llama-stack-mirror/llama_toolchain/agentic_system/api/endpoints.py
Ashwin Bharambe e830814399
Introduce Llama stack distributions (#22)
* Add distribution CLI scaffolding

* More progress towards `llama distribution install`

* getting closer to a distro definition, distro install + configure works

* Distribution server now functioning

* read existing configuration, save enums properly

* Remove inference uvicorn server entrypoint and llama inference CLI command

* updated dependency and client model name

* Improved exception handling

* local imports for faster cli

* undo a typo, add a passthrough distribution

* implement full-passthrough in the server

* add safety adapters, configuration handling, server + clients

* cleanup, moving stuff to common, nuke utils

* Add a Path() wrapper at the earliest place

* fixes

* Bring agentic system api to toolchain

Add adapter dependencies and resolve adapters using a topological sort

* refactor to reduce size of `agentic_system`

* move straggler files and fix some important existing bugs

* ApiSurface -> Api

* refactor a method out

* Adapter -> Provider

* Make each inference provider into its own subdirectory

* installation fixes

* Rename Distribution -> DistributionSpec, simplify RemoteProviders

* dict key instead of attr

* update inference config to take model and not model_dir

* Fix passthrough streaming, send headers properly not part of body :facepalm

* update safety to use model sku ids and not model dirs

* Update cli_reference.md

* minor fixes

* add DistributionConfig, fix a bug in model download

* Make install + start scripts do proper configuration automatically

* Update CLI_reference

* Nuke fp8_requirements, fold fbgemm into common requirements

* Update README, add newline between API surface configurations

* Refactor download functionality out of the Command so can be reused

* Add `llama model download` alias for `llama download`

* Show message about checksum file so users can check themselves

* Simpler intro statements

* get ollama working

* Reduce a bunch of dependencies from toolchain

Some improvements to the distribution install script

* Avoid using `conda run` since it buffers everything

* update dependencies and rely on LLAMA_TOOLCHAIN_DIR for dev purposes

* add validation for configuration input

* resort imports

* make optional subclasses default to yes for configuration

* Remove additional_pip_packages; move deps to providers

* for inline make 8b model the default

* Add scripts to MANIFEST

* allow installing from test.pypi.org

* Fix #2 to help with testing packages

* Must install llama-models at that same version first

* fix PIP_ARGS

---------

Co-authored-by: Hardik Shah <hjshah@fb.com>
Co-authored-by: Hardik Shah <hjshah@meta.com>
2024-08-08 13:38:41 -07:00

130 lines
3.3 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.
from .datatypes import * # noqa: F403
from typing import Protocol
# this dependency is annoying and we need a forked up version anyway
from llama_models.schema_utils import json_schema_type, webmethod
@json_schema_type
class AgenticSystemCreateRequest(BaseModel):
model: str
instance_config: AgenticSystemInstanceConfig
@json_schema_type
class AgenticSystemCreateResponse(BaseModel):
system_id: str
@json_schema_type
class AgenticSystemSessionCreateRequest(BaseModel):
system_id: str
session_name: str
@json_schema_type
class AgenticSystemSessionCreateResponse(BaseModel):
session_id: str
@json_schema_type
# what's the URI?
class AgenticSystemTurnCreateRequest(BaseModel):
system_id: str
session_id: str
messages: List[
Union[
UserMessage,
ToolResponseMessage,
]
]
stream: Optional[bool] = False
override_config: Optional[AgenticSystemInstanceConfig] = None
@json_schema_type(
schema={"description": "Server side event (SSE) stream of these events"}
)
class AgenticSystemTurnResponseStreamChunk(BaseModel):
event: AgenticSystemTurnResponseEvent
@json_schema_type
class AgenticSystemStepResponse(BaseModel):
step: Step
class AgenticSystem(Protocol):
@webmethod(route="/agentic_system/create")
async def create_agentic_system(
self,
request: AgenticSystemCreateRequest,
) -> AgenticSystemCreateResponse: ...
@webmethod(route="/agentic_system/turn/create")
async def create_agentic_system_turn(
self,
request: AgenticSystemTurnCreateRequest,
) -> AgenticSystemTurnResponseStreamChunk: ...
@webmethod(route="/agentic_system/turn/get")
async def get_agentic_system_turn(
self,
agent_id: str,
turn_id: str,
) -> Turn: ...
@webmethod(route="/agentic_system/step/get")
async def get_agentic_system_step(
self, agent_id: str, turn_id: str, step_id: str
) -> AgenticSystemStepResponse: ...
@webmethod(route="/agentic_system/session/create")
async def create_agentic_system_session(
self,
request: AgenticSystemSessionCreateRequest,
) -> AgenticSystemSessionCreateResponse: ...
@webmethod(route="/agentic_system/memory_bank/attach")
async def attach_memory_bank_to_agentic_system(
self,
agent_id: str,
session_id: str,
memory_bank_ids: List[str],
) -> None: ...
@webmethod(route="/agentic_system/memory_bank/detach")
async def detach_memory_bank_from_agentic_system(
self,
agent_id: str,
session_id: str,
memory_bank_ids: List[str],
) -> None: ...
@webmethod(route="/agentic_system/session/get")
async def get_agentic_system_session(
self,
agent_id: str,
session_id: str,
turn_ids: Optional[List[str]] = None,
) -> Session: ...
@webmethod(route="/agentic_system/session/delete")
async def delete_agentic_system_session(
self, agent_id: str, session_id: str
) -> None: ...
@webmethod(route="/agentic_system/delete")
async def delete_agentic_system(
self,
agent_id: str,
) -> None: ...