llama-stack-mirror/tests/external-provider/llama-stack-provider-ollama/run.yaml
Wen Zhou 214b1fe1ae refactor: set proper name for embedding all-minilm:l6-v2 model
- we are using all-minilm:l6-v2 but the model we download from ollama is all-minilm:latest
- even currently they are exactly the same model but if l12-v2 is updated, "latest" might not still valid.
- the only change in this PR is pin the model from ollama

Signed-off-by: Wen Zhou <wenzhou@redhat.com>
2025-07-04 18:04:39 +02:00

124 lines
3.3 KiB
YAML

version: 2
image_name: ollama
apis:
- agents
- datasetio
- eval
- inference
- safety
- scoring
- telemetry
- tool_runtime
- vector_io
providers:
inference:
- provider_id: ollama
provider_type: remote::ollama
config:
url: ${env.OLLAMA_URL:=http://localhost:11434}
vector_io:
- provider_id: faiss
provider_type: inline::faiss
config:
metadata_store:
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: {}
agents:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
agents_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:
metadata_store:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/ollama}/huggingface_datasetio.db
datasetio:
- provider_id: huggingface
provider_type: remote::huggingface
config:
metadata_store:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/ollama}/huggingface_datasetio.db
- provider_id: localfs
provider_type: inline::localfs
config:
metadata_store:
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: {}
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: 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
models:
- metadata: {}
model_id: ${env.INFERENCE_MODEL}
provider_id: custom_ollama
model_type: llm
- metadata:
embedding_dimension: 384
model_id: all-MiniLM-L6-v2
provider_id: custom_ollama
provider_model_id: all-minilm:l6-v2
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
external_providers_dir: ~/.llama/providers.d