Bring Your Own LLM

By default, when asking a question to Navie, your code editor will interact with the AppMap hosted proxy for OpenAI. If you have a requirement to bring your own key or otherwise use your own OpenAI account you can specify your own OpenAI key; this will cause Navie to connect to OpenAI directly, without AppMap proxy acting as an intermediate.

Bring Your Own Model (BYOM)

This feature is in early access. We will post various comparisons of AppMap with models, we currently recommend GPT4 from OpenAI via Open AI or Microsoft Azure, and Mixtral-8x7B-Instruct-v0.1. We will update this section with additional models and more benchmarking details, please check back often for updates.

Another option is to use a different LLM entirely; you can use any OpenAI-compatible model running either locally or remotely. When configured like this, as in the BYOK case, Navie won’t contact the AppMap hosted proxy and your conversations will stay private between you and the model.


In order to configure Navie for your own LLM, certain environment variables need to be set for AppMap services. Please refer to the IDE-specific pages to see how to configure the variables in VS Code and IntelliJ.

You can use the following variables to direct Navie to use any LLM with an OpenAI-compatible API. If only the API key is set, Navie will connect to by default.

  • OPENAI_API_KEY — API key to use with OpenAI API.
  • OPENAI_BASE_URL — base URL for OpenAI API (defaults to the endpoint).
  • APPMAP_NAVIE_MODEL — name of the model to use (the default is GPT-4).
  • APPMAP_NAVIE_TOKEN_LIMIT — maximum context size in tokens (default 8000).

For Azure OpenAI, you need to create a deployment and use these variables instead:

  • AZURE_OPENAI_API_KEY — API key to use with Azure OpenAI API.
  • AZURE_OPENAI_API_VERSION — API version to use when communicating with Azure OpenAI, eg. 2024-02-01
  • AZURE_OPENAI_API_INSTANCE_NAME — Azure OpenAI instance name (ie. the part of the URL before
  • AZURE_OPENAI_API_DEPLOYMENT_NAME — Azure OpenAI deployment name.


Only OPENAI_API_KEY needs to be set, other settings can stay default:


Azure OpenAI

Assuming you created a navie GPT-4 deployment on OpenAI instance:

AZURE_OPENAI_API_KEY e50edc22e83f01802893d654c4268c4f

AnyScale Endpoints

AnyScale Endpoints allows querying a selection of open-source LLMs. After you create an account you can use it by setting:

OPENAI_API_KEY esecret_myxfwgl1iinbz9q5hkexemk8f4xhcou8
APPMAP_NAVIE_MODEL mistralai/Mixtral-8x7B-Instruct-v0.1

Consult AnyScale documentation for model names. Note we recommend using Mixtral models with Navie.


You can use Ollama to run Navie with local models; after you’ve successfully ran a model with ollama run command, you can configure Navie to use it:


Note: Even though it’s running locally a dummy placeholder API key is still required.

Was this page helpful? thumb_up Yes thumb_down No
Thank you for your feedback!