mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-04 10:10:36 +00:00
feabcdd67b
as title
test plan:
```yaml
# custom-ollama-run.yaml
version: 2
image_name: starter
external_providers_dir: /.llama/providers.d
apis:
- inference
- vector_io
- files
- safety
- tool_runtime
- agents
providers:
inference:
# Single Ollama provider for all models
- 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:
persistence:
namespace: vector_io::faiss
backend: kv_default
files:
- provider_id: meta-reference-files
provider_type: inline::localfs
config:
storage_dir: /.llama/files
metadata_store:
table_name: files_metadata
backend: sql_default
safety:
- provider_id: llama-guard
provider_type: inline::llama-guard
config:
excluded_categories: []
tool_runtime:
- provider_id: rag-runtime
provider_type: inline::rag-runtime
agents:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
persistence:
agent_state:
namespace: agents
backend: kv_default
responses:
table_name: responses
backend: sql_default
max_write_queue_size: 10000
num_writers: 4
storage:
backends:
kv_default:
type: kv_sqlite
db_path: /.llama/kvstore.db
sql_default:
type: sql_sqlite
db_path: /.llama/sql_store.db
stores:
metadata:
namespace: registry
backend: kv_default
inference:
table_name: inference_store
backend: sql_default
max_write_queue_size: 10000
num_writers: 4
conversations:
table_name: openai_conversations
backend: sql_default
registered_resources:
models:
# All models use the same 'ollama' provider
- model_id: llama3.2-vision:latest
provider_id: ollama
provider_model_id: llama3.2-vision:latest
model_type: llm
- model_id: llama3.2:3b
provider_id: ollama
provider_model_id: llama3.2:3b
model_type: llm
# Embedding models
- model_id: nomic-embed-text-v2-moe
provider_id: ollama
provider_model_id: toshk0/nomic-embed-text-v2-moe:Q6_K
model_type: embedding
metadata:
embedding_dimension: 768
shields: []
vector_dbs: []
datasets: []
scoring_fns: []
benchmarks: []
tool_groups: []
server:
port: 8321
telemetry:
enabled: true
vector_stores:
default_provider_id: faiss
default_embedding_model:
provider_id: ollama
model_id: toshk0/nomic-embed-text-v2-moe:Q6_K
```
```bash
docker run
-it
--pull always
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT
-v ~/.llama:/root/.llama
-v $CUSTOM_RUN_CONFIG:/app/custom-run.yaml
-e RUN_CONFIG_PATH=/app/custom-run.yaml
-e OLLAMA_URL=http://host.docker.internal:11434/
llamastack/distribution-starter:0.3.0
--port $LLAMA_STACK_PORT
```
|
||
|---|---|---|
| .. | ||
| ci-tests | ||
| dell | ||
| meta-reference-gpu | ||
| nvidia | ||
| open-benchmark | ||
| postgres-demo | ||
| starter | ||
| starter-gpu | ||
| watsonx | ||
| __init__.py | ||
| template.py | ||