langfuse-hello-world
Create a minimal working Langfuse trace example. Use when starting a new Langfuse integration, testing your setup, or learning basic Langfuse tracing patterns. Trigger with phrases like "langfuse hello world", "langfuse example", "langfuse quick start", "first langfuse trace", "simple langfuse code".
- License 许可
- MIT
- 最近更新
- 2026-05-26
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- langfuse-hello-world
- author
- Jeremy Longshore <jeremy@intentsolutions.io>
- license
- MIT
- version
- 1.0.0
- description
- Create a minimal working Langfuse trace example. Use when starting a new Langfuse integration, testing your setup, or learning basic Langfuse tracing patterns. Trigger with phrases like "langfuse hello world", "langfuse example", "langfuse quick start", "first langfuse trace", "simple langfuse code".
- allowed-tools
- Read, Write, Edit
- compatible-with
- claude-code, codex, openclaw
03 SKILL.md 正文
Langfuse Hello World
Overview
Minimal working example demonstrating core Langfuse tracing functionality.
Prerequisites
- Completed
langfuse-install-authsetup - Valid API credentials configured
- Development environment ready
Instructions
Step 1: Create Entry File
Create a new file for your hello world trace.
Step 2: Import and Initialize Client
import { Langfuse } from "langfuse";
const langfuse = new Langfuse({
publicKey: process.env.LANGFUSE_PUBLIC_KEY!,
secretKey: process.env.LANGFUSE_SECRET_KEY!,
baseUrl: process.env.LANGFUSE_HOST,
});
Step 3: Create Your First Trace
async function helloLangfuse() {
// Create a trace (top-level operation)
const trace = langfuse.trace({
name: "hello-world",
userId: "demo-user",
metadata: { source: "hello-world-example" },
tags: ["demo", "getting-started"],
});
// Add a span (child operation)
const span = trace.span({
name: "process-input",
input: { message: "Hello, Langfuse!" },
});
// Simulate some processing
await new Promise((resolve) => setTimeout(resolve, 100));
// End the span with output
span.end({
output: { result: "Processed successfully!" },
});
// Add a generation (LLM call tracking)
trace.generation({
name: "llm-response",
model: "gpt-4",
input: [{ role: "user", content: "Say hello" }],
output: { content: "Hello! How can I help you today?" },
usage: {
promptTokens: 5,
completionTokens: 10,
totalTokens: 15,
},
});
// Flush to ensure data is sent
await langfuse.flushAsync();
console.log("Trace created! View at:", trace.getTraceUrl());
}
helloLangfuse().catch(console.error);
Output
- Working code file with Langfuse client initialization
- A trace visible in Langfuse dashboard containing:
- One span with input/output
- One generation with mock LLM data
- Console output showing:
Trace created! View at: https://cloud.langfuse.com/trace/abc123...
Error Handling
| Error | Cause | Solution |
|---|---|---|
| Import Error | SDK not installed | Verify with npm list langfuse |
| Auth Error | Invalid credentials | Check environment variables are set |
| Trace not appearing | Data not flushed | Ensure flushAsync() is called |
| Network Error | Host unreachable | Verify LANGFUSE_HOST URL |
Examples
TypeScript Complete Example
import { Langfuse } from "langfuse";
const langfuse = new Langfuse();
async function main() {
// Create trace
const trace = langfuse.trace({
name: "hello-world",
input: { query: "What is Langfuse?" },
});
// Simulate LLM call
const generation = trace.generation({
name: "answer-query",
model: "gpt-4",
modelParameters: { temperature: 0.7 },
input: [
{ role: "system", content: "You are a helpful assistant." },
{ role: "user", content: "What is Langfuse?" },
],
});
// Simulate response
await new Promise((r) => setTimeout(r, 500)); # HTTP 500 Internal Server Error
// End generation with output
generation.end({
output: "Langfuse is an open-source LLM observability platform...",
usage: { promptTokens: 25, completionTokens: 50 },
});
// Update trace with final output
trace.update({
output: { answer: "Langfuse is an LLM observability platform." },
});
// Flush and get URL
await langfuse.flushAsync();
console.log("View trace:", trace.getTraceUrl());
}
main();
Python Complete Example
from langfuse import Langfuse
import time
langfuse = Langfuse()
def main():
# Create trace
trace = langfuse.trace(
name="hello-world",
input={"query": "What is Langfuse?"},
user_id="demo-user",
)
# Add a span for processing
span = trace.span(
name="process-query",
input={"query": "What is Langfuse?"},
)
# Simulate processing
time.sleep(0.1)
span.end(output={"processed": True})
# Add LLM generation
generation = trace.generation(
name="answer-query",
model="gpt-4",
model_parameters={"temperature": 0.7},
input=[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "What is Langfuse?"},
],
)
# Simulate LLM response
time.sleep(0.5)
generation.end(
output="Langfuse is an open-source LLM observability platform...",
usage={"prompt_tokens": 25, "completion_tokens": 50},
)
# Update trace with final output
trace.update(
output={"answer": "Langfuse is an LLM observability platform."}
)
# Flush data
langfuse.flush()
print(f"View trace: {trace.get_trace_url()}")
if __name__ == "__main__":
main()
With Decorators (Python)
from langfuse.decorators import observe, langfuse_context
@observe()
def process_query(query: str) -> str:
# This function is automatically traced
return f"Processed: {query}"
@observe(as_type="generation")
def generate_response(messages: list) -> str:
# This is tracked as an LLM generation
langfuse_context.update_current_observation(
model="gpt-4",
usage={"prompt_tokens": 10, "completion_tokens": 20},
)
return "Hello from Langfuse!"
@observe()
def main():
result = process_query("Hello!")
response = generate_response([{"role": "user", "content": "Hi"}])
return response
main()
Resources
Next Steps
Proceed to langfuse-local-dev-loop for development workflow setup.
04 同仓库更多 Skills
zustand-store-ts
Create Zustand stores with TypeScript, subscribeWithSelector middleware, and proper state/action separation. Use when building React state management, creating global stores, or implementing reactive state patterns with Zustand.
zustand-store-creator
Zustand Store Creator - Auto-activating skill for Frontend Development. Triggers on: zustand store creator, zustand store creator Part of the Frontend Development skill category.
zero-trust-config-helper
Zero Trust Config Helper - Auto-activating skill for Security Advanced. Triggers on: zero trust config helper, zero trust config helper Part of the Security Advanced skill category.
zapier-integration-helper
Zapier Integration Helper - Auto-activating skill for Business Automation. Triggers on: zapier integration helper, zapier integration helper Part of the Business Automation skill category.
zai-cli
Execute z.AI CLI providing vision, search, reader, and GitHub exploration via CLI and MCP. Use when user needs image/video analysis, OCR, UI-to-code conversion, error diagnosis, real-time web search, web page to markdown extraction, or GitHub code exploration. Trigger with phrases like "analyze this image", "search the web for", "read this page", "explore this repo", or "use zai". Requires Z_AI_API_KEY.
yt-research
Research competitor YouTube channels, niches, and trending topics for your content strategy. Use this skill whenever the user says "research channels", "analyze competitors", "find trending topics", "niche analysis", "competitive research", "what are other creators doing", "scrape YouTube channels", or wants to understand the competitive landscape for a specific tool or topic area. Use when working with yt research. Trigger with 'yt', 'research'.