chore: sync app/ and src/ from GitHub

app/app.py

@@ -69,6 +69,7 @@ def load_vector_store_cached():
         repo_id="rishadaz/amazon_retriever-storage",
         repo_type="dataset",
         local_dir=str(VECTOR_STORE_DIR),
+        split='full',
         token=HF_TOKEN,
     )
 
@@ -84,7 +85,7 @@ def load_vector_store_cached():
 # local tag will read from your local directory as a default it will
 # read the mini versions of the files we have provided in the repo
 
-data_source = "remote" #"remote" or "local" 
+data_source = os.getenv('DATA_SOURCE')
 
 # note: remote has the full generated corpus and 
 # embeddings which can take a long time to download and 
@@ -136,8 +137,7 @@ hybrid_retriever = HybridRetriever(
     )
 
 def llm_retriever(query: str, top_k: int = 5):
-    retriever = hybrid_retriever
-    answer, docs = run_rag(retriever, query=query, hf_dataset=HF_DATASET['full'])
+    answer, docs = run_rag(hybrid_retriever, query=query, hf_dataset=HF_DATASET['full'])
     return answer, docs