llama-stack-mirror/llama_stack/templates/ollama/run.yaml
Ben Browning fa0b0c13d4
Some checks failed
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 2s
Integration Tests / test-matrix (http, 3.12, agents) (push) Failing after 11s
Integration Tests / test-matrix (http, 3.13, datasets) (push) Failing after 11s
Integration Tests / test-matrix (http, 3.12, providers) (push) Failing after 13s
Integration Tests / test-matrix (http, 3.13, providers) (push) Failing after 12s
Integration Tests / test-matrix (http, 3.12, inspect) (push) Failing after 17s
Integration Tests / test-matrix (http, 3.12, scoring) (push) Failing after 18s
Integration Tests / test-matrix (http, 3.13, inference) (push) Failing after 16s
Integration Tests / test-matrix (library, 3.12, datasets) (push) Failing after 11s
Integration Tests / test-matrix (http, 3.12, datasets) (push) Failing after 20s
Integration Tests / test-matrix (library, 3.12, providers) (push) Failing after 10s
Integration Tests / test-matrix (http, 3.12, vector_io) (push) Failing after 15s
Integration Tests / test-matrix (http, 3.12, inference) (push) Failing after 20s
Integration Tests / test-matrix (http, 3.12, post_training) (push) Failing after 15s
Integration Tests / test-matrix (http, 3.13, agents) (push) Failing after 14s
Integration Tests / test-matrix (library, 3.12, agents) (push) Failing after 11s
Integration Tests / test-matrix (http, 3.13, post_training) (push) Failing after 13s
Integration Tests / test-matrix (library, 3.12, inference) (push) Failing after 9s
Integration Tests / test-matrix (library, 3.12, post_training) (push) Failing after 13s
Integration Tests / test-matrix (http, 3.13, vector_io) (push) Failing after 14s
Integration Tests / test-matrix (http, 3.13, scoring) (push) Failing after 11s
Integration Tests / test-matrix (library, 3.12, scoring) (push) Failing after 9s
Integration Tests / test-matrix (library, 3.12, vector_io) (push) Failing after 9s
Integration Tests / test-matrix (http, 3.12, tool_runtime) (push) Failing after 18s
Integration Tests / test-matrix (library, 3.12, tool_runtime) (push) Failing after 7s
Integration Tests / test-matrix (http, 3.13, inspect) (push) Failing after 16s
Integration Tests / test-matrix (library, 3.12, inspect) (push) Failing after 12s
Integration Tests / test-matrix (http, 3.13, tool_runtime) (push) Failing after 14s
Integration Tests / test-matrix (library, 3.13, inspect) (push) Failing after 8s
Integration Tests / test-matrix (library, 3.13, agents) (push) Failing after 9s
Integration Tests / test-matrix (library, 3.13, inference) (push) Failing after 10s
Integration Tests / test-matrix (library, 3.13, datasets) (push) Failing after 10s
Test Llama Stack Build / generate-matrix (push) Successful in 7s
Python Package Build Test / build (3.12) (push) Failing after 4s
Test Llama Stack Build / build-custom-container-distribution (push) Failing after 5s
Integration Tests / test-matrix (library, 3.13, post_training) (push) Failing after 9s
Integration Tests / test-matrix (library, 3.13, tool_runtime) (push) Failing after 7s
Integration Tests / test-matrix (library, 3.13, providers) (push) Failing after 8s
Integration Tests / test-matrix (library, 3.13, scoring) (push) Failing after 10s
Integration Tests / test-matrix (library, 3.13, vector_io) (push) Failing after 8s
Update ReadTheDocs / update-readthedocs (push) Failing after 4s
Unit Tests / unit-tests (3.12) (push) Failing after 6s
Unit Tests / unit-tests (3.13) (push) Failing after 5s
Test Llama Stack Build / build (push) Failing after 6s
Test Llama Stack Build / build-single-provider (push) Failing after 1m10s
Test Llama Stack Build / build-ubi9-container-distribution (push) Failing after 1m8s
Python Package Build Test / build (3.13) (push) Failing after 1m6s
Test External Providers / test-external-providers (venv) (push) Failing after 1m4s
Pre-commit / pre-commit (push) Successful in 2m33s
fix: Ollama should be optional in starter distro (#2482)
# What does this PR do?

Our starter distro required Ollama to be running (and a large list of
models available in that Ollama) to successfully start. This adjusts
things so that Ollama does not have to be running to use the starter
template / distro.

To accomplish this, a few changes were needed:

* The Ollama provider is now configurable whether it raises an Exception
or just logs a warning when it cannot reach the Ollama server on
startup. The default is to raise an exception (same as previous
behavior), but in the starter template we adjust this to just log a
warning so that we can bring the stack up without needing a running
Ollama server.

* The starter template no longer specifies a default list of models for
Ollama, as any models specified there need to actually be pulled and
available in Ollama. Instead, it adds a new
`OLLAMA_INFERENCE_MODEL` environment variable where users can provide an
optional model to register with the Ollama provider on startup.
Additional models can also be registered via the typical
`models.register(...)` at runtime.

* The vLLM template was adjusted to also allow an optional
`VLLM_INFERENCE_MODEL` specified on startup, so that the behavior
between vLLM and Ollama was consistent here to make it easy to get up
and running quickly.

* The default vector store was changed from sqlite-vec to faiss.
sqlite-vec can enabled via setting the `ENABLE_SQLITE_VEC` environment
variable, like we do for chromadb and pgvector. This is due to
sqlite-vec not shipping proper arm64 binaries, like we previously fixed
in #1530 for the ollama distribution.

## Test Plan

With this change, the following scenarios now work with the starter
template that did not before:

* no Ollama running
* Ollama running but not all of the Llama models pulled locally
* Ollama running with a custom model registered on startup
* vLLM running with a custom model registered on startup
* running the starter template on linux/arm64, like when running
containers on Mac without rosetta emulation

---------

Signed-off-by: Ben Browning <bbrownin@redhat.com>
2025-06-25 15:54:00 +02:00

153 lines
4.2 KiB
YAML

version: '2'
image_name: ollama
apis:
- agents
- datasetio
- eval
- files
- inference
- post_training
- safety
- scoring
- telemetry
- tool_runtime
- vector_io
providers:
inference:
- provider_id: ollama
provider_type: remote::ollama
config:
url: ${env.OLLAMA_URL:http://localhost:11434}
raise_on_connect_error: true
vector_io:
- provider_id: faiss
provider_type: inline::faiss
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/faiss_store.db
safety:
- provider_id: llama-guard
provider_type: inline::llama-guard
config:
excluded_categories: []
agents:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
persistence_store:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/agents_store.db
responses_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/responses_store.db
telemetry:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/trace_store.db
eval:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/meta_reference_eval.db
datasetio:
- provider_id: huggingface
provider_type: remote::huggingface
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/huggingface_datasetio.db
- provider_id: localfs
provider_type: inline::localfs
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/localfs_datasetio.db
scoring:
- provider_id: basic
provider_type: inline::basic
config: {}
- provider_id: llm-as-judge
provider_type: inline::llm-as-judge
config: {}
- provider_id: braintrust
provider_type: inline::braintrust
config:
openai_api_key: ${env.OPENAI_API_KEY:}
files:
- provider_id: meta-reference-files
provider_type: inline::localfs
config:
storage_dir: ${env.FILES_STORAGE_DIR:~/.llama/distributions/ollama/files}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/files_metadata.db
post_training:
- provider_id: huggingface
provider_type: inline::huggingface
config:
checkpoint_format: huggingface
distributed_backend: null
device: cpu
tool_runtime:
- provider_id: brave-search
provider_type: remote::brave-search
config:
api_key: ${env.BRAVE_SEARCH_API_KEY:}
max_results: 3
- provider_id: tavily-search
provider_type: remote::tavily-search
config:
api_key: ${env.TAVILY_SEARCH_API_KEY:}
max_results: 3
- provider_id: rag-runtime
provider_type: inline::rag-runtime
config: {}
- provider_id: model-context-protocol
provider_type: remote::model-context-protocol
config: {}
- provider_id: wolfram-alpha
provider_type: remote::wolfram-alpha
config:
api_key: ${env.WOLFRAM_ALPHA_API_KEY:}
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: ollama
model_type: llm
- metadata:
embedding_dimension: 384
model_id: all-MiniLM-L6-v2
provider_id: ollama
provider_model_id: all-minilm:latest
model_type: embedding
shields: []
vector_dbs: []
datasets: []
scoring_fns: []
benchmarks: []
tool_groups:
- toolgroup_id: builtin::websearch
provider_id: tavily-search
- toolgroup_id: builtin::rag
provider_id: rag-runtime
- toolgroup_id: builtin::wolfram_alpha
provider_id: wolfram-alpha
server:
port: 8321