mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-03 09:53:45 +00:00
unregister API for dataset (#507)
# 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.
This commit is contained in:
parent
64c6df8392
commit
caf1dac114
9 changed files with 134 additions and 0 deletions
|
|
@ -78,6 +78,21 @@ class DatasetsClient(Datasets):
|
|||
|
||||
return [DatasetDefWithProvider(**x) for x in response.json()]
|
||||
|
||||
async def unregister_dataset(
|
||||
self,
|
||||
dataset_id: str,
|
||||
) -> None:
|
||||
async with httpx.AsyncClient() as client:
|
||||
response = await client.delete(
|
||||
f"{self.base_url}/datasets/unregister",
|
||||
params={
|
||||
"dataset_id": dataset_id,
|
||||
},
|
||||
headers={"Content-Type": "application/json"},
|
||||
timeout=60,
|
||||
)
|
||||
response.raise_for_status()
|
||||
|
||||
|
||||
async def run_main(host: str, port: int):
|
||||
client = DatasetsClient(f"http://{host}:{port}")
|
||||
|
|
|
|||
|
|
@ -64,3 +64,9 @@ class Datasets(Protocol):
|
|||
|
||||
@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: ...
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue