feat: Add openAI compatible APIs to Qdrant (#2465)

# What does this PR do?
Adds support to Vector store Open AI APIs in Qdrant.

<!-- If resolving an issue, uncomment and update the line below -->
 Closes #2463 


## Test Plan
<!-- Describe the tests you ran to verify your changes with result
summaries. *Provide clear instructions so the plan can be easily
re-executed.* -->

Signed-off-by: Varsha Prasad Narsing <varshaprasad96@gmail.com>
Co-authored-by: ehhuang <ehhuang@users.noreply.github.com>
Co-authored-by: Francisco Arceo <arceofrancisco@gmail.com>

.github/workflows/integration-vector-io-tests.yml

@@ -24,7 +24,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        vector-io-provider: ["inline::faiss", "inline::sqlite-vec", "inline::milvus", "remote::chromadb", "remote::pgvector", "remote::weaviate"]
+        vector-io-provider: ["inline::faiss", "inline::sqlite-vec", "inline::milvus", "remote::chromadb", "remote::pgvector", "remote::weaviate", "remote::qdrant"]
         python-version: ["3.12", "3.13"]
       fail-fast: false # we want to run all tests regardless of failure
 
@@ -86,6 +86,29 @@ jobs:
           PGPASSWORD=llamastack psql -h localhost -U llamastack -d llamastack \
             -c "CREATE EXTENSION IF NOT EXISTS vector;"
 
+      - name: Setup Qdrant
+        if: matrix.vector-io-provider == 'remote::qdrant'
+        run: |
+          docker run --rm -d --pull always \
+            --name qdrant \
+            -p 6333:6333 \
+            qdrant/qdrant
+
+      - name: Wait for Qdrant to be ready
+        if: matrix.vector-io-provider == 'remote::qdrant'
+        run: |
+          echo "Waiting for Qdrant to be ready..."
+          for i in {1..30}; do
+            if curl -s http://localhost:6333/collections | grep -q '"status":"ok"'; then
+              echo "Qdrant is ready!"
+              exit 0
+            fi
+            sleep 2
+          done
+          echo "Qdrant failed to start"
+          docker logs qdrant
+          exit 1
+
       - name: Wait for ChromaDB to be ready
         if: matrix.vector-io-provider == 'remote::chromadb'
         run: |
@@ -136,9 +159,10 @@ jobs:
           PGVECTOR_DB: ${{ matrix.vector-io-provider == 'remote::pgvector' && 'llamastack' || '' }}
           PGVECTOR_USER: ${{ matrix.vector-io-provider == 'remote::pgvector' && 'llamastack' || '' }}
           PGVECTOR_PASSWORD: ${{ matrix.vector-io-provider == 'remote::pgvector' && 'llamastack' || '' }}
+          ENABLE_QDRANT: ${{ matrix.vector-io-provider == 'remote::qdrant' && 'true' || '' }}
+          QDRANT_URL: ${{ matrix.vector-io-provider == 'remote::qdrant' && 'http://localhost:6333' || '' }}
           ENABLE_WEAVIATE: ${{ matrix.vector-io-provider == 'remote::weaviate' && 'true' || '' }}
           WEAVIATE_CLUSTER_URL: ${{ matrix.vector-io-provider == 'remote::weaviate' && 'localhost:8080' || '' }}
-
         run: |
           uv run pytest -sv --stack-config="inference=inline::sentence-transformers,vector_io=${{ matrix.vector-io-provider }}" \
             tests/integration/vector_io \
@@ -160,6 +184,11 @@ jobs:
         run: |
           docker logs chromadb > chromadb.log
 
+      - name: Write Qdrant logs to file
+        if: ${{ always() && matrix.vector-io-provider == 'remote::qdrant' }}
+        run: |
+          docker logs qdrant > qdrant.log
+
       - name: Upload all logs to artifacts
         if: ${{ always() }}
         uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2

docs/source/providers/vector_io/inline_qdrant.md

@@ -51,11 +51,15 @@ See the [Qdrant documentation](https://qdrant.tech/documentation/) for more deta
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `path` | `<class 'str'>` | No | PydanticUndefined |  |
+| `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig` | No | sqlite |  |
 
 ## Sample Configuration
 
 ```yaml
 path: ${env.QDRANT_PATH:=~/.llama/~/.llama/dummy}/qdrant.db
+kvstore:
+  type: sqlite
+  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/qdrant_registry.db
 
 ```
 

docs/source/providers/vector_io/remote_qdrant.md

@@ -20,11 +20,15 @@ Please refer to the inline provider documentation.
 | `prefix` | `str \| None` | No |  |  |
 | `timeout` | `int \| None` | No |  |  |
 | `host` | `str \| None` | No |  |  |
+| `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig` | No | sqlite |  |
 
 ## Sample Configuration
 
 ```yaml
-api_key: ${env.QDRANT_API_KEY}
+api_key: ${env.QDRANT_API_KEY:=}
+kvstore:
+  type: sqlite
+  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/qdrant_registry.db
 
 ```
 

llama_stack/providers/inline/vector_io/qdrant/__init__.py

@@ -4,14 +4,18 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from llama_stack.providers.datatypes import Api, ProviderSpec
+from typing import Any
+
+from llama_stack.providers.datatypes import Api
 
 from .config import QdrantVectorIOConfig
 
 
-async def get_adapter_impl(config: QdrantVectorIOConfig, deps: dict[Api, ProviderSpec]):
+async def get_provider_impl(config: QdrantVectorIOConfig, deps: dict[Api, Any]):
     from llama_stack.providers.remote.vector_io.qdrant.qdrant import QdrantVectorIOAdapter
 
-    impl = QdrantVectorIOAdapter(config, deps[Api.inference])
+    assert isinstance(config, QdrantVectorIOConfig), f"Unexpected config type: {type(config)}"
+    files_api = deps.get(Api.files)
+    impl = QdrantVectorIOAdapter(config, deps[Api.inference], files_api)
     await impl.initialize()
     return impl

llama_stack/providers/inline/vector_io/qdrant/config.py

@@ -9,15 +9,23 @@ from typing import Any
 
 from pydantic import BaseModel
 
+from llama_stack.providers.utils.kvstore.config import (
+    KVStoreConfig,
+    SqliteKVStoreConfig,
+)
 from llama_stack.schema_utils import json_schema_type
 
 
 @json_schema_type
 class QdrantVectorIOConfig(BaseModel):
     path: str
+    kvstore: KVStoreConfig
 
     @classmethod
     def sample_run_config(cls, __distro_dir__: str) -> dict[str, Any]:
         return {
             "path": "${env.QDRANT_PATH:=~/.llama/" + __distro_dir__ + "}/" + "qdrant.db",
+            "kvstore": SqliteKVStoreConfig.sample_run_config(
+                __distro_dir__=__distro_dir__, db_name="qdrant_registry.db"
+            ),
         }

llama_stack/providers/registry/vector_io.py

@@ -460,6 +460,7 @@ See [Weaviate's documentation](https://weaviate.io/developers/weaviate) for more
             module="llama_stack.providers.inline.vector_io.qdrant",
             config_class="llama_stack.providers.inline.vector_io.qdrant.QdrantVectorIOConfig",
             api_dependencies=[Api.inference],
+            optional_api_dependencies=[Api.files],
             description=r"""
 [Qdrant](https://qdrant.tech/documentation/) is an inline and remote vector database provider for Llama Stack. It
 allows you to store and query vectors directly in memory.
@@ -516,6 +517,7 @@ Please refer to the inline provider documentation.
 """,
             ),
             api_dependencies=[Api.inference],
+            optional_api_dependencies=[Api.files],
         ),
         remote_provider_spec(
             Api.vector_io,

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

@@ -12,6 +12,7 @@ from .config import QdrantVectorIOConfig
 async def get_adapter_impl(config: QdrantVectorIOConfig, deps: dict[Api, ProviderSpec]):
     from .qdrant import QdrantVectorIOAdapter
 
-    impl = QdrantVectorIOAdapter(config, deps[Api.inference])
+    files_api = deps.get(Api.files)
+    impl = QdrantVectorIOAdapter(config, deps[Api.inference], files_api)
     await impl.initialize()
     return impl

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

@@ -8,6 +8,10 @@ from typing import Any
 
 from pydantic import BaseModel
 
+from llama_stack.providers.utils.kvstore.config import (
+    KVStoreConfig,
+    SqliteKVStoreConfig,
+)
 from llama_stack.schema_utils import json_schema_type
 
 
@@ -23,9 +27,14 @@ class QdrantVectorIOConfig(BaseModel):
     prefix: str | None = None
     timeout: int | None = None
     host: str | None = None
+    kvstore: KVStoreConfig
 
     @classmethod
-    def sample_run_config(cls, **kwargs: Any) -> dict[str, Any]:
+    def sample_run_config(cls, __distro_dir__: str, **kwargs: Any) -> dict[str, Any]:
         return {
-            "api_key": "${env.QDRANT_API_KEY}",
+            "api_key": "${env.QDRANT_API_KEY:=}",
+            "kvstore": SqliteKVStoreConfig.sample_run_config(
+                __distro_dir__=__distro_dir__,
+                db_name="qdrant_registry.db",
+            ),
         }

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

@@ -4,6 +4,7 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
+import asyncio
 import logging
 import uuid
 from typing import Any
@@ -13,25 +14,20 @@ from qdrant_client import AsyncQdrantClient, models
 from qdrant_client.models import PointStruct
 
 from llama_stack.apis.common.errors import VectorStoreNotFoundError
+from llama_stack.apis.files import Files
 from llama_stack.apis.inference import InterleavedContent
 from llama_stack.apis.vector_dbs import VectorDB
 from llama_stack.apis.vector_io import (
     Chunk,
     QueryChunksResponse,
-    SearchRankingOptions,
     VectorIO,
     VectorStoreChunkingStrategy,
-    VectorStoreDeleteResponse,
-    VectorStoreFileContentsResponse,
     VectorStoreFileObject,
-    VectorStoreFileStatus,
-    VectorStoreListFilesResponse,
-    VectorStoreListResponse,
-    VectorStoreObject,
-    VectorStoreSearchResponsePage,
 )
 from llama_stack.providers.datatypes import Api, VectorDBsProtocolPrivate
 from llama_stack.providers.inline.vector_io.qdrant import QdrantVectorIOConfig as InlineQdrantVectorIOConfig
+from llama_stack.providers.utils.kvstore import KVStore, kvstore_impl
+from llama_stack.providers.utils.memory.openai_vector_store_mixin import OpenAIVectorStoreMixin
 from llama_stack.providers.utils.memory.vector_store import (
     EmbeddingIndex,
     VectorDBWithIndex,
@@ -42,6 +38,10 @@ from .config import QdrantVectorIOConfig as RemoteQdrantVectorIOConfig
 log = logging.getLogger(__name__)
 CHUNK_ID_KEY = "_chunk_id"
 
+# KV store prefixes for vector databases
+VERSION = "v3"
+VECTOR_DBS_PREFIX = f"vector_dbs:qdrant:{VERSION}::"
+
 
 def convert_id(_id: str) -> str:
     """
@@ -59,6 +59,11 @@ class QdrantIndex(EmbeddingIndex):
         self.client = client
         self.collection_name = collection_name
 
+    async def initialize(self) -> None:
+        # Qdrant collections are created on-demand in add_chunks
+        # If the collection does not exist, it will be created in add_chunks.
+        pass
+
     async def add_chunks(self, chunks: list[Chunk], embeddings: NDArray):
         assert len(chunks) == len(embeddings), (
             f"Chunk length {len(chunks)} does not match embedding length {len(embeddings)}"
@@ -84,7 +89,15 @@ class QdrantIndex(EmbeddingIndex):
         await self.client.upsert(collection_name=self.collection_name, points=points)
 
     async def delete_chunk(self, chunk_id: str) -> None:
-        raise NotImplementedError("delete_chunk is not supported in qdrant")
+        """Remove a chunk from the Qdrant collection."""
+        try:
+            await self.client.delete(
+                collection_name=self.collection_name,
+                points_selector=models.PointIdsList(points=[convert_id(chunk_id)]),
+            )
+        except Exception as e:
+            log.error(f"Error deleting chunk {chunk_id} from Qdrant collection {self.collection_name}: {e}")
+            raise
 
     async def query_vector(self, embedding: NDArray, k: int, score_threshold: float) -> QueryChunksResponse:
         results = (
@@ -136,17 +149,41 @@ class QdrantIndex(EmbeddingIndex):
         await self.client.delete_collection(collection_name=self.collection_name)
 
 
-class QdrantVectorIOAdapter(VectorIO, VectorDBsProtocolPrivate):
+class QdrantVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorDBsProtocolPrivate):
     def __init__(
-        self, config: RemoteQdrantVectorIOConfig | InlineQdrantVectorIOConfig, inference_api: Api.inference
+        self,
+        config: RemoteQdrantVectorIOConfig | InlineQdrantVectorIOConfig,
+        inference_api: Api.inference,
+        files_api: Files | None = None,
     ) -> None:
         self.config = config
         self.client: AsyncQdrantClient = None
         self.cache = {}
         self.inference_api = inference_api
+        self.files_api = files_api
+        self.vector_db_store = None
+        self.kvstore: KVStore | None = None
+        self.openai_vector_stores: dict[str, dict[str, Any]] = {}
+        self._qdrant_lock = asyncio.Lock()
 
     async def initialize(self) -> None:
-        self.client = AsyncQdrantClient(**self.config.model_dump(exclude_none=True))
+        client_config = self.config.model_dump(exclude_none=True, exclude={"kvstore"})
+        self.client = AsyncQdrantClient(**client_config)
+        self.kvstore = await kvstore_impl(self.config.kvstore)
+
+        start_key = VECTOR_DBS_PREFIX
+        end_key = f"{VECTOR_DBS_PREFIX}\xff"
+        stored_vector_dbs = await self.kvstore.values_in_range(start_key, end_key)
+
+        for vector_db_data in stored_vector_dbs:
+            vector_db = VectorDB.model_validate_json(vector_db_data)
+            index = VectorDBWithIndex(
+                vector_db,
+                QdrantIndex(self.client, vector_db.identifier),
+                self.inference_api,
+            )
+            self.cache[vector_db.identifier] = index
+        self.openai_vector_stores = await self._load_openai_vector_stores()
 
     async def shutdown(self) -> None:
         await self.client.close()
@@ -155,6 +192,10 @@ class QdrantVectorIOAdapter(VectorIO, VectorDBsProtocolPrivate):
         self,
         vector_db: VectorDB,
     ) -> None:
+        assert self.kvstore is not None
+        key = f"{VECTOR_DBS_PREFIX}{vector_db.identifier}"
+        await self.kvstore.set(key=key, value=vector_db.model_dump_json())
+
         index = VectorDBWithIndex(
             vector_db=vector_db,
             index=QdrantIndex(self.client, vector_db.identifier),
@@ -168,10 +209,16 @@ class QdrantVectorIOAdapter(VectorIO, VectorDBsProtocolPrivate):
             await self.cache[vector_db_id].index.delete()
             del self.cache[vector_db_id]
 
+        assert self.kvstore is not None
+        await self.kvstore.delete(f"{VECTOR_DBS_PREFIX}{vector_db_id}")
+
     async def _get_and_cache_vector_db_index(self, vector_db_id: str) -> VectorDBWithIndex | None:
         if vector_db_id in self.cache:
             return self.cache[vector_db_id]
 
+        if self.vector_db_store is None:
+            raise ValueError(f"Vector DB not found {vector_db_id}")
+
         vector_db = await self.vector_db_store.get_vector_db(vector_db_id)
         if not vector_db:
             raise VectorStoreNotFoundError(vector_db_id)
@@ -208,61 +255,6 @@ class QdrantVectorIOAdapter(VectorIO, VectorDBsProtocolPrivate):
 
         return await index.query_chunks(query, params)
 
-    async def openai_create_vector_store(
-        self,
-        name: str,
-        file_ids: list[str] | None = None,
-        expires_after: dict[str, Any] | None = None,
-        chunking_strategy: dict[str, Any] | None = None,
-        metadata: dict[str, Any] | None = None,
-        embedding_model: str | None = None,
-        embedding_dimension: int | None = 384,
-        provider_id: str | None = None,
-    ) -> VectorStoreObject:
-        raise NotImplementedError("OpenAI Vector Stores API is not supported in Qdrant")
-
-    async def openai_list_vector_stores(
-        self,
-        limit: int | None = 20,
-        order: str | None = "desc",
-        after: str | None = None,
-        before: str | None = None,
-    ) -> VectorStoreListResponse:
-        raise NotImplementedError("OpenAI Vector Stores API is not supported in Qdrant")
-
-    async def openai_retrieve_vector_store(
-        self,
-        vector_store_id: str,
-    ) -> VectorStoreObject:
-        raise NotImplementedError("OpenAI Vector Stores API is not supported in Qdrant")
-
-    async def openai_update_vector_store(
-        self,
-        vector_store_id: str,
-        name: str | None = None,
-        expires_after: dict[str, Any] | None = None,
-        metadata: dict[str, Any] | None = None,
-    ) -> VectorStoreObject:
-        raise NotImplementedError("OpenAI Vector Stores API is not supported in Qdrant")
-
-    async def openai_delete_vector_store(
-        self,
-        vector_store_id: str,
-    ) -> VectorStoreDeleteResponse:
-        raise NotImplementedError("OpenAI Vector Stores API is not supported in Qdrant")
-
-    async def openai_search_vector_store(
-        self,
-        vector_store_id: str,
-        query: str | list[str],
-        filters: dict[str, Any] | None = None,
-        max_num_results: int | None = 10,
-        ranking_options: SearchRankingOptions | None = None,
-        rewrite_query: bool | None = False,
-        search_mode: str | None = "vector",
-    ) -> VectorStoreSearchResponsePage:
-        raise NotImplementedError("OpenAI Vector Stores API is not supported in Qdrant")
-
     async def openai_attach_file_to_vector_store(
         self,
         vector_store_id: str,
@@ -270,47 +262,14 @@ class QdrantVectorIOAdapter(VectorIO, VectorDBsProtocolPrivate):
         attributes: dict[str, Any] | None = None,
         chunking_strategy: VectorStoreChunkingStrategy | None = None,
     ) -> VectorStoreFileObject:
-        raise NotImplementedError("OpenAI Vector Stores API is not supported in Qdrant")
+        # Qdrant doesn't allow multiple clients to access the same storage path simultaneously.
-
+        async with self._qdrant_lock:
-    async def openai_list_files_in_vector_store(
+            await super().openai_attach_file_to_vector_store(vector_store_id, file_id, attributes, chunking_strategy)
-        self,
-        vector_store_id: str,
-        limit: int | None = 20,
-        order: str | None = "desc",
-        after: str | None = None,
-        before: str | None = None,
-        filter: VectorStoreFileStatus | None = None,
-    ) -> VectorStoreListFilesResponse:
-        raise NotImplementedError("OpenAI Vector Stores API is not supported in Qdrant")
-
-    async def openai_retrieve_vector_store_file(
-        self,
-        vector_store_id: str,
-        file_id: str,
-    ) -> VectorStoreFileObject:
-        raise NotImplementedError("OpenAI Vector Stores API is not supported in Qdrant")
-
-    async def openai_retrieve_vector_store_file_contents(
-        self,
-        vector_store_id: str,
-        file_id: str,
-    ) -> VectorStoreFileContentsResponse:
-        raise NotImplementedError("OpenAI Vector Stores API is not supported in Qdrant")
-
-    async def openai_update_vector_store_file(
-        self,
-        vector_store_id: str,
-        file_id: str,
-        attributes: dict[str, Any] | None = None,
-    ) -> VectorStoreFileObject:
-        raise NotImplementedError("OpenAI Vector Stores API is not supported in Qdrant")
-
-    async def openai_delete_vector_store_file(
-        self,
-        vector_store_id: str,
-        file_id: str,
-    ) -> VectorStoreFileObject:
-        raise NotImplementedError("OpenAI Vector Stores API is not supported in Qdrant")
 
     async def delete_chunks(self, store_id: str, chunk_ids: list[str]) -> None:
-        raise NotImplementedError("OpenAI Vector Stores API is not supported in Qdrant")
+        """Delete chunks from a Qdrant vector store."""
+        index = await self._get_and_cache_vector_db_index(store_id)
+        if not index:
+            raise ValueError(f"Vector DB {store_id} not found")
+        for chunk_id in chunk_ids:
+            await index.index.delete_chunk(chunk_id)

tests/integration/vector_io/test_openai_vector_stores.py

@@ -29,6 +29,8 @@ def skip_if_provider_doesnt_support_openai_vector_stores(client_with_models):
             "inline::chromadb",
             "remote::pgvector",
             "remote::chromadb",
+            "remote::qdrant",
+            "inline::qdrant",
             "remote::weaviate",
         ]:
             return

tests/integration/vector_io/test_vector_io.py

@@ -125,6 +125,8 @@ def test_insert_chunks(client_with_empty_registry, embedding_model_id, embedding
 def test_insert_chunks_with_precomputed_embeddings(client_with_empty_registry, embedding_model_id, embedding_dimension):
     vector_io_provider_params_dict = {
         "inline::milvus": {"score_threshold": -1.0},
+        "remote::qdrant": {"score_threshold": -1.0},
+        "inline::qdrant": {"score_threshold": -1.0},
     }
     vector_db_id = "test_precomputed_embeddings_db"
     client_with_empty_registry.vector_dbs.register(
@@ -168,6 +170,8 @@ def test_query_returns_valid_object_when_identical_to_embedding_in_vdb(
 ):
     vector_io_provider_params_dict = {
         "inline::milvus": {"score_threshold": 0.0},
+        "remote::qdrant": {"score_threshold": 0.0},
+        "inline::qdrant": {"score_threshold": 0.0},
     }
     vector_db_id = "test_precomputed_embeddings_db"
     client_with_empty_registry.vector_dbs.register(

tests/unit/providers/vector_io/conftest.py

@@ -17,10 +17,12 @@ from llama_stack.providers.inline.vector_io.chroma.config import ChromaVectorIOC
 from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig
 from llama_stack.providers.inline.vector_io.faiss.faiss import FaissIndex, FaissVectorIOAdapter
 from llama_stack.providers.inline.vector_io.milvus.config import MilvusVectorIOConfig, SqliteKVStoreConfig
+from llama_stack.providers.inline.vector_io.qdrant import QdrantVectorIOConfig
 from llama_stack.providers.inline.vector_io.sqlite_vec import SQLiteVectorIOConfig
 from llama_stack.providers.inline.vector_io.sqlite_vec.sqlite_vec import SQLiteVecIndex, SQLiteVecVectorIOAdapter
 from llama_stack.providers.remote.vector_io.chroma.chroma import ChromaIndex, ChromaVectorIOAdapter, maybe_await
 from llama_stack.providers.remote.vector_io.milvus.milvus import MilvusIndex, MilvusVectorIOAdapter
+from llama_stack.providers.remote.vector_io.qdrant.qdrant import QdrantVectorIOAdapter
 
 EMBEDDING_DIMENSION = 384
 COLLECTION_PREFIX = "test_collection"
@@ -280,6 +282,57 @@ async def chroma_vec_adapter(chroma_vec_db_path, mock_inference_api, embedding_d
     await adapter.shutdown()
 
 
+@pytest.fixture
+def qdrant_vec_db_path(tmp_path_factory):
+    import uuid
+
+    db_path = str(tmp_path_factory.getbasetemp() / f"test_qdrant_{uuid.uuid4()}.db")
+    return db_path
+
+
+@pytest.fixture
+async def qdrant_vec_adapter(qdrant_vec_db_path, mock_inference_api, embedding_dimension):
+    import uuid
+
+    config = QdrantVectorIOConfig(
+        db_path=qdrant_vec_db_path,
+        kvstore=SqliteKVStoreConfig(),
+    )
+    adapter = QdrantVectorIOAdapter(
+        config=config,
+        inference_api=mock_inference_api,
+        files_api=None,
+    )
+    collection_id = f"qdrant_test_collection_{uuid.uuid4()}"
+    await adapter.initialize()
+    await adapter.register_vector_db(
+        VectorDB(
+            identifier=collection_id,
+            provider_id="test_provider",
+            embedding_model="test_model",
+            embedding_dimension=embedding_dimension,
+        )
+    )
+    adapter.test_collection_id = collection_id
+    yield adapter
+    await adapter.shutdown()
+
+
+@pytest.fixture
+async def qdrant_vec_index(qdrant_vec_db_path, embedding_dimension):
+    import uuid
+
+    from qdrant_client import AsyncQdrantClient
+
+    from llama_stack.providers.remote.vector_io.qdrant.qdrant import QdrantIndex
+
+    client = AsyncQdrantClient(path=qdrant_vec_db_path)
+    collection_name = f"qdrant_test_collection_{uuid.uuid4()}"
+    index = QdrantIndex(client, collection_name)
+    yield index
+    await index.delete()
+
+
 @pytest.fixture
 def vector_io_adapter(vector_provider, request):
     """Returns the appropriate vector IO adapter based on the provider parameter."""
@@ -288,6 +341,7 @@ def vector_io_adapter(vector_provider, request):
         "faiss": "faiss_vec_adapter",
         "sqlite_vec": "sqlite_vec_adapter",
         "chroma": "chroma_vec_adapter",
+        "qdrant": "qdrant_vec_adapter",
     }
     return request.getfixturevalue(vector_provider_dict[vector_provider])
 

tests/unit/providers/vector_io/test_qdrant.py

@@ -23,6 +23,7 @@ from llama_stack.providers.inline.vector_io.qdrant.config import (
 from llama_stack.providers.remote.vector_io.qdrant.qdrant import (
     QdrantVectorIOAdapter,
 )
+from llama_stack.providers.utils.kvstore.config import SqliteKVStoreConfig
 
 # This test is a unit test for the QdrantVectorIOAdapter class. This should only contain
 # tests which are specific to this class. More general (API-level) tests should be placed in
@@ -36,7 +37,8 @@ from llama_stack.providers.remote.vector_io.qdrant.qdrant import (
 
 @pytest.fixture
 def qdrant_config(tmp_path) -> InlineQdrantVectorIOConfig:
-    return InlineQdrantVectorIOConfig(path=os.path.join(tmp_path, "qdrant.db"))
+    kvstore_config = SqliteKVStoreConfig(db_name=os.path.join(tmp_path, "test_kvstore.db"))
+    return InlineQdrantVectorIOConfig(path=os.path.join(tmp_path, "qdrant.db"), kvstore=kvstore_config)
 
 
 @pytest.fixture(scope="session")
@@ -50,6 +52,9 @@ def mock_vector_db(vector_db_id) -> MagicMock:
     mock_vector_db.embedding_model = "embedding_model"
     mock_vector_db.identifier = vector_db_id
     mock_vector_db.embedding_dimension = 384
+    mock_vector_db.model_dump_json.return_value = (
+        '{"identifier": "' + vector_db_id + '", "embedding_model": "embedding_model", "embedding_dimension": 384}'
+    )
     return mock_vector_db
 
 
@@ -69,7 +74,7 @@ def mock_api_service(sample_embeddings):
 
 @pytest.fixture
 async def qdrant_adapter(qdrant_config, mock_vector_db_store, mock_api_service, loop) -> QdrantVectorIOAdapter:
-    adapter = QdrantVectorIOAdapter(config=qdrant_config, inference_api=mock_api_service)
+    adapter = QdrantVectorIOAdapter(config=qdrant_config, inference_api=mock_api_service, files_api=None)
     adapter.vector_db_store = mock_vector_db_store
     await adapter.initialize()
     yield adapter