Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions .gitignore
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
/.idea/
43 changes: 40 additions & 3 deletions README.md
Original file line number Diff line number Diff line change
@@ -1,13 +1,50 @@
# prompting-with-api

This jupyter-based and voilá-ready prompting app gives the ability to use an api key for prompting workshops with an unlimited number of participants (while keeping in mind that some models cost per request). It bridges the temporary situation that there are no institutional LLM accesses yet and solutions such as GPTX are still a work in progress.

# getting started
![img.png](docs/images/screenshot_text2text.png)

## Installation using python virtual environments

* start terminal
* ```git clone "repo"``` to preferred directory
* ```cd``` to "repo"-folder
* ```create venv (windows: python -m venv prompting-venv)```
* ```activate venv (windows: prompting-venv/scripts/activate)```
* ```pip install -r requirements.txt```
* in terminal type ```voila prompting_ui-beautified.ipynb``` for text2text or ```voila image-gen_ui-beautified.ipynb``` for text2img

Attention: you need an OpenAI API Key that is set correctly as an environment variable (do it manually!), see: ```https://platform.openai.com/docs/quickstart?context=python```
## Installation into a conda environment

```
conda create --name prompting python=3.10
```

```
conda activate prompting
```

```
pip install -r requirements.txt
```

## Installation: OpenAI API Key

![CAUTION]
> You need an OpenAI API Key that is set correctly as an environment variable (do it manually!), [read more](https://platform.openai.com/docs/quickstart?context=python)


## Usage

In a terminal type for text2text:

```
voila prompting_ui-beautified.ipynb
```

or if you want to create images (text2img)

```
voila image-gen_ui-beautified.ipynb
```


Binary file added docs/images/screenshot_text2text.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.