llama-stack/llama_stack/distribution/build.py
Ashwin Bharambe 9487ad8294
API Updates (#73)
* 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>
2024-09-17 19:51:35 -07:00

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