aljaz/dev-gpt
1
0
Fork 0
mirror of https://github.com/aljazceru/dev-gpt.git synced 2025-12-20 15:14:20 +01:00
Code Issues Packages Projects Releases Wiki Activity

docs: update readme

Browse Source
This commit is contained in:
Florian Hönicke
2023-04-08 19:19:29 +02:00
parent ee14ef5fab
commit 8f1b654003
2 changed files with 9 additions and 68 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
README.md
View File

@@ -28,6 +28,8 @@ Your imagination is the limit!
<img src="https://img.shields.io/badge/platform-mac%20%7C%20linux%20%7C%20windows-blue" alt="Supported platforms">
</a>
[//]: # ([![Watch the video]&#40;https://i.imgur.com/vKb2F1B.png&#41;]&#40;https://user-images.githubusercontent.com/11627845/226220484-17810f7c-b184-4a03-9af2-3a977fbb014b.mov&#41;)
</p>
This project streamlines the creation and deployment of microservices.
Simply describe your task using natural language, and the system will automatically build and deploy your microservice.
@@ -107,7 +109,7 @@ gptdeploy --description "Create mel spectrograms from audio file" --test "https:
```bash
gptdeploy --description "Convert text to speech" --test "Hello, welcome to GPT Deploy!"
```
<a href=text_to_speech_example.wav><img src="res/text_to_speech_example.png" alt="Text to Speech" width="600" /></a>
<a href=res/text_to_speech_example.wav><img src="res/text_to_speech_example.png" alt="Text to Speech" width="600" /></a>
## QR Code Generator
```bash
@@ -255,4 +257,8 @@ Make sure it is only printed twice in case it changed.
- [ ] bug: it can happen that the code generation is hanging forever - in this case aboard and redo the generation
- [ ] feat: make playground more stylish by adding attributes like: clean design, beautiful, like it was made by a professional designer, ...
[![Watch the video](https://i.imgur.com/vKb2F1B.png)](https://user-images.githubusercontent.com/11627845/226220484-17810f7c-b184-4a03-9af2-3a977fbb014b.mov)
# challenging tasks:
- The executor takes an image as input and returns a list of bounding boxes of all animals in the image.
- The executor takes 3D objects in obj format as input and outputs a 2D image rendering of that object where the full object is shown.
- The executor takes an mp3 file as input and returns bpm and pitch.
- The executor takes a url of a website as input and returns the logo of the website as an image.

65
main.py
View File

@@ -323,68 +323,3 @@ def main(
if __name__ == '__main__':
main()
'''
python main.py --description "Input is a url of a website as input and classifies it as either individual or business." --test "Takes https://jina.ai/ as input and returns 'business'. Takes https://hanxiao.io/ as input and returns 'individual'."
'''
# accomplished tasks:
# main(
# description="Input is a url of a website as input and classifies it as either individual or business.",
# test='Takes https://jina.ai/ as input and returns "business". Takes https://hanxiao.io/ as input and returns "individual". ',
# )
# needs to prove:
# ######## Level 1 task #########
# main(
# description="The executor takes a pdf file as input, parses it and returns the text.",
# input_modality='pdf',
# output_modality='text',
# test='Takes https://www2.deloitte.com/content/dam/Deloitte/de/Documents/about-deloitte/Deloitte-Unternehmensgeschichte.pdf and returns a string that is at least 100 characters long',
# )
# main(
# description="The executor takes a url of a website as input and returns the logo of the website as an image.",
# test='Takes https://jina.ai/ as input and returns an svg image of the logo.',
# )
# # # ######## Level 1 task #########
# main(
# description="The executor takes a pdf file as input, parses it and returns the text.",
# input_modality='pdf',
# output_modality='text',
# test='Takes https://www2.deloitte.com/content/dam/Deloitte/de/Documents/about-deloitte/Deloitte-Unternehmensgeschichte.pdf and returns a string that is at least 100 characters long',
# )
# ######## Level 2 task #########
# main(
# description="OCR detector",
# input_modality='image',
# output_modality='text',
# test='Takes https://miro.medium.com/v2/resize:fit:1024/0*4ty0Adbdg4dsVBo3.png as input and returns a string that contains "Hello, world"',
# )
# ######## Level 3 task #########
# main(
# description="The executor takes an mp3 file as input and returns bpm and pitch in a json.",
# test='Takes https://cdn.pixabay.com/download/audio/2023/02/28/audio_550d815fa5.mp3 as input and returns a json with bpm and pitch',
# )
######### Level 4 task #########
# main(
# description="The executor takes 3D objects in obj format as input "
# "and outputs a 2D image rendering of that object where the full object is shown. ",
# input_modality='3d',
# output_modality='image',
# test='Test that 3d object from https://raw.githubusercontent.com/polygonjs/polygonjs-assets/master/models/wolf.obj '
# 'is put in and out comes a 2d rendering of it',
# )
# ######## Level 8 task #########
# main(
# description="The executor takes an image as input and returns a list of bounding boxes of all animals in the image.",
# input_modality='blob',
# output_modality='json',
# test='Take the image from https://thumbs.dreamstime.com/b/dog-professor-red-bow-tie-glasses-white-background-isolated-dog-professor-glasses-197036807.jpg as input and assert that the list contains at least one bounding box. ',
# )