phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-03 17:29:01 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

update start-stack.sh with missing color and if statment logic

Browse source 
Add conda image name
This commit is contained in:
Aidan Reilly 2025-04-11 10:30:12 +01:00
parent 2fcb70b789
commit dae8fd0a36
No known key found for this signature in database
2 changed files with 5 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

6
docs/source/getting_started/detailed_tutorial.md
View file

@ -69,7 +69,7 @@ which defines the providers and their settings.
Now let's build and run the Llama Stack config for Ollama. Now let's build and run the Llama Stack config for Ollama.
```bash ```bash
INFERENCE_MODEL=llama3.2:3b llama stack build --template ollama --image-type conda --run INFERENCE_MODEL=llama3.2:3b llama stack build --template ollama --image-type conda --image-name llama3-3b-conda --run
``` ```
::: :::
:::{tab-item} Using a Container :::{tab-item} Using a Container
@ -77,10 +77,9 @@ You can use a container image to run the Llama Stack server. We provide several
component that works with different inference providers out of the box. For this guide, we will use component that works with different inference providers out of the box. For this guide, we will use
`llamastack/distribution-ollama` as the container image. If you'd like to build your own image or customize the `llamastack/distribution-ollama` as the container image. If you'd like to build your own image or customize the
configurations, please check out [this guide](../references/index.md). configurations, please check out [this guide](../references/index.md).
First lets setup some environment variables and create a local directory to mount into the container’s file system. First lets setup some environment variables and create a local directory to mount into the container’s file system.
```bash ```bash
export INFERENCE_MODEL="meta-llama/Llama-3.2-3B-Instruct" export INFERENCE_MODEL="llama3.2:3b"
export LLAMA_STACK_PORT=8321 export LLAMA_STACK_PORT=8321
mkdir -p ~/.llama mkdir -p ~/.llama
``` ```
@ -227,6 +226,7 @@ ChatCompletionResponse(
Alternatively, you can run inference using the Llama Stack client SDK. Alternatively, you can run inference using the Llama Stack client SDK.
### i. Create the Script ### i. Create the Script
Create a file `inference.py` and add the following code: Create a file `inference.py` and add the following code:
```python ```python
from llama_stack_client import LlamaStackClient from llama_stack_client import LlamaStackClient

3
llama_stack/distribution/start_stack.sh
View file

@ -18,6 +18,7 @@ VIRTUAL_ENV=${VIRTUAL_ENV:-}
set -euo pipefail set -euo pipefail
RED='\033[0;31m' RED='\033[0;31m'
GREEN='\033[0;32m'
NC='\033[0m' # No Color NC='\033[0m' # No Color
error_handler() { error_handler() {
@ -73,7 +74,7 @@ done
PYTHON_BINARY="python" PYTHON_BINARY="python"
case "$env_type" in case "$env_type" in
"venv") "venv")
if [ -n "$VIRTUAL_ENV" && "$VIRTUAL_ENV" == "$env_path_or_name" ]; then if [ -n "$VIRTUAL_ENV" ] && [ "$VIRTUAL_ENV" == "$env_path_or_name" ]; then
echo -e "${GREEN}Virtual environment already activated${NC}" >&2 echo -e "${GREEN}Virtual environment already activated${NC}" >&2
else else
# Activate virtual environment # Activate virtual environment