This commit is contained in:
Paul Gauthier 2024-06-05 20:55:41 -07:00
parent c5e127d6fa
commit 0b7bee8712
3 changed files with 6 additions and 7 deletions

View file

@ -1,8 +1,8 @@
--- ---
title: Building a better repository map with tree sitter title: Repository map
excerpt: Tree-sitter allows aider to build a repo map that better summarizes large code bases. excerpt: Tree-sitter allows aider to build a repo map that better summarizes large code bases.
highlight_image: /assets/robot-ast.png highlight_image: /assets/robot-ast.png
nav_exclude: true nav_order: 95
--- ---
{% if page.date %} {% if page.date %}
<p class="post-date">{{ page.date | date: "%B %d, %Y" }}</p> <p class="post-date">{{ page.date | date: "%B %d, %Y" }}</p>

View file

@ -16,14 +16,12 @@ Be selective, and just add the files that the LLM will need to edit.
If you add a bunch of unrelated files, the LLM can get overwhelmed If you add a bunch of unrelated files, the LLM can get overwhelmed
and confused (and it costs more tokens). and confused (and it costs more tokens).
Aider will automatically Aider will automatically
share snippets from other, related files with the LLM so it can share snippets from related files with the LLM so it can
[understand the rest of your code base](https://aider.chat/docs/repomap.html). [understand the rest of your code base](https://aider.chat/docs/repomap.html).
You can also just launch aider anywhere in a git repo without naming files. You can also just launch aider anywhere in a git repo without naming files.
You can then add and remove files in the chat You can then add and remove files in the chat
with the `/add` and `/drop` [chat commands](/docs/commands.html). with the `/add` and `/drop` [chat commands](/docs/commands.html).
If you or the LLM mention any of the repo filenames,
aider will ask if you'd like to add them to the chat.
See info about how to [connect to LLMs](/docs/llms.html) for information on See info about how to [connect to LLMs](/docs/llms.html) for information on
telling aider which model to use. telling aider which model to use.

View file

@ -52,8 +52,8 @@ $ aider --opus
- New features, changes, improvements, or bug fixes to your code. - New features, changes, improvements, or bug fixes to your code.
- New test cases, updated documentation or code refactors. - New test cases, updated documentation or code refactors.
- Paste in a GitHub issue url that needs to be solved. - Paste in a GitHub issue url that needs to be solved.
- Aider will edit your files. - Aider will edit your files to complete your request.
- Aider [automatically git commits changes](https://aider.chat/docs/faq.html#how-does-aider-use-git) with a sensible commit message. - Aider [automatically git commits](https://aider.chat/docs/faq.html#how-does-aider-use-git) changes with a sensible commit message.
- Aider works with [most popular languages](https://aider.chat/docs/languages.html): python, javascript, typescript, php, html, css, and more... - Aider works with [most popular languages](https://aider.chat/docs/languages.html): python, javascript, typescript, php, html, css, and more...
- Aider works well with GPT-4o, Claude 3 Opus, GPT-3.5 and supports [connecting to many LLMs](https://aider.chat/docs/llms.html). - Aider works well with GPT-4o, Claude 3 Opus, GPT-3.5 and supports [connecting to many LLMs](https://aider.chat/docs/llms.html).
- Aider can make coordinated changes across multiple files at once. - Aider can make coordinated changes across multiple files at once.
@ -63,6 +63,7 @@ Aider will notice and always use the latest version.
So you can bounce back and forth between aider and your editor, to collaboratively code with AI. So you can bounce back and forth between aider and your editor, to collaboratively code with AI.
- Images can be added to the chat (GPT-4o, GPT-4 Turbo, etc). - Images can be added to the chat (GPT-4o, GPT-4 Turbo, etc).
- URLs can be added to the chat and aider will read their content. - URLs can be added to the chat and aider will read their content.
- [Code with your voice](https://aider.chat/docs/voice.html) using speech recognition.
## Documentation ## Documentation