llama-stack/llama_stack/apis/datasetio/datasetio.py
Xi Yan 39f4dfbf50
feat(api): (1.2/n) datasets.iterrorws pagination api updates (#1656)
# What does this PR do?
- as title
- uses "cursor" pagination scheme for iterrows

[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])

## Test Plan
<img width="1226" alt="image"
src="https://github.com/user-attachments/assets/3220eaac-7117-4d0a-b344-2bbb77a22065"
/>


[//]: # (## Documentation)
2025-03-15 13:58:47 -07:00

55 lines
1.7 KiB
Python

# Copyright (c) Meta Platforms, Inc. and affiliates.
# All rights reserved.
#
# This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree.
from typing import Any, Dict, List, Optional, Protocol, runtime_checkable
from pydantic import BaseModel
from llama_stack.apis.datasets import Dataset
from llama_stack.schema_utils import json_schema_type, webmethod
@json_schema_type
class IterrowsResponse(BaseModel):
"""
A paginated list of rows from a dataset.
:param data: The rows in the current page.
:param next_index: Index into dataset for the first row in the next page. None if there are no more rows.
"""
data: List[Dict[str, Any]]
next_index: Optional[int] = None
class DatasetStore(Protocol):
def get_dataset(self, dataset_id: str) -> Dataset: ...
@runtime_checkable
class DatasetIO(Protocol):
# keeping for aligning with inference/safety, but this is not used
dataset_store: DatasetStore
@webmethod(route="/datasets/{dataset_id}/iterrows", method="GET")
async def iterrows(
self,
dataset_id: str,
start_index: Optional[int] = None,
limit: Optional[int] = None,
) -> IterrowsResponse:
"""Get a paginated list of rows from a dataset. Uses cursor-based pagination.
:param dataset_id: The ID of the dataset to get the rows from.
:param start_index: Index into dataset for the first row to get. Get all rows if None.
:param limit: The number of rows to get per page.
"""
...
@webmethod(route="/datasets/{dataset_id}/append-rows", method="POST")
async def append_rows(
self, dataset_id: str, rows: List[Dict[str, Any]]
) -> None: ...