llama-stack-mirror/docs/source/ui/index.md

Playground UI

Playground UI is currently experimental and subject to change. We welcome feedback and contributions to help improve it.

Llama Stack Playground UI is an simple interface aims to:

• Showcase capabilities and concepts of Llama Stack in an interactive environment
• Demo end-to-end application code to help users get started to build their own applications
• Provide an UI to help users inspect and analyze Llama Stack API providers and resources

Key Features

Playground

Interactive pages for users to play with and explore Llama Stack API capabilities.

Chatbot

.. video:: https://github.com/user-attachments/assets/6ca617e8-32ca-49b2-9774-185020ff5204
    :autoplay:
    :playsinline:
    :muted:
    :loop:
    :width: 100%

• Chat: Chat with Llama models
• RAG: Uploading documents to memory_banks and chat with RAG agent

Evaluations

.. video:: https://github.com/user-attachments/assets/6cc1659f-eba4-49ca-a0a5-7c243557b4f5
    :autoplay:
    :playsinline:
    :muted:
    :loop:
    :width: 100%

• Evaluations (Scoring): Run evaluations on your AI application datasets

.. video:: https://github.com/user-attachments/assets/345845c7-2a2b-4095-960a-9ae40f6a93cf
    :autoplay:
    :playsinline:
    :muted:
    :loop:
    :width: 100%

• Evaluations (Generation + Scoring): Use pre-registered evaluation tasks to evaluate an model or agent candidate

Inspect

.. video:: https://github.com/user-attachments/assets/01d52b2d-92af-4e3a-b623-a9b8ba22ba99
    :autoplay:
    :playsinline:
    :muted:
    :loop:
    :width: 100%

• Inspect Llama Stack API providers and resources (models, datasets, memory_banks, eval_tasks, etc).

Starting the Playground UI

To start the Playground UI, run the following commands:

1. Start up the Llama Stack API server

llama stack build --template together --image-type conda
llama stack run together

2. (Optional) Register datasets and eval tasks as resources. If you want to run pre-configured evaluation flows (e.g. Evaluations (Generation + Scoring) Page).

$ llama-stack-client datasets register \
--dataset-id "mmlu" \
--provider-id "huggingface" \
--url "https://huggingface.co/datasets/llamastack/evals" \
--metadata '{"path": "llamastack/evals", "name": "evals__mmlu__details", "split": "train"}' \
--schema '{"input_query": {"type": "string"}, "expected_answer": {"type": "string", "chat_completion_input": {"type": "string"}}}'

$ llama-stack-client eval_tasks register \
--eval-task-id meta-reference-mmlu \
--provider-id meta-reference \
--dataset-id mmlu \
--scoring-functions basic::regex_parser_multiple_choice_answer

3. Start Streamlit UI

cd llama_stack/distribution/ui
pip install -r requirements.txt
streamlit run app.py