OpenAI GPT-4 With Vision 🔥 This repository features an outfit rating app using OpenAI's GPT-4 with the Vision extension. Users can upload images through a Streamlit interface, and the app provides both a fashion stylist's and a mother's verdict on the outfit. Contributions are welcome!
MIT License
2
stars
0
forks
source link
Sweep: Add fashion stylist and mother features to the app #10
This pull request adds a new feature to the application that allows users to get fashion advice from a simulated fashion stylist or mother. The user can upload an image, and the application will provide a recommendation on whether to keep or return the item, along with a justification for the decision.
Description
The changes in this pull request include:
Migrating the application from Gradio to Streamlit, which provides a more user-friendly and modern interface.
Adding two new functions, ask_openai_with_image and parse_llm_response, to handle the image processing and the response from the language model (GPT-4).
Implementing the fashion stylist and mother roles, where the language model provides different prompts and justifications based on the selected role.
Displaying the recommendation and justification in the Streamlit interface.
Summary
Migrated the application from Gradio to Streamlit
Added new functions to handle image processing and language model response
Implemented fashion stylist and mother roles with different prompts and justifications
Displayed the recommendation and justification in the Streamlit interface
Fixes #7.
[!TIP]
To get Sweep to edit this pull request, you can:
Comment below, and Sweep can edit the entire PR
Comment on a file, Sweep will only modify the commented file
Edit the original issue to get Sweep to recreate the PR from scratch
This is an automated message generated by Sweep AI.
Purpose
This pull request adds a new feature to the application that allows users to get fashion advice from a simulated fashion stylist or mother. The user can upload an image, and the application will provide a recommendation on whether to keep or return the item, along with a justification for the decision.
Description
The changes in this pull request include:
ask_openai_with_image
andparse_llm_response
, to handle the image processing and the response from the language model (GPT-4).Summary
Fixes #7.
This is an automated message generated by Sweep AI.