Cloudflare Workers AI | liteLLM (original) (raw)

from litellm import completion
import os

os.environ['CLOUDFLARE_API_KEY'] = "3dnSGlxxxx"
os.environ['CLOUDFLARE_ACCOUNT_ID'] = "03xxxxx"

response = completion(
    model="cloudflare/@cf/meta/llama-2-7b-chat-int8", 
    messages=[
       {"role": "user", "content": "hello from litellm"}
   ],
)
print(response)
from litellm import completion
import os

os.environ['CLOUDFLARE_API_KEY'] = "3dnSGlxxxx"
os.environ['CLOUDFLARE_ACCOUNT_ID'] = "03xxxxx"

response = completion(
    model="cloudflare/@hf/thebloke/codellama-7b-instruct-awq", 
    messages=[
       {"role": "user", "content": "hello from litellm"}
   ],
    stream=True
)

for chunk in response:
    print(chunk)