dearwolf/aider
1
0
Fork 0
mirror of https://github.com/Aider-AI/aider.git synced 2025-05-29 16:54:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

copy

Browse source
This commit is contained in:
Paul Gauthier 2024-06-06 06:26:57 -07:00
parent c6074c16f3
commit e341fb9baa
3 changed files with 48 additions and 177 deletions
Download patch file Download diff file Expand all files Collapse all files

11
README.md
View file

@ -4,7 +4,7 @@
Aider lets you pair program with LLMs,
to edit code in your local git repository.
Start a new project or work with an existing git repo.
Aider works well with GPT-4o, Claude 3 Opus, GPT-3.5
Aider works best with GPT-4o, Claude 3 Opus
and can [connect to almost any LLM](https://aider.chat/docs/llms.html).
<p align="center">
@ -47,7 +47,8 @@ $ aider --opus
- Aider will edit your files to complete your request.
- 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 well with GPT-4o, Claude 3 Opus, GPT-3.5 and supports [connecting to many LLMs](https://aider.chat/docs/llms.html).
- Aider works best with GPT-4o, Claude 3 Opus
and can [connect to almost any LLM](https://aider.chat/docs/llms.html).
- Aider can make coordinated changes across multiple files at once.
- Aider uses a [map of your entire git repo](https://aider.chat/docs/repomap.html), which helps it work well in larger codebases.
- You can also edit files in your editor while chatting with aider.
@ -72,8 +73,10 @@ So you can bounce back and forth between aider and your editor, to collaborative
## State of the art
Aider has the highest score on the challenging
[SWE Bench benchmark](https://aider.chat/2024/06/02/main-swe-bench.html).
Aider has the
[highest score on SWE Bench](https://aider.chat/2024/06/02/main-swe-bench.html),
a challenging sofrware engineering benchmark where aider
solves GitHub issues.
<p align="center">
<a href="https://aider.chat/2024/06/02/main-swe-bench.html">

203
website/docs/usage.md
View file

@ -2,192 +2,57 @@
nav_order: 30
---
## Usage
# Usage
Run `aider` with the source code files you want to edit.
These files will be "added to the chat session", so that the LLM can see their
contents and edit them according to your instructions.
These files will be "added to the chat session", so that
aider can see their
contents and edit them for you.
```
aider <file1> <file2> ...
```
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
## Adding files
Just add the files that the aider will need to *edit*.
If you add too many files, the LLM can get overwhelmed
and confused (and it costs more tokens).
Aider will automatically
share snippets from related files with the LLM so it can
pull in content from related files so that it can
[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 then add and remove files in the chat
with the `/add` and `/drop` [chat commands](/docs/commands.html).
You can also run aider without naming any files and use the in-chat
`/add` command to add files.
See info about how to [connect to LLMs](/docs/llms.html) for information on
telling aider which model to use.
Or you can skip adding files completely, and aider
will try to figure out which files need to be edited based
on your requests.
Aider also has many other options which can be set with
command line switches, environment variables or via a configuration file.
## LLMs
See `aider --help` below for details.
Aider uses GPT-4o by default, but you can
[connect to many different LLMs](/docs/llms.html).
Claude 3 Opus is another model which works very well with aider,
which you can use by running `aider --opus`.
<!--[[[cog
from aider.args import get_help
cog.outl("```")
cog.out(get_help())
cog.outl("```")
]]]-->
```
usage: aider [-h] [--openai-api-key OPENAI_API_KEY] [--anthropic-api-key ANTHROPIC_API_KEY]
[--model MODEL] [--opus] [--sonnet] [--4] [--4o] [--4-turbo] [--35turbo]
[--models MODEL] [--openai-api-base OPENAI_API_BASE]
[--openai-api-type OPENAI_API_TYPE] [--openai-api-version OPENAI_API_VERSION]
[--openai-api-deployment-id OPENAI_API_DEPLOYMENT_ID]
[--openai-organization-id OPENAI_ORGANIZATION_ID] [--edit-format EDIT_FORMAT]
[--weak-model WEAK_MODEL] [--show-model-warnings | --no-show-model-warnings]
[--map-tokens MAP_TOKENS] [--max-chat-history-tokens MAX_CHAT_HISTORY_TOKENS]
[--env-file ENV_FILE] [--input-history-file INPUT_HISTORY_FILE]
[--chat-history-file CHAT_HISTORY_FILE]
[--restore-chat-history | --no-restore-chat-history] [--dark-mode] [--light-mode]
[--pretty | --no-pretty] [--stream | --no-stream]
[--user-input-color USER_INPUT_COLOR] [--tool-output-color TOOL_OUTPUT_COLOR]
[--tool-error-color TOOL_ERROR_COLOR]
[--assistant-output-color ASSISTANT_OUTPUT_COLOR] [--code-theme CODE_THEME]
[--show-diffs] [--git | --no-git] [--gitignore | --no-gitignore]
[--aiderignore AIDERIGNORE] [--auto-commits | --no-auto-commits]
[--dirty-commits | --no-dirty-commits] [--dry-run | --no-dry-run] [--commit] [--lint]
[--lint-cmd LINT_CMD] [--auto-lint | --no-auto-lint] [--test-cmd TEST_CMD]
[--auto-test | --no-auto-test] [--test] [--voice-language VOICE_LANGUAGE] [--version]
[--check-update] [--skip-check-update] [--apply FILE] [--yes] [-v] [--show-repo-map]
[--show-prompts] [--message COMMAND] [--message-file MESSAGE_FILE]
[--encoding ENCODING] [-c CONFIG_FILE] [--gui]
[FILE ...]
You can run `aider --model XXX` to launch aider with
a specific model.
Or, during your chat you can switch models with the in-chat
`/model` command.
aider is GPT powered coding in your terminal
## Making changes
options:
-h, --help show this help message and exit
Ask aider to make changes to your code.
It will show you some diffs of the changes it is making to
complete you request.
It will git commit all the changes it makes,
so they are easy to track and undo.
Main:
FILE files to edit with an LLM (optional)
--openai-api-key OPENAI_API_KEY
Specify the OpenAI API key [env var: OPENAI_API_KEY]
--anthropic-api-key ANTHROPIC_API_KEY
Specify the OpenAI API key [env var: ANTHROPIC_API_KEY]
--model MODEL Specify the model to use for the main chat (default: gpt-4o)
--opus Use claude-3-opus-20240229 model for the main chat
--sonnet Use claude-3-sonnet-20240229 model for the main chat
--4, -4 Use gpt-4-0613 model for the main chat
--4o Use gpt-4o model for the main chat
--4-turbo Use gpt-4-1106-preview model for the main chat
--35turbo, --35-turbo, --3, -3
Use gpt-3.5-turbo model for the main chat
You can always use the `/undo` command to undo changes you don't
like.
Model Settings:
--models MODEL List known models which match the (partial) MODEL name
--openai-api-base OPENAI_API_BASE
Specify the api base url [env var: OPENAI_API_BASE]
--openai-api-type OPENAI_API_TYPE
Specify the api_type [env var: OPENAI_API_TYPE]
--openai-api-version OPENAI_API_VERSION
Specify the api_version [env var: OPENAI_API_VERSION]
--openai-api-deployment-id OPENAI_API_DEPLOYMENT_ID
Specify the deployment_id [env var: OPENAI_API_DEPLOYMENT_ID]
--openai-organization-id OPENAI_ORGANIZATION_ID
Specify the OpenAI organization ID [env var: OPENAI_ORGANIZATION_ID]
--edit-format EDIT_FORMAT
Specify what edit format the LLM should use (default depends on model)
--weak-model WEAK_MODEL
Specify the model to use for commit messages and chat history
summarization (default depends on --model)
--show-model-warnings, --no-show-model-warnings
Only work with models that have meta-data available (default: True)
--map-tokens MAP_TOKENS
Max number of tokens to use for repo map, use 0 to disable (default: 1024)
--max-chat-history-tokens MAX_CHAT_HISTORY_TOKENS
Maximum number of tokens to use for chat history. If not specified, uses
the model's max_chat_history_tokens.
--env-file ENV_FILE Specify the .env file to load (default: .env in git root)
## See also
History Files:
--input-history-file INPUT_HISTORY_FILE
Specify the chat input history file (default: .aider.input.history)
--chat-history-file CHAT_HISTORY_FILE
Specify the chat history file (default: .aider.chat.history.md)
--restore-chat-history, --no-restore-chat-history
Restore the previous chat history messages (default: False)
Output Settings:
--dark-mode Use colors suitable for a dark terminal background (default: False)
--light-mode Use colors suitable for a light terminal background (default: False)
--pretty, --no-pretty
Enable/disable pretty, colorized output (default: True)
--stream, --no-stream
Enable/disable streaming responses (default: True)
--user-input-color USER_INPUT_COLOR
Set the color for user input (default: #00cc00)
--tool-output-color TOOL_OUTPUT_COLOR
Set the color for tool output (default: None)
--tool-error-color TOOL_ERROR_COLOR
Set the color for tool error messages (default: red)
--assistant-output-color ASSISTANT_OUTPUT_COLOR
Set the color for assistant output (default: #0088ff)
--code-theme CODE_THEME
Set the markdown code theme (default: default, other options include
monokai, solarized-dark, solarized-light)
--show-diffs Show diffs when committing changes (default: False)
Git Settings:
--git, --no-git Enable/disable looking for a git repo (default: True)
--gitignore, --no-gitignore
Enable/disable adding .aider* to .gitignore (default: True)
--aiderignore AIDERIGNORE
Specify the aider ignore file (default: .aiderignore in git root)
--auto-commits, --no-auto-commits
Enable/disable auto commit of LLM changes (default: True)
--dirty-commits, --no-dirty-commits
Enable/disable commits when repo is found dirty (default: True)
--dry-run, --no-dry-run
Perform a dry run without modifying files (default: False)
Fixing and committing:
--commit Commit all pending changes with a suitable commit message, then exit
--lint Lint and fix provided files, or dirty files if none provided
--lint-cmd LINT_CMD Specify lint commands to run for different languages, eg: "python: flake8
--select=..." (can be used multiple times)
--auto-lint, --no-auto-lint
Enable/disable automatic linting after changes (default: True)
--test-cmd TEST_CMD Specify command to run tests
--auto-test, --no-auto-test
Enable/disable automatic testing after changes (default: False)
--test Run tests and fix problems found
Other Settings:
--voice-language VOICE_LANGUAGE
Specify the language for voice using ISO 639-1 code (default: auto)
--version Show the version number and exit
--check-update Check for updates and return status in the exit code
--skip-check-update Skips checking for the update when the program runs
--apply FILE Apply the changes from the given file instead of running the chat (debug)
--yes Always say yes to every confirmation
-v, --verbose Enable verbose output
--show-repo-map Print the repo map and exit (debug)
--show-prompts Print the system prompts and exit (debug)
--message COMMAND, --msg COMMAND, -m COMMAND
Specify a single message to send the LLM, process reply then exit
(disables chat mode)
--message-file MESSAGE_FILE, -f MESSAGE_FILE
Specify a file containing the message to send the LLM, process reply, then
exit (disables chat mode)
--encoding ENCODING Specify the encoding for input and output (default: utf-8)
-c CONFIG_FILE, --config CONFIG_FILE
Specify the config file (default: search for .aider.conf.yml in git root,
cwd or home directory)
--gui, --browser Run aider in your browser
Args that start with '--' can also be set in a config file (specified via -c). Config file syntax
allows: key=value, flag=true, stuff=[a,b,c] (for details, see syntax at https://goo.gl/R74nmi). In
general, command-line values override environment variables which override config file values
which override defaults.
```
<!--[[[end]]]-->
See also the docs on [in-chat commands](/docs/commands.html)
and [configuration and options])/docs/options.html).

11
website/index.md
View file

@ -12,7 +12,7 @@ cog.out(open("README.md").read())
Aider lets you pair program with LLMs,
to edit code in your local git repository.
Start a new project or work with an existing git repo.
Aider works well with GPT-4o, Claude 3 Opus, GPT-3.5
Aider works best with GPT-4o, Claude 3 Opus
and can [connect to almost any LLM](https://aider.chat/docs/llms.html).
<p align="center">
@ -55,7 +55,8 @@ $ aider --opus
- Aider will edit your files to complete your request.
- 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 well with GPT-4o, Claude 3 Opus, GPT-3.5 and supports [connecting to many LLMs](https://aider.chat/docs/llms.html).
- Aider works best with GPT-4o, Claude 3 Opus
and can [connect to almost any LLM](https://aider.chat/docs/llms.html).
- Aider can make coordinated changes across multiple files at once.
- Aider uses a [map of your entire git repo](https://aider.chat/docs/repomap.html), which helps it work well in larger codebases.
- You can also edit files in your editor while chatting with aider.
@ -80,8 +81,10 @@ So you can bounce back and forth between aider and your editor, to collaborative
## State of the art
Aider has the highest score on the challenging
[SWE Bench benchmark](https://aider.chat/2024/06/02/main-swe-bench.html).
Aider has the
[highest score on SWE Bench](https://aider.chat/2024/06/02/main-swe-bench.html),
a challenging sofrware engineering benchmark where aider
solves GitHub issues.
<p align="center">
<a href="https://aider.chat/2024/06/02/main-swe-bench.html">