forked from phoenix-oss/llama-stack-mirror
caf1dac114
# What does this PR do?
1) Implement `unregister_dataset(dataset_id)` API in both llama stack
routing table and providers: It removes {dataset_id -> Dataset} mapping
from routing table and removes the dataset_id references in provider as
well (ex. for huggingface, we use a KV store to store the dataset id =>
dataset. we delete it during unregistering as well)
2) expose the datasets/unregister_dataset api endpoint
## Test Plan
**Unit test:**
`
pytest llama_stack/providers/tests/datasetio/test_datasetio.py -m
"huggingface" -v -s --tb=short --disable-warnings
`
**Test on endpoint:**
tested llama stack using an ollama distribution template:
1) start an ollama server
2) Start a llama stack server with the default ollama distribution
config + dataset/datasetsio APIs + datasetio provider
```
---- .../ollama-run.yaml
...
apis:
- agents
- inference
- memory
- safety
- telemetry
- datasetio
- datasets
providers:
datasetio:
- provider_id: localfs
provider_type: inline::localfs
config: {}
...
```
saw that the new API showed up in startup script
```
Serving API datasets
GET /alpha/datasets/get
GET /alpha/datasets/list
POST /alpha/datasets/register
POST /alpha/datasets/unregister
```
3) query `/alpha/datasets/unregister` through curl (since we have not implemented unregister api in llama stack client)
```
(base) sxyi@sxyi-mbp llama-stack % llama-stack-client datasets register
--dataset-id sixian --url
https://raw.githubusercontent.com/pytorch/torchtune/main/docs/source/tutorials/chat.rst
--schema {}
(base) sxyi@sxyi-mbp llama-stack % llama-stack-client datasets list
┏━━━━━━━━━━━━┳━━━━━━━━━━━━━┳━━━━━━━━━━┳━━━━━━━━━┓
┃ identifier ┃ provider_id ┃ metadata ┃ type ┃
┡━━━━━━━━━━━━╇━━━━━━━━━━━━━╇━━━━━━━━━━╇━━━━━━━━━┩
│ sixian │ localfs │ {} │ dataset │
└────────────┴─────────────┴──────────┴─────────┘
(base) sxyi@sxyi-mbp llama-stack % llama-stack-client datasets register
--dataset-id sixian2 --url
https://raw.githubusercontent.com/pytorch/torchtune/main/docs/source/tutorials/chat.rst
--schema {}
(base) sxyi@sxyi-mbp llama-stack % llama-stack-client datasets list
┏━━━━━━━━━━━━┳━━━━━━━━━━━━━┳━━━━━━━━━━┳━━━━━━━━━┓
┃ identifier ┃ provider_id ┃ metadata ┃ type ┃
┡━━━━━━━━━━━━╇━━━━━━━━━━━━━╇━━━━━━━━━━╇━━━━━━━━━┩
│ sixian │ localfs │ {} │ dataset │
│ sixian2 │ localfs │ {} │ dataset │
└────────────┴─────────────┴──────────┴─────────┘
(base) sxyi@sxyi-mbp llama-stack % curl
http://localhost:5001/alpha/datasets/unregister \
-H "Content-Type: application/json" \
-d '{"dataset_id": "sixian"}'
null%
(base) sxyi@sxyi-mbp llama-stack % llama-stack-client datasets list
┏━━━━━━━━━━━━┳━━━━━━━━━━━━━┳━━━━━━━━━━┳━━━━━━━━━┓
┃ identifier ┃ provider_id ┃ metadata ┃ type ┃
┡━━━━━━━━━━━━╇━━━━━━━━━━━━━╇━━━━━━━━━━╇━━━━━━━━━┩
│ sixian2 │ localfs │ {} │ dataset │
└────────────┴─────────────┴──────────┴─────────┘
(base) sxyi@sxyi-mbp llama-stack % curl
http://localhost:5001/alpha/datasets/unregister \
-H "Content-Type: application/json" \
-d '{"dataset_id": "sixian2"}'
null%
(base) sxyi@sxyi-mbp llama-stack % llama-stack-client datasets list
```
## Sources
## 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.
72 lines
2 KiB
Python
72 lines
2 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 llama_models.llama3.api.datatypes import URL
|
|
|
|
from llama_models.schema_utils import json_schema_type, webmethod
|
|
|
|
from pydantic import BaseModel, Field
|
|
|
|
from llama_stack.apis.common.type_system import ParamType
|
|
from llama_stack.apis.resource import Resource, ResourceType
|
|
|
|
|
|
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 Datasets(Protocol):
|
|
@webmethod(route="/datasets/register", 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/get", method="GET")
|
|
async def get_dataset(
|
|
self,
|
|
dataset_id: str,
|
|
) -> Optional[Dataset]: ...
|
|
|
|
@webmethod(route="/datasets/list", method="GET")
|
|
async def list_datasets(self) -> List[Dataset]: ...
|
|
|
|
@webmethod(route="/datasets/unregister", method="POST")
|
|
async def unregister_dataset(
|
|
self,
|
|
dataset_id: str,
|
|
) -> None: ...
|