fixes

.gitignore

@@ -56,3 +56,4 @@ Thumbs.db
 
 # Streamlit
 .streamlit/
+!.streamlit/config.toml

requirements.txt

@@ -33,5 +33,4 @@ scikit-learn>=1.3.0
 
 openai>=1.0.0
 streamlit
-torch==2.8.0
 huggingface_hub

src/search_final.py

@@ -24,8 +24,20 @@ logging.basicConfig(
 )
 logger = logging.getLogger(__name__)
 
-nltk.download("stopwords")
-STOPWORDS = set(stopwords.words("english"))
+# Set NLTK data path to a writable directory
+nltk_data_dir = os.path.join(os.getcwd(), "nltk_data")
+if not os.path.exists(nltk_data_dir):
+    os.makedirs(nltk_data_dir)
+nltk.data.path.append(nltk_data_dir)
+
+# Download to the custom directory
+try:
+    nltk.download("stopwords", download_dir=nltk_data_dir)
+    STOPWORDS = set(stopwords.words("english"))
+except Exception as e:
+    print(f"NLTK download failed: {e}")
+    # Fallback to basic English stopwords
+    STOPWORDS = set(['i', 'me', 'my', 'myself', 'we', 'our', 'ours', 'ourselves', 'you', 'your', 'yours', 'yourself', 'yourselves', 'he', 'him', 'his', 'himself', 'she', 'her', 'hers', 'herself', 'it', 'its', 'itself', 'they', 'them', 'their', 'theirs', 'themselves', 'what', 'which', 'who', 'whom', 'this', 'that', 'these', 'those', 'am', 'is', 'are', 'was', 'were', 'be', 'been', 'being', 'have', 'has', 'had', 'having', 'do', 'does', 'did', 'doing', 'a', 'an', 'the', 'and', 'but', 'if', 'or', 'because', 'as', 'until', 'while', 'of', 'at', 'by', 'for', 'with', 'through', 'during', 'before', 'after', 'above', 'below', 'up', 'down', 'in', 'out', 'on', 'off', 'over', 'under', 'again', 'further', 'then', 'once'])
 
 os.environ["TOKENIZERS_PARALLELISM"] = "false"
 # ...rest of your imports...

src/streamlit_app.py

@@ -4,7 +4,12 @@ import numpy as np
 import torch
 import os
 from dotenv import load_dotenv
-from transformers import AutoModelForCausalLM, AutoTokenizer
+try:
+    from transformers import AutoModelForCausalLM, AutoTokenizer
+except ImportError as e:
+    st.error(f"Error importing transformers: {e}")
+    st.error("Please ensure transformers library is properly installed.")
+    st.stop()
 from peft import PeftModel
 from search_final import rag_pipeline