chore: Move vector store kvstore implementation into openai_vector_store_mixin.py (llamastack#2748)

Author: franciscojavierarceo

docs/source/providers/vector_io/remote_pgvector.md

@@ -40,6 +40,7 @@ See [PGVector's documentation](https://github.com/pgvector/pgvector) for more de
 | `db` | `str \| None` | No | postgres |  |
 | `user` | `str \| None` | No | postgres |  |
 | `password` | `str \| None` | No | mysecretpassword |  |
+| `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig, annotation=NoneType, required=False, default='sqlite', discriminator='type'` | No |  | Config for KV store backend (SQLite only for now) |
 
 ## Sample Configuration
 
@@ -49,6 +50,9 @@ port: ${env.PGVECTOR_PORT:=5432}
 db: ${env.PGVECTOR_DB}
 user: ${env.PGVECTOR_USER}
 password: ${env.PGVECTOR_PASSWORD}
+kvstore:
+  type: sqlite
+  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/pgvector_registry.db
 
 ```
 

docs/source/providers/vector_io/remote_weaviate.md

@@ -36,7 +36,9 @@ See [Weaviate's documentation](https://weaviate.io/developers/weaviate) for more
 ## Sample Configuration
 
 ```yaml
-{}
+kvstore:
+  type: sqlite
+  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/weaviate_registry.db
 
 ```
 

llama_stack/providers/inline/vector_io/faiss/faiss.py

@@ -181,8 +181,8 @@ async def initialize(self) -> None:
             )
             self.cache[vector_db.identifier] = index
 
-        # Load existing OpenAI vector stores using the mixin method
-        self.openai_vector_stores = await self._load_openai_vector_stores()
+        # Load existing OpenAI vector stores into the in-memory cache
+        await self.initialize_openai_vector_stores()
 
     async def shutdown(self) -> None:
         # Cleanup if needed
@@ -261,42 +261,6 @@ async def query_chunks(
 
         return await index.query_chunks(query, params)
 
-    # OpenAI Vector Store Mixin abstract method implementations
-    async def _save_openai_vector_store(self, store_id: str, store_info: dict[str, Any]) -> None:
-        """Save vector store metadata to kvstore."""
-        assert self.kvstore is not None
-        key = f"{OPENAI_VECTOR_STORES_PREFIX}{store_id}"
-        await self.kvstore.set(key=key, value=json.dumps(store_info))
-        self.openai_vector_stores[store_id] = store_info
-
-    async def _load_openai_vector_stores(self) -> dict[str, dict[str, Any]]:
-        """Load all vector store metadata from kvstore."""
-        assert self.kvstore is not None
-        start_key = OPENAI_VECTOR_STORES_PREFIX
-        end_key = f"{OPENAI_VECTOR_STORES_PREFIX}\xff"
-        stored_openai_stores = await self.kvstore.values_in_range(start_key, end_key)
-
-        stores = {}
-        for store_data in stored_openai_stores:
-            store_info = json.loads(store_data)
-            stores[store_info["id"]] = store_info
-        return stores
-
-    async def _update_openai_vector_store(self, store_id: str, store_info: dict[str, Any]) -> None:
-        """Update vector store metadata in kvstore."""
-        assert self.kvstore is not None
-        key = f"{OPENAI_VECTOR_STORES_PREFIX}{store_id}"
-        await self.kvstore.set(key=key, value=json.dumps(store_info))
-        self.openai_vector_stores[store_id] = store_info
-
-    async def _delete_openai_vector_store_from_storage(self, store_id: str) -> None:
-        """Delete vector store metadata from kvstore."""
-        assert self.kvstore is not None
-        key = f"{OPENAI_VECTOR_STORES_PREFIX}{store_id}"
-        await self.kvstore.delete(key)
-        if store_id in self.openai_vector_stores:
-            del self.openai_vector_stores[store_id]
-
     async def _save_openai_vector_store_file(
         self, store_id: str, file_id: str, file_info: dict[str, Any], file_contents: list[dict[str, Any]]
     ) -> None:

llama_stack/providers/inline/vector_io/sqlite_vec/sqlite_vec.py

@@ -452,8 +452,8 @@ async def initialize(self) -> None:
             )
             self.cache[vector_db.identifier] = VectorDBWithIndex(vector_db, index, self.inference_api)
 
-        # load any existing OpenAI vector stores
-        self.openai_vector_stores = await self._load_openai_vector_stores()
+        # Load existing OpenAI vector stores into the in-memory cache
+        await self.initialize_openai_vector_stores()
 
     async def shutdown(self) -> None:
         # nothing to do since we don't maintain a persistent connection
@@ -501,41 +501,6 @@ async def unregister_vector_db(self, vector_db_id: str) -> None:
         await self.cache[vector_db_id].index.delete()
         del self.cache[vector_db_id]
 
-    # OpenAI Vector Store Mixin abstract method implementations
-    async def _save_openai_vector_store(self, store_id: str, store_info: dict[str, Any]) -> None:
-        """Save vector store metadata to SQLite database."""
-        assert self.kvstore is not None
-        key = f"{OPENAI_VECTOR_STORES_PREFIX}{store_id}"
-        await self.kvstore.set(key=key, value=json.dumps(store_info))
-        self.openai_vector_stores[store_id] = store_info
-
-    async def _load_openai_vector_stores(self) -> dict[str, dict[str, Any]]:
-        """Load all vector store metadata from SQLite database."""
-        assert self.kvstore is not None
-        start_key = OPENAI_VECTOR_STORES_PREFIX
-        end_key = f"{OPENAI_VECTOR_STORES_PREFIX}\xff"
-        stored_openai_stores = await self.kvstore.values_in_range(start_key, end_key)
-        stores = {}
-        for store_data in stored_openai_stores:
-            store_info = json.loads(store_data)
-            stores[store_info["id"]] = store_info
-        return stores
-
-    async def _update_openai_vector_store(self, store_id: str, store_info: dict[str, Any]) -> None:
-        """Update vector store metadata in SQLite database."""
-        assert self.kvstore is not None
-        key = f"{OPENAI_VECTOR_STORES_PREFIX}{store_id}"
-        await self.kvstore.set(key=key, value=json.dumps(store_info))
-        self.openai_vector_stores[store_id] = store_info
-
-    async def _delete_openai_vector_store_from_storage(self, store_id: str) -> None:
-        """Delete vector store metadata from SQLite database."""
-        assert self.kvstore is not None
-        key = f"{OPENAI_VECTOR_STORES_PREFIX}{store_id}"
-        await self.kvstore.delete(key)
-        if store_id in self.openai_vector_stores:
-            del self.openai_vector_stores[store_id]
-
     async def _save_openai_vector_store_file(
         self, store_id: str, file_id: str, file_info: dict[str, Any], file_contents: list[dict[str, Any]]
     ) -> None:

llama_stack/providers/remote/vector_io/milvus/milvus.py

@@ -179,7 +179,8 @@ async def initialize(self) -> None:
             uri = os.path.expanduser(self.config.db_path)
             self.client = MilvusClient(uri=uri)
 
-        self.openai_vector_stores = await self._load_openai_vector_stores()
+        # Load existing OpenAI vector stores into the in-memory cache
+        await self.initialize_openai_vector_stores()
 
     async def shutdown(self) -> None:
         self.client.close()
@@ -248,36 +249,6 @@ async def query_chunks(
 
         return await index.query_chunks(query, params)
 
-    async def _save_openai_vector_store(self, store_id: str, store_info: dict[str, Any]) -> None:
-        """Save vector store metadata to persistent storage."""
-        assert self.kvstore is not None
-        key = f"{OPENAI_VECTOR_STORES_PREFIX}{store_id}"
-        await self.kvstore.set(key=key, value=json.dumps(store_info))
-        self.openai_vector_stores[store_id] = store_info
-
-    async def _update_openai_vector_store(self, store_id: str, store_info: dict[str, Any]) -> None:
-        """Update vector store metadata in persistent storage."""
-        assert self.kvstore is not None
-        key = f"{OPENAI_VECTOR_STORES_PREFIX}{store_id}"
-        await self.kvstore.set(key=key, value=json.dumps(store_info))
-        self.openai_vector_stores[store_id] = store_info
-
-    async def _delete_openai_vector_store_from_storage(self, store_id: str) -> None:
-        """Delete vector store metadata from persistent storage."""
-        assert self.kvstore is not None
-        key = f"{OPENAI_VECTOR_STORES_PREFIX}{store_id}"
-        await self.kvstore.delete(key)
-        if store_id in self.openai_vector_stores:
-            del self.openai_vector_stores[store_id]
-
-    async def _load_openai_vector_stores(self) -> dict[str, dict[str, Any]]:
-        """Load all vector store metadata from persistent storage."""
-        assert self.kvstore is not None
-        start_key = OPENAI_VECTOR_STORES_PREFIX
-        end_key = f"{OPENAI_VECTOR_STORES_PREFIX}\xff"
-        stored = await self.kvstore.values_in_range(start_key, end_key)
-        return {json.loads(s)["id"]: json.loads(s) for s in stored}
-
     async def _save_openai_vector_store_file(
         self, store_id: str, file_id: str, file_info: dict[str, Any], file_contents: list[dict[str, Any]]
     ) -> None:

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

@@ -8,6 +8,10 @@
 
 from pydantic import BaseModel, Field
 
+from llama_stack.providers.utils.kvstore.config import (
+    KVStoreConfig,
+    SqliteKVStoreConfig,
+)
 from llama_stack.schema_utils import json_schema_type
 
 
@@ -18,15 +22,27 @@ class PGVectorVectorIOConfig(BaseModel):
     db: str | None = Field(default="postgres")
     user: str | None = Field(default="postgres")
     password: str | None = Field(default="mysecretpassword")
+    kvstore: KVStoreConfig | None = Field(description="Config for KV store backend (SQLite only for now)", default=None)
 
     @classmethod
     def sample_run_config(
         cls,
+        __distro_dir__: str,
         host: str = "${env.PGVECTOR_HOST:=localhost}",
         port: int = "${env.PGVECTOR_PORT:=5432}",
         db: str = "${env.PGVECTOR_DB}",
         user: str = "${env.PGVECTOR_USER}",
         password: str = "${env.PGVECTOR_PASSWORD}",
         **kwargs: Any,
     ) -> dict[str, Any]:
-        return {"host": host, "port": port, "db": db, "user": user, "password": password}
+        return {
+            "host": host,
+            "port": port,
+            "db": db,
+            "user": user,
+            "password": password,
+            "kvstore": SqliteKVStoreConfig.sample_run_config(
+                __distro_dir__=__distro_dir__,
+                db_name="pgvector_registry.db",
+            ),
+        }