Add provider deprecation support; change directory structure (#397)

* Add provider deprecation support; change directory structure

* fix a couple dangling imports

* move the meta_reference safety dir also

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

@@ -4,10 +4,9 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from pydantic import BaseModel, Field
-
 from llama_stack.providers.utils.kvstore import KVStoreConfig
 from llama_stack.providers.utils.kvstore.config import SqliteKVStoreConfig
+from pydantic import BaseModel, Field
 
 
 class MetaReferenceAgentsImplConfig(BaseModel):

llama_stack/providers/inline/agents/meta_reference/persistence.py

@@ -11,9 +11,8 @@ from datetime import datetime
 
 from typing import List, Optional
 from llama_stack.apis.agents import *  # noqa: F403
-from pydantic import BaseModel
-
 from llama_stack.providers.utils.kvstore import KVStore
+from pydantic import BaseModel
 
 
 class AgentSessionInfo(BaseModel):

llama_stack/providers/inline/agents/meta_reference/rag/context_retriever.py

@@ -10,14 +10,13 @@ from jinja2 import Template
 from llama_models.llama3.api import *  # noqa: F403
 
 
-from termcolor import cprint  # noqa: F401
-
 from llama_stack.apis.agents import (
     DefaultMemoryQueryGeneratorConfig,
     LLMMemoryQueryGeneratorConfig,
     MemoryQueryGenerator,
     MemoryQueryGeneratorConfig,
 )
+from termcolor import cprint  # noqa: F401
 from llama_stack.apis.inference import *  # noqa: F403
 
 

llama_stack/providers/inline/agents/meta_reference/tools/safety.py

@@ -9,8 +9,7 @@ from typing import List
 from llama_stack.apis.inference import Message
 from llama_stack.apis.safety import *  # noqa: F403
 
-from llama_stack.providers.inline.meta_reference.agents.safety import ShieldRunnerMixin
-
+from ..safety import ShieldRunnerMixin
 from .builtin import BaseTool
 
 

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

@@ -10,9 +10,8 @@ from llama_models.datatypes import *  # noqa: F403
 from llama_models.sku_list import resolve_model
 
 from llama_stack.apis.inference import *  # noqa: F401, F403
-from pydantic import BaseModel, Field, field_validator
-
 from llama_stack.providers.utils.inference import supported_inference_models
+from pydantic import BaseModel, Field, field_validator
 
 
 class MetaReferenceInferenceConfig(BaseModel):

llama_stack/providers/inline/inference/meta_reference/generation.py

@@ -35,13 +35,12 @@ from termcolor import cprint
 
 from llama_stack.apis.inference import *  # noqa: F403
 
-from lmformatenforcer import JsonSchemaParser, TokenEnforcer, TokenEnforcerTokenizerData
-
 from llama_stack.distribution.utils.model_utils import model_local_dir
 from llama_stack.providers.utils.inference.prompt_adapter import (
     augment_content_with_response_format_prompt,
     chat_completion_request_to_messages,
 )
+from lmformatenforcer import JsonSchemaParser, TokenEnforcer, TokenEnforcerTokenizerData
 
 from .config import (
     Fp8QuantizationConfig,

llama_stack/providers/inline/inference/meta_reference/parallel_utils.py

@@ -28,13 +28,13 @@ from fairscale.nn.model_parallel.initialize import (
     get_model_parallel_src_rank,
 )
 
+from llama_stack.apis.inference import ChatCompletionRequest, CompletionRequest
+
 from pydantic import BaseModel, Field
 
 from torch.distributed.launcher.api import elastic_launch, LaunchConfig
 from typing_extensions import Annotated
 
-from llama_stack.apis.inference import ChatCompletionRequest, CompletionRequest
-
 from .generation import TokenResult
 
 

llama_stack/providers/inline/inference/meta_reference/quantization/loader.py

@@ -20,16 +20,15 @@ from llama_models.datatypes import CheckpointQuantizationFormat
 from llama_models.llama3.api.args import ModelArgs
 from llama_models.llama3.reference_impl.model import Transformer, TransformerBlock
 from llama_models.sku_list import resolve_model
+
+from llama_stack.apis.inference import QuantizationType
+
 from termcolor import cprint
 from torch import nn, Tensor
 
 from torchao.quantization.GPTQ import Int8DynActInt4WeightLinear
 
-from llama_stack.apis.inference import QuantizationType
-
-from llama_stack.providers.inline.meta_reference.inference.config import (
-    MetaReferenceQuantizedInferenceConfig,
-)
+from ..config import MetaReferenceQuantizedInferenceConfig
 
 
 def swiglu_wrapper(

llama_stack/providers/inline/inference/vllm/config.py

@@ -5,9 +5,9 @@
 # the root directory of this source tree.
 
 from llama_models.schema_utils import json_schema_type
-from pydantic import BaseModel, Field, field_validator
 
 from llama_stack.providers.utils.inference import supported_inference_models
+from pydantic import BaseModel, Field, field_validator
 
 
 @json_schema_type

llama_stack/providers/inline/memory/faiss/config.py

@@ -5,13 +5,13 @@
 # the root directory of this source tree.
 
 from llama_models.schema_utils import json_schema_type
-from pydantic import BaseModel
 
 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
 
 
 @json_schema_type

llama_stack/providers/inline/memory/faiss/faiss.py

@@ -8,10 +8,11 @@ import logging
 
 from typing import Any, Dict, List, Optional
 
-import faiss
 import numpy as np
 from numpy.typing import NDArray
 
+import faiss
+
 from llama_models.llama3.api.datatypes import *  # noqa: F403
 
 from llama_stack.apis.memory import *  # noqa: F403

llama_stack/providers/inline/meta_reference/memory/tests/test_faiss.py

@@ -1,73 +0,0 @@
-# Copyright (c) Meta Platforms, Inc. and affiliates.
-# All rights reserved.
-#
-# This source code is licensed under the terms described in the LICENSE file in
-# the root directory of this source tree.
-
-import tempfile
-
-import pytest
-from llama_stack.apis.memory import MemoryBankType, VectorMemoryBankDef
-from llama_stack.providers.inline.meta_reference.memory.config import FaissImplConfig
-
-from llama_stack.providers.inline.meta_reference.memory.faiss import FaissMemoryImpl
-from llama_stack.providers.utils.kvstore.config import SqliteKVStoreConfig
-
-
-class TestFaissMemoryImpl:
-    @pytest.fixture
-    def faiss_impl(self):
-        # Create a temporary SQLite database file
-        temp_db = tempfile.NamedTemporaryFile(suffix=".db", delete=False)
-        config = FaissImplConfig(kvstore=SqliteKVStoreConfig(db_path=temp_db.name))
-        return FaissMemoryImpl(config)
-
-    @pytest.mark.asyncio
-    async def test_initialize(self, faiss_impl):
-        # Test empty initialization
-        await faiss_impl.initialize()
-        assert len(faiss_impl.cache) == 0
-
-        # Test initialization with existing banks
-        bank = VectorMemoryBankDef(
-            identifier="test_bank",
-            type=MemoryBankType.vector.value,
-            embedding_model="all-MiniLM-L6-v2",
-            chunk_size_in_tokens=512,
-            overlap_size_in_tokens=64,
-        )
-
-        # Register a bank and reinitialize to test loading
-        await faiss_impl.register_memory_bank(bank)
-
-        # Create new instance to test initialization with existing data
-        new_impl = FaissMemoryImpl(faiss_impl.config)
-        await new_impl.initialize()
-
-        assert len(new_impl.cache) == 1
-        assert "test_bank" in new_impl.cache
-
-    @pytest.mark.asyncio
-    async def test_register_memory_bank(self, faiss_impl):
-        bank = VectorMemoryBankDef(
-            identifier="test_bank",
-            type=MemoryBankType.vector.value,
-            embedding_model="all-MiniLM-L6-v2",
-            chunk_size_in_tokens=512,
-            overlap_size_in_tokens=64,
-        )
-
-        await faiss_impl.initialize()
-        await faiss_impl.register_memory_bank(bank)
-
-        assert "test_bank" in faiss_impl.cache
-        assert faiss_impl.cache["test_bank"].bank == bank
-
-        # Verify persistence
-        new_impl = FaissMemoryImpl(faiss_impl.config)
-        await new_impl.initialize()
-        assert "test_bank" in new_impl.cache
-
-
-if __name__ == "__main__":
-    pytest.main([__file__])