mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-07-05 13:40:30 +00:00
24a27baf7c
# What does this PR do? When going through READMEs, I found that I had to keep editing the code blocks since they were prefixed with `$ `. A common pattern is to triple click (highlight all) a block and then copy paste. This minor change will make this easier for folks to follow the READMEs. [//]: # (If resolving an issue, uncomment and update the line below) [//]: # (Closes #[issue-number]) ## Test Plan N/A [//]: # (## Documentation)
42 lines
1.2 KiB
Markdown
42 lines
1.2 KiB
Markdown
# (Experimental) LLama Stack UI
|
|
|
|
## Docker Setup
|
|
|
|
:warning: This is a work in progress.
|
|
|
|
## Developer Setup
|
|
|
|
1. Start up Llama Stack API server. More details [here](https://llama-stack.readthedocs.io/en/latest/getting_started/index.html).
|
|
|
|
```
|
|
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).
|
|
|
|
```bash
|
|
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"}}}'
|
|
```
|
|
|
|
```bash
|
|
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
|
|
```
|
|
|
|
3. Start Streamlit UI
|
|
|
|
```bash
|
|
cd llama_stack/distribution/ui
|
|
pip install -r requirements.txt
|
|
streamlit run app.py
|
|
```
|