forked from phoenix-oss/llama-stack-mirror

History

Michael Clifford fe9b5ef08b fix: tools page on playground resets agent after every interaction (#2044 ) # What does this PR do? This PR updates how the `AgentType` gets set using the radio button on the tools page of the playground. This change is needed due to the fact with its current implementation, the chat interface will resets after every input, preventing users from having a multi-turn conversation with the agent. ## Test Plan Run the Playground without these changes: ```bash streamlit run llama_stack/distribution/ui/app.py ``` Navigate to the tools page and attempt to have a multi-turn conversation. You should see the conversation reset after asking a second question. Repeat the steps above with these changes and you will see that it works as expected when asking the agent multiple questions. Signed-off-by: Michael Clifford <mcliffor@redhat.com>		2025-04-28 23:13:27 +02:00
..
modules	fix: add tavily_search option to playground api (#1909 )	2025-04-09 15:56:41 +02:00
page	fix: tools page on playground resets agent after every interaction (#2044 )	2025-04-28 23:13:27 +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	chore: simplify running the demo UI (#1907 )	2025-04-09 11:22:29 -07:00
requirements.txt	chore: simplify running the demo UI (#1907 )	2025-04-09 11:22:29 -07:00

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

uv run --with ".[ui]" streamlit run llama_stack/distribution/ui/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)