mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-27 18:50:41 +00:00
9487ad8294
* API Keys passed from Client instead of distro configuration * delete distribution registry * Rename the "package" word away * Introduce a "Router" layer for providers Some providers need to be factorized and considered as thin routing layers on top of other providers. Consider two examples: - The inference API should be a routing layer over inference providers, routed using the "model" key - The memory banks API is another instance where various memory bank types will be provided by independent providers (e.g., a vector store is served by Chroma while a keyvalue memory can be served by Redis or PGVector) This commit introduces a generalized routing layer for this purpose. * update `apis_to_serve` * llama_toolchain -> llama_stack * Codemod from llama_toolchain -> llama_stack - added providers/registry - cleaned up api/ subdirectories and moved impls away - restructured api/api.py - from llama_stack.apis.<api> import foo should work now - update imports to do llama_stack.apis.<api> - update many other imports - added __init__, fixed some registry imports - updated registry imports - create_agentic_system -> create_agent - AgenticSystem -> Agent * Moved some stuff out of common/; re-generated OpenAPI spec * llama-toolchain -> llama-stack (hyphens) * add control plane API * add redis adapter + sqlite provider * move core -> distribution * Some more toolchain -> stack changes * small naming shenanigans * Removing custom tool and agent utilities and moving them client side * Move control plane to distribution server for now * Remove control plane from API list * no codeshield dependency randomly plzzzzz * Add "fire" as a dependency * add back event loggers * stack configure fixes * use brave instead of bing in the example client * add init file so it gets packaged * add init files so it gets packaged * Update MANIFEST * bug fix --------- Co-authored-by: Hardik Shah <hjshah@fb.com> Co-authored-by: Xi Yan <xiyan@meta.com> Co-authored-by: Ashwin Bharambe <ashwin@meta.com>
77 lines
2.1 KiB
Python
77 lines
2.1 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 importlib
|
|
import inspect
|
|
from typing import Dict, List
|
|
|
|
from llama_stack.apis.agents import Agents
|
|
from llama_stack.apis.inference import Inference
|
|
from llama_stack.apis.memory import Memory
|
|
from llama_stack.apis.safety import Safety
|
|
from llama_stack.apis.telemetry import Telemetry
|
|
|
|
from .datatypes import Api, ApiEndpoint, ProviderSpec, remote_provider_spec
|
|
|
|
# These are the dependencies needed by the distribution server.
|
|
# `llama-stack` is automatically installed by the installation script.
|
|
SERVER_DEPENDENCIES = [
|
|
"fastapi",
|
|
"fire",
|
|
"uvicorn",
|
|
]
|
|
|
|
|
|
def stack_apis() -> List[Api]:
|
|
return [v for v in Api]
|
|
|
|
|
|
def api_endpoints() -> Dict[Api, List[ApiEndpoint]]:
|
|
apis = {}
|
|
|
|
protocols = {
|
|
Api.inference: Inference,
|
|
Api.safety: Safety,
|
|
Api.agents: Agents,
|
|
Api.memory: Memory,
|
|
Api.telemetry: Telemetry,
|
|
}
|
|
|
|
for api, protocol in protocols.items():
|
|
endpoints = []
|
|
protocol_methods = inspect.getmembers(protocol, predicate=inspect.isfunction)
|
|
|
|
for name, method in protocol_methods:
|
|
if not hasattr(method, "__webmethod__"):
|
|
continue
|
|
|
|
webmethod = method.__webmethod__
|
|
route = webmethod.route
|
|
|
|
if webmethod.method == "GET":
|
|
method = "get"
|
|
elif webmethod.method == "DELETE":
|
|
method = "delete"
|
|
else:
|
|
method = "post"
|
|
endpoints.append(ApiEndpoint(route=route, method=method, name=name))
|
|
|
|
apis[api] = endpoints
|
|
|
|
return apis
|
|
|
|
|
|
def api_providers() -> Dict[Api, Dict[str, ProviderSpec]]:
|
|
ret = {}
|
|
for api in stack_apis():
|
|
name = api.name.lower()
|
|
module = importlib.import_module(f"llama_stack.providers.registry.{name}")
|
|
ret[api] = {
|
|
"remote": remote_provider_spec(api),
|
|
**{a.provider_id: a for a in module.available_providers()},
|
|
}
|
|
|
|
return ret
|