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.
This commit is contained in:
Xi Yan 2024-12-05 16:29:32 -08:00 committed by GitHub
parent a4daf4d3ec
commit 7301403ce3
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
47 changed files with 841 additions and 195 deletions

View file

@ -44,36 +44,37 @@ class RunConfigSettings(BaseModel):
provider_configs[api_str] = api_providers
continue
provider_type = provider_types[0]
provider_id = provider_type.split("::")[-1]
provider_configs[api_str] = []
for provider_type in provider_types:
provider_id = provider_type.split("::")[-1]
api = Api(api_str)
if provider_type not in provider_registry[api]:
raise ValueError(
f"Unknown provider type: {provider_type} for API: {api_str}"
api = Api(api_str)
if provider_type not in provider_registry[api]:
raise ValueError(
f"Unknown provider type: {provider_type} for API: {api_str}"
)
config_class = provider_registry[api][provider_type].config_class
assert (
config_class is not None
), f"No config class for provider type: {provider_type} for API: {api_str}"
config_class = instantiate_class_type(config_class)
if hasattr(config_class, "sample_run_config"):
config = config_class.sample_run_config(
__distro_dir__=f"distributions/{name}"
)
else:
config = {}
provider_configs[api_str].append(
Provider(
provider_id=provider_id,
provider_type=provider_type,
config=config,
)
)
config_class = provider_registry[api][provider_type].config_class
assert (
config_class is not None
), f"No config class for provider type: {provider_type} for API: {api_str}"
config_class = instantiate_class_type(config_class)
if hasattr(config_class, "sample_run_config"):
config = config_class.sample_run_config(
__distro_dir__=f"distributions/{name}"
)
else:
config = {}
provider_configs[api_str] = [
Provider(
provider_id=provider_id,
provider_type=provider_type,
config=config,
)
]
# Get unique set of APIs from providers
apis = list(sorted(providers.keys()))