mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-08-06 02:32:40 +00:00
updated doc
This commit is contained in:
parent
28e6c8478b
commit
dc8a72f864
2 changed files with 69 additions and 0 deletions
68
llama_stack/templates/watsonx/doc_template.md
Normal file
68
llama_stack/templates/watsonx/doc_template.md
Normal file
|
@ -0,0 +1,68 @@
|
|||
---
|
||||
orphan: true
|
||||
---
|
||||
# WatsonX Distribution
|
||||
|
||||
```{toctree}
|
||||
:maxdepth: 2
|
||||
:hidden:
|
||||
|
||||
self
|
||||
```
|
||||
|
||||
The `llamastack/distribution-{{ name }}` distribution consists of the following provider configurations.
|
||||
|
||||
{{ providers_table }}
|
||||
|
||||
{% if run_config_env_vars
|
||||
### Environment Variables
|
||||
|
||||
The following environment variables can be configured:
|
||||
|
||||
{% for var, (default_value, description) in run_config_env_vars.items() %}
|
||||
- `{{ var }}`: {{ description }} (default: `{{ default_value }}`)
|
||||
{% endfor %}
|
||||
{% endif %}
|
||||
|
||||
{% if default_models %}
|
||||
### Models
|
||||
|
||||
The following models are available by default:
|
||||
|
||||
{% for model in default_models %}
|
||||
- `{{ model.model_id }} {{ model.doc_string }}`
|
||||
{% endfor %}
|
||||
{% endif %}
|
||||
|
||||
|
||||
### Prerequisite: API Keys
|
||||
|
||||
Make sure you have access to a WatsonX API Key. You can get one by referring [watsonx.ai](https://www.ibm.com/docs/en/masv-and-l/maximo-manage/continuous-delivery?topic=setup-create-watsonx-api-key).
|
||||
|
||||
|
||||
## Running Llama Stack with WatsonX
|
||||
|
||||
You can do this via Conda (build code) or Docker which has a pre-built image.
|
||||
|
||||
### Via Docker
|
||||
|
||||
This method allows you to get started quickly without having to build the distribution code.
|
||||
|
||||
```bash
|
||||
LLAMA_STACK_PORT=5001
|
||||
docker run \
|
||||
-it \
|
||||
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
|
||||
llamastack/distribution-{{ name }} \
|
||||
--port $LLAMA_STACK_PORT \
|
||||
--env WATSONX_API_KEY=$WATSONX_API_KEY --env WATSONX_PROJECT_ID=$WATSONX_PROJECT_ID
|
||||
```
|
||||
|
||||
### Via Conda
|
||||
|
||||
```bash
|
||||
llama stack build --template watsonx --image-type conda
|
||||
llama stack run ./run.yaml \
|
||||
--port $LLAMA_STACK_PORT \
|
||||
--env WATSONX_API_KEY=$WATSONX_API_KEY --env WATSONX_PROJECT_ID=$WATSONX_PROJECT_ID
|
||||
```
|
|
@ -264,6 +264,7 @@ exclude = [
|
|||
"^llama_stack/providers/remote/inference/tgi/",
|
||||
"^llama_stack/providers/remote/inference/together/",
|
||||
"^llama_stack/providers/remote/inference/vllm/",
|
||||
"^llama_stack/providers/remote/inference/watsonx/",
|
||||
"^llama_stack/providers/remote/safety/bedrock/",
|
||||
"^llama_stack/providers/remote/safety/nvidia/",
|
||||
"^llama_stack/providers/remote/safety/sample/",
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue