rename all folders, fix docker path

Dockerfile

@@ -10,7 +10,7 @@ RUN apt-get update && apt-get install -y \
 
 COPY requirements.txt ./
 COPY src/ ./src/
-COPY utils/ ./utils/
+COPY app/ ./app/
 
 RUN pip3 install -r requirements.txt
 
@@ -18,4 +18,4 @@ EXPOSE 8501
 
 HEALTHCHECK CMD curl --fail http://localhost:8501/_stcore/health
 
-ENTRYPOINT ["streamlit", "run", "src/streamlit_app.py", "--server.port=8501", "--server.address=0.0.0.0"]
+ENTRYPOINT ["streamlit", "run", "app/app.py", "--server.port=8501", "--server.address=0.0.0.0"]

src/streamlit_app.py → app/app.py

@@ -5,13 +5,12 @@ from pathlib import Path
 import streamlit as st
 
 # ─── Repo root is the working directory on HF Spaces ─────────────────────────
-ROOT = Path(__file__).resolve().parent.parent          # app.py lives at repo root
-sys.path.append(str(ROOT))
-sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..', 'src'))
+ROOT = Path(__file__).resolve().parent.parent
 
-os.environ["HF_HOME"] = str(ROOT / ".hf_cache")
-os.environ["TRANSFORMERS_CACHE"] = str(ROOT / ".hf_cache" / "transformers")
 
+# os.environ["HF_HOME"] = str("./.hf_cache")
+sys.path.append(str(ROOT))
+sys.path.insert(0, str(ROOT / "utils"))
 from utils.retrieval_helpers import enrich_search_results, enrich_bm25_search_results
 from utils.bm25 import load
 from utils.semantic import load_vector_store
@@ -56,6 +55,7 @@ def load_hf_dataset():
     return load_dataset(
         "McAuley-Lab/Amazon-Reviews-2023",
         "raw_meta_Grocery_and_Gourmet_Food",
+        split='full',
         trust_remote_code=True,
         token=HF_TOKEN
     )
@@ -74,7 +74,7 @@ def load_vector_store_cached():
         token=HF_TOKEN,
     )
 
-    mini_index_path = Path(snapshot_path) / "tokenisation" / "bm25_index.pkl"
+    mini_index_path = Path(snapshot_path) / "tokenisation" / "bm25_index_mini.pkl"
     embeddings_dir  = Path(snapshot_path) / "embeddings"
 
     vector_store    = load_vector_store(embeddings_dir)
@@ -98,7 +98,7 @@ HF_DATASET = load_hf_dataset()
 if data_source == 'local':
     MINI_INDEX_PATH  = ROOT / "data" / "processed" / "tokenisation" / "bm25_index_mini.pkl"
 
-    vector_store = load_vector_store(ROOT_FOLDER / 'data' / 'processed' / 'embeddings')
+    vector_store = load_vector_store(ROOT / 'data' / 'processed' / 'embeddings')
     retriever = load(MINI_INDEX_PATH)
 else: