Update src/streamlit_app.py

src/streamlit_app.py

@@ -8,6 +8,9 @@ import streamlit as st
 ROOT = Path(__file__).resolve().parent.parent          # app.py lives at repo root
 sys.path.append(str(ROOT))
 
+os.environ["HF_HOME"] = str(ROOT / ".hf_cache")
+os.environ["TRANSFORMERS_CACHE"] = str(ROOT / ".hf_cache" / "transformers")
+
 from utils.retrieval_helpers import enrich_search_results
 from utils.semantic import load_vector_store
 
@@ -40,18 +43,27 @@ def load_hf_dataset():
 HF_DATASET = load_hf_dataset()
 
 # ─── Download vector store from your HF dataset repo ─────────────────────────
-from huggingface_hub import hf_hub_download, snapshot_download
+from huggingface_hub import hf_hub_download, snapshot_download, login
 
 VECTOR_STORE_DIR = ROOT / "embeddings" / "semantic_vector_store"
 
 @st.cache_resource
 def load_vector_store_cached():
+    # Authenticate explicitly — raises a clear error if token is missing
+    hf_token = os.environ.get("HF_TOKEN")
+    if not hf_token:
+        st.error("HF_TOKEN secret is not set. Go to Space Settings → Secrets.")
+        st.stop()
+
+    login(token=hf_token, add_to_git_credential=False)
+
     VECTOR_STORE_DIR.mkdir(parents=True, exist_ok=True)
 
     snapshot_download(
         repo_id="rishadaz/amazon_retriever-storage",
         repo_type="dataset",
         local_dir=str(VECTOR_STORE_DIR),
+        token=hf_token,
     )
 
     return load_vector_store(VECTOR_STORE_DIR)