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

Fixes to the llama stack configure script + inference adapters

Browse source
This commit is contained in:
Ashwin Bharambe 2024-09-03 23:22:21 -07:00
parent 4869f2b983
commit 1380d78c19
11 changed files with 124 additions and 37 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_toolchain/inference/adapters/fireworks/__init__.py
View file

@ -7,7 +7,7 @@
from .config import FireworksImplConfig
async def get_adapter_impl(config: FireworksImplConfig, _deps) -> Inference:
async def get_adapter_impl(config: FireworksImplConfig, _deps):
from .fireworks import FireworksInferenceAdapter
assert isinstance(

2
llama_toolchain/inference/adapters/fireworks/config.py
View file

@ -11,7 +11,7 @@ from pydantic import BaseModel, Field
@json_schema_type
class FireworksImplConfig(BaseModel):
url: str = Field(
default="https://api.fireworks.api/inference",
default="https://api.fireworks.ai/inference",
description="The URL for the Fireworks server",
)
api_key: str = Field(

2
llama_toolchain/inference/adapters/together/__init__.py
View file

@ -7,7 +7,7 @@
from .config import TogetherImplConfig
async def get_adapter_impl(config: TogetherImplConfig, _deps) -> Inference:
async def get_adapter_impl(config: TogetherImplConfig, _deps):
from .together import TogetherInferenceAdapter
assert isinstance(

8
llama_toolchain/inference/providers.py
View file

@ -42,8 +42,8 @@ def available_inference_providers() -> List[ProviderSpec]:
pip_packages=[
"fireworks-ai",
],
module="llama_toolchain.inference.fireworks",
config_class="llama_toolchain.inference.fireworks.FireworksImplConfig",
module="llama_toolchain.inference.adapters.fireworks",
config_class="llama_toolchain.inference.adapters.fireworks.FireworksImplConfig",
),
),
remote_provider_spec(
@ -53,8 +53,8 @@ def available_inference_providers() -> List[ProviderSpec]:
pip_packages=[
"together",
],
module="llama_toolchain.inference.together",
config_class="llama_toolchain.inference.together.TogetherImplConfig",
module="llama_toolchain.inference.adapters.together",
config_class="llama_toolchain.inference.adapters.together.TogetherImplConfig",
),
),
]