mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-06 18:40:57 +00:00
chore: Updating how default embedding model is set in stack (#3818)
# What does this PR do?
Refactor setting default vector store provider and embedding model to
use an optional `vector_stores` config in the `StackRunConfig` and clean
up code to do so (had to add back in some pieces of VectorDB). Also
added remote Qdrant and Weaviate to starter distro (based on other PR
where inference providers were added for UX).
New config is simply (default for Starter distro):
```yaml
vector_stores:
default_provider_id: faiss
default_embedding_model:
provider_id: sentence-transformers
model_id: nomic-ai/nomic-embed-text-v1.5
```
## Test Plan
CI and Unit tests.
---------
Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
This commit is contained in:
parent
2c43285e22
commit
48581bf651
48 changed files with 973 additions and 818 deletions
|
|
@ -29,6 +29,7 @@ from llama_stack.apis.scoring_functions import ScoringFunctions
|
|||
from llama_stack.apis.shields import Shields
|
||||
from llama_stack.apis.telemetry import Telemetry
|
||||
from llama_stack.apis.tools import ToolGroups, ToolRuntime
|
||||
from llama_stack.apis.vector_dbs import VectorDBs
|
||||
from llama_stack.apis.vector_io import VectorIO
|
||||
from llama_stack.apis.version import LLAMA_STACK_API_V1ALPHA
|
||||
from llama_stack.core.client import get_client_impl
|
||||
|
|
@ -81,6 +82,7 @@ def api_protocol_map(external_apis: dict[Api, ExternalApiSpec] | None = None) ->
|
|||
Api.inspect: Inspect,
|
||||
Api.batches: Batches,
|
||||
Api.vector_io: VectorIO,
|
||||
Api.vector_dbs: VectorDBs,
|
||||
Api.models: Models,
|
||||
Api.safety: Safety,
|
||||
Api.shields: Shields,
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue