proper usage of embedding models if defined in .env

services/rag/langchain/vector_storage.py

@@ -4,10 +4,11 @@ import os
 from typing import Optional
 
 from dotenv import load_dotenv
-from langchain_qdrant import QdrantVectorStore
 from langchain_core.documents import Document
 from langchain_ollama import OllamaEmbeddings
 from langchain_openai import OpenAIEmbeddings
+from langchain_qdrant import QdrantVectorStore
+from loguru import logger
 from qdrant_client import QdrantClient
 
 # Load environment variables
@@ -43,7 +44,9 @@ def initialize_vector_store(
     if EMBEDDING_STRATEGY == "openai":
         # Validate required OpenAI embedding variables
         if not OPENAI_EMBEDDING_API_KEY or not OPENAI_EMBEDDING_BASE_URL:
-            raise ValueError("OPENAI_EMBEDDING_API_KEY and OPENAI_EMBEDDING_BASE_URL must be set when using OpenAI embedding strategy")
+            raise ValueError(
+                "OPENAI_EMBEDDING_API_KEY and OPENAI_EMBEDDING_BASE_URL must be set when using OpenAI embedding strategy"
+            )
 
         # Initialize OpenAI embeddings
         embeddings = OpenAIEmbeddings(
@@ -51,6 +54,10 @@ def initialize_vector_store(
             openai_api_base=OPENAI_EMBEDDING_BASE_URL,
             openai_api_key=OPENAI_EMBEDDING_API_KEY,
         )
+    elif EMBEDDING_STRATEGY == "none":
+        embeddings = None
+
+        logger.warning("Embedding strategy for vector storage is NONE! FYI")
     else:  # Default to ollama
         # Initialize Ollama embeddings
         embeddings = OllamaEmbeddings(
@@ -118,7 +125,9 @@ def add_documents_to_vector_store(
         vector_store.add_documents(batch)
 
 
-def search_vector_store(vector_store: QdrantVectorStore, query: str, top_k: int = 5) -> list:
+def search_vector_store(
+    vector_store: QdrantVectorStore, query: str, top_k: int = 5
+) -> list:
     """
     Search the vector store for similar documents.