• Chat server
• Embeddings server

This is a conversation with the local AI. It uses the project information and therefore is slower than Chat with AI, but could answer questions related to the project.

• Press Ctrl+Shift+; inside an editor (or select from llama.vscode menu Chat with AI with project context)
• Enter your question
• llama-vscode collects a relevant context information from the project and sends it to the AI together with your question
• Project context information is sent to the AI only if the question is entered with Ctrl+Shift+;. If the question is written directly in the chat window - no new context information is sent to the AI.
• If the AI answers too slowly - close the VS Code chat window and open a new one with Ctrl+Shift+;
• Press Esc if you want to return from the chat to the editor

It is possible to configure rag_* settings to adjust the rag search according to models and hardware ressources