mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-28 19:04:19 +00:00
a062723d03
# What does this PR do?
currently the `inspect` API for providers is really a `list` API. Create
a new `providers` API which has a GET `providers/{provider_id}` inspect
API
which returns "user friendly" configuration to the end user. Also add a
GET `/providers` endpoint which returns the list of providers as
`inspect/providers` does today.
This API follows CRUD and is more intuitive/RESTful.
This work is part of the RFC at
https://github.com/meta-llama/llama-stack/pull/1359
sensitive fields are redacted using `redact_sensetive_fields` on the
server side before returning a response:
<img width="456" alt="Screenshot 2025-03-13 at 4 40 21 PM"
src="https://github.com/user-attachments/assets/9465c221-2a26-42f8-a08a-6ac4a9fecce8"
/>
## Test Plan
using https://github.com/meta-llama/llama-stack-client-python/pull/181 a
user is able to to run the following:
`llama stack build --template ollama --image-type venv`
`llama stack run --image-type venv
~/.llama/distributions/ollama/ollama-run.yaml`
`llama-stack-client providers inspect ollama`
<img width="378" alt="Screenshot 2025-03-13 at 4 39 35 PM"
src="https://github.com/user-attachments/assets/8273d05d-8bc3-44c6-9e4b-ef95e48d5466"
/>
also, was able to run the new test_list integration test locally with
ollama:
<img width="1509" alt="Screenshot 2025-03-13 at 11 03 40 AM"
src="https://github.com/user-attachments/assets/9b9db166-f02f-45b0-86a4-306d85149bc8"
/>
Signed-off-by: Charlie Doern <cdoern@redhat.com>
69 lines
1.9 KiB
Python
69 lines
1.9 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.
|
|
|
|
import importlib
|
|
from typing import Dict, List
|
|
|
|
from pydantic import BaseModel
|
|
|
|
from llama_stack.providers.datatypes import Api, ProviderSpec
|
|
|
|
|
|
def stack_apis() -> List[Api]:
|
|
return list(Api)
|
|
|
|
|
|
class AutoRoutedApiInfo(BaseModel):
|
|
routing_table_api: Api
|
|
router_api: Api
|
|
|
|
|
|
def builtin_automatically_routed_apis() -> List[AutoRoutedApiInfo]:
|
|
return [
|
|
AutoRoutedApiInfo(
|
|
routing_table_api=Api.models,
|
|
router_api=Api.inference,
|
|
),
|
|
AutoRoutedApiInfo(
|
|
routing_table_api=Api.shields,
|
|
router_api=Api.safety,
|
|
),
|
|
AutoRoutedApiInfo(
|
|
routing_table_api=Api.vector_dbs,
|
|
router_api=Api.vector_io,
|
|
),
|
|
AutoRoutedApiInfo(
|
|
routing_table_api=Api.datasets,
|
|
router_api=Api.datasetio,
|
|
),
|
|
AutoRoutedApiInfo(
|
|
routing_table_api=Api.scoring_functions,
|
|
router_api=Api.scoring,
|
|
),
|
|
AutoRoutedApiInfo(
|
|
routing_table_api=Api.benchmarks,
|
|
router_api=Api.eval,
|
|
),
|
|
AutoRoutedApiInfo(
|
|
routing_table_api=Api.tool_groups,
|
|
router_api=Api.tool_runtime,
|
|
),
|
|
]
|
|
|
|
|
|
def providable_apis() -> List[Api]:
|
|
routing_table_apis = {x.routing_table_api for x in builtin_automatically_routed_apis()}
|
|
return [api for api in Api if api not in routing_table_apis and api != Api.inspect and api != Api.providers]
|
|
|
|
|
|
def get_provider_registry() -> Dict[Api, Dict[str, ProviderSpec]]:
|
|
ret = {}
|
|
for api in providable_apis():
|
|
name = api.name.lower()
|
|
module = importlib.import_module(f"llama_stack.providers.registry.{name}")
|
|
ret[api] = {a.provider_type: a for a in module.available_providers()}
|
|
|
|
return ret
|