fix: textembedding gecko 003 change from latest (#1572)

# Description

As described in the issue #1571 the gecko version can't load if it's specified as the latest, it's also
not recommended by the documentation, I've changed it to the version
003.

Fixes #1571 🦕

gemini/use-cases/retrieval-augmented-generation/utils/intro_multimodal_rag_utils.py

@@ -20,7 +20,7 @@
 from vertexai.vision_models import Image as vision_model_Image
 from vertexai.vision_models import MultiModalEmbeddingModel
 
-text_embedding_model = TextEmbeddingModel.from_pretrained("textembedding-gecko@latest")
+text_embedding_model = TextEmbeddingModel.from_pretrained("textembedding-gecko@003")
 multimodal_embedding_model = MultiModalEmbeddingModel.from_pretrained(
     "multimodalembedding@001"
 )