llama-stack-mirror/llama_stack/apis/datasets/datasets.py
Ashwin Bharambe 314ee09ae3
chore: move all Llama Stack types from llama-models to llama-stack (#1098)
llama-models should have extremely minimal cruft. Its sole purpose
should be didactic -- show the simplest implementation of the llama
models and document the prompt formats, etc.

This PR is the complement to
https://github.com/meta-llama/llama-models/pull/279

## Test Plan

Ensure all `llama` CLI `model` sub-commands work:

```bash
llama model list
llama model download --model-id ...
llama model prompt-format -m ...
```

Ran tests:
```bash
cd tests/client-sdk
LLAMA_STACK_CONFIG=fireworks pytest -s -v inference/
LLAMA_STACK_CONFIG=fireworks pytest -s -v vector_io/
LLAMA_STACK_CONFIG=fireworks pytest -s -v agents/
```

Create a fresh venv `uv venv && source .venv/bin/activate` and run
`llama stack build --template fireworks --image-type venv` followed by
`llama stack run together --image-type venv` <-- the server runs

Also checked that the OpenAPI generator can run and there is no change
in the generated files as a result.

```bash
cd docs/openapi_generator
sh run_openapi_generator.sh
```
2025-02-14 09:10:59 -08:00

74 lines
2.1 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, Literal, Optional, Protocol
from pydantic import BaseModel, Field
from llama_stack.apis.common.content_types import URL
from llama_stack.apis.common.type_system import ParamType
from llama_stack.apis.resource import Resource, ResourceType
from llama_stack.schema_utils import json_schema_type, webmethod
class CommonDatasetFields(BaseModel):
dataset_schema: Dict[str, ParamType]
url: URL
metadata: Dict[str, Any] = Field(
default_factory=dict,
description="Any additional metadata for this dataset",
)
@json_schema_type
class Dataset(CommonDatasetFields, Resource):
type: Literal[ResourceType.dataset.value] = ResourceType.dataset.value
@property
def dataset_id(self) -> str:
return self.identifier
@property
def provider_dataset_id(self) -> str:
return self.provider_resource_id
class DatasetInput(CommonDatasetFields, BaseModel):
dataset_id: str
provider_id: Optional[str] = None
provider_dataset_id: Optional[str] = None
class ListDatasetsResponse(BaseModel):
data: List[Dataset]
class Datasets(Protocol):
@webmethod(route="/datasets", method="POST")
async def register_dataset(
self,
dataset_id: str,
dataset_schema: Dict[str, ParamType],
url: URL,
provider_dataset_id: Optional[str] = None,
provider_id: Optional[str] = None,
metadata: Optional[Dict[str, Any]] = None,
) -> None: ...
@webmethod(route="/datasets/{dataset_id:path}", method="GET")
async def get_dataset(
self,
dataset_id: str,
) -> Optional[Dataset]: ...
@webmethod(route="/datasets", method="GET")
async def list_datasets(self) -> ListDatasetsResponse: ...
@webmethod(route="/datasets/{dataset_id:path}", method="DELETE")
async def unregister_dataset(
self,
dataset_id: str,
) -> None: ...