updated fact_check.py

backend/api/fact_check.py

@@ -15,6 +15,8 @@ from sumy.parsers.plaintext import PlaintextParser
 from sumy.nlp.tokenizers import Tokenizer
 from sumy.summarizers.lsa import LsaSummarizer
 import nltk
+from nltk.corpus import stopwords
+from nltk.tokenize import word_tokenize
 
 load_dotenv()
 
@@ -25,8 +27,17 @@ USER_AGENT = {"User-Agent": "Mozilla/5.0"}
 session = requests.Session()
 session.headers.update(USER_AGENT)
 
-# nltk data for tokenization once
-nltk.download('punkt')
+
+# Set NLTK data path to a writable directory
+nltk_data_dir = "/tmp/nltk_data"
+os.makedirs(nltk_data_dir, exist_ok=True)
+
+# Download necessary NLTK data to that directory
+nltk.download("punkt", download_dir=nltk_data_dir)
+nltk.download("stopwords", download_dir=nltk_data_dir)
+
+# Tell NLTK to look here for data
+nltk.data.path.append(nltk_data_dir)
 
 logging.basicConfig(level=logging.INFO)