containers/ramalama
1
0
Fork 0
mirror of https://github.com/containers/ramalama.git synced 2026-02-05 06:46:39 +01:00
Code Issues Wiki Activity

llama-stack: add missing milvus-lite dependency

Browse Source 
The ramalama-run.yaml file provided by ramalama-stack 0.2.5 declares milvus as
the vector_io provider, but milvus is not declared as a dependency in
pyproject.yaml. Explicitly install milvus-lite in the Containerfile to fix a
runtime dependency error.

Signed-off-by: Mike Bonnet <mikeb@redhat.com>
This commit is contained in:
Mike Bonnet
2025-12-01 17:48:23 -08:00
parent 17c2a463bd
commit 1bfcbf03b2
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
container-images/llama-stack/Containerfile
View File

@@ -7,12 +7,12 @@ ARG RAMALAMA_STACK_VERSION=0.2.5
RUN curl --create-dirs --output ~/.llama/providers.d/remote/inference/ramalama.yaml https://raw.githubusercontent.com/containers/ramalama-stack/refs/tags/v${RAMALAMA_STACK_VERSION}/src/ramalama_stack/providers.d/remote/inference/ramalama.yaml && \
curl --create-dirs --output /etc/ramalama/ramalama-run.yaml https://raw.githubusercontent.com/containers/ramalama-stack/refs/tags/v${RAMALAMA_STACK_VERSION}/src/ramalama_stack/ramalama-run.yaml
RUN dnf -y update && \
dnf -y install uv cmake gcc gcc-c++ python3-devel pkg-config sentencepiece-devel && \
RUN dnf -y install uv gcc python3-devel && \
dnf -y clean all
RUN uv venv && \
uv pip install ramalama-stack==${RAMALAMA_STACK_VERSION}
uv pip install ramalama-stack==${RAMALAMA_STACK_VERSION} \
milvus-lite
COPY --chmod=755 container-images/llama-stack/entrypoint.sh /usr/bin/entrypoint.sh