From aac77d965987261163bf97b8a6f998a9cb39079d Mon Sep 17 00:00:00 2001 From: Paul Gauthier Date: Sun, 21 May 2023 14:22:51 -0700 Subject: [PATCH] aider: Improve para starting 'Of course for large repos' in ctags.md. # Context: USER: improve the para starting "Of course for large repos" ASSISTANT: ```markdown docs/ctags.md <<<<<<< ORIGINAL Of course, for large repos even their map might be too large for the context window. But this mapping approach enables collaboration with GPT-4 on larger code bases than was previously possible. And it reduces the need to manually curate which files to add to the chat, giving GPT itself more ability to identify which files are relevant to the task at hand. ======= Of course, for large repositories, even their map might be too large for the context window. However, this mapping approach significantly improves collaboration with GPT-4 on larger codebases compared to previous methods. It also minimizes the need for manual curation of files to add to the chat, empowering GPT to autonomously identify relevant files for the task at hand. >>>>>>> UPDATED ``` --- docs/ctags.md | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) diff --git a/docs/ctags.md b/docs/ctags.md index 5cb811ae9..f3c3b5bbf 100644 --- a/docs/ctags.md +++ b/docs/ctags.md @@ -68,14 +68,7 @@ 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 details shown in the map. - If it needs to see more code, GPT can 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, for large repos even their map might be too large for -the context window. -But this mapping approach enables -collaboration with GPT-4 on larger code bases -than was previously possible. -And it reduces the need to manually curate which files to add -to the chat, giving GPT itself more ability to identify which files -are relevant to the task at hand. +Of course, for large repositories, even their map might be too large for the context window. However, this mapping approach significantly improves collaboration with GPT-4 on larger codebases compared to previous methods. It also minimizes the need for manual curation of files to add to the chat, empowering GPT to autonomously identify relevant files for the task at hand. ## Using ctags to make the map