fix: Getting embeddings using text-embedding-005 (#12725)

Author: lee1premium-2024

generative_ai/embeddings/code_retrieval_example.py

@@ -17,14 +17,14 @@
 # [START generativeaionvertexai_embedding_code_retrieval]
 from vertexai.language_models import TextEmbeddingInput, TextEmbeddingModel
 
-MODEL_NAME = "text-embedding-preview-0815"
+MODEL_NAME = "text-embedding-005"
 DIMENSIONALITY = 256
 
 
 def embed_text(
     texts: list[str] = ["Retrieve a function that adds two numbers"],
     task: str = "CODE_RETRIEVAL_QUERY",
-    model_name: str = "text-embedding-preview-0815",
+    model_name: str = "text-embedding-005",
     dimensionality: int | None = 256,
 ) -> list[list[float]]:
     """Embeds texts with a pre-trained, foundational model."""

generative_ai/embeddings/document_retrieval_example.py

@@ -32,7 +32,7 @@ def embed_text() -> list[list[float]]:
     # The task type for embedding. Check the available tasks in the model's documentation.
     task = "RETRIEVAL_DOCUMENT"
 
-    model = TextEmbeddingModel.from_pretrained("text-embedding-004")
+    model = TextEmbeddingModel.from_pretrained("text-embedding-005")
     inputs = [TextEmbeddingInput(text, task) for text in texts]
     kwargs = dict(output_dimensionality=dimensionality) if dimensionality else {}
     embeddings = model.get_embeddings(inputs, **kwargs)

generative_ai/embeddings/model_tuning_example.py

@@ -21,7 +21,7 @@
 
 def tune_embedding_model(
     api_endpoint: str,
-    base_model_name: str = "text-embedding-004",
+    base_model_name: str = "text-embedding-005",
     corpus_path: str = "gs://cloud-samples-data/ai-platform/embedding/goog-10k-2024/r11/corpus.jsonl",
     queries_path: str = "gs://cloud-samples-data/ai-platform/embedding/goog-10k-2024/r11/queries.jsonl",
     train_label_path: str = "gs://cloud-samples-data/ai-platform/embedding/goog-10k-2024/r11/train.tsv",