phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-17 15:32:36 +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

24
llama_stack/templates/ollama/ollama.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.ollama import OllamaImplConfig
from llama_stack.templates.template import DistributionTemplate, RunConfigSettings
@ -29,6 +34,11 @@ def get_distribution_template() -> DistributionTemplate:
provider_type="remote::ollama",
config=OllamaImplConfig.sample_run_config(),
)
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",
@ -43,6 +53,14 @@ def get_distribution_template() -> DistributionTemplate:
model_id="${env.SAFETY_MODEL}",
provider_id="ollama",
)
embedding_model = ModelInput(
model_id="all-MiniLM-L6-v2",
provider_id="sentence-transformers",
model_type=ModelType.embedding,
metadata={
"embedding_dim": 384,
},
)
return DistributionTemplate(
name=name,
@ -55,21 +73,23 @@ def get_distribution_template() -> DistributionTemplate:
run_configs={
"run.yaml": RunConfigSettings(
provider_overrides={
"inference": [inference_provider],
"inference": [inference_provider, embedding_provider],
"memory": [memory_provider],
},
default_models=[inference_model],
default_models=[inference_model, embedding_model],
),
"run-with-safety.yaml": RunConfigSettings(
provider_overrides={
"inference": [
inference_provider,
embedding_provider,
],
"memory": [memory_provider],
},
default_models=[
inference_model,
safety_model,
embedding_model,
],
default_shields=[ShieldInput(shield_id="${env.SAFETY_MODEL}")],
),