fix: Fix /vector-stores/create API when vector store with duplicate name (#2617)

# What does this PR do?

Resolves https://github.com/meta-llama/llama-stack/issues/2735

Currently, if you test against OpenAI's Vector Stores API the
`client.vector_stores.search` call fails with an invalid vector_db
during routing (see the script referenced in the clickable item under
the Test Plan section).

This PR ensures that `client.vector_stores.search()` is compatible with
OpenAI's Vector Stores API.

Two biggest changes:
1. The `name`, which was previously used as the `vector_db_id`, has been
changed to be consistent with OpenAI's `vs_{uuid}` format.
2. The vector store ID has to be referenced by the ID, the name is not
reliable as every `client.vector_stores.create` results in a new vector
store.

NOTE: I believe this is a breaking change for end users as they'll need
to update their VectorDB identifiers.

## Test Plan
Unit tests:
```bash
./scripts/unit-tests.sh tests/unit/providers/vector_io/ -v
```
Integration tests:
```bash
ENABLE_MILVUS=milvus llama stack run /Users/farceo/dev/llama-stack/llama_stack/templates/starter/run.yaml --image-type venv

LLAMA_STACK_CONFIG=http://localhost:8321 pytest -sv tests/integration/vector_io/test_openai_vector_stores.py --embedding-model=all-MiniLM-L6-v2 -vv
```

Unit tests and test script below 👇 

<details> 
<summary>Click here for script used to test OpenAI and Llama Stack
Vector Store implementation</summary>

```python
import json
import argparse
from openai import OpenAI, pagination
import logging
from colorama import Fore, Style, init
import traceback
import os

# Initialize colorama for color support in terminal
init(autoreset=True)

# Setup basic logging
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')

DEMO_VECTOR_STORE_NAME = "Support FAQ FJA"
global DEMO_VECTOR_STORE_ID
global DEMO_VECTOR_STORE_ID2


def colored_print(color, text):
    """Prints text to the console with the specified color."""
    print(f"{color}{text}{Style.RESET_ALL}")


def log_and_print(color, message, level=logging.INFO):
    """Logs a message and prints it to the console with the specified color."""
    logging.log(level, message)
    colored_print(color, message)


def run_tests(client, prefix="openai"):
    """
    Runs all tests using the provided OpenAI client and saves the output
    to JSON files with the given prefix.
    """
    # Create the directory if it doesn't exist
    os.makedirs('openai_testing', exist_ok=True)

    # Default values in case tests fail
    global DEMO_VECTOR_STORE_ID, DEMO_VECTOR_STORE_ID2
    DEMO_VECTOR_STORE_ID = None
    DEMO_VECTOR_STORE_ID2 = None

    def test_idempotent_vector_store_creation():
        """
        Test that creating a vector store with the same name is idempotent.
        """
        log_and_print(Fore.BLUE, "Starting vector store creation test...")
        try:
            vector_store = client.vector_stores.create(
                name=DEMO_VECTOR_STORE_NAME,
            )

            # Attempt to create the same vector store again
            vector_store2 = client.vector_stores.create(
                name=DEMO_VECTOR_STORE_NAME,
            )

            # Check instead of assert
            if vector_store2.id != vector_store.id:
                log_and_print(Fore.YELLOW, f"FAILED IDEMPOTENCY: the same VectorStore name for {prefix.upper()} does not return the same ID",
                              level=logging.WARNING)
            else:
                log_and_print(Fore.GREEN, f"PASSED IDEMPOTENCY: f{vector_store2.id} == {vector_store.id} the same VectorStore name for {prefix.upper()} returns the same ID")

            vector_store_data = vector_store.to_dict()
            log_and_print(Fore.WHITE, f"vector_stores.create = {json.dumps(vector_store_data, indent=2)}")
            with open(f'openai_testing/{prefix}_vector_store_create.json', 'w') as f:
                json.dump(vector_store_data, f, indent=2)

            global DEMO_VECTOR_STORE_ID, DEMO_VECTOR_STORE_ID2
            DEMO_VECTOR_STORE_ID = vector_store.id
            DEMO_VECTOR_STORE_ID2 = vector_store2.id
            return DEMO_VECTOR_STORE_ID, DEMO_VECTOR_STORE_ID2
        except Exception as e:
            log_and_print(Fore.RED, f"Idempotent vector store creation test failed: {e}", level=logging.ERROR)
            logging.error(traceback.format_exc())
            # Create a fallback vector store ID if needed
            if 'vector_store' in locals() and vector_store:
                DEMO_VECTOR_STORE_ID = vector_store.id
            return DEMO_VECTOR_STORE_ID, DEMO_VECTOR_STORE_ID2

    def test_vector_store_list():
        """
        Test listing vector stores.
        """
        log_and_print(Fore.BLUE, "Starting vector store list test...")
        try:
            vector_stores = client.vector_stores.list()

            # Check instead of assert
            if not isinstance(vector_stores, pagination.SyncCursorPage):
                log_and_print(Fore.YELLOW, f"FAILED: Expected a list of vector stores, got {type(vector_stores)}",
                              level=logging.WARNING)
            else:
                log_and_print(Fore.GREEN, "Vector store list test passed!")

            vector_stores_data = vector_stores.to_dict()
            log_and_print(Fore.WHITE, f"vector_stores.list = {json.dumps(vector_stores_data, indent=2)}")
            with open(f'openai_testing/{prefix}_vector_store_list.json', 'w') as f:
                json.dump(vector_stores_data, f, indent=2)
        except Exception as e:
            log_and_print(Fore.RED, f"Vector store list test failed: {e}", level=logging.ERROR)
            logging.error(traceback.format_exc())

    def test_retrieve_vector_store():
        """
        Test retrieving a specific vector store.
        """
        log_and_print(Fore.BLUE, "Starting retrieve vector store test...")
        if not DEMO_VECTOR_STORE_ID:
            log_and_print(Fore.YELLOW, "Skipping retrieve vector store test - no vector store ID available",
                          level=logging.WARNING)
            return

        try:
            vector_store = client.vector_stores.retrieve(
                vector_store_id=DEMO_VECTOR_STORE_ID,
            )

            # Check instead of assert
            if vector_store.id != DEMO_VECTOR_STORE_ID:
                log_and_print(Fore.YELLOW, "FAILED: Retrieved vector store ID does not match", level=logging.WARNING)
            else:
                log_and_print(Fore.GREEN, "Retrieve vector store test passed!")

            vector_store_data = vector_store.to_dict()
            log_and_print(Fore.WHITE, f"vector_stores.retrieve = {json.dumps(vector_store_data, indent=2)}")
            with open(f'openai_testing/{prefix}_vector_store_retrieve.json', 'w') as f:
                json.dump(vector_store_data, f, indent=2)
        except Exception as e:
            log_and_print(Fore.RED, f"Retrieve vector store test failed: {e}", level=logging.ERROR)
            logging.error(traceback.format_exc())

    def test_modify_vector_store():
        """
        Test modifying a vector store.
        """
        log_and_print(Fore.BLUE, "Starting modify vector store test...")
        if not DEMO_VECTOR_STORE_ID:
            log_and_print(Fore.YELLOW, "Skipping modify vector store test - no vector store ID available",
                          level=logging.WARNING)
            return

        try:
            updated_vector_store = client.vector_stores.update(
                vector_store_id=DEMO_VECTOR_STORE_ID,
                name="Updated Support FAQ FJA",
            )

            # Check instead of assert
            if updated_vector_store.name != "Updated Support FAQ FJA":
                log_and_print(Fore.YELLOW, "FAILED: Vector store name was not updated correctly", level=logging.WARNING)
            else:
                log_and_print(Fore.GREEN, "Modify vector store test passed!")

            updated_vector_store_data = updated_vector_store.to_dict()
            log_and_print(Fore.WHITE, f"vector_stores.modify = {json.dumps(updated_vector_store_data, indent=2)}")
            with open(f'openai_testing/{prefix}_vector_store_modify.json', 'w') as f:
                json.dump(updated_vector_store_data, f, indent=2)
        except Exception as e:
            log_and_print(Fore.RED, f"Modify vector store test failed: {e}", level=logging.ERROR)
            logging.error(traceback.format_exc())

    def test_delete_vector_store():
        """
        Test deleting a vector store.
        """
        log_and_print(Fore.BLUE, "Starting delete vector store test...")
        if not DEMO_VECTOR_STORE_ID2:
            log_and_print(Fore.YELLOW, "Skipping delete vector store test - no second vector store ID available",
                          level=logging.WARNING)
            return

        try:
            response = client.vector_stores.delete(
                vector_store_id=DEMO_VECTOR_STORE_ID2,
            )

            log_and_print(Fore.GREEN, "Delete vector store test passed!")

            response_data = response.to_dict()
            log_and_print(Fore.WHITE, f"Vector store delete response = {json.dumps(response_data, indent=2)}")
            with open(f'openai_testing/{prefix}_vector_store_delete.json', 'w') as f:
                json.dump(response_data, f, indent=2)
        except Exception as e:
            log_and_print(Fore.RED, f"Delete vector store test failed: {e}", level=logging.ERROR)
            logging.error(traceback.format_exc())

    def test_create_vector_store_file():
        log_and_print(Fore.BLUE, "Starting create vector store file test...")
        if not DEMO_VECTOR_STORE_ID:
            log_and_print(Fore.YELLOW, "Skipping create vector store file test - no vector store ID available",
                          level=logging.WARNING)
            return

        try:
            # create jsonl of files as an example
            with open("mydata.jsonl", "w") as f:
                f.write('{"text": "What is the return policy?", "metadata": {"category": "support"}}\n')
                f.write('{"text": "How do I reset my password?", "metadata": {"category": "support"}}\n')
                f.write('{"text": "Where can I find my order history?", "metadata": {"category": "support"}}\n')
                f.write('{"text": "What are the shipping options?", "metadata": {"category": "support"}}\n')
                f.write('{"text": "What is your favorite banana?", "metadata": {"category": "support"}}\n')

            # Create a simple text file if my_data_small.txt doesn't exist
            if not os.path.exists("my_data_small.txt"):
                with open("my_data_small.txt", "w") as f:
                    f.write("This is a test file for vector store testing.\n")

            created_file = client.files.create(
                file=open("my_data_small.txt", "rb"),
                purpose="assistants",
            )

            created_file_data = created_file.to_dict()
            log_and_print(Fore.WHITE, f"Created file {json.dumps(created_file_data, indent=2)}")
            with open(f'openai_testing/{prefix}_file_create.json', 'w') as f:
                json.dump(created_file_data, f, indent=2)

            retrieved_files = client.files.retrieve(created_file.id)
            retrieved_files_data = retrieved_files.to_dict()
            log_and_print(Fore.WHITE, f"Retrieved file {json.dumps(retrieved_files_data, indent=2)}")
            with open(f'openai_testing/{prefix}_file_retrieve.json', 'w') as f:
                json.dump(retrieved_files_data, f, indent=2)

            vector_store_file = client.vector_stores.files.create(
                vector_store_id=DEMO_VECTOR_STORE_ID,
                file_id=created_file.id,
            )
            log_and_print(Fore.GREEN, "Create vector store file test passed!")
        except Exception as e:
            log_and_print(Fore.RED, f"Create vector store file test failed: {e}", level=logging.ERROR)
            logging.error(traceback.format_exc())

    def test_search_vector_store():
        """
        Test searching a vector store.
        """
        log_and_print(Fore.BLUE, "Starting search vector store test...")
        if not DEMO_VECTOR_STORE_ID:
            log_and_print(Fore.YELLOW, "Skipping search vector store test - no vector store ID available",
                          level=logging.WARNING)
            return

        try:
            query = "What is the banana policy?"
            search_results = client.vector_stores.search(
                vector_store_id=DEMO_VECTOR_STORE_ID,
                query=query,
                max_num_results=10,
                ranking_options={
                    'ranker': 'default-2024-11-15',
                    'score_threshold': 0.0,
                },
                rewrite_query=False,
            )

            # Check instead of assert
            if not isinstance(search_results, pagination.SyncPage):
                log_and_print(Fore.YELLOW, f"FAILED: Expected a list of search results, got {type(search_results)}",
                              level=logging.WARNING)
            else:
                log_and_print(Fore.GREEN, "Search vector store test passed!")

            search_results_dict = search_results.to_dict()
            log_and_print(Fore.WHITE, f"Search results = {search_results_dict}")
            with open(f'openai_testing/{prefix}_vector_store_search.json', 'w') as f:
                json.dump(search_results_dict, f, indent=2)

            log_and_print(Fore.WHITE, f"vector_stores.search = {search_results.to_json()}")
        except Exception as e:
            log_and_print(Fore.RED, f"Search vector store test failed: {e}", level=logging.ERROR)
            logging.error(traceback.format_exc())

    # Run all tests in sequence, even if some fail
    test_results = []

    try:
        result = test_idempotent_vector_store_creation()
        if result and len(result) == 2:
            DEMO_VECTOR_STORE_ID, DEMO_VECTOR_STORE_ID2 = result
        test_results.append(True)
    except Exception as e:
        log_and_print(Fore.RED, f"Vector store creation test failed: {e}", level=logging.ERROR)
        logging.error(traceback.format_exc())
        test_results.append(False)

    for test_func in [
        test_vector_store_list,
        test_retrieve_vector_store,
        test_modify_vector_store,
        test_delete_vector_store,
        test_create_vector_store_file,
        test_search_vector_store
    ]:
        try:
            test_func()
            test_results.append(True)
        except Exception as e:
            log_and_print(Fore.RED, f"{test_func.__name__} failed: {e}", level=logging.ERROR)
            logging.error(traceback.format_exc())
            test_results.append(False)

    if all(test_results):
        log_and_print(Fore.GREEN, f"All {prefix} tests completed successfully!")
    else:
        failed_count = test_results.count(False)
        log_and_print(Fore.YELLOW, f"{failed_count} {prefix} test(s) failed, but script completed.")


if __name__ == "__main__":
    parser = argparse.ArgumentParser(description="Run OpenAI and/or LlamaStack tests.")
    parser.add_argument(
        "--provider",
        type=str,
        default="llama",
        choices=["openai", "llama", "both"],
        help="Specify which environment to test: openai, llama, or both. Default is both.",
    )
    args = parser.parse_args()

    try:
        if args.provider in ("openai", "both"):
            openai_client = OpenAI()
            run_tests(openai_client, prefix="openai")

        if args.provider in ("llama", "both"):
            llama_client = OpenAI(base_url="http://localhost:8321/v1/openai/v1", api_key="none")
            run_tests(llama_client, prefix="llama")

        log_and_print(Fore.GREEN, "All tests completed!")

    except Exception as e:
        log_and_print(Fore.RED, f"Tests failed to complete: {e}", level=logging.ERROR)
        logging.error(traceback.format_exc())
```
</details>

---------

Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>

docs/_static/llama-stack-spec.html

@@ -11340,6 +11340,9 @@
                     },
                     "embedding_dimension": {
                         "type": "integer"
+                    },
+                    "vector_db_name": {
+                        "type": "string"
                     }
                 },
                 "additionalProperties": false,
@@ -13590,10 +13593,6 @@
                     "provider_id": {
                         "type": "string",
                         "description": "The ID of the provider to use for this vector store."
-                    },
-                    "provider_vector_db_id": {
-                        "type": "string",
-                        "description": "The provider-specific vector database ID."
                     }
                 },
                 "additionalProperties": false,
@@ -15634,6 +15633,10 @@
                         "type": "string",
                         "description": "The identifier of the provider."
                     },
+                    "vector_db_name": {
+                        "type": "string",
+                        "description": "The name of the vector database."
+                    },
                     "provider_vector_db_id": {
                         "type": "string",
                         "description": "The identifier of the vector database in the provider."

docs/_static/llama-stack-spec.yaml

@@ -7984,6 +7984,8 @@ components:
           type: string
         embedding_dimension:
           type: integer
+        vector_db_name:
+          type: string
       additionalProperties: false
       required:
         - identifier
@@ -9494,10 +9496,6 @@ components:
           type: string
           description: >-
             The ID of the provider to use for this vector store.
-        provider_vector_db_id:
-          type: string
-          description: >-
-            The provider-specific vector database ID.
       additionalProperties: false
       required:
         - name
@@ -10945,6 +10943,9 @@ components:
         provider_id:
           type: string
           description: The identifier of the provider.
+        vector_db_name:
+          type: string
+          description: The name of the vector database.
         provider_vector_db_id:
           type: string
           description: >-

llama_stack/apis/vector_dbs/vector_dbs.py

@@ -19,6 +19,7 @@ class VectorDB(Resource):
 
     embedding_model: str
     embedding_dimension: int
+    vector_db_name: str | None = None
 
     @property
     def vector_db_id(self) -> str:
@@ -70,6 +71,7 @@ class VectorDBs(Protocol):
         embedding_model: str,
         embedding_dimension: int | None = 384,
         provider_id: str | None = None,
+        vector_db_name: str | None = None,
         provider_vector_db_id: str | None = None,
     ) -> VectorDB:
         """Register a vector database.
@@ -78,6 +80,7 @@ class VectorDBs(Protocol):
         :param embedding_model: The embedding model to use.
         :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.
         :returns: A VectorDB.
         """

llama_stack/apis/vector_io/vector_io.py

@@ -346,7 +346,6 @@ class VectorIO(Protocol):
         embedding_model: str | None = None,
         embedding_dimension: int | None = 384,
         provider_id: str | None = None,
-        provider_vector_db_id: str | None = None,
     ) -> VectorStoreObject:
         """Creates a vector store.
 
@@ -358,7 +357,6 @@ class VectorIO(Protocol):
         :param embedding_model: The embedding model to use for this vector store.
         :param embedding_dimension: The dimension of the embedding vectors (default: 384).
         :param provider_id: The ID of the provider to use for this vector store.
-        :param provider_vector_db_id: The provider-specific vector database ID.
         :returns: A VectorStoreObject representing the created vector store.
         """
         ...

llama_stack/distribution/routers/vector_io.py

@@ -5,6 +5,7 @@
 # the root directory of this source tree.
 
 import asyncio
+import uuid
 from typing import Any
 
 from llama_stack.apis.common.content_types import (
@@ -81,6 +82,7 @@ class VectorIORouter(VectorIO):
         embedding_model: str,
         embedding_dimension: int | None = 384,
         provider_id: str | None = None,
+        vector_db_name: str | None = None,
         provider_vector_db_id: str | None = None,
     ) -> None:
         logger.debug(f"VectorIORouter.register_vector_db: {vector_db_id}, {embedding_model}")
@@ -89,6 +91,7 @@ class VectorIORouter(VectorIO):
             embedding_model,
             embedding_dimension,
             provider_id,
+            vector_db_name,
             provider_vector_db_id,
         )
 
@@ -123,7 +126,6 @@ class VectorIORouter(VectorIO):
         embedding_model: str | None = None,
         embedding_dimension: int | None = None,
         provider_id: str | None = None,
-        provider_vector_db_id: str | None = None,
     ) -> VectorStoreObject:
         logger.debug(f"VectorIORouter.openai_create_vector_store: name={name}, provider_id={provider_id}")
 
@@ -135,17 +137,17 @@ class VectorIORouter(VectorIO):
             embedding_model, embedding_dimension = embedding_model_info
             logger.info(f"No embedding model specified, using first available: {embedding_model}")
 
-        vector_db_id = name
+        vector_db_id = f"vs_{uuid.uuid4()}"
         registered_vector_db = await self.routing_table.register_vector_db(
-            vector_db_id,
-            embedding_model,
-            embedding_dimension,
-            provider_id,
-            provider_vector_db_id,
+            vector_db_id=vector_db_id,
+            embedding_model=embedding_model,
+            embedding_dimension=embedding_dimension,
+            provider_id=provider_id,
+            provider_vector_db_id=vector_db_id,
+            vector_db_name=name,
         )
-
         return await self.routing_table.get_provider_impl(registered_vector_db.identifier).openai_create_vector_store(
-            vector_db_id,
+            name=name,
             file_ids=file_ids,
             expires_after=expires_after,
             chunking_strategy=chunking_strategy,

llama_stack/distribution/routing_tables/vector_dbs.py

@@ -36,6 +36,7 @@ class VectorDBsRoutingTable(CommonRoutingTableImpl, VectorDBs):
         embedding_dimension: int | None = 384,
         provider_id: str | None = None,
         provider_vector_db_id: str | None = None,
+        vector_db_name: str | None = None,
     ) -> VectorDB:
         if provider_vector_db_id is None:
             provider_vector_db_id = vector_db_id
@@ -62,6 +63,7 @@ class VectorDBsRoutingTable(CommonRoutingTableImpl, VectorDBs):
             "provider_resource_id": provider_vector_db_id,
             "embedding_model": embedding_model,
             "embedding_dimension": model.metadata["embedding_dimension"],
+            "vector_db_name": vector_db_name,
         }
         vector_db = TypeAdapter(VectorDBWithOwner).validate_python(vector_db_data)
         await self.register_object(vector_db)

llama_stack/providers/remote/vector_io/chroma/chroma.py

@@ -217,7 +217,6 @@ class ChromaVectorIOAdapter(VectorIO, VectorDBsProtocolPrivate):
         embedding_model: str | None = None,
         embedding_dimension: int | None = 384,
         provider_id: str | None = None,
-        provider_vector_db_id: str | None = None,
     ) -> VectorStoreObject:
         raise NotImplementedError("OpenAI Vector Stores API is not supported in Chroma")
 

llama_stack/providers/remote/vector_io/qdrant/qdrant.py

@@ -214,7 +214,6 @@ class QdrantVectorIOAdapter(VectorIO, VectorDBsProtocolPrivate):
         embedding_model: str | None = None,
         embedding_dimension: int | None = 384,
         provider_id: str | None = None,
-        provider_vector_db_id: str | None = None,
     ) -> VectorStoreObject:
         raise NotImplementedError("OpenAI Vector Stores API is not supported in Qdrant")
 

llama_stack/providers/utils/memory/openai_vector_store_mixin.py

@@ -172,8 +172,9 @@ class OpenAIVectorStoreMixin(ABC):
         provider_vector_db_id: str | None = None,
     ) -> VectorStoreObject:
         """Creates a vector store."""
-        store_id = name or str(uuid.uuid4())
         created_at = int(time.time())
+        # Derive the canonical vector_db_id (allow override, else generate)
+        vector_db_id = provider_vector_db_id or f"vs_{uuid.uuid4()}"
 
         if provider_id is None:
             raise ValueError("Provider ID is required")
@@ -181,19 +182,19 @@ class OpenAIVectorStoreMixin(ABC):
         if embedding_model is None:
             raise ValueError("Embedding model is required")
 
-        # Use provided embedding dimension or default to 384
+        # Embedding dimension is required (defaulted to 384 if not provided)
         if embedding_dimension is None:
             raise ValueError("Embedding dimension is required")
 
-        provider_vector_db_id = provider_vector_db_id or store_id
+        # Register the VectorDB backing this vector store
         vector_db = VectorDB(
-            identifier=store_id,
+            identifier=vector_db_id,
             embedding_dimension=embedding_dimension,
             embedding_model=embedding_model,
             provider_id=provider_id,
-            provider_resource_id=provider_vector_db_id,
+            provider_resource_id=vector_db_id,
+            vector_db_name=name,
         )
-        # Register the vector DB
         await self.register_vector_db(vector_db)
 
         # Create OpenAI vector store metadata
@@ -207,11 +208,11 @@ class OpenAIVectorStoreMixin(ABC):
             in_progress=0,
             total=0,
         )
-        store_info = {
-            "id": store_id,
+        store_info: dict[str, Any] = {
+            "id": vector_db_id,
             "object": "vector_store",
             "created_at": created_at,
-            "name": store_id,
+            "name": name,
             "usage_bytes": 0,
             "file_counts": file_counts.model_dump(),
             "status": status,
@@ -231,18 +232,18 @@ class OpenAIVectorStoreMixin(ABC):
         store_info["metadata"] = metadata
 
         # Save to persistent storage (provider-specific)
-        await self._save_openai_vector_store(store_id, store_info)
+        await self._save_openai_vector_store(vector_db_id, store_info)
 
         # Store in memory cache
-        self.openai_vector_stores[store_id] = store_info
+        self.openai_vector_stores[vector_db_id] = store_info
 
         # Now that our vector store is created, attach any files that were provided
         file_ids = file_ids or []
-        tasks = [self.openai_attach_file_to_vector_store(store_id, file_id) for file_id in file_ids]
+        tasks = [self.openai_attach_file_to_vector_store(vector_db_id, file_id) for file_id in file_ids]
         await asyncio.gather(*tasks)
 
         # Get the updated store info and return it
-        store_info = self.openai_vector_stores[store_id]
+        store_info = self.openai_vector_stores[vector_db_id]
         return VectorStoreObject.model_validate(store_info)
 
     async def openai_list_vector_stores(

tests/integration/vector_io/test_openai_vector_stores.py

@@ -821,6 +821,59 @@ def test_openai_vector_store_update_file(compat_client_with_empty_stores, client
     assert retrieved_file.attributes["foo"] == "baz"
 
 
+def test_create_vector_store_files_duplicate_vector_store_name(compat_client_with_empty_stores, client_with_models):
+    """
+    This test confirms that client.vector_stores.create() creates a unique ID
+    """
+    skip_if_provider_doesnt_support_openai_vector_stores(client_with_models)
+    skip_if_provider_doesnt_support_openai_vector_store_files_api(client_with_models)
+
+    if isinstance(compat_client_with_empty_stores, LlamaStackClient):
+        pytest.skip("Vector Store Files create is not yet supported with LlamaStackClient")
+
+    compat_client = compat_client_with_empty_stores
+
+    # Create a vector store with files
+    file_ids = []
+    for i in range(3):
+        with BytesIO(f"This is a test file {i}".encode()) as file_buffer:
+            file_buffer.name = f"openai_test_{i}.txt"
+            file = compat_client.files.create(file=file_buffer, purpose="assistants")
+        file_ids.append(file.id)
+
+    vector_store = compat_client.vector_stores.create(
+        name="test_store_with_files",
+    )
+    assert vector_store.file_counts.completed == 0
+    assert vector_store.file_counts.total == 0
+    assert vector_store.file_counts.cancelled == 0
+    assert vector_store.file_counts.failed == 0
+    assert vector_store.file_counts.in_progress == 0
+
+    vector_store2 = compat_client.vector_stores.create(
+        name="test_store_with_files",
+    )
+
+    vector_stores_list = compat_client.vector_stores.list()
+    assert len(vector_stores_list.data) == 2
+
+    created_file = compat_client.vector_stores.files.create(
+        vector_store_id=vector_store.id,
+        file_id=file_ids[0],
+    )
+    assert created_file.status == "completed"
+
+    _ = compat_client.vector_stores.delete(vector_store2.id)
+    created_file_from_non_deleted_vector_store = compat_client.vector_stores.files.create(
+        vector_store_id=vector_store.id,
+        file_id=file_ids[1],
+    )
+    assert created_file_from_non_deleted_vector_store.status == "completed"
+
+    vector_stores_list_post_delete = compat_client.vector_stores.list()
+    assert len(vector_stores_list_post_delete.data) == 1
+
+
 @pytest.mark.skip(reason="Client library needs to be scaffolded to support search_mode parameter")
 def test_openai_vector_store_search_modes():
     """Test OpenAI vector store search with different search modes.