llamaindex update + unpacking archives in data

services/rag/llamaindex/retrieval.py

@@ -16,33 +16,8 @@ from pathlib import Path
 
 from vector_storage import get_vector_store_and_index
 
-
-from llama_index.embeddings.ollama import OllamaEmbedding
-import os
-
-
-def setup_global_models():
-    """Set up the global models to prevent defaulting to OpenAI."""
-    # Set up the embedding model
-    ollama_embed_model = os.getenv("OLLAMA_EMBEDDING_MODEL", "qwen3-embedding:4b")
-    ollama_base_url = "http://localhost:11434"
-
-    embed_model = OllamaEmbedding(
-        model_name=ollama_embed_model,
-        base_url=ollama_base_url
-    )
-
-    # Set as the global embedding model
-    Settings.embed_model = embed_model
-
-    # Set up the LLM model
-    ollama_chat_model = os.getenv("OLLAMA_CHAT_MODEL", "nemotron-mini:4b")
-
-    from llama_index.llms.ollama import Ollama
-    llm = Ollama(model=ollama_chat_model, base_url=ollama_base_url)
-
-    # Set as the global LLM
-    Settings.llm = llm
+# Import the new configuration module
+from config import setup_global_models
 
 
 def initialize_retriever(