https://github.com/ashish10alex/vscode-ollama-chat
Experimental extension to chat with models available to download from Ollama
https://github.com/ashish10alex/vscode-ollama-chat
chatbot ollama vscode-extension
Last synced: 4 months ago
JSON representation
Experimental extension to chat with models available to download from Ollama
- Host: GitHub
- URL: https://github.com/ashish10alex/vscode-ollama-chat
- Owner: ashish10alex
- License: mit
- Created: 2025-02-02T00:42:11.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2025-02-17T23:24:46.000Z (over 1 year ago)
- Last Synced: 2026-02-11T01:41:54.071Z (6 months ago)
- Topics: chatbot, ollama, vscode-extension
- Language: TypeScript
- Homepage: https://marketplace.visualstudio.com/items?itemName=ashishalex.ollama-chat
- Size: 17.4 MB
- Stars: 4
- Watchers: 2
- Forks: 1
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- Changelog: CHANGELOG.md
- License: LICENSE
Awesome Lists containing this project
README
# Ollama Chat
VS Code extension that allows you to chat with self hosted models offline that can be downloaded from [ollama](https://ollama.com/download).
## Features
- [x] Chat with a model
- [x] Chat with a selection
- [ ] Add file as context to the chat
## How to use ?
1. Install [Ollama](https://ollama.com/download) and download a model.
```bash
ollama run qwen2.5-coder
```
2. Open terminal and run `ollama serve` or manually open Ollama app
3. Open the command palette in VSCode by pressing Cmd+Shift+P (Mac) or Ctrl+Shift+P (Windows/Linux), then run the Ollama Chat command. This will open the chat window shown in the screenshot.
## TODO
* [ ] feat: show error if user does not have ollama started either manually via opening the app or using `ollama serve`
* [ ] feat: show error if user does not have a model. Show them example command to install model
* [ ] feat: restrict user to certain number of tokens when sending message ?
* [ ] feat: processes pdfs ?
* [ ] feat: audio search
* [ ] build: Do we need to use a build system like web pack ?