Common problems and troubleshooting methods include:
- API connection failure: Check the key validity, network connection, and confirm that the
CUSTOM_LLM_ENDPOINTSetting is correct - Multimodal Handling Exception: confirm that the model supports the feature (e.g., DeepSeek-R1 does not support image analysis)
- Output truncation: Adjustments
CUSTOM_LLM_MAX_TOKENSEnvironment variables (default 8192) - Performance issues: Switching to a lighter model or checking local resource usage
Exclusion Tool:
1. Operation elc logs View detailed error logs
2. check the project's troubleshooting documentation
3. Submit the issue to GitHub with the bug report and steps to reproduce it.
It is recommended to perform simple text generation tests to verify the basic functionality for the first time, and then try complex scenarios step by step.
This answer comes from the articleeasy-llm-cli: enable Gemini CLI support for calling multiple large language modelsThe






























