Update faq_store.py

faq_store.py

@@ -5,9 +5,8 @@ import numpy as np
 from openai import OpenAI
 
 _current_dir = os.path.dirname(__file__)
-_parent_dir = os.path.dirname(_current_dir)
-_FAQS_FILE = os.path.join(_parent_dir, "data", "medical_faqs.jsonl")
-_EMBED_CACHE_FILE = os.path.join(_parent_dir, "data", "medical_faqs_embeddings.pkl")
+_FAQS_FILE = os.path.join(_current_dir, "medical_faqs.jsonl")
+_EMBED_CACHE_FILE = os.path.join(_current_dir, "medical_faqs_embeddings.pkl")
 _EMBED_MODEL = "text-embedding-3-small"
 
 client = OpenAI(api_key=os.getenv("OPENAI_API_KEY"))
@@ -21,14 +20,12 @@ def initialize_faq_store():
     FAQ_ENTRIES.clear()
     FAQ_VECS.clear()
 
-    # Load cached embeddings if present
     cached_vecs: dict[str, np.ndarray] = {}
     if os.path.exists(_EMBED_CACHE_FILE):
         with open(_EMBED_CACHE_FILE, "rb") as f:
             cached_entries, cached_vecs = pickle.load(f)
         FAQ_ENTRIES.update(cached_entries)
 
-    # Load (or reload) FAQ entries from JSONL
     with open(_FAQS_FILE, "r", encoding="utf-8") as f:
         for line in f:
             line = line.strip()
@@ -37,7 +34,6 @@ def initialize_faq_store():
             obj = json.loads(line)
             FAQ_ENTRIES[obj["id"]] = obj
 
-    # Embed any entries not yet in cache
     new_vecs: dict[str, np.ndarray] = {}
     for fid, entry in FAQ_ENTRIES.items():
         if fid in cached_vecs:
@@ -48,7 +44,6 @@ def initialize_faq_store():
             new_vecs[fid] = vec
         FAQ_VECS.append((fid, vec))
 
-    # Persist updated cache
     all_vecs = {**cached_vecs, **new_vecs}
     with open(_EMBED_CACHE_FILE, "wb") as f:
         pickle.dump((FAQ_ENTRIES, all_vecs), f)