From aa68e98b7a8858f1e05a9b30ceadf6cb87c99b05 Mon Sep 17 00:00:00 2001 From: Jeff MAURY Date: Wed, 26 Mar 2025 15:51:05 +0100 Subject: [PATCH] fix: rewording Signed-off-by: Jeff MAURY --- .../distributions/self_hosted_distro/podman-ai-lab.md | 9 ++++----- llama_stack/templates/podman-ai-lab/doc_template.md | 7 +++---- llama_stack/templates/podman-ai-lab/podman_ai_lab.py | 4 ++-- llama_stack/templates/podman-ai-lab/report.md | 2 +- llama_stack/templates/podman-ai-lab/run-with-safety.yaml | 2 +- 5 files changed, 11 insertions(+), 13 deletions(-) diff --git a/docs/source/distributions/self_hosted_distro/podman-ai-lab.md b/docs/source/distributions/self_hosted_distro/podman-ai-lab.md index ec4371154..238b0d74f 100644 --- a/docs/source/distributions/self_hosted_distro/podman-ai-lab.md +++ b/docs/source/distributions/self_hosted_distro/podman-ai-lab.md @@ -26,7 +26,7 @@ The `llamastack/distribution-podman-ai-lab` distribution consists of the followi | vector_io | `inline::faiss`, `remote::chromadb`, `remote::pgvector` | -You should use this distribution if you have a regular desktop machine without very powerful GPUs. Of course, if you have powerful GPUs, you can still continue using this distribution since Ollama supports GPU acceleration. +You should use this distribution if you have a regular desktop machine without very powerful GPUs. Of course, if you have powerful GPUs, you can still continue using this distribution since Podman AI Lab supports GPU acceleration. ### Environment Variables @@ -34,12 +34,12 @@ The following environment variables can be configured: - `LLAMA_STACK_PORT`: Port for the Llama Stack distribution server (default: `5001`) - `PODMAN_AI_LAB_URL`: URL of the Podman AI Lab server (default: `http://127.0.0.1:10434`) -- `SAFETY_MODEL`: Safety model loaded into the Ollama server (default: `meta-llama/Llama-Guard-3-1B`) +- `SAFETY_MODEL`: Safety model loaded into the Podman AI Lab server (default: `meta-llama/Llama-Guard-3-1B`) ## Setting up Podman AI Lab server -Please check the [Podman AI Lab Documentation](https://github.com/containers/podman-desktop-extension-ai-lab) on how to install and run Ollama. After installing Ollama, you need to run `ollama serve` to start the server. +Please check the [Podman AI Lab Documentation](https://github.com/containers/podman-desktop-extension-ai-lab) on how to install and run Podman AI Lab. If you are using Llama Stack Safety / Shield APIs, you will also need to pull and run the safety model. @@ -47,7 +47,6 @@ If you are using Llama Stack Safety / Shield APIs, you will also need to pull an ```bash export SAFETY_MODEL="meta-llama/Llama-Guard-3-1B" -# ollama names this model differently, and we must use the ollama name when loading the model export PODMAN_AI_LAB_SAFETY_MODEL="llama-guard3:1b" ``` @@ -81,7 +80,7 @@ docker run \ -it \ -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \ -v ~/.llama:/root/.llama \ - -v ./llama_stack/templates/ollama/run-with-safety.yaml:/root/my-run.yaml \ + -v ./llama_stack/templates/podman-ai-lab/run-with-safety.yaml:/root/my-run.yaml \ llamastack/distribution-podman-ai-lab \ --yaml-config /root/my-run.yaml \ --port $LLAMA_STACK_PORT \ diff --git a/llama_stack/templates/podman-ai-lab/doc_template.md b/llama_stack/templates/podman-ai-lab/doc_template.md index a09aa857a..9815a28c0 100644 --- a/llama_stack/templates/podman-ai-lab/doc_template.md +++ b/llama_stack/templates/podman-ai-lab/doc_template.md @@ -14,7 +14,7 @@ The `llamastack/distribution-{{ name }}` distribution consists of the following {{ providers_table }} -You should use this distribution if you have a regular desktop machine without very powerful GPUs. Of course, if you have powerful GPUs, you can still continue using this distribution since Ollama supports GPU acceleration. +You should use this distribution if you have a regular desktop machine without very powerful GPUs. Of course, if you have powerful GPUs, you can still continue using this distribution since Podman AI Lab supports GPU acceleration. {% if run_config_env_vars %} ### Environment Variables @@ -29,7 +29,7 @@ The following environment variables can be configured: ## Setting up Podman AI Lab server -Please check the [Podman AI Lab Documentation](https://github.com/containers/podman-desktop-extension-ai-lab) on how to install and run Ollama. After installing Ollama, you need to run `ollama serve` to start the server. +Please check the [Podman AI Lab Documentation](https://github.com/containers/podman-desktop-extension-ai-lab) on how to install and run Podman AI Lab. If you are using Llama Stack Safety / Shield APIs, you will also need to pull and run the safety model. @@ -37,7 +37,6 @@ If you are using Llama Stack Safety / Shield APIs, you will also need to pull an ```bash export SAFETY_MODEL="meta-llama/Llama-Guard-3-1B" -# ollama names this model differently, and we must use the ollama name when loading the model export PODMAN_AI_LAB_SAFETY_MODEL="llama-guard3:1b" ``` @@ -71,7 +70,7 @@ docker run \ -it \ -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \ -v ~/.llama:/root/.llama \ - -v ./llama_stack/templates/ollama/run-with-safety.yaml:/root/my-run.yaml \ + -v ./llama_stack/templates/podman-ai-lab/run-with-safety.yaml:/root/my-run.yaml \ llamastack/distribution-{{ name }} \ --yaml-config /root/my-run.yaml \ --port $LLAMA_STACK_PORT \ diff --git a/llama_stack/templates/podman-ai-lab/podman_ai_lab.py b/llama_stack/templates/podman-ai-lab/podman_ai_lab.py index b3b12e03c..43c845026 100644 --- a/llama_stack/templates/podman-ai-lab/podman_ai_lab.py +++ b/llama_stack/templates/podman-ai-lab/podman_ai_lab.py @@ -50,7 +50,7 @@ def get_distribution_template() -> DistributionTemplate: safety_model = ModelInput( model_id="${env.SAFETY_MODEL}", - provider_id="ollama", + provider_id="podman-ai-lab", ) default_tool_groups = [ ToolGroupInput( @@ -131,7 +131,7 @@ def get_distribution_template() -> DistributionTemplate: ), "SAFETY_MODEL": ( "meta-llama/Llama-Guard-3-1B", - "Safety model loaded into the Ollama server", + "Safety model loaded into the Podman AI Lab server", ), }, ) diff --git a/llama_stack/templates/podman-ai-lab/report.md b/llama_stack/templates/podman-ai-lab/report.md index 5223f1bf8..3f2e71c10 100644 --- a/llama_stack/templates/podman-ai-lab/report.md +++ b/llama_stack/templates/podman-ai-lab/report.md @@ -1,7 +1,7 @@ # Report for Podman AI Lab distribution ## Supported Models -| Model Descriptor | ollama | +| Model Descriptor | Podman AI Lab | |:---|:---| | Llama-3-8B-Instruct | ❌ | | Llama-3-70B-Instruct | ❌ | diff --git a/llama_stack/templates/podman-ai-lab/run-with-safety.yaml b/llama_stack/templates/podman-ai-lab/run-with-safety.yaml index 1fd68d322..d61e09854 100644 --- a/llama_stack/templates/podman-ai-lab/run-with-safety.yaml +++ b/llama_stack/templates/podman-ai-lab/run-with-safety.yaml @@ -109,7 +109,7 @@ metadata_store: models: - metadata: {} model_id: ${env.SAFETY_MODEL} - provider_id: ollama + provider_id: podman-ai-lab model_type: llm shields: - shield_id: ${env.SAFETY_MODEL}