mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-22 08:17:18 +00:00
bd3c473208
Reverts llamastack/llama-stack#3871 This PR broke RAG (even from Responses -- there _is_ a dependency)
29 lines
747 B
YAML
29 lines
747 B
YAML
version: 2
|
|
distribution_spec:
|
|
description: Use NVIDIA NIM for running LLM inference, evaluation and safety
|
|
providers:
|
|
inference:
|
|
- provider_type: remote::nvidia
|
|
vector_io:
|
|
- provider_type: inline::faiss
|
|
safety:
|
|
- provider_type: remote::nvidia
|
|
agents:
|
|
- provider_type: inline::meta-reference
|
|
eval:
|
|
- provider_type: remote::nvidia
|
|
post_training:
|
|
- provider_type: remote::nvidia
|
|
datasetio:
|
|
- provider_type: inline::localfs
|
|
- provider_type: remote::nvidia
|
|
scoring:
|
|
- provider_type: inline::basic
|
|
tool_runtime:
|
|
- provider_type: inline::rag-runtime
|
|
files:
|
|
- provider_type: inline::localfs
|
|
image_type: venv
|
|
additional_pip_packages:
|
|
- aiosqlite
|
|
- sqlalchemy[asyncio]
|