llama-stack-mirror/llama_stack/distributions/starter/build.yaml
Sébastien Han 046d85fa79
feat: ability to use postgres as store for starter distro
The starter distribution now comes with all the required packages to
support persistent stores—like the agent store, metadata, and
inference—using PostgreSQL.  We’ve added a new run YAML file,
run-with-postgres-store.yaml, to make this setup easy. The file is
included in the container image, so users can simply override the
entrypoint to use the Postgres-specific config.  The documentation has
been updated with instructions on how to do that.

Closes: #2619
Signed-off-by: Sébastien Han <seb@redhat.com>
2025-09-16 15:37:26 +02:00

61 lines
1.9 KiB
YAML

version: 2
distribution_spec:
description: Quick start template for running Llama Stack with several popular providers.
This distribution is intended for CPU-only environments.
providers:
inference:
- provider_type: remote::cerebras
- provider_type: remote::ollama
- provider_type: remote::vllm
- provider_type: remote::tgi
- provider_type: remote::fireworks
- provider_type: remote::together
- provider_type: remote::bedrock
- provider_type: remote::nvidia
- provider_type: remote::openai
- provider_type: remote::anthropic
- provider_type: remote::gemini
- provider_type: remote::vertexai
- provider_type: remote::groq
- provider_type: remote::sambanova
- provider_type: remote::azure
- provider_type: inline::sentence-transformers
vector_io:
- provider_type: inline::faiss
- provider_type: inline::sqlite-vec
- provider_type: inline::milvus
- provider_type: remote::chromadb
- provider_type: remote::pgvector
files:
- provider_type: inline::localfs
safety:
- provider_type: inline::llama-guard
- provider_type: inline::code-scanner
agents:
- provider_type: inline::meta-reference
telemetry:
- provider_type: inline::meta-reference
post_training:
- provider_type: inline::torchtune-cpu
eval:
- provider_type: inline::meta-reference
datasetio:
- provider_type: remote::huggingface
- provider_type: inline::localfs
scoring:
- provider_type: inline::basic
- provider_type: inline::llm-as-judge
- provider_type: inline::braintrust
tool_runtime:
- provider_type: remote::brave-search
- provider_type: remote::tavily-search
- provider_type: inline::rag-runtime
- provider_type: remote::model-context-protocol
batches:
- provider_type: inline::reference
image_type: venv
additional_pip_packages:
- aiosqlite
- asyncpg
- psycopg2-binary
- sqlalchemy[asyncio]