Aherobo Ovie Victor
beed04d05c
✅ Network & Model Optimization: - Fixed Sentence Transformers path to use local model - Configured real semantic embeddings (384-dimensional) - Replaced hash-based fallback with AI-powered similarity ✅ Advanced AI Features Integration: - Added ai_analyzer.py with Groq LLM integration - Implemented article summarization, sentiment analysis, keyword extraction - Added AI endpoints: /analyze-article, /generate-insights, /ai-status ✅ API Enhancement & User Experience: - Enhanced articles endpoint with pagination (offset/limit, metadata) - Added advanced filtering (date ranges, source, category) - Improved search with semantic similarity + multi-parameter filters ✅ Production Polish & Performance: - Implemented in-memory caching system in vector_store.py - Added rate limiting (100 req/min per IP) - Enhanced API documentation with deployment guide - Fixed file structure compliance System now production-ready with 1000+ articles indexed and full AI capabilities.
47 lines
1.5 KiB
Python
47 lines
1.5 KiB
Python
"""Configuration settings for DS Task AI News"""
|
|
import os
|
|
from typing import List
|
|
from pydantic_settings import BaseSettings
|
|
from dotenv import load_dotenv
|
|
|
|
load_dotenv()
|
|
|
|
class Settings(BaseSettings):
|
|
# API Keys
|
|
cohere_api_key: str = os.getenv("COHERE_API_KEY", "")
|
|
groq_api_key: str = os.getenv("GROQ_API_KEY", "")
|
|
|
|
# Vector Database
|
|
vector_db_type: str = os.getenv("VECTOR_DB_TYPE", "faiss")
|
|
vector_dimension: int = int(os.getenv("VECTOR_DIMENSION", "384"))
|
|
|
|
# RSS Feeds
|
|
@property
|
|
def rss_feeds(self) -> List[str]:
|
|
feeds_str = os.getenv(
|
|
"RSS_FEEDS",
|
|
"https://feeds.bbci.co.uk/news/technology/rss.xml,"
|
|
"https://techcrunch.com/feed/,"
|
|
"https://www.wired.com/feed/rss"
|
|
)
|
|
return [feed.strip() for feed in feeds_str.split(",") if feed.strip()]
|
|
|
|
# Server Settings
|
|
host: str = os.getenv("HOST", "0.0.0.0")
|
|
port: int = int(os.getenv("PORT", "8000"))
|
|
debug: bool = os.getenv("DEBUG", "true").lower() == "true"
|
|
|
|
# Data Storage (paths relative to project root)
|
|
raw_news_dir: str = os.getenv("RAW_NEWS_DIR", "../data/raw_news")
|
|
processed_news_dir: str = os.getenv("PROCESSED_NEWS_DIR", "../data/processed_news")
|
|
vector_index_path: str = os.getenv("VECTOR_INDEX_PATH", "../data/news_vectors.faiss")
|
|
|
|
# Embedding Model (Local)
|
|
embedding_model: str = "./models/all-MiniLM-L6-v2"
|
|
|
|
# News Processing
|
|
max_articles_per_feed: int = 50
|
|
similarity_threshold: float = 0.7
|
|
|
|
settings = Settings()
|