mirror of
https://github.com/NVIDIA/OpenShell.git
synced 2026-10-20 06:00:06 +08:00
John T. Myers
f4dc6be4b2
* refactor(inference): remove managed inference routes Closes #3172 Remove the inference route control plane, inference.local data path, built-in router crate, and SDK surface. Move inference workloads to explicitly imported provider profiles and native endpoints, with migration cleanup and updated tests and documentation. Signed-off-by: John Myers <9696606+johntmyers@users.noreply.github.com> * fix(policy): preserve alternate upstream isolation Restore the provider policy activation guard so legacy OpenAI and Anthropic providers configured for alternate base URLs do not grant egress to the built-in public vendor endpoints. Signed-off-by: John Myers <9696606+johntmyers@users.noreply.github.com> --------- Signed-off-by: John Myers <9696606+johntmyers@users.noreply.github.com>
30 lines
821 B
YAML
30 lines
821 B
YAML
# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
|
|
# SPDX-License-Identifier: Apache-2.0
|
|
|
|
id: nvidia-inference
|
|
display_name: NVIDIA Inference
|
|
description: NVIDIA API Catalog access for native Python clients
|
|
category: inference
|
|
# Informational only. This field does not enable routing or request transformation.
|
|
inference_capable: true
|
|
credentials:
|
|
- name: api_key
|
|
description: NVIDIA API key
|
|
env_vars: [NVIDIA_API_KEY]
|
|
required: true
|
|
auth_style: bearer
|
|
header_name: authorization
|
|
discovery:
|
|
credentials: [api_key]
|
|
endpoints:
|
|
- host: integrate.api.nvidia.com
|
|
port: 443
|
|
protocol: rest
|
|
access: read-write
|
|
enforcement: enforce
|
|
binaries:
|
|
- /usr/bin/python3
|
|
- /usr/bin/python3.13
|
|
- /usr/local/bin/python
|
|
- /sandbox/.venv/**
|