What's included?
You can edit this quickstart to add helpful components. View the repository and open a pull request.
Why monitor your LangChain application?
LangChain is a framework for developing applications powered by language models. By monitoring your LangChain app, we are providing you visibility on the chains, tools as well as inputs and outputs. By using the LangChain quickstart, you will be able to:
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.
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 the query performance of your Vector DB
Track the behavior of your vector stores. Monitor the latency, queries, the number of documents retrieved, and the content of the documents so that you can evaluate their relevance.
Comprehensive monitoring quickstart for your LangChain app
Our LangChain quickstart provides metrics including error rate, input & output, latency, queries, retrieved document content and lets you integrate with different LLM providers and vector stores.
What’s included in this quickstart?
New Relic LangChain monitoring quickstart provides a variety of pre-built dashboards, which will help you gain insights into the health and performance of your LangChain app. These reports include:
- LLM calls and chains
- Tools
- Vector searches
- Alerts for errors, requests per model, and response time