dearwolf/aider
1
0
Fork 0
mirror of https://github.com/Aider-AI/aider.git synced 2025-06-02 02:34:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 5

copy

Browse source
This commit is contained in:
Paul Gauthier 2024-04-29 06:35:45 -07:00
parent 8a9005eed1
commit 03908c5ab6
1 changed files with 16 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

22
docs/llms.md
View file

@ -28,10 +28,12 @@ Aider can work also with local models, for example using [Ollama](#ollama).
## Other models ## Other models
Aider supports connecting to almost any LLM, Aider supports connecting to almost any LLM,
but it may not work well with some models depending on their capabilities. but it may not work well with less capable models.
For example, GPT-3.5 is just barely capable of reliably *editing code* to provide aider's If you see the model returning code, but aider isn't able to edit your files
interactive "pair programming" style workflow. and commit the changes...
So you should expect that models which are less capable than GPT-3.5 may struggle to perform well with aider. this is usually because the model isn't capable of properly
returning "code edits".
Models weaker than GPT 3.5 may have problems working well with aider.
## Configuring models ## Configuring models
@ -288,8 +290,16 @@ for more details.
## Model warnings ## Model warnings
On startup, aider tries to sanity check that it is configured correctly Aider supports connecting to almost any LLM,
to work with the specified models: but it may not work well with less capable models.
If you see the model returning code, but aider isn't able to edit your files
and commit the changes...
this is usually because the model isn't capable of properly
returning "code edits".
Models weaker than GPT 3.5 may have problems working well with aider.
Aider tries to sanity check that it is configured correctly
to work with the specified model:
- It checks to see that all required environment variables are set for the model. These variables are required to configure things like API keys, API base URLs, etc. - It checks to see that all required environment variables are set for the model. These variables are required to configure things like API keys, API base URLs, etc.
- It checks a metadata database to look up the context window size and token costs for the model. - It checks a metadata database to look up the context window size and token costs for the model.