mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-07-16 18:08:09 +00:00
404708e99d
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. 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>
153 lines
4.2 KiB
YAML
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
|