forked from phoenix-oss/llama-stack-mirror
datasets api
Summary: Test Plan: Reviewers: Subscribers: Tasks: Tags:
This commit is contained in:
parent
5f90be5388
commit
bc551e6459
1 changed files with 42 additions and 8 deletions
|
@ -4,6 +4,7 @@
|
||||||
# This source code is licensed under the terms described in the LICENSE file in
|
# This source code is licensed under the terms described in the LICENSE file in
|
||||||
# the root directory of this source tree.
|
# the root directory of this source tree.
|
||||||
|
|
||||||
|
from enum import Enum
|
||||||
from typing import Any, Dict, List, Literal, Optional, Protocol
|
from typing import Any, Dict, List, Literal, Optional, Protocol
|
||||||
|
|
||||||
from pydantic import BaseModel, Field
|
from pydantic import BaseModel, Field
|
||||||
|
@ -14,9 +15,26 @@ from llama_stack.apis.resource import Resource, ResourceType
|
||||||
from llama_stack.schema_utils import json_schema_type, webmethod
|
from llama_stack.schema_utils import json_schema_type, webmethod
|
||||||
|
|
||||||
|
|
||||||
|
@json_schema_type
|
||||||
|
class Schema(Enum):
|
||||||
|
"""
|
||||||
|
Schema of the dataset. Each type has a different column format.
|
||||||
|
:cvar jsonl_messages: The dataset is a JSONL file with messages. Examples:
|
||||||
|
{
|
||||||
|
"messages": [
|
||||||
|
{"role": "user", "content": "Hello, world!"},
|
||||||
|
{"role": "assistant", "content": "Hello, world!"},
|
||||||
|
]
|
||||||
|
}
|
||||||
|
"""
|
||||||
|
|
||||||
|
jsonl_messages = "jsonl_messages"
|
||||||
|
# TODO: add more schemas here
|
||||||
|
|
||||||
|
|
||||||
class CommonDatasetFields(BaseModel):
|
class CommonDatasetFields(BaseModel):
|
||||||
dataset_schema: Dict[str, ParamType]
|
schema: Schema
|
||||||
url: URL
|
uri: str
|
||||||
metadata: Dict[str, Any] = Field(
|
metadata: Dict[str, Any] = Field(
|
||||||
default_factory=dict,
|
default_factory=dict,
|
||||||
description="Any additional metadata for this dataset",
|
description="Any additional metadata for this dataset",
|
||||||
|
@ -50,13 +68,29 @@ class Datasets(Protocol):
|
||||||
@webmethod(route="/datasets", method="POST")
|
@webmethod(route="/datasets", method="POST")
|
||||||
async def register_dataset(
|
async def register_dataset(
|
||||||
self,
|
self,
|
||||||
dataset_id: str,
|
schema: Schema,
|
||||||
dataset_schema: Dict[str, ParamType],
|
uri: str,
|
||||||
url: URL,
|
uri_params: Optional[Dict[str, Any]] = None,
|
||||||
provider_dataset_id: Optional[str] = None,
|
|
||||||
provider_id: Optional[str] = None,
|
|
||||||
metadata: Optional[Dict[str, Any]] = None,
|
metadata: Optional[Dict[str, Any]] = None,
|
||||||
) -> None: ...
|
dataset_id: Optional[str] = None,
|
||||||
|
) -> Dataset:
|
||||||
|
"""
|
||||||
|
Register a new dataset through a file or
|
||||||
|
|
||||||
|
:param schema: The schema format of the dataset. One of
|
||||||
|
- jsonl_messages: The dataset is a JSONL file with messages in column format
|
||||||
|
:param uri: The URI of the dataset. Examples:
|
||||||
|
- file://mydata.jsonl
|
||||||
|
- s3://mybucket/myfile.jsonl
|
||||||
|
- https://mywebsite.com/myfile.jsonl
|
||||||
|
- huggingface://tatsu-lab/alpaca
|
||||||
|
:param uri_params: The parameters for the URI.
|
||||||
|
- E.g. If URL is a huggingface dataset, parameters could be uri_params={"split": "train"}
|
||||||
|
:param metadata: The metadata for the dataset.
|
||||||
|
- E.g. {"description": "My dataset"}
|
||||||
|
:param dataset_id: The ID of the dataset. If not provided, a random ID will be generated.
|
||||||
|
"""
|
||||||
|
...
|
||||||
|
|
||||||
@webmethod(route="/datasets/{dataset_id:path}", method="GET")
|
@webmethod(route="/datasets/{dataset_id:path}", method="GET")
|
||||||
async def get_dataset(
|
async def get_dataset(
|
||||||
|
|
Loading…
Add table
Add a link
Reference in a new issue