phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

add embedding model by default to distribution templates (#617)

Browse source 
# What does this PR do?
Adds the sentence transformer provider and the `all-MiniLM-L6-v2`
embedding model to the default models to register in the run.yaml for
all providers.

## Test Plan
llama stack build --template together --image-type conda
llama stack run
~/.llama/distributions/llamastack-together/together-run.yaml
This commit is contained in:
Dinesh Yeduguru 2024-12-13 12:48:00 -08:00 • committed by GitHub
parent e893b22868
commit 516e1a3e59
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
41 changed files with 473 additions and 64 deletions
Download patch file Download diff file Expand all files Collapse all files

24
llama_stack/templates/remote-vllm/vllm.py
View file

@ -6,7 +6,12 @@
from pathlib import Path
from llama_stack.apis.models.models import ModelType
from llama_stack.distribution.datatypes import ModelInput, Provider, ShieldInput
from llama_stack.providers.inline.inference.sentence_transformers import (
SentenceTransformersInferenceConfig,
)
from llama_stack.providers.inline.memory.faiss.config import FaissImplConfig
from llama_stack.providers.remote.inference.vllm import VLLMInferenceAdapterConfig
from llama_stack.templates.template import DistributionTemplate, RunConfigSettings
@ -28,6 +33,11 @@ def get_distribution_template() -> DistributionTemplate:
url="${env.VLLM_URL}",
),
)
embedding_provider = Provider(
provider_id="sentence-transformers",
provider_type="inline::sentence-transformers",
config=SentenceTransformersInferenceConfig.sample_run_config(),
)
memory_provider = Provider(
provider_id="faiss",
provider_type="inline::faiss",
@ -42,6 +52,14 @@ def get_distribution_template() -> DistributionTemplate:
model_id="${env.SAFETY_MODEL}",
provider_id="vllm-safety",
)
embedding_model = ModelInput(
model_id="all-MiniLM-L6-v2",
provider_id="sentence-transformers",
model_type=ModelType.embedding,
metadata={
"embedding_dimension": 384,
},
)
return DistributionTemplate(
name=name,
@ -53,10 +71,10 @@ def get_distribution_template() -> DistributionTemplate:
run_configs={
"run.yaml": RunConfigSettings(
provider_overrides={
"inference": [inference_provider],
"inference": [inference_provider, embedding_provider],
"memory": [memory_provider],
},
default_models=[inference_model],
default_models=[inference_model, embedding_model],
),
"run-with-safety.yaml": RunConfigSettings(
provider_overrides={
@ -69,12 +87,14 @@ def get_distribution_template() -> DistributionTemplate:
url="${env.SAFETY_VLLM_URL}",
),
),
embedding_provider,
],
"memory": [memory_provider],
},
default_models=[
inference_model,
safety_model,
embedding_model,
],
default_shields=[ShieldInput(shield_id="${env.SAFETY_MODEL}")],
),