obsidian-copilot
copilot.vim
obsidian-copilot | copilot.vim | |
---|---|---|
5 | 61 | |
450 | 7,754 | |
- | 4.0% | |
6.9 | 7.6 | |
6 days ago | 11 days ago | |
Python | Vim Script | |
Apache License 2.0 | GNU General Public License v3.0 or later |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
obsidian-copilot
-
Ask HN: Has Anyone Trained a personal LLM using their personal notes?
hadn't seen your repo yet [1] - adding it to my list right now.
Your blog post is really neat on top - thanks for sharing
https://github.com/eugeneyan/obsidian-copilot
-
Obsidian-Copilot: A Prototype Assistant for Writing and Thinking
Um... can someone explain what this actually does?
In the video the user chooses the 'Copilot: Draft' action, and wow, it generates code...
...but, the 'draft' action [1] calls `/get_chunks` and then runs 'queryLLM' [2] which then just invokes 'https://api.openai.com/v1/chat/completions' directly.
So, generating text this way is 100% not interesting or relevant.
What's interesting here is how it's building the prompt to send to the openai-api.
So... can anyone shed some light on what the actual code [3] in get_chunks() does, and why you would... hm... I guess, do a lookup and pass the results to the openai api, instead of just the raw text?
The repo says: "You write a section header and the copilot retrieves relevant notes & docs to draft that section for you.", and you can see in the linked post [4], this is basically what the OP is trying to implement here; you write 'I want X', and the plugin (a bit like copilot) does a lookup of related documents, crafts a meta-prompt and passes the prompt to the openai api.
...but, it doesn't seem to do that. It seems to ignore your actual prompt, lookup related documents by embedding similarity... and then... pass those documents in as the prompt?
I'm pretty confused as to why you would want that.
It basically requires that you write your prompt separately before hand, so you can invoke it magically with a one-line prompt later. Did I misunderstand how this works?
[1] - https://github.com/eugeneyan/obsidian-copilot/blob/bdabdc422...
[2] - https://github.com/eugeneyan/obsidian-copilot/blob/bdabdc422...
[3] - https://github.com/eugeneyan/obsidian-copilot/blob/main/src/...
[4] - https://eugeneyan.com/writing/llm-experiments/#shortcomings-...
copilot.vim
- Copilot.vim: Neovim Plugin for GitHub Copilot
-
Show HN: Use Code Llama as Drop-In Replacement for Copilot Chat
I use copilot in neovim[1]. It was remarkably simple to get installed. Highly recommend
[1]: https://github.com/github/copilot.vim
- How to use GitHub copilot in Vim?
- Obsidian-Copilot: A Prototype Assistant for Writing and Thinking
- Re: I Don't Use Copilot
-
Using Github Copilot.vim within Markdown fenced code blocks
I use Plug 'tpope/vim-markdown' and markdown fenced codeblocks fairly extensively, and recently installed Copilot.vim.
-
Neovim Integrations with AI and the rest of Internet
Anyways. Yes, neovim has AI integration like copilot ( https://github.com/github/copilot.vim ) and chatgpt ( https://github.com/jackMort/ChatGPT.nvim )
- Copilot nightly for Neovim?
-
I like Tabasco.
I do think VSCode is a great tool and I recommend it frequently to people, but I still want to set the record straight here. Yes, vim is obviously limited in the sense that as a CLI app it doesn't draw it's own PDF or HTML windows, that's fair. But it can remote control your favorite PDF viewer or browser for roughly the same functionality. I'm currently writing my thesis using vimtex and it's quite smooth. And all the other stuff you mention is implemented quite competently by various plugins like vim-fugitive, coc.nvim, vimspector and copilot.vim.
- [Neovim] Uso de GitHub Copilot en Neovim: <Bab> El mapa ha sido deshabilitado o es reclamado por otro complemento
What are some alternatives?
obsidian-smart-connections - Chat with your notes & see links to related content with AI embeddings. Use local models or 100+ via APIs like Claude, Gemini, ChatGPT & Llama 3
helix - A post-modern modal text editor.
llmware - Providing enterprise-grade LLM-based development framework, tools, and fine-tuned models.
copilot-cmp - Lua plugin to turn github copilot into a cmp source
tonic_validate - Metrics to evaluate the quality of responses of your Retrieval Augmented Generation (RAG) applications.
gpt-code-clippy - Full description can be found here: https://discuss.huggingface.co/t/pretrain-gpt-neo-for-open-source-github-copilot-model/7678?u=ncoop57
chroma-langchain
neovim-copilot-nix-bundle - Run Neovim with GitHub Copilot out of the box
ResuLLMe - Enhance your résumé with Large Language Models
SpaceVim - A community-driven modular vim/neovim distribution - The ultimate vimrc
markdown-embeddings-search - Obisidan notes to pinecone embeddings plus other files in effor to learn llama_index
vscode-neovim - Vim mode for VSCode, powered by Neovim