24 lines
611 B
Python
24 lines
611 B
Python
|
import os
|
||
|
|
from huggingface_hub import InferenceClient
|
||
|
|
|
||
|
|
# Required env vars:
|
||
|
|
# export HF_TOKEN="..."
|
||
|
|
# export HF_ENDPOINT_BASE_URL="https://xxxx.endpoints.huggingface.cloud"
|
||
|
|
|
||
|
|
client = InferenceClient(
|
||
|
|
base_url=os.environ["HF_ENDPOINT_BASE_URL"],
|
||
|
|
api_key=os.environ["HF_TOKEN"],
|
||
|
|
)
|
||
|
|
|
||
|
|
resp = client.chat.completions.create(
|
||
|
|
messages=[
|
||
|
|
{"role": "system", "content": "You are a helpful assistant."},
|
||
|
|
{"role": "user", "content": "Write a short joke in the style of The Office."},
|
||
|
|
],
|
||
|
|
max_tokens=2560,
|
||
|
|
temperature=1.2,
|
||
|
|
top_p=0.95,
|
||
|
|
)
|
||
|
|
|
||
|
|
print(resp.choices[0].message.content)
|