feat(ollama): provide a helper to enable ollama when service is available

Ollama is disabled by default, as it normally does not require API keys
to be defined. Users are supposed to override is_env_set() method in
their configs to enable Ollama.

Provide check_endpoint_alive() helper in Ollama provider module that can
be used directly in place of is_env_set() and checks whether the server
replies to "get list of models" query:

...
  ollama = {
    is_env_set = require("avante.providers.ollama").check_endpoint_alive,
  },
...
This commit is contained in:
Dmitry Torokhov
2025-10-12 22:30:46 -07:00
parent 3e8557a29e
commit 2f9daf2bc6
3 changed files with 45 additions and 23 deletions

View File

@@ -1163,14 +1163,17 @@ This approach ensures that the apply model can quickly and accurately merge your
## Ollama
ollama is a first-class provider for avante.nvim. You can use it by setting `provider = "ollama"` in the configuration, and set the `model` field in `ollama` to the model you want to use. For example:
Ollama is a first-class provider for avante.nvim. To start using it you need to set `provider = "ollama"`
in the configuration, set the `model` field in `ollama` to the model you want to use. Ollama is disabled
by default, you need to provide an implementation for its `is_env_set` method to properly enable it.
For example:
```lua
provider = "ollama",
providers = {
ollama = {
endpoint = "http://localhost:11434",
model = "qwq:32b",
is_env_set = require("avante.providers.ollama").check_endpoint_alive,
},
}
```