Omit Logs

When handling sensitive data or operating under strict compliance requirements, you may need to track LLM metrics without storing the actual request and response content. Omit Logs lets you maintain observability for costs, latency, and usage patterns while excluding sensitive data from storage.

Why use Omit Logs

• Maintain compliance: Meet GDPR, HIPAA, and other regulatory requirements by excluding sensitive content from logs
• Protect sensitive data: Prevent PII, financial data, or proprietary information from being stored in observability systems
• Keep essential metrics: Still track costs, latency, token usage, and performance without storing actual content

There are two ways to omit logs:

1. Headers: Use this if you're not using CoreValue's Python Asynchronous Logging.
2. CoreValue Python Async Logging: Use this if you're using CoreValue's Python Asynchronous Logging and don't want to send the request or response to our backend.

Headers

To omit logging requests, set Cova-Omit-Request to true.

To omit logging responses, set Cova-Omit-Response to true.

curl https://gateway.corevalue.dev/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $COVA_API_KEY" \
  -H "Cova-Omit-Request: true" \
  -H "Cova-Omit-Response: true" \
 -d '{
    "model": "gpt-4o-mini",
    "messages": [
      {
        "role": "user",
        "content": "How do I enable custom rate limit policies?"
      }
    ]
}'

client = OpenAI(
    api_key=COVA_API_KEY,
    base_url="https://gateway.corevalue.dev/v1",
)
client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "How do I enable retries?"}],
    headers={
        "Cova-Omit-Request": "true", # Add this header and set to true
         "Cova-Omit-Response": "true", # Add this header and set to true
    }
)

import { OpenAI } from "openai";
const openai = new OpenAI({
  apiKey: process.env.COVA_API_KEY,
  baseURL: "https://gateway.corevalue.dev/v1",
  defaultHeaders: {
    "Cova-Omit-Request": "true", // Add this header and set to true
    "Cova-Omit-Response": "true", // Add this header and set to true
  },
});

Python Async Logging

If you are using CoreValue's Asynchronous Logging, you have the option to not even send the request or response to our backend.

from cova_async import CovaAsyncLogger
from openai import OpenAI

logger = CovaAsyncLogger(
  api_key=COVA_API_KEY,
)

logger.init()

client = OpenAI(api_key=OPENAI_API_KEY)

logger.disable_content_tracing() # This will omit the request and response from being sent to our backend till the time you call logger.enable_content_tracing()

# Make the OpenAI call
response = client.chat.completions.create(
  model="gpt-4o-mini",
  messages=[{"role": "system", "content": "You are a helpful assistant."},
            {"role": "user", "content": "Who won the world series in 2020?"},
            {"role": "assistant",
             "content": "The Los Angeles Dodgers won the World Series in 2020."},
            {"role": "user", "content": "Where was it played?"}]
)

print(response.choices[0])
logger.enable_content_tracing() # All future requests will be sent with the request and response

Request View

You can still see the key metrics for each request, without the request or response contents.

Completely Disabling Logging

If you are using CoreValue's Asynchronous Logging, you can also completely disable all logging to CoreValue:

from cova_async import CovaAsyncLogger
from openai import OpenAI

logger = CovaAsyncLogger(
  api_key=COVA_API_KEY,
)

logger.init()

# Completely disable all logging
logger.disable_logging()

# Your OpenAI calls here
# No data will be sent to CoreValue

# Later, re-enable logging if needed
logger.enable_logging()

When logging is disabled, no traces will be sent to CoreValue at all. This is different from disable_content_tracing() which only omits request and response content but still sends other metrics. Note that this feature is only available when using CoreValue's async integration mode and not with the proxy integration.

Request View

You can still see the key metrics for each request, without the request or response contents.