.get_articles_by_source(source, limit)
|
||||
else:
|
||||
all_articles = recommender.vector_store.get_all_articles()
|
||||
articles = sorted(all_articles, key=lambda x: x.get('published_date', ''), reverse=True)[:limit]
|
||||
|
||||
return {
|
||||
"success": True,
|
||||
"articles": articles,
|
||||
"count": len(articles),
|
||||
"source_filter": source
|
||||
}
|
||||
|
||||
except Exception as e:
|
||||
raise HTTPException(status_code=500, detail=f"Error getting articles: {str(e)}")
|
||||
|
||||
@app.post("/search")
|
||||
async def search_articles(search_data: SearchQuery):
|
||||
"""Advanced search with filters"""
|
||||
try:
|
||||
filters = {}
|
||||
if search_data.source:
|
||||
filters['source'] = search_data.source
|
||||
|
||||
results = recommender.search_articles(search_data.query, filters, search_data.top_k)
|
||||
|
||||
return {
|
||||
"success": True,
|
||||
"query": search_data.query,
|
||||
"filters": filters,
|
||||
"results": results,
|
||||
"count": len(results)
|
||||
}
|
||||
|
||||
except Exception as e:
|
||||
raise HTTPException(status_code=500, detail=f"Error searching articles: {str(e)}")
|
||||
|
||||
@app.get("/stats")
|
||||
async def get_stats():
|
||||
"""Get system statistics"""
|
||||
try:
|
||||
stats = recommender.get_store_stats()
|
||||
|
||||
# Add RSS feed information
|
||||
stats['rss_feeds'] = settings.rss_feeds
|
||||
stats['embedding_model'] = settings.embedding_model
|
||||
|
||||
return {
|
||||
"success": True,
|
||||
"statistics": stats
|
||||
}
|
||||
|
||||
except Exception as e:
|
||||
raise HTTPException(status_code=500, detail=f"Error getting stats: {str(e)}")
|
||||
|
||||
# Run the application
|
||||
if __name__ == "__main__":
|
||||
uvicorn.run(
|
||||
"main:app",
|
||||
host=settings.host,
|
||||
port=settings.port,
|
||||
reload=settings.debug
|
||||
)
|
||||
Reference in New Issue
Block a user