Using /help

Type /help <question> and aider will respond with helpful information. You can ask questions about using aider, customizing settings, troubleshooting, using LLMs, etc.

Behind the scenes, aider has indexed all of its documentation. It uses the question to find relevant docs and share them with the LLM to do retrieval augmented generation (RAG) The LLM also has the full context of your ongoing aider chat, so it can help with the exact issue you might be facing.

Aider v0.42.1-dev
Models: claude-3-5-sonnet with diff edit format
Repo-map: using 1024 tokens
Use /help <question> to ask for help, run with –help to see cmd line args

/help is the .env file global or for a git repo?

Based on the provided documentation, here’s the answer to your question about the .env file in aider:

The .env file in aider can be both global and specific to a git repository. Aider looks for .env files in multiple locations, with the following priority order:

  1. Your home directory (global)
  2. The root of your git repo (repo-specific)
  3. The current directory
  4. A file specified with the --env-file <filename> parameter

If multiple .env files exist in these locations, they are loaded in the order listed above, with files loaded last taking priority. This means you can have a global .env file in your home directory with general settings, and then override or add to those settings with a repo-specific .env file in your git repository root.

Here are some relevant documentation links that you might find helpful:

  • https://aider.chat/docs/config.html
  • https://aider.chat/docs/config/dotenv.html

The ability to use both global and repo-specific .env files allows for flexible configuration, where you can set default values globally and override them on a per-project basis as needed.

/help can i use local LLMs?

Yes, you can use local LLMs with Aider. Here’s a summary of the options:

  1. Ollama: Aider supports using local models through Ollama.

  2. OpenAI-compatible API: Aider can access local models that provide an OpenAI-compatible API.

  3. Other local models: Aider uses the LiteLLM package to connect to various LLM providers, which may include options for running models locally.

However, it’s important to note that Aider works best with more capable models. Less capable models may have difficulty properly returning “code edits,” which could result in Aider not being able to edit your files and commit changes effectively.

For more detailed information on using local LLMs and connecting to various models, you might want to check out these relevant documentation pages:

  • https://aider.chat/docs/llms.html
  • https://aider.chat/docs/llms/ollama.html
  • https://aider.chat/docs/llms/openai-compat.html

Keep in mind that the performance and capabilities of local LLMs may vary depending on the specific model and your hardware resources.

Getting more help

If you need more help, please check our GitHub issues and file a new issue if your problem isn’t discussed. Or drop into our Discord to chat with us.

When reporting problems, it is very helpful if you can provide:

  • Aider version
  • LLM model you are using

Including the “announcement” lines that aider prints at startup is an easy way to share this helpful info.

Aider v0.37.1-dev
Models: gpt-4o with diff edit format, weak model gpt-3.5-turbo
Git repo: .git with 243 files
Repo-map: using 1024 tokens

Use /help <question> to ask for help about using aider, customizing settings, troubleshooting, using LLMs, etc.