CLI Update: build -> configure -> run (#69)

* remove configure from build

* remove config from build

* configure to regenerate file

* update memory providers

* remove comments

* udpate build script

* add reedme

* update doc

* rename getting started

* update build cli

* update docker build script

* configure update

* clean up configure

* [tmp fix] hardware requirement tmp fix

* clean up build

* fix configure

* add example build files for conda & docker

* remove resolve_distribution_spec

* remove available_distribution_specs

* example build files

* update example build files

* more clean up on build

* add name args to override name

* move distribution to yaml files

* generate distribution specs

* getting started guide

* getting started

* add build yaml to Dockerfile

* cleanup distribution_dependencies

* configure from  docker image name

* build relative paths

* minor comment

* getting started

* Update getting_started.md

* Update getting_started.md

* address comments, configure within docker file

* remove distribution types!

* update getting started

* update documentation

* remove listing distribution

* minor heading

* address nits, remove docker_image=null

* gitignore

llama_toolchain/core/build_conda_env.sh

@@ -19,17 +19,15 @@ fi
 
 set -euo pipefail
 
-if [ "$#" -ne 4 ]; then
+if [ "$#" -ne 2 ]; then
   echo "Usage: $0 <distribution_type> <build_name> <pip_dependencies>" >&2
   echo "Example: $0 <distribution_type> mybuild 'numpy pandas scipy'" >&2
   exit 1
 fi
 
-distribution_type="$1"
-build_name="$2"
+build_name="$1"
 env_name="llamastack-$build_name"
-config_file="$3"
-pip_dependencies="$4"
+pip_dependencies="$2"
 
 # Define color codes
 RED='\033[0;31m'
@@ -115,7 +113,3 @@ ensure_conda_env_python310() {
 }
 
 ensure_conda_env_python310 "$env_name" "$pip_dependencies"
-
-printf "${GREEN}Successfully setup conda environment. Configuring build...${NC}\n"
-
-$CONDA_PREFIX/bin/python3 -m llama_toolchain.cli.llama stack configure $config_file

llama_toolchain/core/build_container.sh

@@ -4,18 +4,17 @@ LLAMA_MODELS_DIR=${LLAMA_MODELS_DIR:-}
 LLAMA_TOOLCHAIN_DIR=${LLAMA_TOOLCHAIN_DIR:-}
 TEST_PYPI_VERSION=${TEST_PYPI_VERSION:-}
 
-if [ "$#" -ne 5 ]; then
-  echo "Usage: $0 <distribution_type> <build_name> <docker_base> <pip_dependencies>
-  echo "Example: $0 distribution_type my-fastapi-app python:3.9-slim 'fastapi uvicorn'
+if [ "$#" -ne 4 ]; then
+  echo "Usage: $0 <build_name> <docker_base> <pip_dependencies>
+  echo "Example: $0 my-fastapi-app python:3.9-slim 'fastapi uvicorn'
   exit 1
 fi
 
-distribution_type=$1
-build_name="$2"
+build_name="$1"
 image_name="llamastack-$build_name"
-docker_base=$3
-config_file=$4
-pip_dependencies=$5
+docker_base=$2
+build_file_path=$3
+pip_dependencies=$4
 
 # Define color codes
 RED='\033[0;31m'
@@ -26,6 +25,8 @@ set -euo pipefail
 
 SCRIPT_DIR=$(dirname "$(readlink -f "$0")")
 REPO_DIR=$(dirname $(dirname "$SCRIPT_DIR"))
+DOCKER_BINARY=${DOCKER_BINARY:-docker}
+DOCKER_OPTS=${DOCKER_OPTS:-}
 
 TEMP_DIR=$(mktemp -d)
 
@@ -93,6 +94,8 @@ add_to_docker <<EOF
 
 EOF
 
+add_to_docker "ADD $build_file_path ./llamastack-build.yaml"
+
 printf "Dockerfile created successfully in $TEMP_DIR/Dockerfile"
 cat $TEMP_DIR/Dockerfile
 printf "\n"
@@ -105,10 +108,10 @@ if [ -n "$LLAMA_MODELS_DIR" ]; then
   mounts="$mounts -v $(readlink -f $LLAMA_MODELS_DIR):$models_mount"
 fi
 set -x
-podman build -t $image_name -f "$TEMP_DIR/Dockerfile" "$REPO_DIR" $mounts
+$DOCKER_BINARY build $DOCKER_OPTS -t $image_name -f "$TEMP_DIR/Dockerfile" "$REPO_DIR" $mounts
 set +x
 
-printf "${GREEN}Succesfully setup Podman image. Configuring build...${NC}"
 echo "You can run it with: podman run -p 8000:8000 $image_name"
 
-$CONDA_PREFIX/bin/python3 -m llama_toolchain.cli.llama stack configure $config_file
+echo "Checking image builds..."
+podman run -it $image_name cat llamastack-build.yaml

llama_toolchain/core/configure_container.sh

@@ -0,0 +1,31 @@
+#!/bin/bash
+
+# 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.
+
+set -euo pipefail
+
+error_handler() {
+  echo "Error occurred in script at line: ${1}" >&2
+  exit 1
+}
+
+trap 'error_handler ${LINENO}' ERR
+
+if [ $# -lt 2 ]; then
+  echo "Usage: $0 <container name> <build file path>"
+  exit 1
+fi
+
+docker_image="$1"
+host_build_dir="$2"
+container_build_dir="/app/builds"
+
+set -x
+podman run -it \
+  -v $host_build_dir:$container_build_dir \
+  $docker_image \
+  llama stack configure ./llamastack-build.yaml --output-dir $container_build_dir

llama_toolchain/core/datatypes.py

@@ -151,11 +151,12 @@ def remote_provider_spec(
 
 @json_schema_type
 class DistributionSpec(BaseModel):
-    distribution_type: str
-    description: str
-
+    description: Optional[str] = Field(
+        default="",
+        description="Description of the distribution",
+    )
     docker_image: Optional[str] = None
-    providers: Dict[Api, str] = Field(
+    providers: Dict[str, str] = Field(
         default_factory=dict,
         description="Provider Types for each of the APIs provided by this distribution",
     )
@@ -172,8 +173,6 @@ Reference to the distribution this package refers to. For unregistered (adhoc) p
 this could be just a hash
 """,
     )
-    distribution_type: Optional[str] = None
-
     docker_image: Optional[str] = Field(
         default=None,
         description="Reference to the docker image if this package refers to a container",
@@ -194,12 +193,8 @@ the dependencies of these providers as well.
 @json_schema_type
 class BuildConfig(BaseModel):
     name: str
-    distribution: str = Field(
-        default="local", description="Type of distribution to build (adhoc | {})"
-    )
-    api_providers: Optional[str] = Field(
-        default_factory=list,
-        description="List of API provider names to build",
+    distribution_spec: DistributionSpec = Field(
+        description="The distribution spec to build including API providers. "
     )
     image_type: str = Field(
         default="conda",

llama_toolchain/core/distribution.py

@@ -31,16 +31,6 @@ SERVER_DEPENDENCIES = [
 ]
 
 
-def distribution_dependencies(distribution: DistributionSpec) -> List[str]:
-    # only consider InlineProviderSpecs when calculating dependencies
-    return [
-        dep
-        for provider_spec in distribution.provider_specs.values()
-        if isinstance(provider_spec, InlineProviderSpec)
-        for dep in provider_spec.pip_packages
-    ] + SERVER_DEPENDENCIES
-
-
 def stack_apis() -> List[Api]:
     return [v for v in Api]
 

llama_toolchain/core/distribution_registry.py

@@ -5,84 +5,19 @@
 # the root directory of this source tree.
 
 from functools import lru_cache
+from pathlib import Path
 from typing import List, Optional
-
 from .datatypes import *  # noqa: F403
+import yaml
 
 
 @lru_cache()
 def available_distribution_specs() -> List[DistributionSpec]:
-    return [
-        DistributionSpec(
-            distribution_type="local",
-            description="Use code from `llama_toolchain` itself to serve all llama stack APIs",
-            providers={
-                Api.inference: "meta-reference",
-                Api.memory: "meta-reference-faiss",
-                Api.safety: "meta-reference",
-                Api.agentic_system: "meta-reference",
-                Api.telemetry: "console",
-            },
-        ),
-        DistributionSpec(
-            distribution_type="remote",
-            description="Point to remote services for all llama stack APIs",
-            providers={
-                **{x: "remote" for x in Api},
-                Api.telemetry: "console",
-            },
-        ),
-        DistributionSpec(
-            distribution_type="local-ollama",
-            description="Like local, but use ollama for running LLM inference",
-            providers={
-                Api.inference: remote_provider_type("ollama"),
-                Api.safety: "meta-reference",
-                Api.agentic_system: "meta-reference",
-                Api.memory: "meta-reference-faiss",
-                Api.telemetry: "console",
-            },
-        ),
-        DistributionSpec(
-            distribution_type="local-plus-fireworks-inference",
-            description="Use Fireworks.ai for running LLM inference",
-            providers={
-                Api.inference: remote_provider_type("fireworks"),
-                Api.safety: "meta-reference",
-                Api.agentic_system: "meta-reference",
-                Api.memory: "meta-reference-faiss",
-                Api.telemetry: "console",
-            },
-        ),
-        DistributionSpec(
-            distribution_type="local-plus-together-inference",
-            description="Use Together.ai for running LLM inference",
-            providers={
-                Api.inference: remote_provider_type("together"),
-                Api.safety: "meta-reference",
-                Api.agentic_system: "meta-reference",
-                Api.memory: "meta-reference-faiss",
-                Api.telemetry: "console",
-            },
-        ),
-        DistributionSpec(
-            distribution_type="local-plus-tgi-inference",
-            description="Use TGI for running LLM inference",
-            providers={
-                Api.inference: remote_provider_type("tgi"),
-                Api.safety: "meta-reference",
-                Api.agentic_system: "meta-reference",
-                Api.memory: "meta-reference-faiss",
-            },
-        ),
-    ]
+    distribution_specs = []
+    for p in Path("llama_toolchain/configs/distributions/distribution_registry").rglob(
+        "*.yaml"
+    ):
+        with open(p, "r") as f:
+            distribution_specs.append(DistributionSpec(**yaml.safe_load(f)))
 
-
-@lru_cache()
-def resolve_distribution_spec(
-    distribution_type: str,
-) -> Optional[DistributionSpec]:
-    for spec in available_distribution_specs():
-        if spec.distribution_type == distribution_type:
-            return spec
-    return None
+    return distribution_specs

llama_toolchain/core/package.py

@@ -21,6 +21,8 @@ from pydantic import BaseModel
 from termcolor import cprint
 
 from llama_toolchain.core.datatypes import *  # noqa: F403
+from pathlib import Path
+
 from llama_toolchain.core.distribution import api_providers, SERVER_DEPENDENCIES
 
 
@@ -39,87 +41,35 @@ class ApiInput(BaseModel):
     provider: str
 
 
-def build_package(
-    api_inputs: List[ApiInput],
-    image_type: ImageType,
-    name: str,
-    distribution_type: Optional[str] = None,
-    docker_image: Optional[str] = None,
-):
-    if not distribution_type:
-        distribution_type = "adhoc"
-
-    build_dir = BUILDS_BASE_DIR / distribution_type / image_type.value
-    os.makedirs(build_dir, exist_ok=True)
-
-    package_name = name.replace("::", "-")
-    package_file = build_dir / f"{package_name}.yaml"
-
-    all_providers = api_providers()
-
+def build_package(build_config: BuildConfig, build_file_path: Path):
     package_deps = Dependencies(
-        docker_image=docker_image or "python:3.10-slim",
+        docker_image=build_config.distribution_spec.docker_image or "python:3.10-slim",
         pip_packages=SERVER_DEPENDENCIES,
     )
 
-    stub_config = {}
-    for api_input in api_inputs:
-        api = api_input.api
-        providers_for_api = all_providers[api]
-        if api_input.provider not in providers_for_api:
+    # extend package dependencies based on providers spec
+    all_providers = api_providers()
+    for api_str, provider in build_config.distribution_spec.providers.items():
+        providers_for_api = all_providers[Api(api_str)]
+        if provider not in providers_for_api:
             raise ValueError(
-                f"Provider `{api_input.provider}` is not available for API `{api}`"
+                f"Provider `{provider}` is not available for API `{api_str}`"
             )
 
-        provider = providers_for_api[api_input.provider]
-        package_deps.pip_packages.extend(provider.pip_packages)
-        if provider.docker_image:
+        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")
 
-        stub_config[api.value] = {"provider_type": api_input.provider}
-
-    if package_file.exists():
-        cprint(
-            f"Build `{package_name}` exists; will reconfigure",
-            color="yellow",
-        )
-        c = PackageConfig(**yaml.safe_load(package_file.read_text()))
-        for api_str, new_config in stub_config.items():
-            if api_str not in c.providers:
-                c.providers[api_str] = new_config
-            else:
-                existing_config = c.providers[api_str]
-                if existing_config["provider_type"] != new_config["provider_type"]:
-                    cprint(
-                        f"Provider `{api_str}` has changed from `{existing_config}` to `{new_config}`",
-                        color="yellow",
-                    )
-                    c.providers[api_str] = new_config
-    else:
-        c = PackageConfig(
-            built_at=datetime.now(),
-            package_name=package_name,
-            providers=stub_config,
-        )
-
-    c.distribution_type = distribution_type
-    c.docker_image = package_name if image_type == ImageType.docker else None
-    c.conda_env = package_name if image_type == ImageType.conda else None
-
-    with open(package_file, "w") as f:
-        to_write = json.loads(json.dumps(c.dict(), cls=EnumEncoder))
-        f.write(yaml.dump(to_write, sort_keys=False))
-
-    if image_type == ImageType.docker:
+    if build_config.image_type == ImageType.docker.value:
         script = pkg_resources.resource_filename(
             "llama_toolchain", "core/build_container.sh"
         )
         args = [
             script,
-            distribution_type,
-            package_name,
+            build_config.name,
             package_deps.docker_image,
-            str(package_file),
+            str(build_file_path),
             " ".join(package_deps.pip_packages),
         ]
     else:
@@ -128,21 +78,14 @@ def build_package(
         )
         args = [
             script,
-            distribution_type,
-            package_name,
-            str(package_file),
+            build_config.name,
             " ".join(package_deps.pip_packages),
         ]
 
     return_code = run_with_pty(args)
     if return_code != 0:
         cprint(
-            f"Failed to build target {package_name} with return code {return_code}",
+            f"Failed to build target {build_config.name} with return code {return_code}",
             color="red",
         )
         return
-
-    cprint(
-        f"Target `{package_name}` built with configuration at {str(package_file)}",
-        color="green",
-    )