For the complete documentation index, see llms.txt. This page is also available as Markdown.

Common Issues

Common SDK issues — installation, client init, evaluations, trace upload, timeouts, network.

This guide covers frequently encountered issues when using the LayerLens Python SDK and how to resolve them.

Installation Issues

Package Not Found

Error: Could not find a version that satisfies the requirement layerlens

Make sure to include the custom package index:

pip install layerlens --extra-index-url https://sdk.layerlens.ai/package

Python Version Incompatibility

Error: Requires-Python >=3.8

The SDK requires Python 3.8 or higher. Check your version:

python --version

Client Initialization

Missing API Key

Error: StratixError: The api_key client option must be set either by passing api_key to the client or by setting the LAYERLENS_STRATIX_API_KEY environment variable

Set the environment variable or pass the key explicitly:

Organization Not Found

Error: NotFoundError during client initialization

Your API key may be invalid or expired. Verify it in the LayerLens dashboard.

Evaluation Issues

Evaluation Stuck in Progress

If wait_for_completion seems to hang, the evaluation may be queued behind other jobs. You can check the status manually:

Model or Benchmark Not Found

When using get_by_key, ensure the key matches exactly (case-sensitive):

Trace Upload Issues

File Too Large

Trace files must be under 50 MB. For larger datasets, split the file into smaller chunks.

Invalid File Format

Trace uploads accept .json and .jsonl files only. Ensure your file contains valid JSON.

Timeout Errors

Error: APITimeoutError

The default timeout is 10 minutes. For long-running operations, increase it:

Network Issues

Error: APIConnectionError

  • Verify your internet connection

  • Check if https://api.layerlens.ai is reachable

  • If behind a proxy, configure httpx accordingly

See Also

Last updated

Was this helpful?