phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 12:07:34 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

bunch more work to make adapters work

Browse source
This commit is contained in:
Ashwin Bharambe 2024-08-27 19:15:42 -07:00
parent 68f3db62e9
commit c4fe72c3a3
20 changed files with 461 additions and 173 deletions
Download patch file Download diff file Expand all files Collapse all files

8
llama_toolchain/inference/client.py
View file

@ -13,6 +13,8 @@ import httpx
from pydantic import BaseModel
from termcolor import cprint
from llama_toolchain.distribution.datatypes import RemoteProviderConfig
from .api import (
ChatCompletionRequest,
ChatCompletionResponse,
@ -24,8 +26,8 @@ from .api import (
from .event_logger import EventLogger
async def get_client_impl(base_url: str):
return InferenceClient(base_url)
async def get_adapter_impl(config: RemoteProviderConfig) -> Inference:
return InferenceClient(config.url)
def encodable_dict(d: BaseModel):
@ -34,7 +36,7 @@ def encodable_dict(d: BaseModel):
class InferenceClient(Inference):
def __init__(self, base_url: str):
print(f"Initializing client for {base_url}")
print(f"Inference passthrough to -> {base_url}")
self.base_url = base_url
async def initialize(self) -> None: