dearwolf/aider
1
0
Fork 0
mirror of https://github.com/Aider-AI/aider.git synced 2025-05-28 16:25:00 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 4

copy

Browse source
This commit is contained in:
Paul Gauthier 2024-04-19 13:45:51 -07:00
parent 6cecbd02d6
commit aac110f078
4 changed files with 58 additions and 92 deletions
Download patch file Download diff file Expand all files Collapse all files

53
docs/connect.md
View file

@ -4,11 +4,13 @@
Aider works well with OpenAI's GPT 3.5, GPT-4, GPT-4 Turbo with Vision and
Anthropic's Claude 3 Opus and Sonnet.
GPT-4 Turbo and Claude 3 Opus are recommended for the best results.
Aider also has support for connecting to almost any LLM, but may not be as effective
because of the reduced capabilities of such alternative models.
depending on the capabilities of the model.
For comparison, GPT-3.5 is just barely capable of *editing code* to provide aider's
interactive "pair programming" style workflow.
So models that are less capable than GPT-3.5 may struggle to perform well with aider.
Models that are less capable than GPT-3.5 may struggle to perform well with aider.
## OpenAI
@ -20,11 +22,13 @@ via the `--openai-api-key` command line switch.
Aider has some built in shortcuts for the most popular OpenAI models and
has been tested and benchmarked to work well with them:
- OpenAI's GPT-4 Turbo: `aider` with no args uses GPT-4 Turbo by default.
- OpenAI's GPT-4 Turbo with Vision: `aider --4turbo` will use this vision capable model, allowing you to share images with GPT by adding them to the chat with `/add` or by naming them on the command line.
- OpenAI's GPT-3.5 Turbo: `aider --35turbo`
- OpenAI's GPT-4 Turbo: run `aider` with no args uses GPT-4 Turbo by default.
- OpenAI's GPT-4 Turbo with Vision: run `aider --4-turbo-vision` to use this vision capable model, allowing you to share images with GPT by adding them to the chat with `/add` or by naming them on the command line.
- OpenAI's GPT-3.5 Turbo: Run `aider --35-turbo`.
You can use `aider --model <model-name>` to use any other OpenAI model.
For example, if you want to use a specific version of GPT-4 Turbo
you could do `aider --model gpt-4-0125-preview`.
## Anthropic
@ -40,6 +44,8 @@ has been tested and benchmarked to work well with them:
- Anthropic's Claude 3 Sonnet: `aider --sonnet`
You can use `aider --model <model-name>` to use any other Anthropic model.
For example, if you want to use a specific version of Opus
you could do `aider --model claude-3-opus-20240229`.
## Azure
@ -88,33 +94,30 @@ you can use `--openai-api-base` to connect to a different API endpoint.
## Other LLMs
Aider uses the [litellm](https://docs.litellm.ai/docs/providers) package
to provide connections to hundreds of other models.
You can use `aider --model <provider-name>/<model-name>` to use any supported model.
Depending on which model you access, you may need to provide an API key
or other configuration parameters by setting certain environment variables.
If any required variables are not set, aider will print a brief
error message listing which parameters are needed.
to connect to hundreds of other models.
You can use `aider --model <model-name>` to use any supported model.
To explore the list of supported models you can run `aider --model <name>`.
If it's not an exact match for a model, aider will
return a list of possible matching models.
For example `aider --model 3.5` will return the following list of models:
For example:
```
$ aider --model turbo
Unknown model turbo, did you mean one of these?
- gpt-4-turbo-preview
- gpt-4-turbo
- gpt-4-turbo-2024-04-09
- gpt-3.5-turbo
- gpt-3.5-turbo-0301
- gpt-3.5-turbo-0613
- gpt-3.5-turbo-1106
- gpt-3.5-turbo-0125
- gpt-3.5-turbo-16k
- gpt-3.5-turbo-16k-0613
- ft:gpt-3.5-turbo
- azure/gpt-3.5-turbo-instruct-0914
- gpt-3.5-turbo-instruct
- gpt-3.5-turbo-instruct-0914
- openrouter/openai/gpt-3.5-turbo
- openrouter/openai/gpt-3.5-turbo-16k
- deepinfra/openchat/openchat_3.5
...
```
Depending on which model you access, you may need to provide an API key
or other configuration parameters by setting certain environment variables.
If any required variables are not set, aider will print an
error message listing which parameters are needed.
Or, see the [list of providers supported by litellm](https://docs.litellm.ai/docs/providers)
for more details.

92
docs/faq.md
View file

@ -2,14 +2,13 @@
# Frequently asked questions
- [How does aider use git?](#how-does-aider-use-git)
- [Can I use aider with other LLMs, local LLMs, etc?](#can-i-use-aider-with-other-llms-local-llms-etc)
- [Accessing other LLMs with OpenRouter](#accessing-other-llms-with-openrouter)
- [Aider isn't editing my files?](#aider-isnt-editing-my-files)
- [Can I use aider with other LLMs, local LLMs, etc?](https://aider.chat/docs/connect.html)
- [Can I run aider in Google Colab?](#can-i-run-aider-in-google-colab)
- [How can I run aider locally from source code?](#how-can-i-run-aider-locally-from-source-code)
- [Can I script aider?](#can-i-script-aider)
- [What code languages does aider support?](#what-code-languages-does-aider-support)
- [How to use pipx to avoid python package conflicts?](#how-to-use-pipx-to-avoid-python-package-conflicts)
- [Aider isn't editing my files?](#aider-isnt-editing-my-files)
- [How can I add ALL the files to the chat?](#how-can-i-add-all-the-files-to-the-chat)
- [Can I specify guidelines or conventions?](#can-i-specify-guidelines-or-conventions)
- [Can I change the system prompts that aider uses?](#can-i-change-the-system-prompts-that-aider-uses)
@ -39,68 +38,6 @@ While it is not recommended, you can disable aider's use of git in a few ways:
- `--no-dirty-commits` will stop aider from committing dirty files before applying GPT's edits.
- `--no-git` will completely stop aider from using git on your files. You should ensure you are keeping sensible backups of the files you are working with.
## Can I use aider with other LLMs, local LLMs, etc?
Aider provides experimental support for LLMs other than OpenAI's GPT-3.5 and GPT-4. The support is currently only experimental for two reasons:
- GPT-3.5 is just barely capable of *editing code* to provide aider's interactive "pair programming" style workflow. None of the other models seem to be as capable as GPT-3.5 yet.
- Just "hooking up" aider to a new model by connecting to its API is almost certainly not enough to get it working in a useful way. Getting aider working well with GPT-3.5 and GPT-4 was a significant undertaking, involving [specific code editing prompts and backends for each model and extensive benchmarking](https://aider.chat/docs/benchmarks.html). Officially supporting each new LLM will probably require a similar effort to tailor the prompts and editing backends.
Numerous users have done experiments with numerous models. None of these experiments have yet identified other models that look like they are capable of working well with aider.
Once we see signs that a *particular* model is capable of code editing, it would be reasonable for aider to attempt to officially support such a model. Until then, aider will simply maintain experimental support for using alternative models.
There are ongoing discussions about [LLM integrations in the aider discord](https://discord.gg/yaUk7JqJ9G).
Here are some [GitHub issues which may contain relevant information](https://github.com/paul-gauthier/aider/issues?q=is%3Aissue+%23172).
### OpenAI API compatible LLMs
If you can make the model accessible via an OpenAI compatible API,
you can use `--openai-api-base` to connect to a different API endpoint.
### Local LLMs
[LiteLLM](https://github.com/BerriAI/litellm) and
[LocalAI](https://github.com/go-skynet/LocalAI)
are relevant tools to serve local models via an OpenAI compatible API.
### Azure
See the documentation on connection to LLMs for details on
[connecting aider to Azure]().
## Accessing other LLMs with OpenRouter
See the documentation on connection to LLMs for details on
[connecting aider to OpenRouter]().
## Aider isn't editing my files?
Sometimes GPT will reply with some code changes that don't get applied to your local files.
In these cases, aider might say something like "Failed to apply edit to *filename*".
This usually happens because GPT is not specifying the edits
to make in the format that aider expects.
GPT-3.5 is especially prone to disobeying the system prompt instructions in this manner, but it also happens with GPT-4.
Aider makes every effort to get GPT to conform, and works hard to deal with
replies that are "almost" correctly formatted.
If Aider detects an improperly formatted reply, it gives GPT feedback to try again.
Also, before each release new versions of aider are
[benchmarked](https://aider.chat/docs/benchmarks.html).
This helps prevent regressions in the code editing
performance of GPT that could have been inadvertantly
introduced.
But sometimes GPT just won't cooperate.
In these cases, here are some things you might try:
- Try the older GPT-4 model `gpt-4-0613` not GPT-4 Turbo by running `aider --model gpt-4-0613`.
- Use `/drop` to remove files from the chat session which aren't needed for the task at hand. This will reduce distractions and may help GPT produce properly formatted edits.
- Use `/clear` to remove the conversation history, again to help GPT focus.
## Can I run aider in Google Colab?
@ -275,6 +212,31 @@ Install [pipx](https://pipx.pypa.io/stable/) then just do:
pipx install aider-chat
```
## Aider isn't editing my files?
Sometimes GPT will reply with some code changes that don't get applied to your local files.
In these cases, aider might say something like "Failed to apply edit to *filename*".
This usually happens because GPT is not specifying the edits
to make in the format that aider expects.
GPT-3.5 is especially prone to disobeying the system prompt instructions in this manner, but it also happens with GPT-4.
Aider makes every effort to get GPT to conform, and works hard to deal with
replies that are "almost" correctly formatted.
If Aider detects an improperly formatted reply, it gives GPT feedback to try again.
Also, before each release new versions of aider are
[benchmarked](https://aider.chat/docs/benchmarks.html).
This helps prevent regressions in the code editing
performance of GPT that could have been inadvertantly
introduced.
But sometimes GPT just won't cooperate.
In these cases, here are some things you might try:
- Try the older GPT-4 model `gpt-4-0613` not GPT-4 Turbo by running `aider --model gpt-4-0613`.
- Use `/drop` to remove files from the chat session which aren't needed for the task at hand. This will reduce distractions and may help GPT produce properly formatted edits.
- Use `/clear` to remove the conversation history, again to help GPT focus.
## How can I add ALL the files to the chat?
People regularly ask about how to add **many or all of their repo's files** to the chat.