跳到主要内容

Cloudflare Workers AI

https://developers.cloudflare.com/workers-ai/models/text-generation/

API 密钥​

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

示例用法​

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)

示例用法 - 流式处理​

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)

支持的模型​

此处列出的所有模型 https://developers.cloudflare.com/workers-ai/models/text-generation/ 都支持

模型名称函数调用
@cf/meta/llama-2-7b-chat-fp16completion(model="mistral/mistral-tiny", messages)
@cf/meta/llama-2-7b-chat-int8completion(model="mistral/mistral-small", messages)
@cf/mistral/mistral-7b-instruct-v0.1completion(model="mistral/mistral-medium", messages)
@hf/thebloke/codellama-7b-instruct-awqcompletion(model="codellama/codellama-medium", messages)