forked from phoenix-oss/llama-stack-mirror

Add eval/scoring/datasetio API providers to distribution templates & UI developer guide (#564 )

# What does this PR do?

- add /eval, /scoring, /datasetio API providers to distribution
templates
- regenerate build.yaml / run.yaml files
- fix `template.py` to take in list of providers instead of only first
one
- override memory provider as faiss default for all distro (as only 1
memory provider is needed to start basic flow, chromadb/pgvector need
additional setup step).
```
python llama_stack/scripts/distro_codegen.py
```

- updated README to start UI via conda builds. 

## Test Plan

```
python llama_stack/scripts/distro_codegen.py
```

- Use newly generated `run.yaml` to start server
```
llama stack run ./llama_stack/templates/together/run.yaml
```
<img width="1191" alt="image"
src="https://github.com/user-attachments/assets/62f7d179-0cd0-427c-b6e8-e087d4648f09">


#### Registration
```
❯ 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 datasets list
┏━━━━━━━━━━━━┳━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━┓
┃ identifier ┃ provider_id ┃ metadata                                ┃ type    ┃
┡━━━━━━━━━━━━╇━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━┩
│ mmlu       │ huggingface │ {'path': 'llamastack/evals', 'name':    │ dataset │
│            │             │ 'evals__mmlu__details', 'split':        │         │
│            │             │ 'train'}                                │         │
└────────────┴─────────────┴─────────────────────────────────────────┴─────────┘
```

```
❯ llama-stack-client datasets register \
--dataset-id "simpleqa" \
--provider-id "huggingface" \
--url "https://huggingface.co/datasets/llamastack/evals" \
--metadata '{"path": "llamastack/evals", "name": "evals__simpleqa", "split": "train"}' \
--schema '{"input_query": {"type": "string"}, "expected_answer": {"type": "string", "chat_completion_input": {"type": "string"}}}'
❯ llama-stack-client datasets list
┏━━━━━━━━━━━━┳━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━┓
┃ identifier ┃ provider_id ┃ metadata                                                      ┃ type    ┃
┡━━━━━━━━━━━━╇━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━┩
│ mmlu       │ huggingface │ {'path': 'llamastack/evals', 'name': 'evals__mmlu__details',  │ dataset │
│            │             │ 'split': 'train'}                                             │         │
│ simpleqa   │ huggingface │ {'path': 'llamastack/evals', 'name': 'evals__simpleqa',       │ dataset │
│            │             │ 'split': 'train'}                                             │         │
└────────────┴─────────────┴───────────────────────────────────────────────────────────────┴─────────┘
```

```
❯ 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
❯ llama-stack-client eval_tasks register \
--eval-task-id meta-reference-simpleqa \
--provider-id meta-reference \
--dataset-id simpleqa \
--scoring-functions llm-as-judge::405b-simpleqa
❯ llama-stack-client eval_tasks list
┏━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━┳━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━┓
┃ dataset_id ┃ identifier       ┃ metadata ┃ provider_id    ┃ provider_resour… ┃ scoring_functio… ┃ type      ┃
┡━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━╇━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━┩
│ mmlu       │ meta-reference-… │ {}       │ meta-reference │ meta-reference-… │ ['basic::regex_… │ eval_task │
│ simpleqa   │ meta-reference-… │ {}       │ meta-reference │ meta-reference-… │ ['llm-as-judge:… │ eval_task │
└────────────┴──────────────────┴──────────┴────────────────┴──────────────────┴──────────────────┴───────────┘
```

#### Test with UI
```
streamlit run app.py
```

## Before submitting

- [ ] This PR fixes a typo or improves the docs (you can dismiss the
other checks if that's the case).
- [ ] Ran pre-commit to handle lint / formatting issues.
- [ ] Read the [contributor
guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md),
      Pull Request section?
- [ ] Updated relevant documentation.
- [ ] Wrote necessary unit or integration tests.

2024-12-05 16:29:32 -08:00

3.4 KiB

Raw Blame History

orphan
true

Meta Reference Distribution

:maxdepth: 2
:hidden:

self

The llamastack/distribution-meta-reference-gpu distribution consists of the following provider configurations:

API	Provider(s)
agents	`inline::meta-reference`
datasetio	`remote::huggingface`, `inline::localfs`
eval	`inline::meta-reference`
inference	`inline::meta-reference`
memory	`inline::faiss`, `remote::chromadb`, `remote::pgvector`
safety	`inline::llama-guard`
scoring	`inline::basic`, `inline::llm-as-judge`, `inline::braintrust`
telemetry	`inline::meta-reference`

Note that you need access to nvidia GPUs to run this distribution. This distribution is not compatible with CPU-only machines or machines with AMD GPUs.

Environment Variables

The following environment variables can be configured:

LLAMASTACK_PORT: Port for the Llama Stack distribution server (default: 5001)
INFERENCE_MODEL: Inference model loaded into the Meta Reference server (default: meta-llama/Llama-3.2-3B-Instruct)
INFERENCE_CHECKPOINT_DIR: Directory containing the Meta Reference model checkpoint (default: null)
SAFETY_MODEL: Name of the safety (Llama-Guard) model to use (default: meta-llama/Llama-Guard-3-1B)
SAFETY_CHECKPOINT_DIR: Directory containing the Llama-Guard model checkpoint (default: null)

Prerequisite: Downloading Models

Please make sure you have llama model checkpoints downloaded in ~/.llama before proceeding. See installation guide here to download the models. Run llama model list to see the available models to download, and llama model download to download the checkpoints.

$ ls ~/.llama/checkpoints
Llama3.1-8B           Llama3.2-11B-Vision-Instruct  Llama3.2-1B-Instruct  Llama3.2-90B-Vision-Instruct  Llama-Guard-3-8B
Llama3.1-8B-Instruct  Llama3.2-1B                   Llama3.2-3B-Instruct  Llama-Guard-3-1B              Prompt-Guard-86M

Running the Distribution

You can do this via Conda (build code) or Docker which has a pre-built image.

Via Docker

This method allows you to get started quickly without having to build the distribution code.

LLAMA_STACK_PORT=5001
docker run \
  -it \
  -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
  llamastack/distribution-meta-reference-gpu \
  --port $LLAMA_STACK_PORT \
  --env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct

If you are using Llama Stack Safety / Shield APIs, use:

docker run \
  -it \
  -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
  llamastack/distribution-meta-reference-gpu \
  --port $LLAMA_STACK_PORT \
  --env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
  --env SAFETY_MODEL=meta-llama/Llama-Guard-3-1B

Via Conda

Make sure you have done pip install llama-stack and have the Llama Stack CLI available.

llama stack build --template meta-reference-gpu --image-type conda
llama stack run distributions/meta-reference-gpu/run.yaml \
  --port 5001 \
  --env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct