phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-06-28 02:53:30 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

chore: Consistent naming for VectorIO providers (#1023)

Browse source 
# What does this PR do?

This changes all VectorIO providers classes to follow the pattern
`<ProviderName>VectorIOConfig` and `<ProviderName>VectorIOAdapter`. All
API endpoints for VectorIOs are currently consistent with `/vector-io`.

Note that API endpoint for VectorDB stay unchanged as `/vector-dbs`. 

## Test Plan

I don't have a way to test all providers. This is a simple renaming so
things should work as expected.

---------

Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
This commit is contained in:
Yuan Tang 2025-02-13 13:15:49 -05:00 • committed by GitHub
parent e4a1579e63
commit 8ff27b58fa
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
34 changed files with 85 additions and 86 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama_stack/templates/bedrock/bedrock.py
View file

@ -10,7 +10,7 @@ from llama_models.sku_list import all_registered_models
from llama_stack.apis.models import ModelInput
from llama_stack.distribution.datatypes import Provider, ToolGroupInput
from llama_stack.providers.inline.vector_io.faiss.config import FaissImplConfig
from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig
from llama_stack.providers.remote.inference.bedrock.bedrock import MODEL_ALIASES
from llama_stack.templates.template import DistributionTemplate, RunConfigSettings
@ -37,7 +37,7 @@ def get_distribution_template() -> DistributionTemplate:
vector_io_provider = Provider(
provider_id="faiss",
provider_type="inline::faiss",
config=FaissImplConfig.sample_run_config(f"distributions/{name}"),
config=FaissVectorIOConfig.sample_run_config(f"distributions/{name}"),
)
core_model_to_hf_repo = {m.descriptor(): m.huggingface_repo for m in all_registered_models()}

4
llama_stack/templates/cerebras/cerebras.py
View file

@ -13,7 +13,7 @@ from llama_stack.distribution.datatypes import ModelInput, Provider, ToolGroupIn
from llama_stack.providers.inline.inference.sentence_transformers import (
SentenceTransformersInferenceConfig,
)
from llama_stack.providers.inline.vector_io.faiss.config import FaissImplConfig
from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig
from llama_stack.providers.remote.inference.cerebras import CerebrasImplConfig
from llama_stack.providers.remote.inference.cerebras.cerebras import model_aliases
from llama_stack.templates.template import DistributionTemplate, RunConfigSettings
@ -69,7 +69,7 @@ def get_distribution_template() -> DistributionTemplate:
vector_io_provider = Provider(
provider_id="faiss",
provider_type="inline::faiss",
config=FaissImplConfig.sample_run_config(f"distributions/{name}"),
config=FaissVectorIOConfig.sample_run_config(f"distributions/{name}"),
)
default_tool_groups = [
ToolGroupInput(

4
llama_stack/templates/fireworks/fireworks.py
View file

@ -18,7 +18,7 @@ from llama_stack.distribution.datatypes import (
from llama_stack.providers.inline.inference.sentence_transformers import (
SentenceTransformersInferenceConfig,
)
from llama_stack.providers.inline.vector_io.faiss.config import FaissImplConfig
from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig
from llama_stack.providers.remote.inference.fireworks import FireworksImplConfig
from llama_stack.providers.remote.inference.fireworks.fireworks import MODEL_ALIASES
from llama_stack.templates.template import DistributionTemplate, RunConfigSettings
@ -58,7 +58,7 @@ def get_distribution_template() -> DistributionTemplate:
vector_io_provider = Provider(
provider_id="faiss",
provider_type="inline::faiss",
config=FaissImplConfig.sample_run_config(f"distributions/{name}"),
config=FaissVectorIOConfig.sample_run_config(f"distributions/{name}"),
)
core_model_to_hf_repo = {m.descriptor(): m.huggingface_repo for m in all_registered_models()}

4
llama_stack/templates/hf-endpoint/hf_endpoint.py
View file

@ -14,7 +14,7 @@ from llama_stack.distribution.datatypes import (
from llama_stack.providers.inline.inference.sentence_transformers import (
SentenceTransformersInferenceConfig,
)
from llama_stack.providers.inline.vector_io.faiss.config import FaissImplConfig
from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig
from llama_stack.providers.remote.inference.tgi import InferenceEndpointImplConfig
from llama_stack.templates.template import DistributionTemplate, RunConfigSettings
@ -51,7 +51,7 @@ def get_distribution_template() -> DistributionTemplate:
vector_io_provider = Provider(
provider_id="faiss",
provider_type="inline::faiss",
config=FaissImplConfig.sample_run_config(f"distributions/{name}"),
config=FaissVectorIOConfig.sample_run_config(f"distributions/{name}"),
)
inference_model = ModelInput(

4
llama_stack/templates/hf-serverless/hf_serverless.py
View file

@ -14,7 +14,7 @@ from llama_stack.distribution.datatypes import (
from llama_stack.providers.inline.inference.sentence_transformers import (
SentenceTransformersInferenceConfig,
)
from llama_stack.providers.inline.vector_io.faiss.config import FaissImplConfig
from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig
from llama_stack.providers.remote.inference.tgi import InferenceAPIImplConfig
from llama_stack.templates.template import DistributionTemplate, RunConfigSettings
@ -52,7 +52,7 @@ def get_distribution_template() -> DistributionTemplate:
vector_io_provider = Provider(
provider_id="faiss",
provider_type="inline::faiss",
config=FaissImplConfig.sample_run_config(f"distributions/{name}"),
config=FaissVectorIOConfig.sample_run_config(f"distributions/{name}"),
)
inference_model = ModelInput(

4
llama_stack/templates/meta-reference-gpu/meta_reference.py
View file

@ -19,7 +19,7 @@ from llama_stack.providers.inline.inference.meta_reference import (
from llama_stack.providers.inline.inference.sentence_transformers import (
SentenceTransformersInferenceConfig,
)
from llama_stack.providers.inline.vector_io.faiss.config import FaissImplConfig
from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig
from llama_stack.templates.template import DistributionTemplate, RunConfigSettings
@ -58,7 +58,7 @@ def get_distribution_template() -> DistributionTemplate:
vector_io_provider = Provider(
provider_id="faiss",
provider_type="inline::faiss",
config=FaissImplConfig.sample_run_config(f"distributions/{name}"),
config=FaissVectorIOConfig.sample_run_config(f"distributions/{name}"),
)
inference_model = ModelInput(

4
llama_stack/templates/meta-reference-quantized-gpu/meta_reference.py
View file

@ -14,7 +14,7 @@ from llama_stack.providers.inline.inference.meta_reference import (
from llama_stack.providers.inline.inference.sentence_transformers import (
SentenceTransformersInferenceConfig,
)
from llama_stack.providers.inline.vector_io.faiss.config import FaissImplConfig
from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig
from llama_stack.templates.template import DistributionTemplate, RunConfigSettings
@ -67,7 +67,7 @@ def get_distribution_template() -> DistributionTemplate:
vector_io_provider = Provider(
provider_id="faiss",
provider_type="inline::faiss",
config=FaissImplConfig.sample_run_config(f"distributions/{name}"),
config=FaissVectorIOConfig.sample_run_config(f"distributions/{name}"),
)
inference_model = ModelInput(

4
llama_stack/templates/ollama/ollama.py
View file

@ -16,7 +16,7 @@ from llama_stack.distribution.datatypes import (
from llama_stack.providers.inline.inference.sentence_transformers import (
SentenceTransformersInferenceConfig,
)
from llama_stack.providers.inline.vector_io.faiss.config import FaissImplConfig
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
@ -53,7 +53,7 @@ def get_distribution_template() -> DistributionTemplate:
vector_io_provider_faiss = Provider(
provider_id="faiss",
provider_type="inline::faiss",
config=FaissImplConfig.sample_run_config(f"distributions/{name}"),
config=FaissVectorIOConfig.sample_run_config(f"distributions/{name}"),
)
vector_io_provider_sqlite = Provider(
provider_id="sqlite_vec",

4
llama_stack/templates/remote-vllm/vllm.py
View file

@ -16,7 +16,7 @@ from llama_stack.distribution.datatypes import (
from llama_stack.providers.inline.inference.sentence_transformers import (
SentenceTransformersInferenceConfig,
)
from llama_stack.providers.inline.vector_io.faiss.config import FaissImplConfig
from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig
from llama_stack.providers.remote.inference.vllm import VLLMInferenceAdapterConfig
from llama_stack.templates.template import DistributionTemplate, RunConfigSettings
@ -55,7 +55,7 @@ def get_distribution_template() -> DistributionTemplate:
vector_io_provider = Provider(
provider_id="faiss",
provider_type="inline::faiss",
config=FaissImplConfig.sample_run_config(f"distributions/{name}"),
config=FaissVectorIOConfig.sample_run_config(f"distributions/{name}"),
)
inference_model = ModelInput(

4
llama_stack/templates/tgi/tgi.py
View file

@ -16,7 +16,7 @@ from llama_stack.distribution.datatypes import (
from llama_stack.providers.inline.inference.sentence_transformers import (
SentenceTransformersInferenceConfig,
)
from llama_stack.providers.inline.vector_io.faiss.config import FaissImplConfig
from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig
from llama_stack.providers.remote.inference.tgi import TGIImplConfig
from llama_stack.templates.template import DistributionTemplate, RunConfigSettings
@ -55,7 +55,7 @@ def get_distribution_template() -> DistributionTemplate:
vector_io_provider = Provider(
provider_id="faiss",
provider_type="inline::faiss",
config=FaissImplConfig.sample_run_config(f"distributions/{name}"),
config=FaissVectorIOConfig.sample_run_config(f"distributions/{name}"),
)
inference_model = ModelInput(

4
llama_stack/templates/together/together.py
View file

@ -18,7 +18,7 @@ from llama_stack.distribution.datatypes import (
from llama_stack.providers.inline.inference.sentence_transformers import (
SentenceTransformersInferenceConfig,
)
from llama_stack.providers.inline.vector_io.faiss.config import FaissImplConfig
from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig
from llama_stack.providers.remote.inference.together import TogetherImplConfig
from llama_stack.providers.remote.inference.together.together import MODEL_ALIASES
from llama_stack.templates.template import DistributionTemplate, RunConfigSettings
@ -51,7 +51,7 @@ def get_distribution_template() -> DistributionTemplate:
vector_io_provider = Provider(
provider_id="faiss",
provider_type="inline::faiss",
config=FaissImplConfig.sample_run_config(f"distributions/{name}"),
config=FaissVectorIOConfig.sample_run_config(f"distributions/{name}"),
)
embedding_provider = Provider(
provider_id="sentence-transformers",

4
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.vector_io.faiss.config import FaissImplConfig
from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig
from llama_stack.templates.template import (
DistributionTemplate,
RunConfigSettings,
@ -46,7 +46,7 @@ def get_distribution_template() -> DistributionTemplate:
vector_io_provider = Provider(
provider_id="faiss",
provider_type="inline::faiss",
config=FaissImplConfig.sample_run_config(f"distributions/{name}"),
config=FaissVectorIOConfig.sample_run_config(f"distributions/{name}"),
)
embedding_provider = Provider(
provider_id="sentence-transformers",