mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-28 02:53:30 +00:00
This PR makes several core changes to the developer experience surrounding Llama Stack. Background: PR #92 introduced the notion of "routing" to the Llama Stack. It introduces three object types: (1) models, (2) shields and (3) memory banks. Each of these objects can be associated with a distinct provider. So you can get model A to be inferenced locally while model B, C can be inference remotely (e.g.) However, this had a few drawbacks: you could not address the provider instances -- i.e., if you configured "meta-reference" with a given model, you could not assign an identifier to this instance which you could re-use later. the above meant that you could not register a "routing_key" (e.g. model) dynamically and say "please use this existing provider I have already configured" for a new model. the terms "routing_table" and "routing_key" were exposed directly to the user. in my view, this is way too much overhead for a new user (which almost everyone is.) people come to the stack wanting to do ML and encounter a completely unexpected term. What this PR does: This PR structures the run config with only a single prominent key: - providers Providers are instances of configured provider types. Here's an example which shows two instances of the remote::tgi provider which are serving two different models. providers: inference: - provider_id: foo provider_type: remote::tgi config: { ... } - provider_id: bar provider_type: remote::tgi config: { ... } Secondly, the PR adds dynamic registration of { models | shields | memory_banks } to the API surface. The distribution still acts like a "routing table" (as previously) except that it asks the backing providers for a listing of these objects. For example it asks a TGI or Ollama inference adapter what models it is serving. Only the models that are being actually served can be requested by the user for inference. Otherwise, the Stack server will throw an error. When dynamically registering these objects, you can use the provider IDs shown above. Info about providers can be obtained using the Api.inspect set of endpoints (/providers, /routes, etc.) The above examples shows the correspondence between inference providers and models registry items. Things work similarly for the safety <=> shields and memory <=> memory_banks pairs. Registry: This PR also makes it so that Providers need to implement additional methods for registering and listing objects. For example, each Inference provider is now expected to implement the ModelsProtocolPrivate protocol (naming is not great!) which consists of two methods register_model list_models The goal is to inform the provider that a certain model needs to be supported so the provider can make any relevant backend changes if needed (or throw an error if the model cannot be supported.) There are many other cleanups included some of which are detailed in a follow-up comment.
161 lines
4.8 KiB
Python
161 lines
4.8 KiB
Python
# 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 json
|
|
import logging
|
|
import uuid
|
|
from typing import AsyncGenerator
|
|
|
|
from llama_stack.apis.inference import Inference
|
|
from llama_stack.apis.memory import Memory
|
|
from llama_stack.apis.memory_banks import MemoryBanks
|
|
from llama_stack.apis.safety import Safety
|
|
from llama_stack.apis.agents import * # noqa: F403
|
|
|
|
from llama_stack.providers.utils.kvstore import InmemoryKVStoreImpl, kvstore_impl
|
|
|
|
from .agent_instance import ChatAgent
|
|
from .config import MetaReferenceAgentsImplConfig
|
|
|
|
logger = logging.getLogger()
|
|
logger.setLevel(logging.INFO)
|
|
|
|
|
|
class MetaReferenceAgentsImpl(Agents):
|
|
def __init__(
|
|
self,
|
|
config: MetaReferenceAgentsImplConfig,
|
|
inference_api: Inference,
|
|
memory_api: Memory,
|
|
safety_api: Safety,
|
|
memory_banks_api: MemoryBanks,
|
|
):
|
|
self.config = config
|
|
self.inference_api = inference_api
|
|
self.memory_api = memory_api
|
|
self.safety_api = safety_api
|
|
self.memory_banks_api = memory_banks_api
|
|
|
|
self.in_memory_store = InmemoryKVStoreImpl()
|
|
|
|
async def initialize(self) -> None:
|
|
self.persistence_store = await kvstore_impl(self.config.persistence_store)
|
|
|
|
async def create_agent(
|
|
self,
|
|
agent_config: AgentConfig,
|
|
) -> AgentCreateResponse:
|
|
agent_id = str(uuid.uuid4())
|
|
|
|
await self.persistence_store.set(
|
|
key=f"agent:{agent_id}",
|
|
value=agent_config.json(),
|
|
)
|
|
return AgentCreateResponse(
|
|
agent_id=agent_id,
|
|
)
|
|
|
|
async def get_agent(self, agent_id: str) -> ChatAgent:
|
|
agent_config = await self.persistence_store.get(
|
|
key=f"agent:{agent_id}",
|
|
)
|
|
if not agent_config:
|
|
raise ValueError(f"Could not find agent config for {agent_id}")
|
|
|
|
try:
|
|
agent_config = json.loads(agent_config)
|
|
except json.JSONDecodeError as e:
|
|
raise ValueError(
|
|
f"Could not JSON decode agent config for {agent_id}"
|
|
) from e
|
|
|
|
try:
|
|
agent_config = AgentConfig(**agent_config)
|
|
except Exception as e:
|
|
raise ValueError(
|
|
f"Could not validate(?) agent config for {agent_id}"
|
|
) from e
|
|
|
|
return ChatAgent(
|
|
agent_id=agent_id,
|
|
agent_config=agent_config,
|
|
inference_api=self.inference_api,
|
|
safety_api=self.safety_api,
|
|
memory_api=self.memory_api,
|
|
memory_banks_api=self.memory_banks_api,
|
|
persistence_store=(
|
|
self.persistence_store
|
|
if agent_config.enable_session_persistence
|
|
else self.in_memory_store
|
|
),
|
|
)
|
|
|
|
async def create_agent_session(
|
|
self,
|
|
agent_id: str,
|
|
session_name: str,
|
|
) -> AgentSessionCreateResponse:
|
|
agent = await self.get_agent(agent_id)
|
|
|
|
session_id = await agent.create_session(session_name)
|
|
return AgentSessionCreateResponse(
|
|
session_id=session_id,
|
|
)
|
|
|
|
def create_agent_turn(
|
|
self,
|
|
agent_id: str,
|
|
session_id: str,
|
|
messages: List[
|
|
Union[
|
|
UserMessage,
|
|
ToolResponseMessage,
|
|
]
|
|
],
|
|
attachments: Optional[List[Attachment]] = None,
|
|
stream: Optional[bool] = False,
|
|
) -> AsyncGenerator:
|
|
request = AgentTurnCreateRequest(
|
|
agent_id=agent_id,
|
|
session_id=session_id,
|
|
messages=messages,
|
|
attachments=attachments,
|
|
stream=True,
|
|
)
|
|
if stream:
|
|
return self._create_agent_turn_streaming(request)
|
|
else:
|
|
raise NotImplementedError("Non-streaming agent turns not yet implemented")
|
|
|
|
async def _create_agent_turn_streaming(
|
|
self,
|
|
request: AgentTurnCreateRequest,
|
|
) -> AsyncGenerator:
|
|
agent = await self.get_agent(request.agent_id)
|
|
async for event in agent.create_and_execute_turn(request):
|
|
yield event
|
|
|
|
async def get_agents_turn(self, agent_id: str, turn_id: str) -> Turn:
|
|
raise NotImplementedError()
|
|
|
|
async def get_agents_step(
|
|
self, agent_id: str, turn_id: str, step_id: str
|
|
) -> AgentStepResponse:
|
|
raise NotImplementedError()
|
|
|
|
async def get_agents_session(
|
|
self,
|
|
agent_id: str,
|
|
session_id: str,
|
|
turn_ids: Optional[List[str]] = None,
|
|
) -> Session:
|
|
raise NotImplementedError()
|
|
|
|
async def delete_agents_session(self, agent_id: str, session_id: str) -> None:
|
|
raise NotImplementedError()
|
|
|
|
async def delete_agents(self, agent_id: str) -> None:
|
|
raise NotImplementedError()
|