As of September 2024, this version of Wave Terminal is deprecated. To learn more about our new version (>=v0.8.0), check out www.waveterm.dev. To find documentation for our new version, check out docs.waveterm.dev.
Wave AI supports the integration of any LLM provider that uses the OpenAI Chat Completions API. This feature allows you to bring your own compatible LLM provider and seamlessly integrate it into your workflow. While we strive to test and include as many LLM providers as possible, we simply cannot add them all. This is where the ability to add your own, custom LLM comes in — it allows you to configure your own LLM provider with just a couple of simple changes, even if it’s not officially listed as supported by Wave AI.
To see a full list of supported LLM providers, please visit the Third-Party LLM Support section in the Wave AI features page.

​
Configuration

For local LLMs, you should you should be able to start using it in Wave by setting two parameters, aibaseurl and aimodel. Additionally, cloud-based LLMs will most likely require an API Key, which can be easily set with the aiapitoken parameter.

​
Parameters

  • AI Base URL: Set this parameter to the base URL or endpoint that Wave AI should query.
  • AI Model: Specify the model name that you want to use. For local LLMs this setting is often not needed.
  • AI Token: When configuring a cloud-based LLM, set this parameter to the API key or access token required for authentication.
These parameters can be set either through the UI or from the command line, but please note that the parameter names are slightly different depending on the method you choose. Note: If the provided Base URL (e.g., http://localhost:8080/v1/chat/completions) doesn’t work, try removing the /chat/completions directories from the end of the URL or using just the hostname and port (e.g., http://localhost:8080). This often resolves compatibility issues and allows Wave AI to communicate with your LLM provider successfully.

​
Configuring via the UI

To configure your LLM provider from the Wave AI user interface, navigate to the “Settings” menu and set the AI Base URL, AI Model, and AI Token (if required) parameters as described in the previous section.

​
Configuring via the CLI

To configure your LLM provider using the command line, set the aibaseurl, aimodel, and aiapitoken (if required) parameters using the /client:set command, as shown in the example below. 
/client:set aibaseurl=<your-base-url>
/client:set aimodel=<your-model-name>
/client:set aiapitoken=<your-token>

​
Usage

Once you have configured your LLM provider, you can start using it in Wave. There are two primary ways to interact with your newly configured LLM: Interactive Mode and by using the /chat command.
  • Interactive Mode: To enter Interactive Mode, click the “Wave AI” button in the command box or use the ctrl + space shortcut. This will open an interactive chat session where you can have a continuous conversation with the AI assistant powered by your LLM provider model.
  • /chat: Alternatively, you can use the /chat command followed by your question to get a quick answer from your LLM provider model directly in the terminal.

​
Troubleshooting

If you encounter issues while using your LLM provider with Wave AI, consider the following troubleshooting steps:
  • Connection failures: If Wave AI fails to connect to your LLM provider or returns an error message, verify that your LLM provider is running.
  • Authentication errors: Ensure that the aiapitoken parameter is set to use the correct API Token for the configured service.
  • Timeouts: If you’re unable to complete a query or incur frequent timeouts, try adjusting the aitimeout parameter to a higher value. This will give your LLM provider more time to process and respond to your requests, especially if you are running it on a system with limited hardware resources.
  • Incorrect base URL or port: Ensure that the aibaseurl parameter points to the correct URL and port number where your LLM provider is running. If you have changed the default port or are running your own LLM provider on a remote server, update the URL accordingly.
  • Incorrect model selection: If you have multiple LLMs installed, make sure to set the aimodel parameter to the specific model you want to use.
  • Unexpected behavior or inconsistent results: If you encounter unexpected behavior or inconsistent results when using your LLM provider with Wave AI, try resetting the aibaseurl, aimodel, and aiapitoken parameters to their default values and reconfiguring your LLM provider from scratch.
If you continue to face issues after trying these troubleshooting steps, feel free to reach out to us on Discord.

​
Reset Wave AI

At any time if you find that you wish to return to the default Wave AI experience, you can reset the aibaseurl, aimodel, and aiapitoken parameters to their default state by using the following commands. 
/client:set aibaseurl=
/client:set aimodel=
/client:set aiapitoken=
Note: This can also be done in the UI just as described in previous steps.