From 697553fdc50ac3897dc25315ebc426c64b618915 Mon Sep 17 00:00:00 2001
From: Lars Grammel <lars.grammel@gmail.com>
Date: Wed, 4 Oct 2023 20:46:46 +0200
Subject: [PATCH] Update page.

---
 app/vscode/asset/README.md | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/app/vscode/asset/README.md b/app/vscode/asset/README.md
index ccd7522..218133d 100644
--- a/app/vscode/asset/README.md
+++ b/app/vscode/asset/README.md
@@ -2,11 +2,15 @@
 
 > #### AI chat in the Visual Studio Code side bar. Rubberduck can [generate code](#generate-code), [edit code](#edit-code), [explain code](#explain-code), [generate tests](#generate-tests), [find bugs](#find-bugs), [diagnose errors](#diagnose-errors), and more. You can even add [your own conversation templates](https://github.com/rubberduck-ai/rubberduck-vscode/blob/main/doc/rubberduck-templates.md).
 
-# Setup
+# Setup with OpenAI
 
 1. Get an OpenAI API key from [platform.openai.com/account/api-keys](https://platform.openai.com/account/api-keys) (you'll need to sign up for an account)
 2. Enter the API key with the `Rubberduck: Enter OpenAI API key` command
 
+# Alternative: use local AI models with Llama.cpp (experimental)
+
+You can use Rubberduck with local models, e.g. [CodeLlama-7B-Instruct](https://huggingface.co/TheBloke/CodeLlama-7B-Instruct-GGUF) running in [Llama.cpp](https://github.com/ggerganov/llama.cpp) (see [ModelFusion Llama.cpp setup](https://modelfusion.dev/integration/model-provider/llamacpp#setup)). To enable llama.cpp in Rubberduck, set the `Rubberduck: Model` setting to `llama.cpp`.
+
 # Configuration Options
 
 - **rubberduck.syntaxHighlighting.useVisualStudioCodeColors**: Use the Visual Studio Code Theme colors for syntax highlighting in the diff viewer. Might not work with all themes. Default is `false`.