phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-06-30 03:44:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

chore: move embedding deps to RAG tool where they are needed (#1210)

Browse source 
`EMBEDDING_DEPS` were wrongly associated with `vector_io` providers.
They are needed by
https://github.com/meta-llama/llama-stack/blob/main/llama_stack/providers/utils/memory/vector_store.py#L142
and related code and is used by the RAG tool and as such should only be
needed by the `inline::rag-runtime` provider.
This commit is contained in:
Ashwin Bharambe 2025-02-21 11:33:41 -08:00 • committed by GitHub
parent 11697f85c5
commit 992f865b2e
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
34 changed files with 85 additions and 132 deletions
Download patch file Download diff file Expand all files Collapse all files

33
llama_stack/templates/ollama/ollama.py
View file

@ -13,10 +13,6 @@ from llama_stack.distribution.datatypes import (
ShieldInput,
ToolGroupInput,
)
from llama_stack.providers.inline.inference.sentence_transformers import (
SentenceTransformersInferenceConfig,
)
from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig
from llama_stack.providers.inline.vector_io.sqlite_vec.config import SQLiteVectorIOConfig
from llama_stack.providers.remote.inference.ollama import OllamaImplConfig
from llama_stack.templates.template import DistributionTemplate, RunConfigSettings
@ -25,7 +21,7 @@ from llama_stack.templates.template import DistributionTemplate, RunConfigSettin
def get_distribution_template() -> DistributionTemplate:
providers = {
"inference": ["remote::ollama"],
"vector_io": ["inline::faiss", "inline::sqlite_vec", "remote::chromadb", "remote::pgvector"],
"vector_io": ["inline::sqlite-vec", "remote::chromadb", "remote::pgvector"],
"safety": ["inline::llama-guard"],
"agents": ["inline::meta-reference"],
"telemetry": ["inline::meta-reference"],
@ -45,19 +41,9 @@ 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(),
)
vector_io_provider_faiss = Provider(
provider_id="faiss",
provider_type="inline::faiss",
config=FaissVectorIOConfig.sample_run_config(f"distributions/{name}"),
)
vector_io_provider_sqlite = Provider(
provider_id="sqlite_vec",
provider_type="inline::sqlite_vec",
provider_id="sqlite-vec",
provider_type="inline::sqlite-vec",
config=SQLiteVectorIOConfig.sample_run_config(f"distributions/{name}"),
)
@ -104,19 +90,16 @@ def get_distribution_template() -> DistributionTemplate:
run_configs={
"run.yaml": RunConfigSettings(
provider_overrides={
"inference": [inference_provider, embedding_provider],
"vector_io": [vector_io_provider_faiss, vector_io_provider_sqlite],
"inference": [inference_provider],
"vector_io": [vector_io_provider_sqlite],
},
default_models=[inference_model, embedding_model],
default_models=[inference_model],
default_tool_groups=default_tool_groups,
),
"run-with-safety.yaml": RunConfigSettings(
provider_overrides={
"inference": [
inference_provider,
embedding_provider,
],
"vector_io": [vector_io_provider_faiss, vector_io_provider_faiss],
"inference": [inference_provider],
"vector_io": [vector_io_provider_sqlite],
"safety": [
Provider(
provider_id="llama-guard",