Skip to content

Commit f2309d0

Browse files
committed
docs: update building distro to use container commands over llama stack run
1 parent 0e78afd commit f2309d0

File tree

1 file changed

+27
-1
lines changed

1 file changed

+27
-1
lines changed

docs/source/distributions/building_distro.md

Lines changed: 27 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -260,7 +260,33 @@ Containerfile created successfully in /tmp/tmp.viA3a3Rdsg/ContainerfileFROM pyth
260260
You can now edit ~/meta-llama/llama-stack/tmp/configs/ollama-run.yaml and run `llama stack run ~/meta-llama/llama-stack/tmp/configs/ollama-run.yaml`
261261
```
262262

263-
After this step is successful, you should be able to find the built container image and test it with `llama stack run <path/to/run.yaml>`.
263+
After this step is successful, you should be able to find the built container image and test it with:
264+
```
265+
# This docker command will run the Llama Stack server based on the image built before
266+
# The following is a list of docker flags and their use in running the server:
267+
# -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT: Maps the container port to the host port for accessing the server
268+
# -v ~/.llama:/root/.llama: Mounts the local .llama directory to persist configurations and data
269+
# -v <path/to/run.yaml>:/app/run.yaml: Mounts the run configuration file into the container
270+
# --entrypoint python: Specifies the entry point to run Python directly
271+
# localhost/distribution-ollama:dev: The name and tag of the container image to run
272+
# -m llama_stack.distribution.server.server: The Python module to execute
273+
# --config /app/run.yaml: Path to the configuration file inside the container
274+
# --port $LLAMA_STACK_PORT: Port number for the server to listen on
275+
# --env INFERENCE_MODEL=$INFERENCE_MODEL: Sets the model to use for inference
276+
# --env OLLAMA_URL=http://host.docker.internal:11434: Configures the URL for the Ollama service
277+
278+
docker run -it \
279+
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
280+
-v ~/.llama:/root/.llama \
281+
-v <path/to/run.yaml>:/app/run.yaml \
282+
--entrypoint python \
283+
localhost/distribution-ollama:dev \
284+
-m llama_stack.distribution.server.server \
285+
--config /app/run.yaml \
286+
--port $LLAMA_STACK_PORT \
287+
--env INFERENCE_MODEL=$INFERENCE_MODEL \
288+
--env OLLAMA_URL=http://host.docker.internal:11434
289+
```
264290
:::
265291

266292
::::

0 commit comments

Comments
 (0)