phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2026-01-03 21:52:17 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'refs/heads/main' into preprocessors

Browse source 
# Conflicts:
#	llama_stack/distribution/routers/routers.py
#	llama_stack/templates/ollama/build.yaml
#	llama_stack/templates/ollama/run-with-safety.yaml
#	llama_stack/templates/ollama/run.yaml
#	llama_stack/templates/remote-vllm/build.yaml
#	llama_stack/templates/remote-vllm/run-with-safety.yaml
#	llama_stack/templates/remote-vllm/run.yaml
#	llama_stack/templates/together/build.yaml
#	llama_stack/templates/together/run-with-safety.yaml
#	llama_stack/templates/together/run.yaml
This commit is contained in:
ilya-kolchinsky 2025-03-07 16:20:30 +01:00
commit 6b9f673fdb
313 changed files with 181388 additions and 7064 deletions
Download patch file Download diff file Expand all files Collapse all files

28
llama_stack/templates/sambanova/sambanova.py
View file

@ -12,8 +12,11 @@ from llama_stack.distribution.datatypes import (
ShieldInput,
ToolGroupInput,
)
from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig
from llama_stack.providers.remote.inference.sambanova import SambaNovaImplConfig
from llama_stack.providers.remote.inference.sambanova.models import MODEL_ENTRIES
from llama_stack.providers.remote.vector_io.chroma.config import ChromaVectorIOConfig
from llama_stack.providers.remote.vector_io.pgvector.config import PGVectorVectorIOConfig
from llama_stack.templates.template import DistributionTemplate, RunConfigSettings, get_model_registry
@ -40,6 +43,30 @@ def get_distribution_template() -> DistributionTemplate:
config=SambaNovaImplConfig.sample_run_config(),
)
vector_io_providers = [
Provider(
provider_id="faiss",
provider_type="inline::faiss",
config=FaissVectorIOConfig.sample_run_config(
__distro_dir__=f"~/.llama/distributions/{name}",
),
),
Provider(
provider_id="${env.ENABLE_CHROMADB+chromadb}",
provider_type="remote::chromadb",
config=ChromaVectorIOConfig.sample_run_config(url="${env.CHROMADB_URL:}"),
),
Provider(
provider_id="${env.ENABLE_PGVECTOR+pgvector}",
provider_type="remote::pgvector",
config=PGVectorVectorIOConfig.sample_run_config(
db="${env.PGVECTOR_DB:}",
user="${env.PGVECTOR_USER:}",
password="${env.PGVECTOR_PASSWORD:}",
),
),
]
available_models = {
name: MODEL_ENTRIES,
}
@ -81,6 +108,7 @@ def get_distribution_template() -> DistributionTemplate:
"run.yaml": RunConfigSettings(
provider_overrides={
"inference": [inference_provider],
"vector_io": vector_io_providers,
},
default_models=default_models,
default_shields=[ShieldInput(shield_id="meta-llama/Llama-Guard-3-8B")],