Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion .pre-commit-config.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -56,7 +56,7 @@ repos:
always_run: true
files: ^distribution/.*$
additional_dependencies:
- llama-stack==0.2.22
- llama-stack==0.2.23

- id: doc-gen
name: Distribution Documentation
Expand Down
16 changes: 8 additions & 8 deletions distribution/Containerfile
Original file line number Diff line number Diff line change
Expand Up @@ -6,28 +6,28 @@ WORKDIR /opt/app-root

RUN pip install sqlalchemy # somehow sqlalchemy[asyncio] is not sufficient
RUN pip install \
'datasets>=4.0.0' \
'mcp>=1.8.1' \
'pymilvus[milvus-lite]>=2.4.10' \
aiosqlite \
asyncpg \
autoevals \
boto3 \
chardet \
'datasets>=4.0.0' \
fastapi \
fire \
google-cloud-aiplatform \
httpx \
ibm_watsonx_ai \
litellm \
matplotlib \
'mcp>=1.8.1' \
nltk \
numpy \
opentelemetry-exporter-otlp-proto-http \
opentelemetry-sdk \
pandas \
pillow \
psycopg2-binary \
'pymilvus[milvus-lite]>=2.4.10' \
pymongo \
pypdf \
redis \
Expand All @@ -40,16 +40,16 @@ RUN pip install \
transformers \
uvicorn
RUN pip install \
llama_stack_provider_lmeval==0.2.4
llama_stack_provider_lmeval==0.3.0
RUN pip install \
llama_stack_provider_ragas==0.3.0
llama_stack_provider_ragas==0.3.1
RUN pip install \
llama_stack_provider_ragas[remote]==0.3.0
llama_stack_provider_ragas[remote]==0.3.1
RUN pip install \
llama_stack_provider_trustyai_fms==0.2.3
RUN pip install --extra-index-url https://download.pytorch.org/whl/cpu torch 'torchao>=0.12.0' torchvision
RUN pip install 'torchao>=0.12.0' --extra-index-url https://download.pytorch.org/whl/cpu torch torchvision
RUN pip install --no-deps sentence-transformers
RUN pip install --no-cache llama-stack==0.2.22
RUN pip install --no-cache llama-stack==0.2.23
RUN mkdir -p ${HOME}/.llama ${HOME}/.cache
COPY distribution/run.yaml ${APP_ROOT}/run.yaml

Expand Down
2 changes: 1 addition & 1 deletion distribution/Containerfile.in
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@ WORKDIR /opt/app-root

RUN pip install sqlalchemy # somehow sqlalchemy[asyncio] is not sufficient
{dependencies}
RUN pip install --no-cache llama-stack==0.2.22
RUN pip install --no-cache llama-stack==0.2.23
RUN mkdir -p ${{HOME}}/.llama ${{HOME}}/.cache
COPY distribution/run.yaml ${{APP_ROOT}}/run.yaml

Expand Down
8 changes: 4 additions & 4 deletions distribution/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@

This image contains the official Open Data Hub Llama Stack distribution, with all the packages and configuration needed to run a Llama Stack server in a containerized environment.

The image is currently shipping with upstream Llama Stack version [0.2.22](https://github.com/llamastack/llama-stack/releases/tag/v0.2.22)
The image is currently shipping with upstream Llama Stack version [0.2.23](https://github.com/llamastack/llama-stack/releases/tag/v0.2.23)

You can see an overview of the APIs and Providers the image ships with in the table below.

Expand All @@ -13,9 +13,9 @@ You can see an overview of the APIs and Providers the image ships with in the ta
| agents | inline::meta-reference | No | ✅ | N/A |
| datasetio | inline::localfs | No | ✅ | N/A |
| datasetio | remote::huggingface | No | ✅ | N/A |
| eval | inline::trustyai_ragas | Yes (version 0.3.0) | ❌ | Set the `EMBEDDING_MODEL` environment variable |
| eval | remote::trustyai_lmeval | Yes (version 0.2.4) | ✅ | N/A |
| eval | remote::trustyai_ragas | Yes (version 0.3.0) | ❌ | Set the `KUBEFLOW_LLAMA_STACK_URL` environment variable |
| eval | inline::trustyai_ragas | Yes (version 0.3.1) | ❌ | Set the `EMBEDDING_MODEL` environment variable |
| eval | remote::trustyai_lmeval | Yes (version 0.3.0) | ✅ | N/A |
| eval | remote::trustyai_ragas | Yes (version 0.3.1) | ❌ | Set the `KUBEFLOW_LLAMA_STACK_URL` environment variable |
| files | inline::localfs | No | ✅ | N/A |
| inference | inline::sentence-transformers | No | ✅ | N/A |
| inference | remote::azure | No | ❌ | Set the `AZURE_API_KEY` environment variable |
Expand Down
3 changes: 2 additions & 1 deletion distribution/build.py
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,7 @@
from pathlib import Path

BASE_REQUIREMENTS = [
"llama-stack==0.2.22",
"llama-stack==0.2.23",
]


Expand Down Expand Up @@ -95,6 +95,7 @@ def get_dependencies():
else package
for package in packages
]
packages = sorted(set(packages))

# Determine command type and format accordingly
if ("--index-url" in line) or ("--extra-index-url" in line):
Expand Down
6 changes: 3 additions & 3 deletions distribution/build.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -20,11 +20,11 @@ distribution_spec:
- provider_type: inline::meta-reference
eval:
- provider_type: remote::trustyai_lmeval
module: llama_stack_provider_lmeval==0.2.4
module: llama_stack_provider_lmeval==0.3.0
- provider_type: inline::trustyai_ragas
module: llama_stack_provider_ragas==0.3.0
module: llama_stack_provider_ragas==0.3.1
- provider_type: remote::trustyai_ragas
module: llama_stack_provider_ragas[remote]==0.3.0
module: llama_stack_provider_ragas[remote]==0.3.1
datasetio:
- provider_type: remote::huggingface
- provider_type: inline::localfs
Expand Down
4 changes: 2 additions & 2 deletions distribution/run.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -85,7 +85,7 @@ providers:
safety:
- provider_id: trustyai_fms
provider_type: remote::trustyai_fms
module: llama_stack_provider_trustyai_fms==0.2.3
module: llama_stack_provider_trustyai_fms
config:
orchestrator_url: ${env.FMS_ORCHESTRATOR_URL:=}
ssl_cert_path: ${env.FMS_SSL_CERT_PATH:=}
Expand All @@ -104,7 +104,7 @@ providers:
eval:
- provider_id: trustyai_lmeval
provider_type: remote::trustyai_lmeval
module: llama_stack_provider_lmeval==0.2.4
module: llama_stack_provider_lmeval
config:
use_k8s: ${env.TRUSTYAI_LMEVAL_USE_K8S:=true}
base_url: ${env.VLLM_URL:=}
Expand Down
Loading