From e64353ada1de9bca90f1bee4d0b502337321e7e1 Mon Sep 17 00:00:00 2001 From: Paul Gauthier Date: Sun, 21 May 2023 14:18:57 -0700 Subject: [PATCH] copy --- docs/ctags.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/docs/ctags.md b/docs/ctags.md index ac286e0f9..98b683073 100644 --- a/docs/ctags.md +++ b/docs/ctags.md @@ -65,8 +65,8 @@ aider/ Mapping out the repo like this provides some benefits: - - GPT can see the variables, classes, methods and function signatures from everywhere in the repo. This alone may give it enough context to solve many tasks. For example, it can probably figure out how to use the API exported from a module based on the class, method and argument names shown in the map. - - If it needs to see more code, GPT use the map to figure out by itself which files it needs to look at. GPT then asks to see these files, and `aider` will automatically add them to the chat context (with user approval). + - GPT can see the variables, classes, methods and function signatures from everywhere in the repo. This alone may give it enough context to solve many tasks. For example, it can probably figure out how to use the API exported from a module based on the details shown in the map. + - If it needs to see more code, GPT use the map to figure out by itself which files it needs to look at. GPT will then ask to see these specific files, and `aider` will automatically add them to the chat context (with user approval). Of course, large repos will probably have maps that are too large for the context window. But this mapping approach makes enables