[CLI] simplify docker run (#159)

* bake run.yaml inside docker, simplify run

* add docker template examples

* delete generated Dockerfile

* unique deps

* clean up debug

* default entrypoint

* address comments, update output msg

* update msg

* build output msg

* configure msg

* unique special_deps

* remove quotes in configure

llama_stack/cli/stack/configure.py

@@ -112,12 +112,6 @@ class StackConfigure(Subcommand):
             )
             return
 
-        build_name = docker_image.removeprefix("llamastack-")
-        saved_file = str(builds_dir / f"{build_name}-run.yaml")
-        cprint(
-            f"YAML configuration has been written to {saved_file}. You can now run `llama stack run {saved_file}`",
-            color="green",
-        )
         return
 
     def _configure_llama_distribution(

llama_stack/distribution/build.py

@@ -73,6 +73,8 @@ def build_image(build_config: BuildConfig, build_file_path: Path):
             special_deps.append(package)
         else:
             deps.append(package)
+    deps = list(set(deps))
+    special_deps = list(set(special_deps))
 
     if build_config.image_type == ImageType.docker.value:
         script = pkg_resources.resource_filename(

llama_stack/distribution/build_container.sh

@@ -29,9 +29,12 @@ SCRIPT_DIR=$(dirname "$(readlink -f "$0")")
 REPO_DIR=$(dirname $(dirname "$SCRIPT_DIR"))
 DOCKER_BINARY=${DOCKER_BINARY:-docker}
 DOCKER_OPTS=${DOCKER_OPTS:-}
+REPO_CONFIGS_DIR="$REPO_DIR/tmp/configs"
 
 TEMP_DIR=$(mktemp -d)
 
+llama stack configure $build_file_path --output-dir $REPO_CONFIGS_DIR
+
 add_to_docker() {
   local input
   output_file="$TEMP_DIR/Dockerfile"
@@ -103,11 +106,12 @@ add_to_docker <<EOF
 # This would be good in production but for debugging flexibility lets not add it right now
 # We need a more solid production ready entrypoint.sh anyway
 #
-# ENTRYPOINT ["python", "-m", "llama_stack.distribution.server.server"]
+ENTRYPOINT ["python", "-m", "llama_stack.distribution.server.server"]
 
 EOF
 
 add_to_docker "ADD tmp/configs/$(basename "$build_file_path") ./llamastack-build.yaml"
+add_to_docker "ADD tmp/configs/$build_name-run.yaml ./llamastack-run.yaml"
 
 printf "Dockerfile created successfully in $TEMP_DIR/Dockerfile"
 cat $TEMP_DIR/Dockerfile
@@ -128,7 +132,4 @@ set -x
 $DOCKER_BINARY build $DOCKER_OPTS -t $image_name -f "$TEMP_DIR/Dockerfile" "$REPO_DIR" $mounts
 set +x
 
-echo "You can run it with: podman run -p 8000:8000 $image_name"
-
-echo "Checking image builds..."
-$DOCKER_BINARY run $DOCKER_OPTS -it $image_name cat llamastack-build.yaml
+echo "Success! You can run it with: $DOCKER_BINARY $DOCKER_OPTS run -p 5000:5000 $image_name"

llama_stack/distribution/configure_container.sh

@@ -38,7 +38,8 @@ fi
 
 set -x
 $DOCKER_BINARY run $DOCKER_OPTS -it \
+  --entrypoint "/usr/local/bin/llama" \
   -v $host_build_dir:$container_build_dir \
   $mounts \
   $docker_image \
-  llama stack configure ./llamastack-build.yaml --output-dir $container_build_dir
+  stack configure ./llamastack-build.yaml --output-dir $container_build_dir

llama_stack/distribution/server/server.py

@@ -408,7 +408,11 @@ async def resolve_impls_with_routing(run_config: StackRunConfig) -> Dict[Api, An
     return impls, specs
 
 
-def main(yaml_config: str, port: int = 5000, disable_ipv6: bool = False):
+def main(
+    yaml_config: str = "llamastack-run.yaml",
+    port: int = 5000,
+    disable_ipv6: bool = False,
+):
     with open(yaml_config, "r") as fp:
         config = StackRunConfig(**yaml.safe_load(fp))
 

llama_stack/distribution/templates/docker/llamastack-local-cpu/build.yaml

@@ -0,0 +1,15 @@
+name: local-cpu
+distribution_spec:
+  description: remote inference + local safety/agents/memory
+  docker_image: null
+  providers:
+    inference:
+    - remote::ollama
+    - remote::tgi
+    - remote::together
+    - remote::fireworks
+    safety: meta-reference
+    agents: meta-reference
+    memory: meta-reference
+    telemetry: meta-reference
+image_type: docker

llama_stack/distribution/templates/docker/llamastack-local-cpu/run.yaml

@@ -0,0 +1,64 @@
+built_at: '2024-09-30T09:04:30.533391'
+image_name: local-cpu
+docker_image: local-cpu
+conda_env: null
+apis_to_serve:
+- agents
+- inference
+- models
+- memory
+- safety
+- shields
+- memory_banks
+api_providers:
+  inference:
+    providers:
+    - remote::ollama
+  safety:
+    providers:
+    - meta-reference
+  agents:
+    provider_id: meta-reference
+    config:
+      persistence_store:
+        namespace: null
+        type: sqlite
+        db_path: /home/xiyan/.llama/runtime/kvstore.db
+  memory:
+    providers:
+    - meta-reference
+  telemetry:
+    provider_id: meta-reference
+    config: {}
+routing_table:
+  inference:
+  - provider_id: remote::ollama
+    config:
+      host: localhost
+      port: 6000
+    routing_key: Meta-Llama3.1-8B-Instruct
+  safety:
+  - provider_id: meta-reference
+    config:
+      llama_guard_shield: null
+      prompt_guard_shield: null
+    routing_key: llama_guard
+  - provider_id: meta-reference
+    config:
+      llama_guard_shield: null
+      prompt_guard_shield: null
+    routing_key: code_scanner_guard
+  - provider_id: meta-reference
+    config:
+      llama_guard_shield: null
+      prompt_guard_shield: null
+    routing_key: injection_shield
+  - provider_id: meta-reference
+    config:
+      llama_guard_shield: null
+      prompt_guard_shield: null
+    routing_key: jailbreak_shield
+  memory:
+  - provider_id: meta-reference
+    config: {}
+    routing_key: vector

llama_stack/distribution/templates/docker/llamastack-local-gpu/build.yaml

@@ -0,0 +1,11 @@
+name: local-gpu
+distribution_spec:
+  description: local meta reference
+  docker_image: null
+  providers:
+    inference: meta-reference
+    safety: meta-reference
+    agents: meta-reference
+    memory: meta-reference
+    telemetry: meta-reference
+image_type: docker

llama_stack/distribution/templates/docker/llamastack-local-gpu/run.yaml

@@ -0,0 +1,67 @@
+built_at: '2024-09-30T09:00:56.693751'
+image_name: local-gpu
+docker_image: local-gpu
+conda_env: null
+apis_to_serve:
+- memory
+- inference
+- agents
+- shields
+- safety
+- models
+- memory_banks
+api_providers:
+  inference:
+    providers:
+    - meta-reference
+  safety:
+    providers:
+    - meta-reference
+  agents:
+    provider_id: meta-reference
+    config:
+      persistence_store:
+        namespace: null
+        type: sqlite
+        db_path: /home/xiyan/.llama/runtime/kvstore.db
+  memory:
+    providers:
+    - meta-reference
+  telemetry:
+    provider_id: meta-reference
+    config: {}
+routing_table:
+  inference:
+  - provider_id: meta-reference
+    config:
+      model: Llama3.1-8B-Instruct
+      quantization: null
+      torch_seed: null
+      max_seq_len: 4096
+      max_batch_size: 1
+    routing_key: Llama3.1-8B-Instruct
+  safety:
+  - provider_id: meta-reference
+    config:
+      llama_guard_shield: null
+      prompt_guard_shield: null
+    routing_key: llama_guard
+  - provider_id: meta-reference
+    config:
+      llama_guard_shield: null
+      prompt_guard_shield: null
+    routing_key: code_scanner_guard
+  - provider_id: meta-reference
+    config:
+      llama_guard_shield: null
+      prompt_guard_shield: null
+    routing_key: injection_shield
+  - provider_id: meta-reference
+    config:
+      llama_guard_shield: null
+      prompt_guard_shield: null
+    routing_key: jailbreak_shield
+  memory:
+  - provider_id: meta-reference
+    config: {}
+    routing_key: vector