forked from phoenix-oss/llama-stack-mirror

History

Michael Clifford 9657105304 feat: Add tools page to playground (#1904 ) # What does this PR do? This PR adds an additional page to the playground called "Tools". This page connects to a llama-stack server and lists all the available LLM models, builtin tools and MCP tools in the sidebar. Users can select whatever combination of model and tools they want from the sidebar for their agent. Once the selections are made, users can chat with their agent similarly to the RAG page and test out agent tool use. closes #1902 ## Test Plan Ran the following commands with a llama-stack server and the updated playground worked as expected. ``` export LLAMA_STACK_ENDPOINT="http://localhost:8321" streamlit run llama_stack/distribution/ui/app.py ``` [//]: # (## Documentation) Signed-off-by: Michael Clifford <mcliffor@redhat.com>		2025-04-09 15:26:52 +02:00
..
modules	build: format codebase imports using ruff linter (#1028 )	2025-02-13 10:06:21 -08:00
page	feat: Add tools page to playground (#1904 )	2025-04-09 15:26:52 +02:00
__init__.py	move playground ui to llama-stack repo (#536 )	2024-11-26 22:04:21 -08:00
app.py	feat: Add tools page to playground (#1904 )	2025-04-09 15:26:52 +02:00
Containerfile	fix: Playground Container Issue (#1868 )	2025-04-09 11:45:15 +02:00
README.md	feat: Created Playground Containerfile and Image Workflow (#1256 )	2025-03-18 09:26:49 -07:00
requirements.txt	fix: Playground Container Issue (#1868 )	2025-04-09 11:45:15 +02:00

README.md

(Experimental) LLama Stack UI

Docker Setup

⚠️ This is a work in progress.

Developer Setup

Start up Llama Stack API server. More details here.

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

llama stack run together

(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 benchmarks register \
--eval-task-id meta-reference-mmlu \
--provider-id meta-reference \
--dataset-id mmlu \
--scoring-functions basic::regex_parser_multiple_choice_answer

Start Streamlit UI

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

Environment Variables

Environment Variable	Description	Default Value
LLAMA_STACK_ENDPOINT	The endpoint for the Llama Stack	http://localhost:8321
FIREWORKS_API_KEY	API key for Fireworks provider	(empty string)
TOGETHER_API_KEY	API key for Together provider	(empty string)
SAMBANOVA_API_KEY	API key for SambaNova provider	(empty string)
OPENAI_API_KEY	API key for OpenAI provider	(empty string)