forked from phoenix-oss/llama-stack-mirror
2603f10f95
# What does this PR do? * Added support postgresql inference store * Added 'oracle' template that demos how to config postgresql stores (except for telemetry, which is not supported currently) ## Test Plan llama stack build --template oracle --image-type conda --run LLAMA_STACK_CONFIG=http://localhost:8321 pytest -s -v tests/integration/ --text-model accounts/fireworks/models/llama-v3p3-70b-instruct -k 'inference_store'
29 lines
596 B
YAML
29 lines
596 B
YAML
version: '2'
|
|
distribution_spec:
|
|
description: Use NVIDIA NIM for running LLM inference, evaluation and safety
|
|
providers:
|
|
inference:
|
|
- remote::nvidia
|
|
vector_io:
|
|
- inline::faiss
|
|
safety:
|
|
- remote::nvidia
|
|
agents:
|
|
- inline::meta-reference
|
|
telemetry:
|
|
- inline::meta-reference
|
|
eval:
|
|
- remote::nvidia
|
|
post_training:
|
|
- remote::nvidia
|
|
datasetio:
|
|
- inline::localfs
|
|
- remote::nvidia
|
|
scoring:
|
|
- inline::basic
|
|
tool_runtime:
|
|
- inline::rag-runtime
|
|
image_type: conda
|
|
additional_pip_packages:
|
|
- aiosqlite
|
|
- sqlalchemy[asyncio]
|