proKBD commited on
Commit
2816e54
·
verified ·
1 Parent(s): a72976d

Update config.py

Browse files
Files changed (1) hide show
  1. config.py +1 -86
config.py CHANGED
@@ -76,95 +76,10 @@ MIN_ARTICLES = 20
76
  MAX_ARTICLES_PER_SOURCE = 10 # Adjusted for more sources
77
  MAX_ARTICLES = 50 # Increased to accommodate more sources
78
 
79
- # Browser Headers
80
- HEADERS = {
81
- "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win"""Configuration settings for the News Summarization application."""
82
-
83
- import os
84
- from dotenv import load_dotenv
85
-
86
- # Load environment variables
87
- load_dotenv()
88
-
89
- # API Settings - Modified for direct processing
90
- API_HOST = "localhost" # Changed from 0.0.0.0
91
- API_PORT = 8501 # Changed to Streamlit's default port
92
- API_BASE_URL = "http://localhost:8501" # Direct URL for local processing
93
-
94
- # News Scraping Settings
95
- ARTICLES_PER_SOURCE = int(os.getenv("ARTICLES_PER_SOURCE", "10"))
96
- USER_AGENT = os.getenv("USER_AGENT", "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36")
97
-
98
- # RSS Feed Settings
99
- RSS_FEEDS = {
100
- "BBC": "http://feeds.bbci.co.uk/news/business/rss.xml",
101
- "CNN": "http://rss.cnn.com/rss/money_news_international.rss",
102
- "FoxBusiness": "http://feeds.foxnews.com/foxbusiness/latest"
103
- }
104
-
105
- # Model Settings
106
- SENTIMENT_MODEL = "yiyanghkust/finbert-tone" # More advanced financial sentiment model
107
- SENTIMENT_FINE_GRAINED_MODEL = "mrm8488/distilroberta-finetuned-financial-news-sentiment-analysis"
108
- SUMMARIZATION_MODEL = "t5-base"
109
-
110
- # Additional Fine-Grained Sentiment Models
111
- FINE_GRAINED_MODELS = {
112
- "financial": "mrm8488/distilroberta-finetuned-financial-news-sentiment-analysis",
113
- "emotion": "j-hartmann/emotion-english-distilroberta-base",
114
- "aspect": "yangheng/deberta-v3-base-absa-v1.1",
115
- "esg": "yiyanghkust/finbert-esg",
116
- "news_tone": "ProsusAI/finbert"
117
- }
118
-
119
- # Fine-Grained Sentiment Categories
120
- SENTIMENT_CATEGORIES = {
121
- "financial": ["positive", "negative", "neutral"],
122
- "emotion": ["joy", "sadness", "anger", "fear", "surprise", "disgust", "neutral"],
123
- "aspect": ["positive", "negative", "neutral"],
124
- "esg": ["environmental", "social", "governance", "neutral"],
125
- "news_tone": ["positive", "negative", "neutral"]
126
- }
127
-
128
- # Cache Settings
129
- CACHE_DIR = os.getenv("CACHE_DIR", ".cache")
130
- CACHE_EXPIRY = int(os.getenv("CACHE_EXPIRY", "3600")) # 1 hour
131
- CACHE_DURATION = int(os.getenv("CACHE_DURATION", "300")) # 5 minutes in seconds
132
-
133
- # Audio Settings
134
- AUDIO_OUTPUT_DIR = os.getenv("AUDIO_OUTPUT_DIR", "audio_output")
135
- DEFAULT_LANG = os.getenv("DEFAULT_LANG", "hi") # Hindi
136
-
137
- # News Sources
138
- NEWS_SOURCES = {
139
- # Major News Aggregators
140
- "google": "https://www.google.com/search?q={}&tbm=nws",
141
- "bing": "https://www.bing.com/news/search?q={}",
142
- "yahoo": "https://news.search.yahoo.com/search?p={}",
143
-
144
- # Financial News
145
- "reuters": "https://www.reuters.com/search/news?blob={}",
146
- "marketwatch": "https://www.marketwatch.com/search?q={}&ts=0&tab=All%20News",
147
- "investing": "https://www.investing.com/search/?q={}&tab=news",
148
-
149
- # Tech News
150
- "techcrunch": "https://techcrunch.com/search/{}",
151
- "zdnet": "https://www.zdnet.com/search/?q={}",
152
- }
153
-
154
- # Article limits
155
- MIN_ARTICLES = 20
156
- MAX_ARTICLES_PER_SOURCE = 10 # Adjusted for more sources
157
- MAX_ARTICLES = 50 # Increased to accommodate more sources
158
-
159
  # Browser Headers
160
  HEADERS = {
161
  "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36",
162
  "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
163
  "Accept-Language": "en-US,en;q=0.5",
164
  "Connection": "keep-alive"
165
- }
166
- 64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36",
167
- "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
168
- "Accept-Language": "en-US,en;q=0.5",
169
- "Connection": "keep-alive"
170
- }
 
76
  MAX_ARTICLES_PER_SOURCE = 10 # Adjusted for more sources
77
  MAX_ARTICLES = 50 # Increased to accommodate more sources
78
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
79
  # Browser Headers
80
  HEADERS = {
81
  "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36",
82
  "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
83
  "Accept-Language": "en-US,en;q=0.5",
84
  "Connection": "keep-alive"
85
+ }