phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 12:07:34 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

docs: improve vector store config documentation and fix test isolation

Browse source
This commit is contained in:
skamenan7 2025-08-13 17:13:57 -04:00
parent ecb06a0384
commit 534c227058
3 changed files with 24 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

19
docs/source/distributions/configuration.md
View file

@ -801,13 +801,26 @@ shields:
...
```
### Global Vector-Store Defaults
## Global Vector Store Defaults
You can provide a *stack-level* default embedding model that will be used whenever a new vector-store is created and the caller does **not** specify an `embedding_model` parameter.
You can provide a stack-level default embedding model that will be used whenever a new vector store is created and the caller does not specify an `embedding_model` parameter.
Add a top-level block next to `models:` and `vector_io:` in your build/run YAML:
Add a top-level `vector_store_config` block at the root of your build/run YAML, alongside other root-level keys such as `models`, `shields`, `server`, and `metadata_store`:
```yaml
# ... other configuration sections ...
metadata_store:
namespace: null
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/ollama}/registry.db
models:
- metadata: {}
model_id: ${env.INFERENCE_MODEL}
provider_id: ollama
provider_model_id: null
shields: []
server:
port: 8321
vector_store_config:
default_embedding_model: ${env.LLAMA_STACK_DEFAULT_EMBEDDING_MODEL:=all-MiniLM-L6-v2}
# optional - if omitted, defaults to 384