Update src/qa.py

src/qa.py

@@ -1,17 +1,18 @@
-import os
-
 # ----------------------------
-# Force Hugging Face to use /tmp for cache
+# Hugging Face cache bootstrap
 # ----------------------------
-CACHE_DIR = "/tmp/huggingface"
+import os
+
+CACHE_DIR = "/home/user/huggingface"
 os.makedirs(CACHE_DIR, exist_ok=True)
 
 os.environ["HF_HOME"] = CACHE_DIR
 os.environ["TRANSFORMERS_CACHE"] = CACHE_DIR
 os.environ["HF_DATASETS_CACHE"] = CACHE_DIR
+os.environ["HF_MODULES_CACHE"] = CACHE_DIR
 
 # ----------------------------
-# Now import libraries (they'll respect env vars)
+# Imports AFTER cache bootstrap
 # ----------------------------
 from sentence_transformers import SentenceTransformer
 from transformers import pipeline
@@ -47,12 +48,4 @@ def retrieve_chunks(query, index, chunks, top_k=3):
 
 def generate_answer(query, retrieved_chunks):
     if not retrieved_chunks:
-        return "Sorry, I could not find relevant information."
-
-    context = " ".join(retrieved_chunks)
-    prompt = (
-        "You are an assistant. Use the context to answer the question clearly.\n"
-        f"Context:\n{context}\n\nQuestion:\n{query}\n\nAnswer:"
-    )
-    result = _answer_model(prompt, max_length=300, do_sample=False)
-    return result[0]["generated_text"].strip()
+        return "Sorry,