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>
96 lines
2.7 KiB
Python
96 lines
2.7 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 enum import Enum
|
|
from typing import List, Optional
|
|
|
|
import pkg_resources
|
|
from pydantic import BaseModel
|
|
|
|
from termcolor import cprint
|
|
|
|
from llama_stack.distribution.utils.exec import run_with_pty
|
|
|
|
from llama_stack.distribution.datatypes import * # noqa: F403
|
|
from pathlib import Path
|
|
|
|
from llama_stack.distribution.distribution import api_providers, SERVER_DEPENDENCIES
|
|
|
|
|
|
class ImageType(Enum):
|
|
docker = "docker"
|
|
conda = "conda"
|
|
|
|
|
|
class Dependencies(BaseModel):
|
|
pip_packages: List[str]
|
|
docker_image: Optional[str] = None
|
|
|
|
|
|
class ApiInput(BaseModel):
|
|
api: Api
|
|
provider: str
|
|
|
|
|
|
def build_image(build_config: BuildConfig, build_file_path: Path):
|
|
package_deps = Dependencies(
|
|
docker_image=build_config.distribution_spec.docker_image or "python:3.10-slim",
|
|
pip_packages=SERVER_DEPENDENCIES,
|
|
)
|
|
|
|
# extend package dependencies based on providers spec
|
|
all_providers = api_providers()
|
|
for (
|
|
api_str,
|
|
provider_or_providers,
|
|
) in build_config.distribution_spec.providers.items():
|
|
providers_for_api = all_providers[Api(api_str)]
|
|
|
|
providers = (
|
|
provider_or_providers
|
|
if isinstance(provider_or_providers, list)
|
|
else [provider_or_providers]
|
|
)
|
|
|
|
for provider in providers:
|
|
if provider not in providers_for_api:
|
|
raise ValueError(
|
|
f"Provider `{provider}` is not available for API `{api_str}`"
|
|
)
|
|
|
|
provider_spec = providers_for_api[provider]
|
|
package_deps.pip_packages.extend(provider_spec.pip_packages)
|
|
if provider_spec.docker_image:
|
|
raise ValueError("A stack's dependencies cannot have a docker image")
|
|
|
|
if build_config.image_type == ImageType.docker.value:
|
|
script = pkg_resources.resource_filename(
|
|
"llama_stack", "distribution/build_container.sh"
|
|
)
|
|
args = [
|
|
script,
|
|
build_config.name,
|
|
package_deps.docker_image,
|
|
str(build_file_path),
|
|
" ".join(package_deps.pip_packages),
|
|
]
|
|
else:
|
|
script = pkg_resources.resource_filename(
|
|
"llama_stack", "distribution/build_conda_env.sh"
|
|
)
|
|
args = [
|
|
script,
|
|
build_config.name,
|
|
" ".join(package_deps.pip_packages),
|
|
]
|
|
|
|
return_code = run_with_pty(args)
|
|
if return_code != 0:
|
|
cprint(
|
|
f"Failed to build target {build_config.name} with return code {return_code}",
|
|
color="red",
|
|
)
|
|
return
|