phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 20:14:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

[1/n] migrate inference/chat_completion

Browse source
This commit is contained in:
Xi Yan 2024-09-11 12:21:19 -07:00
parent 1433aaf9f7
commit 0c7c6b7e02
3 changed files with 35 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

8
llama_toolchain/inference/client.py
View file

@ -10,10 +10,10 @@ from typing import Any, AsyncGenerator
import fire
import httpx
from pydantic import BaseModel
from termcolor import cprint
from llama_toolchain.core.datatypes import RemoteProviderConfig
from pydantic import BaseModel
from termcolor import cprint
from .api import (
ChatCompletionRequest,
@ -52,9 +52,7 @@ class InferenceClient(Inference):
async with client.stream(
"POST",
f"{self.base_url}/inference/chat_completion",
json={
"request": encodable_dict(request),
},
json=encodable_dict(request),
headers={"Content-Type": "application/json"},
timeout=20,
) as response: