Enable Insights ↗

Documentation Index#

Fetch the complete documentation index at: https://docs.langchain.com/llms.txt Use this file to discover all available pages before exploring further.

Insights provides AI-powered analysis of your traces and application data within LangSmith. This page explains how to enable Insights on a self-hosted LangSmith instance.

Self-hosted LangSmith is an add-on to the Enterprise plan. For more details, refer to Pricing. Contact our sales team if you want to get a license key to trial LangSmith in your environment.

Prerequisites#

Before enabling Insights, you must complete the following setup steps:

1. Install the base LangSmith platform:
   • Install on Kubernetes.
   • Install on Docker.
2. Enable LangSmith Deployment (agent deployment capabilities).

Components#

Insights consists of two main components:

• agentBootstrap: Job that deploys the LangSmith Deployment (agent) needed for Insights.
• insightsAgent: The main agent that will handle insights generation.

Enable Insights#

To enable Insights, add the following to your values.yaml:

backend:
  agentBootstrap:
    enabled: true

config:
  insights:
    enabled: true
    encryptionKey: "<your-encryption-key>"

Generate an encryption key#

Insights requires a Fernet encryption key to securely store secrets. Generate one using Python:

python -c "from cryptography.fernet import Fernet; print(Fernet.generate_key().decode())"

You can store the encryption key in a predefined Kubernetes secret using the insights_encryption_key parameter. See Use an existing secret for details.

Edit this page on GitHub or file an issue.

Connect these docs to Claude, VSCode, and more via MCP for real-time answers.