Fabelous-Autocoder/README.md

# Fabelous Autocoder

A simple to use Ollama autocompletion engine with options exposed and streaming functionality


## Requirements

- Ollama must be serving on the API endpoint applied in settings
  - For installation of Ollama, visit [ollama.ai](https://ollama.ai)
- Ollama must have the model applied in settings installed.

## How to Use

1. In a text document, press space *(or any character in the `completion keys` setting)*. The option `Autocomplete with Ollama` or a preview of the first line of autocompletion will appear. Press `enter` to start generation.
   - Alternatively, you can run the `Autocomplete with Ollama` command from the command pallete (or set a keybind).
2. After startup, the tokens will be streamed to your cursor.
3. To stop the generation early, press the "Cancel" button on the "Ollama Autocoder" notification or type something.
4. Once generation stops, the notification will disappear.

## Notes

- For fastest results, an Nvidia GPU or Apple Silicon is recommended. CPU still works on small models.
- The prompt only sees behind the cursor. The model is unaware of text in front of its position.
- For CPU-only, low end, or battery powered devices, it is highly recommended to disable the `response preview` option, as it automatically triggers the model. *This will cause `continue inline` to be always on.* You can also increase the `preview delay` time.
- If you don't want inline generation to continue beyond the response preview, change the `continue inline` option in settings to false. *This doesn't apply to the command pallete.*
first commit as Fableous coder main changes commited 2024-06-02 13:42:29 +00:00			`# Fabelous Autocoder`
forgot to start a git history 2023-12-20 09:36:55 +00:00
chnaged description wording 2023-12-21 00:30:34 +00:00			`A simple to use Ollama autocompletion engine with options exposed and streaming functionality`
settings only update on config change, better progress reporting, changed name, added README and icon, added categories & keywords, changed activation event 2023-12-21 00:27:42 +00:00
added example gif 2023-12-23 04:45:27 +00:00
settings only update on config change, better progress reporting, changed name, added README and icon, added categories & keywords, changed activation event 2023-12-21 00:27:42 +00:00			`## Requirements`

			`- Ollama must be serving on the API endpoint applied in settings`
			`- For installation of Ollama, visit [ollama.ai](https://ollama.ai)`
			`- Ollama must have the model applied in settings installed.`

			`## How to Use`

QOL + battery draining problem 2024-01-28 02:22:47 +00:00			1. In a text document, press space (or any character in the `completion keys` setting). The option `Autocomplete with Ollama` or a preview of the first line of autocompletion will appear. Press `enter` to start generation.
removed the cursor thing because it was silly, added toggle for ask on space, exposed autocomplete command to command pallete 2023-12-21 06:33:07 +00:00			- Alternatively, you can run the `Autocomplete with Ollama` command from the command pallete (or set a keybind).
settings only update on config change, better progress reporting, changed name, added README and icon, added categories & keywords, changed activation event 2023-12-21 00:27:42 +00:00			`2. After startup, the tokens will be streamed to your cursor.`
changed README language toa ccount for stop on user input 2023-12-27 01:16:44 +00:00			`3. To stop the generation early, press the "Cancel" button on the "Ollama Autocoder" notification or type something.`
settings only update on config change, better progress reporting, changed name, added README and icon, added categories & keywords, changed activation event 2023-12-21 00:27:42 +00:00			`4. Once generation stops, the notification will disappear.`
fixed improper indentation and overwriting when inserting in the middle of preexisting code, clarified some information, added cursor-follows option. 2023-12-21 02:22:39 +00:00
			`## Notes`

			`- For fastest results, an Nvidia GPU or Apple Silicon is recommended. CPU still works on small models.`
			`- The prompt only sees behind the cursor. The model is unaware of text in front of its position.`
QOL + battery draining problem 2024-01-28 02:22:47 +00:00			- For CPU-only, low end, or battery powered devices, it is highly recommended to disable the `response preview` option, as it automatically triggers the model. This will cause `continue inline` to be always on. You can also increase the `preview delay` time.
			- If you don't want inline generation to continue beyond the response preview, change the `continue inline` option in settings to false. This doesn't apply to the command pallete.