mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-07-24 13:19:54 +00:00
47 lines
1.2 KiB
YAML
47 lines
1.2 KiB
YAML
version: '2'
|
|
distribution_spec:
|
|
description: Use (an external) Ollama server for running LLM inference
|
|
providers:
|
|
inference:
|
|
- remote::ollama
|
|
vector_io:
|
|
- remote::chromadb
|
|
safety:
|
|
- inline::llama-guard
|
|
agents:
|
|
- inline::meta-reference
|
|
telemetry:
|
|
- inline::meta-reference
|
|
eval:
|
|
- inline::meta-reference
|
|
datasetio:
|
|
- inline::localfs
|
|
scoring:
|
|
- inline::basic
|
|
- inline::llm-as-judge
|
|
tool_runtime:
|
|
- remote::brave-search
|
|
- remote::tavily-search
|
|
- inline::rag-runtime
|
|
- remote::model-context-protocol
|
|
- remote::wolfram-alpha
|
|
metadata_store:
|
|
type: sqlite
|
|
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/registry.db
|
|
inference_store:
|
|
type: sqlite
|
|
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/inference_store.db
|
|
models:
|
|
- metadata: {}
|
|
model_id: ${env.INFERENCE_MODEL}
|
|
provider_id: remote::ollama
|
|
model_type: llm
|
|
- metadata:
|
|
embedding_dimension: 384
|
|
model_id: all-MiniLM-L6-v2
|
|
provider_id: remote::ollama
|
|
provider_model_id: all-minilm:latest
|
|
model_type: embedding
|
|
image_type: container
|
|
additional_pip_packages:
|
|
- sqlalchemy[asyncio]
|