Troubleshoot variable caching

If you’re not seeing traces in your tracing project or notice traces logged to the wrong project/workspace, the issue might be due to LangSmith’s default environment variable caching. This is especially common when running LangSmith within a Jupyter notebook. Follow these steps to diagnose and resolve the issue:

1. Verify your environment variables

First, check that the environment variables are set correctly by running:

import os
print(os.getenv("LANGSMITH_PROJECT"))
print(os.getenv("LANGSMITH_TRACING"))
print(os.getenv("LANGSMITH_ENDPOINT"))
print(os.getenv("LANGSMITH_API_KEY"))

If the output does not match what’s defined in your .env file, it’s likely due to environment variable caching.

2. Clear the cache

Clear the cached environment variables with the following command:

utils.get_env_var.cache_clear()

3. Reload the environment variables

Reload your environment variables from the .env file by executing:

from dotenv import load_dotenv
import os
load_dotenv(<path to .env file>, override=True)

After reloading, your environment variables should be set correctly.

If you continue to experience issues, please reach out to us via a shared Slack channel or email support (available for Plus and Enterprise plans), or in the LangChain Forum.

---

Edit the source of this page on GitHub.

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