phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-06-27 18:50:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat(api): (1/n) datasets api clean up (#1573)

Browse source 
## PR Stack
- https://github.com/meta-llama/llama-stack/pull/1573
- https://github.com/meta-llama/llama-stack/pull/1625
- https://github.com/meta-llama/llama-stack/pull/1656
- https://github.com/meta-llama/llama-stack/pull/1657
- https://github.com/meta-llama/llama-stack/pull/1658
- https://github.com/meta-llama/llama-stack/pull/1659
- https://github.com/meta-llama/llama-stack/pull/1660

**Client SDK**
- https://github.com/meta-llama/llama-stack-client-python/pull/203

**CI**
- 1391130488
<img width="1042" alt="image"
src="https://github.com/user-attachments/assets/69636067-376d-436b-9204-896e2dd490ca"
/>
-- the test_rag_agent_with_attachments is flaky and not related to this
PR

## Doc
<img width="789" alt="image"
src="https://github.com/user-attachments/assets/b88390f3-73d6-4483-b09a-a192064e32d9"
/>


## Client Usage
```python
client.datasets.register(
    source={
        "type": "uri",
        "uri": "lsfs://mydata.jsonl",
    },
    schema="jsonl_messages",
    # optional 
    dataset_id="my_first_train_data"
)

# quick prototype debugging
client.datasets.register(
    data_reference={
        "type": "rows",
        "rows": [
                "messages": [...],
        ],
    },
    schema="jsonl_messages",
)
```

## Test Plan
- CI:
1387805545

```
LLAMA_STACK_CONFIG=fireworks pytest -v tests/integration/datasets/test_datasets.py
```

```
LLAMA_STACK_CONFIG=fireworks pytest -v tests/integration/scoring/test_scoring.py
```

```
pytest -v -s --nbval-lax ./docs/notebooks/Llama_Stack_Benchmark_Evals.ipynb
```
This commit is contained in:
Xi Yan 2025-03-17 16:55:45 -07:00 • committed by GitHub
parent 3b35a39b8b
commit 5287b437ae
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
29 changed files with 2593 additions and 2296 deletions
Download patch file Download diff file Expand all files Collapse all files

76
llama_stack/templates/open-benchmark/open_benchmark.py
View file

@ -6,7 +6,7 @@
from typing import Dict, List, Tuple
from llama_stack.apis.common.content_types import URL
from llama_stack.apis.datasets import DatasetPurpose, URIDataSource
from llama_stack.apis.models.models import ModelType
from llama_stack.distribution.datatypes import (
BenchmarkInput,
@ -171,76 +171,42 @@ def get_distribution_template() -> DistributionTemplate:
DatasetInput(
dataset_id="simpleqa",
provider_id="huggingface",
url=URL(uri="https://huggingface.co/datasets/llamastack/simpleqa"),
metadata={
"path": "llamastack/simpleqa",
"split": "train",
},
dataset_schema={
"input_query": {"type": "string"},
"expected_answer": {"type": "string"},
"chat_completion_input": {"type": "string"},
},
purpose=DatasetPurpose.eval_messages_answer,
source=URIDataSource(
uri="huggingface://datasets/llamastack/simpleqa?split=train",
),
),
DatasetInput(
dataset_id="mmlu_cot",
provider_id="huggingface",
url=URL(uri="https://huggingface.co/datasets/llamastack/mmlu_cot"),
metadata={
"path": "llamastack/mmlu_cot",
"name": "all",
"split": "test",
},
dataset_schema={
"input_query": {"type": "string"},
"expected_answer": {"type": "string"},
"chat_completion_input": {"type": "string"},
},
purpose=DatasetPurpose.eval_messages_answer,
source=URIDataSource(
uri="huggingface://datasets/llamastack/mmlu_cot?split=test&name=all",
),
),
DatasetInput(
dataset_id="gpqa_cot",
provider_id="huggingface",
url=URL(uri="https://huggingface.co/datasets/llamastack/gpqa_0shot_cot"),
metadata={
"path": "llamastack/gpqa_0shot_cot",
"name": "gpqa_main",
"split": "train",
},
dataset_schema={
"input_query": {"type": "string"},
"expected_answer": {"type": "string"},
"chat_completion_input": {"type": "string"},
},
purpose=DatasetPurpose.eval_messages_answer,
source=URIDataSource(
uri="huggingface://datasets/llamastack/gpqa_0shot_cot?split=test&name=gpqa_main",
),
),
DatasetInput(
dataset_id="math_500",
provider_id="huggingface",
url=URL(uri="https://huggingface.co/datasets/llamastack/math_500"),
metadata={
"path": "llamastack/math_500",
"split": "test",
},
dataset_schema={
"input_query": {"type": "string"},
"expected_answer": {"type": "string"},
"chat_completion_input": {"type": "string"},
},
purpose=DatasetPurpose.eval_messages_answer,
source=URIDataSource(
uri="huggingface://datasets/llamastack/math_500?split=test",
),
),
DatasetInput(
dataset_id="bfcl",
provider_id="huggingface",
url=URL(uri="https://huggingface.co/datasets/llamastack/bfcl_v3"),
metadata={
"path": "llamastack/bfcl_v3",
"split": "train",
},
dataset_schema={
"function": {"type": "string"},
"language": {"type": "string"},
"ground_truth": {"type": "string"},
"id": {"type": "string"},
"chat_completion_input": {"type": "string"},
},
purpose=DatasetPurpose.eval_messages_answer,
source=URIDataSource(
uri="huggingface://datasets/llamastack/bfcl_v3?split=train",
),
),
]