phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-17 20:39:47 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

add embedding model by default

Browse source
This commit is contained in:
Dinesh Yeduguru 2024-12-12 14:46:51 -08:00
parent 2a9b13dd52
commit 2f88006bd0
43 changed files with 446 additions and 85 deletions
Download patch file Download diff file Expand all files Collapse all files

27
llama_stack/templates/meta-reference-quantized-gpu/meta_reference.py
View file

@ -6,17 +6,25 @@
from pathlib import Path
from llama_stack.apis.models.models import ModelType
from llama_stack.distribution.datatypes import ModelInput, Provider
from llama_stack.providers.inline.inference.meta_reference import (
MetaReferenceQuantizedInferenceConfig,
)
from llama_stack.providers.inline.inference.sentence_transformers import (
SentenceTransformersInferenceConfig,
)
from llama_stack.providers.inline.memory.faiss.config import FaissImplConfig
from llama_stack.templates.template import DistributionTemplate, RunConfigSettings
def get_distribution_template() -> DistributionTemplate:
providers = {
"inference": ["inline::meta-reference-quantized"],
"inference": [
"inline::meta-reference-quantized",
"remote::sentence-transformers",
],
"memory": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
"safety": ["inline::llama-guard"],
"agents": ["inline::meta-reference"],
@ -34,6 +42,11 @@ def get_distribution_template() -> DistributionTemplate:
checkpoint_dir="${env.INFERENCE_CHECKPOINT_DIR:null}",
),
)
embedding_provider = Provider(
provider_id="sentence-transformers",
provider_type="inline::sentence-transformers",
config=SentenceTransformersInferenceConfig.sample_run_config(),
)
memory_provider = Provider(
provider_id="faiss",
provider_type="inline::faiss",
@ -44,6 +57,14 @@ def get_distribution_template() -> DistributionTemplate:
model_id="${env.INFERENCE_MODEL}",
provider_id="meta-reference-inference",
)
embedding_model = ModelInput(
model_id="all-MiniLM-L6-v2",
provider_id="sentence-transformers",
model_type=ModelType.embedding,
metadata={
"embedding_dim": 384,
},
)
return DistributionTemplate(
name=name,
distro_type="self_hosted",
@ -54,10 +75,10 @@ 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_config_env_vars={