phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-12 20:12:33 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix test

Browse source 
Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>

updating structure of default

Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>

fix model id creation

Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
This commit is contained in:
Francisco Javier Arceo 2025-10-20 14:50:57 -04:00
parent b3addc94d1
commit 7ffd20d112
10 changed files with 119 additions and 62 deletions
Download patch file Download diff file Expand all files Collapse all files

28
docs/docs/building_applications/rag.mdx
View file

@ -87,20 +87,19 @@ Llama Stack provides OpenAI-compatible RAG capabilities through:
To enable automatic vector store creation without specifying embedding models, configure a default embedding model in your run.yaml like so:
```yaml
models:
- model_id: nomic-ai/nomic-embed-text-v1.5
provider_id: inline::sentence-transformers
metadata:
embedding_dimension: 768
vector_stores:
default_embedding_model_id: nomic-ai/nomic-embed-text-v1.5
default_provider_id: faiss
default_embedding_model:
provider_id: sentence-transformers
model_id: nomic-ai/nomic-embed-text-v1.5
```
With this configuration:
- `client.vector_stores.create()` works without requiring embedding model parameters
- The system automatically uses the default model and its embedding dimension for any newly created vector store
- The `vector_stores` section explicitly configures which embedding model to use as default
- `client.vector_stores.create()` works without requiring embedding model or provider parameters
- The system automatically uses the default vector store provider (`faiss`) when multiple providers are available
- The system automatically uses the default embedding model (`sentence-transformers/nomic-ai/nomic-embed-text-v1.5`) for any newly created vector store
- The `default_provider_id` specifies which vector storage backend to use
- The `default_embedding_model` specifies both the inference provider and model for embeddings
## Vector Store Operations
@ -109,14 +108,15 @@ With this configuration:
You can create vector stores with automatic or explicit embedding model selection:
```python
# Automatic - uses default configured embedding model
# Automatic - uses default configured embedding model and vector store provider
vs = client.vector_stores.create()
# Explicit - specify embedding model when you need a specific one
# Explicit - specify embedding model and/or provider when you need specific ones
vs = client.vector_stores.create(
extra_body={
"embedding_model": "nomic-ai/nomic-embed-text-v1.5",
"embedding_dimension": 768
"provider_id": "faiss", # Optional: specify vector store provider
"embedding_model": "sentence-transformers/nomic-ai/nomic-embed-text-v1.5",
"embedding_dimension": 768 # Optional: will be auto-detected if not provided
}
)
```