continue.dev config.json free edition
Continue.dev itself is already free and open-sourced. However, to use it, you'll need API keys to access various providers, many of which are paid services.
While you can run models locally using Ollama, doing so requires a powerful machine with a GPU, which typically comes at a high cost. Additionally, models that can be run locally with ease typically have fewer parameters and are lighter, resulting in lower performance compared to API-provided models.
Fortunately, Google Gemini offers free quotas if you agree to allow the use of your usage data. Additionally, Mistral provides free Codestral API access, which can be used for auto-completion.
This config.json
file is preset to use these free services with continue.dev, so you don't need to pay to use it. An important aspect is the embeddingsProvider
setting. The default setting is not compatible with JetBrains' IDEs. Therefore, we use Google's text-embedding-004
model to ensure that this configuration works seamlessly with both VSCode and JetBrains IDEs.
-
Obtain Your API Keys:
-
Install the Extension in Your IDE:
-
Configure
config.json
:- Overwrite your existing
config.json
with the provided configuration below. The default location is~/.continue/config.json
.
- Overwrite your existing
-
Restart Your IDE:
- After updating the
config.json
, restart your IDE to apply the changes.
- After updating the
{
"models": [
{
"title": "Gemini 1.5 Flash",
"model": "gemini-1.5-flash-latest",
"provider": "gemini",
"apiKey": "your-gemini-api-key (see above)"
},
{
"title": "Gemini 1.5 Flash 002",
"model": "gemini-1.5-flash-002",
"provider": "gemini",
"apiKey": "your-gemini-api-key (see above)"
},
{
"title": "Gemini 1.5 Pro",
"model": "gemini-1.5-pro-latest",
"provider": "gemini",
"apiKey": "your-gemini-api-key (see above)"
},
{
"title": "Gemini 1.5 Pro 002",
"model": "gemini-1.5-pro-002",
"provider": "gemini",
"apiKey": "your-gemini-api-key (see above)"
},
{
"title": "Codestral",
"provider": "mistral",
"model": "codestral-latest",
"apiKey": "your-codestral-api-key (see above)"
}
],
"embeddingsProvider": {
"model": "models/text-embedding-004",
"provider": "gemini",
"apiKey": "your-gemini-api-key (see above)"
},
"tabAutocompleteModel": {
"title": "Codestral",
"provider": "mistral",
"model": "codestral-latest",
"apiKey": "your-codestral-api-key (see above)"
},
"customCommands": [
{
"name": "test",
"prompt": "{{{ input }}}\n\nWrite a comprehensive set of unit tests for the selected code. It should setup, run tests that check for correctness including important edge cases, and teardown. Ensure that the tests are complete and sophisticated. Give the tests just as chat output, don't edit any file.",
"description": "Write unit tests for highlighted code"
}
],
"contextProviders": [
{
"name": "code",
"params": {}
},
{
"name": "docs",
"params": {}
},
{
"name": "diff",
"params": {}
},
{
"name": "terminal",
"params": {}
},
{
"name": "problems",
"params": {}
},
{
"name": "folder",
"params": {}
},
{
"name": "codebase",
"params": {}
}
],
"slashCommands": [
{
"name": "edit",
"description": "Edit selected code"
},
{
"name": "comment",
"description": "Write comments for the selected code"
},
{
"name": "share",
"description": "Export the current chat session to markdown"
},
{
"name": "cmd",
"description": "Generate a shell command"
},
{
"name": "commit",
"description": "Generate a git commit message"
}
]
}
- Google uses the usage data from their free API access to improve their products.
- Google's Gemini models may have lower performance compared to other competing models.