Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

document helix + gemini #90

Open
sigmaSd opened this issue Jan 5, 2025 · 0 comments
Open

document helix + gemini #90

sigmaSd opened this issue Jan 5, 2025 · 0 comments

Comments

@sigmaSd
Copy link

sigmaSd commented Jan 5, 2025

I tried helix + gemini with this project, here is where I landed
helix.toml

[language-server.lsp-ai]
command = "/home/mrcool/Downloads/lsp-ai-x86_64-unknown-linux-gnu"

[language-server.lsp-ai.config.memory]
file_store = { }

[language-server.lsp-ai.config.models.gemini2]
type = "gemini"
completions_endpoint = "https://generativelanguage.googleapis.com/v1beta/models/"
chat_endpoint = "https://generativelanguage.googleapis.com/v1beta/models/"
model = "gemini-2.0-flash-exp"
auth_token_env_var_name = "GOOGLE_API_KEY"

[language-server.lsp-ai.config.completion]
model = "gemini2"
parameters = {contents = [{role = "user", parts = [{text = "{CONTEXT} and {CODE}"}]}],  systemInstruction = {role = "system", parts = [{text = "You're giving the user input completion for code in his editor"}]}}

Almost works but the output needs some polishing

Screencast.From.2025-01-05.08-38-28.mp4

Also its slow, maybe gemini is not suited for completion, is adding supermaven support possible ? since its the fastest in completion

Gemini/Supermaven/Copilot are free so maybe its a good idea to make using them more straight forward

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant