Update manabUtils.py

manabUtils.py

@@ -1,4 +1,4 @@
-#to be updated
+#manabUtils.py
 from langchain_community.vectorstores import FAISS
 from langchain_huggingface import HuggingFaceEmbeddings
 from huggingface_hub import hf_hub_download
@@ -32,6 +32,44 @@ def retrieve_chunks(repo_id, embedding_model="sentence-transformers/all-MiniLM-L
           allow_dangerous_deserialization=True
       )
 
+      # Step 4: Create retriever
+      retriever = vectorstore.as_retriever(search_kwargs={"k": 3})
+    except Exception as e:
+      print(f"Error in generate_qa_chain: {e}")
+      return None
+    return retriever
+
+def retrieve_chunks_GPC():
+    """
+    Retreive chunks from HF dataset for GPC
+    """    
+    embedding_model="sentence-transformers/all-MiniLM-L6-v2"
+    repo_id="manabb/NRLGPC"
+    
+    try:
+      # Step 1: Create embeddings (FIX: was missing)
+      embeddings = HuggingFaceEmbeddings(model_name=embedding_model)
+
+      # Step 2: Download FAISS files from HF Hub
+      faiss_path = hf_hub_download(
+          repo_id=repo_id,
+          filename="faiss_gpc_goods_merged/index.faiss",
+          repo_type="dataset"
+      )
+      pkl_path = hf_hub_download(
+          repo_id=repo_id,
+          filename="faiss_gpc_goods_merged/index.pkl",
+          repo_type="dataset"
+      )
+
+      # Step 3: Load FAISS vectorstore (FIX: pass embeddings object, not string)
+      folder_path = os.path.dirname(faiss_path)
+      vectorstore = FAISS.load_local(
+          folder_path=folder_path,
+          embeddings=embeddings,  # FIXED: was 'embedding_model' string
+          allow_dangerous_deserialization=True
+      )
+
       # Step 4: Create retriever
       retriever = vectorstore.as_retriever(search_kwargs={"k": 3})
     except Exception as e: