What's included?
Why should you monitor your usage of Hugging Face?
Monitor your application powered by Hugging Face language models to ensure, get visibility to what you send to Hugging Face, responses received from Hugging Face, latency, usage and errors. By monitoring the usage, you can infer the cost.
Track the LLM's performance:
Monitor the input & output, latency and errors of your LLM provider. Track performance changes with the providers and versions of your LLM. Monitor usage to understand the cost, rate limits, and general performance.
Track your app:
By tracking key metrics like latency, throughput, error rates, and input & output, you can gain insights into your LangChain app's performance and identify areas of improvement.
Early issue detection:
Detect and address issues early to prevent them from affecting model performance.
Comprehensive Hugging Face monitoring quickstart
Our Hugging Face quickstart provides metrics including error rate, input & output, latency, queries, and lets you integrate with different language models.
What’s included in the Hugging Face quickstart?
New Relic Hugging Face monitoring quickstart provides a variety of pre-built dashboards, which will help you gain insights into the health and performance of your Hugging Face usage. These reports include:
- Dashboards (average tokens, LLM completion’s details, chain’s details, tool details, top tool names and many more)
- Alerts (errors, request per model and response time)