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

[memory refactor][5/n] Migrate all vector_io providers (#835)

Browse source 
See https://github.com/meta-llama/llama-stack/issues/827 for the broader
design.

This PR finishes off all the stragglers and migrates everything to the
new naming.
This commit is contained in:
Ashwin Bharambe 2025-01-22 10:17:59 -08:00 • committed by GitHub
parent 63f37f9b7c
commit c9e5578151
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
78 changed files with 504 additions and 623 deletions
Download patch file Download diff file Expand all files Collapse all files

8
llama_stack/templates/vllm-gpu/vllm.py
View file

@ -10,7 +10,7 @@ from llama_stack.providers.inline.inference.sentence_transformers import (
SentenceTransformersInferenceConfig,
)
from llama_stack.providers.inline.inference.vllm import VLLMConfig
from llama_stack.providers.inline.memory.faiss.config import FaissImplConfig
from llama_stack.providers.inline.vector_io.faiss.config import FaissImplConfig
from llama_stack.templates.template import (
DistributionTemplate,
RunConfigSettings,
@ -21,7 +21,7 @@ from llama_stack.templates.template import (
def get_distribution_template() -> DistributionTemplate:
providers = {
"inference": ["inline::vllm"],
"memory": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
"vector_io": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
"safety": ["inline::llama-guard"],
"agents": ["inline::meta-reference"],
"telemetry": ["inline::meta-reference"],
@ -43,7 +43,7 @@ def get_distribution_template() -> DistributionTemplate:
provider_type="inline::vllm",
config=VLLMConfig.sample_run_config(),
)
memory_provider = Provider(
vector_io_provider = Provider(
provider_id="faiss",
provider_type="inline::faiss",
config=FaissImplConfig.sample_run_config(f"distributions/{name}"),
@ -93,7 +93,7 @@ def get_distribution_template() -> DistributionTemplate:
"run.yaml": RunConfigSettings(
provider_overrides={
"inference": [inference_provider, embedding_provider],
"memory": [memory_provider],
"vector_io": [vector_io_provider],
},
default_models=[inference_model, embedding_model],
default_tool_groups=default_tool_groups,