persist eval_tasks

llama_stack/providers/inline/eval/meta_reference/config.py

@@ -3,7 +3,15 @@
 #
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
-from llama_stack.apis.eval import *  # noqa: F401, F403
+from llama_stack.distribution.utils.config_dirs import RUNTIME_BASE_DIR
+from llama_stack.providers.utils.kvstore.config import (
+    KVStoreConfig,
+    SqliteKVStoreConfig,
+)
+from pydantic import BaseModel
 
 
-class MetaReferenceEvalConfig(BaseModel): ...
+class MetaReferenceEvalConfig(BaseModel):
+    kvstore: KVStoreConfig = SqliteKVStoreConfig(
+        db_path=(RUNTIME_BASE_DIR / "meta_reference_eval.db").as_posix()
+    )  # Uses SQLite config specific to Meta Reference Eval storage

llama_stack/providers/inline/eval/meta_reference/eval.py

@@ -15,10 +15,13 @@ from llama_stack.apis.eval_tasks import EvalTask
 from llama_stack.apis.inference import Inference
 from llama_stack.apis.scoring import Scoring
 from llama_stack.providers.datatypes import EvalTasksProtocolPrivate
+from llama_stack.providers.utils.kvstore import kvstore_impl
 from tqdm import tqdm
 
 from .config import MetaReferenceEvalConfig
 
+EVAL_TASKS_PREFIX = "eval_tasks:"
+
 
 class ColumnName(Enum):
     input_query = "input_query"
@@ -49,11 +52,29 @@ class MetaReferenceEvalImpl(Eval, EvalTasksProtocolPrivate):
         self.eval_tasks = {}
 
     async def initialize(self) -> None:
-        pass
+        self.kvstore = await kvstore_impl(self.config.kvstore)
+        # Load existing datasets from kvstore
+        start_key = EVAL_TASKS_PREFIX
+        end_key = f"{EVAL_TASKS_PREFIX}\xff"
+        stored_eval_tasks = await self.kvstore.range(start_key, end_key)
+
+        for eval_task in stored_eval_tasks:
+            eval_task = EvalTask.model_validate_json(eval_task)
+            self.eval_tasks[eval_task.identifier] = eval_task
+
+        print(f"Meta Reference Eval initialized with {self.eval_tasks}")
 
     async def shutdown(self) -> None: ...
 
     async def register_eval_task(self, task_def: EvalTask) -> None:
+        print("REGISTER EVAL TASK")
+        # Store in kvstore
+        key = f"{EVAL_TASKS_PREFIX}{task_def.identifier}"
+        await self.kvstore.set(
+            key=key,
+            value=task_def.json(),
+        )
+        print(self.eval_tasks)
         self.eval_tasks[task_def.identifier] = task_def
 
     async def validate_eval_input_dataset_schema(self, dataset_id: str) -> None: