diff --git a/docs/_static/llama-stack-spec.html b/docs/_static/llama-stack-spec.html
index 6ca572a76..b3d133658 100644
--- a/docs/_static/llama-stack-spec.html
+++ b/docs/_static/llama-stack-spec.html
@@ -15624,7 +15624,7 @@
                     },
                     "vector_db_name": {
                         "type": "string",
-                        "description": "The name of the vector database. :param provider_vector_db_id: The identifier of the vector database in the provider."
+                        "description": "The name of the vector database."
                     },
                     "provider_vector_db_id": {
                         "type": "string",
diff --git a/docs/_static/llama-stack-spec.yaml b/docs/_static/llama-stack-spec.yaml
index fd3945d85..14f7701f6 100644
--- a/docs/_static/llama-stack-spec.yaml
+++ b/docs/_static/llama-stack-spec.yaml
@@ -10933,9 +10933,7 @@ components:
           description: The identifier of the provider.
         vector_db_name:
           type: string
-          description: >-
-            The name of the vector database. :param provider_vector_db_id: The identifier
-            of the vector database in the provider.
+          description: The name of the vector database.
         provider_vector_db_id:
           type: string
           description: >-
diff --git a/llama_stack/apis/vector_dbs/vector_dbs.py b/llama_stack/apis/vector_dbs/vector_dbs.py
index d6d638f97..1b6d3cc84 100644
--- a/llama_stack/apis/vector_dbs/vector_dbs.py
+++ b/llama_stack/apis/vector_dbs/vector_dbs.py
@@ -82,7 +82,7 @@ class VectorDBs(Protocol):
         :param embedding_dimension: The dimension of the embedding model.
         :param provider_id: The identifier of the provider.
         :param vector_db_name: The name of the vector database.
-                :param provider_vector_db_id: The identifier of the vector database in the provider.
+        :param provider_vector_db_id: The identifier of the vector database in the provider.
         :returns: A VectorDB.
         """
         ...
diff --git a/llama_stack/providers/utils/memory/openai_vector_store_mixin.py b/llama_stack/providers/utils/memory/openai_vector_store_mixin.py
index 7d47bf747..19147c43f 100644
--- a/llama_stack/providers/utils/memory/openai_vector_store_mixin.py
+++ b/llama_stack/providers/utils/memory/openai_vector_store_mixin.py
@@ -8,6 +8,7 @@ import asyncio
 import logging
 import mimetypes
 import time
+import uuid
 from abc import ABC, abstractmethod
 from typing import Any
 
@@ -148,7 +149,7 @@ class OpenAIVectorStoreMixin(ABC):
         """Creates a vector store."""
         created_at = int(time.time())
         if provider_vector_db_id is None:
-            raise ValueError("Provider vector DB ID is required")
+            provider_vector_db_id = f"vs_{uuid.uuid4()}"
 
         if provider_id is None:
             raise ValueError("Provider ID is required")
diff --git a/tests/integration/vector_io/test_vector_io.py b/tests/integration/vector_io/test_vector_io.py
index f6953a4f1..9cd4fc18c 100644
--- a/tests/integration/vector_io/test_vector_io.py
+++ b/tests/integration/vector_io/test_vector_io.py
@@ -53,7 +53,6 @@ def test_vector_db_retrieve(client_with_empty_registry, embedding_model_id, embe
         vector_db_id=vector_db_id,
         embedding_model=embedding_model_id,
         embedding_dimension=embedding_dimension,
-        provider_vector_db_id=vector_db_id,
     )
 
     # Retrieve the memory bank and validate its properties
@@ -70,7 +69,6 @@ def test_vector_db_register(client_with_empty_registry, embedding_model_id, embe
         vector_db_id=vector_db_id,
         embedding_model=embedding_model_id,
         embedding_dimension=embedding_dimension,
-        provider_vector_db_id=vector_db_id,
     )
 
     vector_dbs_after_register = [vector_db.identifier for vector_db in client_with_empty_registry.vector_dbs.list()]
@@ -98,7 +96,6 @@ def test_insert_chunks(client_with_empty_registry, embedding_model_id, embedding
         vector_db_id=vector_db_id,
         embedding_model=embedding_model_id,
         embedding_dimension=embedding_dimension,
-        provider_vector_db_id=vector_db_id,
     )
 
     client_with_empty_registry.vector_io.insert(
@@ -134,7 +131,6 @@ def test_insert_chunks_with_precomputed_embeddings(client_with_empty_registry, e
         vector_db_id=vector_db_id,
         embedding_model=embedding_model_id,
         embedding_dimension=embedding_dimension,
-        provider_vector_db_id=vector_db_id,
     )
 
     chunks_with_embeddings = [