From 8c3f2762fb8b85fe66c2c15f0cb2f7d419da8b5a Mon Sep 17 00:00:00 2001
From: Wen Zhou <wenzhou@redhat.com>
Date: Fri, 27 Jun 2025 10:23:12 +0200
Subject: [PATCH] build: update temp. created Containerfile (#2492)

# What does this PR do?
<!-- Provide a short summary of what this PR does and why. Link to
relevant issues if applicable. -->
- conditionally created folder /.llama/providers.d if
external_providers_dir is set
- do not create /.cache folder, not in use anywhere
- combine chmod and copy to one command


<!-- If resolving an issue, uncomment and update the line below -->
<!-- Closes #[issue-number] -->

## Test Plan
<!-- Describe the tests you ran to verify your changes with result
summaries. *Provide clear instructions so the plan can be easily
re-executed.* -->
updated test:

```
export CONTAINER_BINARY=podman
LLAMA_STACK_DIR=. uv run llama stack build --template remote-vllm --image-type container --image-name  <name>
```
log:
```
Containerfile created successfully in /tmp/tmp.rPMunE39Aw/Containerfile

FROM python:3.11-slim
WORKDIR /app

RUN apt-get update && apt-get install -y        iputils-ping net-tools iproute2 dnsutils telnet        curl wget telnet git       procps psmisc lsof        traceroute        bubblewrap        gcc        && rm -rf /var/lib/apt/lists/*

ENV UV_SYSTEM_PYTHON=1
RUN pip install uv
RUN uv pip install --no-cache sentencepiece pillow pypdf transformers pythainlp faiss-cpu opentelemetry-sdk requests datasets chardet scipy nltk numpy matplotlib psycopg2-binary aiosqlite langdetect autoevals tree_sitter tqdm pandas chromadb-client opentelemetry-exporter-otlp-proto-http redis scikit-learn openai pymongo emoji sqlalchemy[asyncio] mcp aiosqlite fastapi fire httpx uvicorn opentelemetry-sdk opentelemetry-exporter-otlp-proto-http
RUN uv pip install --no-cache sentence-transformers --no-deps
RUN uv pip install --no-cache torch torchvision --index-url https://download.pytorch.org/whl/cpu
# Allows running as non-root user
RUN mkdir -p /.llama/providers.d /.cache
RUN uv pip install --no-cache llama-stack
RUN pip uninstall -y uv
ENTRYPOINT ["python", "-m", "llama_stack.distribution.server.server", "--template", "remote-vllm"]

RUN chmod -R g+rw /app /.llama /.cache

PWD: /tmp/llama-stack
Containerfile: /tmp/tmp.rPMunE39Aw/Containerfile
+ podman build --progress=plain --security-opt label=disable --platform linux/amd64 -t distribution-remote-vllm:0.2.12 -f /tmp/tmp.rPMunE39Aw/Containerfile /tmp/llama-stack
....
Success!
Build Successful!
You can find the newly-built template here: /tmp/llama-stack/llama_stack/templates/remote-vllm/run.yaml
You can run the new Llama Stack distro via: llama stack run /tmp/llama-stack/llama_stack/templates/remote-vllm/run.yaml --image-type container
```

```
podman tag localhost/distribution-remote-vllm:dev quay.io/wenzhou/distribution-remote-vllm:2492_2
podman push quay.io/wenzhou/distribution-remote-vllm:2492_2



docker run --rm -p 8321:8321 -e INFERENCE_MODEL="meta-llama/Llama-2-7b-chat-hf" -e VLLM_URL="http://localhost:8000/v1" quay.io/wenzhou/distribution-remote-vllm:2492_2 --port 8321

INFO     2025-06-26 13:47:31,813 __main__:436 server: Using template remote-vllm config file:
         /app/llama-stack-source/llama_stack/templates/remote-vllm/run.yaml
INFO     2025-06-26 13:47:31,818 __main__:438 server: Run configuration:
INFO     2025-06-26 13:47:31,826 __main__:440 server: apis:
         - agents
         - datasetio
         - eval
         - inference
         - safety
         - scoring
         - telemetry
         - tool_runtime
         - vector_io
         benchmarks: []
         container_image: null
....
```
-----
previous test:
local run` >llama stack build --template remote-vllm --image-type
container`
image stored in  `quay.io/wenzhou/distribution-remote-vllm:2492`

---------

Signed-off-by: Wen Zhou <wenzhou@redhat.com>
---
 llama_stack/distribution/build_container.sh | 10 ++--------
 1 file changed, 2 insertions(+), 8 deletions(-)

diff --git a/llama_stack/distribution/build_container.sh b/llama_stack/distribution/build_container.sh
index 2b2ce3e81..d9a918fb5 100755
--- a/llama_stack/distribution/build_container.sh
+++ b/llama_stack/distribution/build_container.sh
@@ -154,12 +154,6 @@ get_python_cmd() {
     fi
 }
 
-# Add other required item commands generic to all containers
-add_to_container << EOF
-# Allows running as non-root user
-RUN mkdir -p /.llama/providers.d /.cache
-EOF
-
 if [ -n "$run_config" ]; then
   # Copy the run config to the build context since it's an absolute path
   cp "$run_config" "$BUILD_CONTEXT_DIR/run.yaml"
@@ -175,7 +169,7 @@ if [ -n "$run_config" ]; then
     echo "Copying external providers directory: $external_providers_dir"
     cp -r "$external_providers_dir" "$BUILD_CONTEXT_DIR/providers.d"
     add_to_container << EOF
-COPY providers.d /.llama/providers.d
+COPY --chmod=g+w providers.d /.llama/providers.d
 EOF
     fi
 
@@ -268,7 +262,7 @@ fi
 # Add other require item commands genearic to all containers
 add_to_container << EOF
 
-RUN chmod -R g+rw /app /.llama /.cache
+RUN mkdir -p /.llama /.cache && chmod -R g+rw /app /.llama /.cache
 EOF
 
 printf "Containerfile created successfully in %s/Containerfile\n\n" "$TEMP_DIR"