forked from phoenix-oss/llama-stack-mirror
389767010b
# What does this PR do?
Providers that live outside of the llama-stack codebase are now
supported.
A new property `external_providers_dir` has been added to the main
config and can be configured as follow:
```
external_providers_dir: /etc/llama-stack/providers.d/
```
Where the expected structure is:
```
providers.d/
inference/
custom_ollama.yaml
vllm.yaml
vector_io/
qdrant.yaml
```
Where `custom_ollama.yaml` is:
```
adapter:
adapter_type: custom_ollama
pip_packages: ["ollama", "aiohttp"]
config_class: llama_stack_ollama_provider.config.OllamaImplConfig
module: llama_stack_ollama_provider
api_dependencies: []
optional_api_dependencies: []
```
Obviously the package must be installed on the system, here is the
`llama_stack_ollama_provider` example:
```
$ uv pip show llama-stack-ollama-provider
Using Python 3.10.16 environment at: /Users/leseb/Documents/AI/llama-stack/.venv
Name: llama-stack-ollama-provider
Version: 0.1.0
Location: /Users/leseb/Documents/AI/llama-stack/.venv/lib/python3.10/site-packages
Editable project location: /private/var/folders/mq/rnm5w_7s2d3fxmtkx02knvhm0000gn/T/tmp.ZBHU5Ezxg4/ollama/llama-stack-ollama-provider
Requires:
Required-by:
```
Closes: https://github.com/meta-llama/llama-stack/issues/658
Signed-off-by: Sébastien Han <seb@redhat.com>
93 lines
3.1 KiB
YAML
93 lines
3.1 KiB
YAML
name: Test External Providers
|
|
|
|
on:
|
|
push:
|
|
branches: [ main ]
|
|
pull_request:
|
|
branches: [ main ]
|
|
|
|
jobs:
|
|
test-external-providers:
|
|
runs-on: ubuntu-latest
|
|
steps:
|
|
- name: Checkout repository
|
|
uses: actions/checkout@v4
|
|
|
|
- name: Install uv
|
|
uses: astral-sh/setup-uv@v5
|
|
with:
|
|
python-version: "3.10"
|
|
|
|
- name: Install Ollama
|
|
run: |
|
|
curl -fsSL https://ollama.com/install.sh | sh
|
|
|
|
- name: Pull Ollama image
|
|
run: |
|
|
ollama pull llama3.2:3b-instruct-fp16
|
|
|
|
- name: Start Ollama in background
|
|
run: |
|
|
nohup ollama run llama3.2:3b-instruct-fp16 --keepalive=30m > ollama.log 2>&1 &
|
|
|
|
- name: Set Up Environment and Install Dependencies
|
|
run: |
|
|
uv sync --extra dev --extra test
|
|
uv pip install -e .
|
|
|
|
- name: Install Ollama custom provider
|
|
run: |
|
|
mkdir -p tests/external-provider/llama-stack-provider-ollama/src/
|
|
cp -a llama_stack/providers/remote/inference/ollama/ tests/external-provider/llama-stack-provider-ollama/src/llama_stack_provider_ollama
|
|
uv pip install tests/external-provider/llama-stack-provider-ollama
|
|
|
|
- name: Create provider configuration
|
|
run: |
|
|
mkdir -p /tmp/providers.d/remote/inference
|
|
cp tests/external-provider/llama-stack-provider-ollama/custom_ollama.yaml /tmp/providers.d/remote/inference/custom_ollama.yaml
|
|
|
|
- name: Wait for Ollama to start
|
|
run: |
|
|
echo "Waiting for Ollama..."
|
|
for i in {1..30}; do
|
|
if curl -s http://localhost:11434 | grep -q "Ollama is running"; then
|
|
echo "Ollama is running!"
|
|
exit 0
|
|
fi
|
|
sleep 1
|
|
done
|
|
echo "Ollama failed to start"
|
|
ollama ps
|
|
ollama.log
|
|
exit 1
|
|
|
|
- name: Start Llama Stack server in background
|
|
env:
|
|
INFERENCE_MODEL: "meta-llama/Llama-3.2-3B-Instruct"
|
|
run: |
|
|
source .venv/bin/activate
|
|
nohup uv run llama stack run tests/external-provider/llama-stack-provider-ollama/run.yaml --image-type venv > server.log 2>&1 &
|
|
|
|
- name: Wait for Llama Stack server to be ready
|
|
run: |
|
|
echo "Waiting for Llama Stack server..."
|
|
for i in {1..30}; do
|
|
if curl -s http://localhost:8321/v1/health | grep -q "OK"; then
|
|
echo "Llama Stack server is up!"
|
|
if grep -q "remote::custom_ollama from /tmp/providers.d/remote/inference/custom_ollama.yaml" server.log; then
|
|
echo "Llama Stack server is using custom Ollama provider"
|
|
exit 0
|
|
else
|
|
echo "Llama Stack server is not using custom Ollama provider"
|
|
exit 1
|
|
fi
|
|
fi
|
|
sleep 1
|
|
done
|
|
echo "Llama Stack server failed to start"
|
|
cat server.log
|
|
exit 1
|
|
|
|
- name: run inference tests
|
|
run: |
|
|
uv run pytest -v tests/integration/inference/test_text_inference.py --stack-config="http://localhost:8321" --text-model="meta-llama/Llama-3.2-3B-Instruct" --embedding-model=all-MiniLM-L6-v2
|