phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-15 06:37:58 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

refactor: replace default all-MiniLM-L6-v2 embedding model by nomic-embed-text-v1.5 in Llama Stack (#3183)

Browse source 
# What does this PR do?
<!-- Provide a short summary of what this PR does and why. Link to
relevant issues if applicable. -->
The purpose of this PR is to replace the Llama Stack's default embedding
model by nomic-embed-text-v1.5.

These are the key reasons why Llama Stack community decided to switch
from all-MiniLM-L6-v2 to nomic-embed-text-v1.5:
1. The training data for
[all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2#training-data)
includes a lot of data sets with various licensing terms, so it is
tricky to know when/whether it is appropriate to use this model for
commercial applications.
2. The model is not particularly competitive on major benchmarks. For
example, if you look at the [MTEB
Leaderboard](https://huggingface.co/spaces/mteb/leaderboard) and click
on Miscellaneous/BEIR to see English information retrieval accuracy, you
see that the top of the leaderboard is dominated by enormous models but
also that there are many, many models of relatively modest size whith
much higher Retrieval scores. If you want to look closely at the data, I
recommend clicking "Download Table" because it is easier to browse that
way.

More discussion info can be founded
[here](https://github.com/llamastack/llama-stack/issues/2418)

<!-- If resolving an issue, uncomment and update the line below -->
<!-- Closes #[issue-number] -->
Closes #2418 

## Test Plan
<!-- Describe the tests you ran to verify your changes with result
summaries. *Provide clear instructions so the plan can be easily
re-executed.* -->
1. Run `./scripts/unit-tests.sh`
2. Integration tests via CI wokrflow

---------

Signed-off-by: Sébastien Han <seb@redhat.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Francisco Arceo <arceofrancisco@gmail.com>
Co-authored-by: Sébastien Han <seb@redhat.com>
This commit is contained in:
IAN MILLER 2025-10-14 15:44:20 +01:00 • committed by GitHub
parent 0dbf79c328
commit 007efa6eb5
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
68 changed files with 32176 additions and 84 deletions
Download patch file Download diff file Expand all files Collapse all files

2
tests/unit/providers/vector_io/conftest.py
View file

@ -20,7 +20,7 @@ from llama_stack.providers.remote.vector_io.pgvector.config import PGVectorVecto
from llama_stack.providers.remote.vector_io.pgvector.pgvector import PGVectorIndex, PGVectorVectorIOAdapter
from llama_stack.providers.utils.kvstore.config import SqliteKVStoreConfig
EMBEDDING_DIMENSION = 384
EMBEDDING_DIMENSION = 768
COLLECTION_PREFIX = "test_collection"

2
tests/unit/providers/vector_io/test_faiss.py
View file

@ -39,7 +39,7 @@ def loop():
@pytest.fixture
def embedding_dimension():
return 384
return 768
@pytest.fixture