Welcome to avante.nvim Discussions!

[yetone]

👋 Welcome!

We’re using Discussions as a place to connect with other members of our community. We hope that you:

• Ask questions you’re wondering about.
• Share ideas.
• Engage with other community members.
• Welcome others and are open-minded. Remember that this is a community we
  build together 💪.

To get started, comment below with an introduction of yourself and tell us about what you do with this community.

[skw1335]

is there a free way to use this? lol

[aarnphm]

you can run your local model with ollama, or any openai compatible endpoint. Check wiki for more information

[thechillday1]

Get

[RubenSmn]

I am using the free version of Gemini Flash. See https://ai.google.dev/pricing

[danielju91]

Hello! Loving the outlook of this project. Hoping it will catch up to and surpass Cursor AI in the long run. @aarnphm A quick question about running a local model. Is it compatible with LM Studio?

[thechillday1]

is there a free way to use this? lol

[raiku-dev]

@yetone Amazing project! How long did it take you to build this?

[yetone]

It took a total of two days, one of which was spent on prompt engineering-related tasks.

[thechillday1]

Can you share your project with me?

[gurius]

Is it possible to configure the plugin to work with other local LLMs providers like LM Studio? I've tried configuring it, but my attempts were unsuccessful.

[aarnphm]

afaict it supports openai-compatible endpoint, so it should support.

[hyprsh]

Just wanna ask if there is a offical Discord?

A lot of AI Tooling use Discord to stay in touch. Would be nice if avante also supports this way to talk about releases/ use cases and tips and tricks.

[aarnphm]

Hi there, running a discord is very hard to maintain. I refrain from doing this for now.

maybe once we have more ppl then sure, but github issues and PR will keep us focused.

[eyalk11]

I think that moderators are relatively easy to recurit. Though I don't see downside to having it , even if not moderated (unless in really exterme case) .

[thechillday1]

Fixed!

…

On Thu, 31 Oct 2024 at 09:12, Peter Petrov Miroshnikov < ***@***.***> wrote: Hello, I have successfully, to a degree, setup Avante with my nvim to use ollama locally. The requests to the AI seem to work as expected, but avante does not load the code from my project or file. Any question or request i send seems to default to Python, and a fresh new project without a context. While i am in the file and check the Repo Map it seems to read the file and understand it. But once i open the chat window <ladder>aa - it seems it doesnt catch none of the buffers. What could be the issues as this seems to be the main point of the product 😓 { "yetone/avante.nvim", event = "VeryLazy", lazy = true, version = false, -- set this if you want to always pull the latest change opts = { --providers = "copilot", provider = "ollama", use_absolute_path = true, vendors = { ***@***.*** AvanteProvider ollama = { ["local"] = true, endpoint = "127.0.0.1:11434/v1", model = "codegemma", parse_curl_args = function(opts, code_opts) return { url = opts.endpoint .. "/chat/completions", headers = { ["Accept"] = "application/json", ["Content-Type"] = "application/json", }, body = { model = opts.model, messages = require("avante.providers").copilot.parse_message(code_opts), -- you can make your own message, but this is very advanced max_tokens = 2048, stream = true, }, } end, parse_response_data = function(data_stream, event_state, opts) require("avante.providers").openai.parse_response(data_stream, event_state, opts) end, }, }, -- add any opts here }, -- if you want to build from source then do `make BUILD_FROM_SOURCE=true` build = "make", -- build = "powershell -ExecutionPolicy Bypass -File Build.ps1 -BuildFromSource false" -- for windows dependencies = { "stevearc/dressing.nvim", "nvim-lua/plenary.nvim", "MunifTanjim/nui.nvim", --- The below dependencies are optional, "nvim-tree/nvim-web-devicons", -- or echasnovski/mini.icons "zbirenbaum/copilot.lua", -- for providers='copilot' { -- support for image pasting "HakonHarnes/img-clip.nvim", event = "VeryLazy", opts = { -- recommended settings default = { embed_image_as_base64 = false, prompt_for_file_name = false, drag_and_drop = { insert_mode = true, }, -- required for Windows users use_absolute_path = true, }, }, }, { -- Make sure to set this up properly if you have lazy=true "MeanderingProgrammer/render-markdown.nvim", opts = { file_types = { "markdown", "Avante" }, }, ft = { "markdown", "Avante" }, }, }, }, — Reply to this email directly, view it on GitHub <#368 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/BK2XR6SYXFUPU3LWWY74F6DZ6HQ6DAVCNFSM6AAAAABNKWGZBGVHI2DSMVQWIX3LMV43URDJONRXK43TNFXW4Q3PNVWWK3TUHMYTCMJQHA3DKMQ> . You are receiving this because you commented.Message ID: <yetone/avante. ***@***.***>

[peter-miroshnikov]

I am sorry, i deleted my comment here as i figured out is the wrong place to ask a question.
Could you point me to the place where the fix is done so i can get a better perspective and not ask stupid questions.

[thechillday1]

Alright