Langfuse SDK
Langfuse 透传端点 - 使用 LiteLLM 虚拟密钥调用 Langfuse 端点。
只需将 https://us.cloud.langfuse.com 替换为 LITELLM_PROXY_BASE_URL/langfuse 🚀
示例用法
from langfuse import Langfuse
langfuse = Langfuse(
host="http://localhost:4000/langfuse", # your litellm proxy endpoint
public_key="anything", # no key required since this is a pass through
secret_key="LITELLM_VIRTUAL_KEY", # no key required since this is a pass through
)
print("sending langfuse trace request")
trace = langfuse.trace(name="test-trace-litellm-proxy-passthrough")
print("flushing langfuse request")
langfuse.flush()
print("flushed langfuse request")
支持 所有 Langfuse 端点。
快速入门
让我们向 Langfuse 记录一个跟踪。
- 将 Langfuse 公钥/私钥添加到环境变量
export LANGFUSE_PUBLIC_KEY=""
export LANGFUSE_PRIVATE_KEY=""
- 启动 LiteLLM 代理
litellm
# RUNNING on http://0.0.0.0:4000
- 测试一下！
让我们向 Langfuse 记录一个跟踪！
from langfuse import Langfuse
langfuse = Langfuse(
host="http://localhost:4000/langfuse", # your litellm proxy endpoint
public_key="anything", # no key required since this is a pass through
secret_key="anything", # no key required since this is a pass through
)
print("sending langfuse trace request")
trace = langfuse.trace(name="test-trace-litellm-proxy-passthrough")
print("flushing langfuse request")
langfuse.flush()
print("flushed langfuse request")
高级 - 与虚拟密钥一起使用
前提条件
使用此方法可以避免向开发者提供原始的 Google AI Studio 密钥，但仍然让他们能够使用 Google AI Studio 端点。
用法
- 设置环境变量
export DATABASE_URL=""
export LITELLM_MASTER_KEY=""
export LANGFUSE_PUBLIC_KEY=""
export LANGFUSE_PRIVATE_KEY=""
litellm
# RUNNING on http://0.0.0.0:4000
- 生成虚拟密钥
curl -X POST 'http://0.0.0.0:4000/key/generate' \
-H 'Authorization: Bearer sk-1234' \
-H 'Content-Type: application/json' \
-d '{}'
预期响应
{
...
"key": "sk-1234ewknldferwedojwojw"
}
- 测试一下！
from langfuse import Langfuse
langfuse = Langfuse(
host="http://localhost:4000/langfuse", # your litellm proxy endpoint
public_key="anything", # no key required since this is a pass through
secret_key="sk-1234ewknldferwedojwojw", # no key required since this is a pass through
)
print("sending langfuse trace request")
trace = langfuse.trace(name="test-trace-litellm-proxy-passthrough")
print("flushing langfuse request")
langfuse.flush()
print("flushed langfuse request")