原始请求/响应日志记录

日志记录

在您的日志记录提供商（OTEL/Langfuse 等）中查看 LiteLLM 发送的原始请求/响应。

SDK

# pip install langfuse 
import litellm
import os

# log raw request/response
litellm.log_raw_request_response = True

# from https://cloud.langfuse.com/
os.environ["LANGFUSE_PUBLIC_KEY"] = ""
os.environ["LANGFUSE_SECRET_KEY"] = ""
# Optional, defaults to https://cloud.langfuse.com
os.environ["LANGFUSE_HOST"] # optional

# LLM API Keys
os.environ['OPENAI_API_KEY']=""

# set langfuse as a callback, litellm will send the data to langfuse
litellm.success_callback = ["langfuse"] 
 
# openai call
response = litellm.completion(
  model="gpt-3.5-turbo",
  messages=[
    {"role": "user", "content": "Hi 👋 - i'm openai"}
  ]
)

代理

litellm_settings:
  log_raw_request_response: True

预期日志

返回原始响应头

返回 LLM 提供商的原始响应头。

目前仅支持 openai。

SDK

import litellm
import os

litellm.return_response_headers = True

## set ENV variables
os.environ["OPENAI_API_KEY"] = "your-api-key"

response = litellm.completion(
  model="gpt-3.5-turbo",
  messages=[{ "content": "Hello, how are you?","role": "user"}]
)

print(response._hidden_params)

代理

1. 设置 config.yaml

model_list:
  - model_name: gpt-3.5-turbo
    litellm_params:
      model: gpt-3.5-turbo
      api_key: os.environ/GROQ_API_KEY

litellm_settings:
  return_response_headers: true

2. 测试一下！

curl -X POST 'http://0.0.0.0:4000/chat/completions' \
-H 'Content-Type: application/json' \
-H 'Authorization: Bearer sk-1234' \
-D '{
    "model": "gpt-3.5-turbo",
    "messages": [
        { "role": "system", "content": "Use your tools smartly"},
        { "role": "user", "content": "What time is it now? Use your tool"}
    ]
}'

预期响应