Chat with AI
Use the AI Assistant tool window to have a conversation with the LLM (Large Language Model), ask questions about your project, or iterate on a task.
AI Assistant takes into consideration the language and technologies used in your project, as well as local changes and version control system commits. You can search for files, classes, and element usages.
Start a new chat
Click to open AI Assistant.
In the input field, type your question.
The AI chat now supports slash commands to streamline your interactions. You can use the following commands to perform specific actions directly within the chat:
/chat_new: Opens a new AI chat tab.
/chat_stop: Stops the ongoing response generation.
/chat_regenerate: Deletes the latest response and regenerates it.
/docs: Queries Fleet and other JetBrains documentation directly.
To disable slash commands, add the following setting to your settings.json file:
ai.chat.commands.enabled=falseThis setting disables all slash commands in the AI chat.
Press ⏎ to submit your query.
Ask about the selected code or the opened file
You can ask the AI Assistant questions about some particular code in your file or about all the code in the file.
Ask about This File: right-click any place in the opened file and navigate to . Alternatively, to open the popup with AI Assistant actions, press ⌥ ⏎.
Ask about This Code: select code in the file and navigate to . Alternatively, to open the popup with AI Assistant actions, press ⌥ ⏎.
In the query field, type your question about the code or file.
Find code with Smart Mode disabled
Click to open AI Assistant.
Type your search request in the prompt field. For example,
find the Person class.
Use AI Assistant to retrieve context-based answers
Click to open AI Assistant.
Use natural language to request information based on the context of your workspace. Here are some examples:
Request recent files: to retrieve a list of files you have recently viewed.
Ask for the current file: to display the full content of the currently opened file.
Request visible code: to retrieve the code currently visible in your editor.
Ask for local changes: to display uncommitted changes in your file tree.
Find information in README: to search for relevant information within README files.
Check recently changed files: to list files modified in the ten latest commits.
