通过 OpenTelemetry 接入 OpenLLMetry

%pip install openai traceloop-sdk langfuse

import os
import base64
 
# Get keys for your project from the project settings page: https://litefuse.cloud
os.environ["LANGFUSE_PUBLIC_KEY"] = "pk-lf-..." 
os.environ["LANGFUSE_SECRET_KEY"] = "sk-lf-..." 
os.environ["LANGFUSE_BASE_URL"] = "https://litefuse.cloud"
 
# Build Basic Auth header.
LANGFUSE_AUTH = base64.b64encode(
    f"{os.environ.get('LANGFUSE_PUBLIC_KEY')}:{os.environ.get('LANGFUSE_SECRET_KEY')}".encode()
).decode()
 
# Configure OpenTelemetry endpoint & headers
os.environ["OTEL_EXPORTER_OTLP_ENDPOINT"] = os.environ.get("LANGFUSE_BASE_URL") + "/api/public/otel"
os.environ["OTEL_EXPORTER_OTLP_HEADERS"] = f"Authorization=Basic {LANGFUSE_AUTH}"
 
# Your openai key
os.environ["OPENAI_API_KEY"] = "sk-proj-..."

from langfuse import get_client
 
langfuse = get_client()
 
# Verify connection
if langfuse.auth_check():
    print("Langfuse client is authenticated and ready!")
else:
    print("Authentication failed. Please check your credentials and host.")

Langfuse client is authenticated and ready!

from traceloop.sdk import Traceloop
 
Traceloop.init(disable_batch=True,
               api_endpoint=os.environ.get("OTEL_EXPORTER_OTLP_ENDPOINT"),
               headers=os.environ.get(f"Authorization=Basic {LANGFUSE_AUTH}"),)

[39m


ERROR:root:Error initializing redis instrumentor: No module named 'opentelemetry.instrumentation.redis'

from openai import OpenAI
 
openai_client = OpenAI()
 
chat_completion = openai_client.chat.completions.create(
    messages=[
        {
          "role": "user",
          "content": "What is LLM Observability?",
        }
    ],
    model="gpt-4o-mini",
)
 
print(chat_completion)

ChatCompletion(id='chatcmpl-BjRWj0Gn9A1PdPYslJ9rDNW730I97', choices=[Choice(finish_reason='stop', index=0, logprobs=None, message=ChatCompletionMessage(content="LLM observability refers to the practices, tools, and methodologies used to monitor, analyze, and understand the behavior and performance of Large Language Models (LLMs) in real time. As organizations increasingly rely on LLMs for various applications—such as natural language processing, chatbots, content generation, and more—ensuring their reliability, accuracy, and ethical alignment has become critical.\n\nKey components of LLM observability include:\n\n1. **Monitoring Performance**: Tracking metrics such as response time, resource utilization, and throughput to ensure that the model operates efficiently under load.\n\n2. **Quality Analysis**: Evaluating the quality of the model's outputs through various means, including user feedback, automated evaluation metrics, and comparison to ground truth data.\n\n3. **Behavior Analysis**: Analyzing the model's behavior in different contexts to identify biases, unintentional outputs, or other anomalies. This includes examining edge cases where the model might fail or produce unexpected results.\n\n4. **Debugging Tools**: Implementing tools that help trace issues or problems back to specific inputs, configurations, or model parameters that may be causing suboptimal performance.\n\n5. **Data Drift Detection**: Monitoring the input data for changes over time that could affect the model's performance, such as shifts in language use, terminology, or user behavior.\n\n6. **Feedback Loops**: Establishing mechanisms for continuous feedback from users and incorporating that information back into the model development lifecycle for fine-tuning and improvements.\n\n7. **Compliance and Safety**: Ensuring that the model adheres to ethical standards and legal requirements, especially regarding data usage and content generation.\n\nEffective observability can help organizations better manage their LLM deployments, minimize risks, and enhance the overall user experience by ensuring that models perform accurately and reliably in a wide range of scenarios.", refusal=None, role='assistant', annotations=[], audio=None, function_call=None, tool_calls=None))], created=1750170273, model='gpt-4o-mini-2024-07-18', object='chat.completion', service_tier='default', system_fingerprint='fp_34a54ae93c', usage=CompletionUsage(completion_tokens=368, prompt_tokens=14, total_tokens=382, completion_tokens_details=CompletionTokensDetails(accepted_prediction_tokens=0, audio_tokens=0, reasoning_tokens=0, rejected_prediction_tokens=0), prompt_tokens_details=PromptTokensDetails(audio_tokens=0, cached_tokens=0)))