So when I try to do that my MIT app companion on the phone just kicks out of the screen
What should I do to make this not happen?
Is there any way I can set the max_tokens and the temperature when using .requestChatGPTVision?
What are the choiceIndex, promptTokens, completionTokens, and totalTokens in .RespondedtoChat block?
Thanks!
In the next update, I will add the option to add image as base64 code
@Black_Knight , Could you update the zip file since I bought the new version but there is only the aia file in it and there is no aix file? Thank you.
I have sent you the extension check your PM .
Thanks for reporting this problem and I hope you find my extension useful for your word
The ChatGPTVision does not work for me any more. It returned a error message "https://api.openai.com/v1/chat/completions". It worked in April and May. Do you have the same problem?
Thank you
I have just tested it and it worked well 
Big Update! ChatGPT Extension Now Supports GPT-4 and More! 
Exciting news! The ChatGPT extension has been significantly upgraded and now boasts full compatibility with the latest and greatest OpenAI models, including:
-
GPT-4
-
GPT-4-Turbo
-
GPT-4o
-
GPT-4o-mini
-
And all your favorite GPT-3.5 models!
This means you can now harness the incredible power of these advanced language models directly in your App Inventor projects. Build even more sophisticated chatbots, unlock next-level creative potential, and explore the cutting edge of AI-powered apps.
What's New?
-
Seamless Integration: Easily switch between different GPT models within the extension.
-
Enhanced Streaming: Enjoy a smoother and more responsive streaming experience for real-time chat interactions.
-
Future-Proof: The extension is designed to support new OpenAI models as they become available, ensuring you stay ahead of the curve.
Ready to experience the future of AI?
Get the updated ChatGPT extension today! 
Pay Here and you will be automatically redirected to the download page of the extension after completing payment
Are you using the new update today or the May 2024 version? I just tried the May version again and it did not work.
The may update
Make sure to put images as a list of paths
I used base64 code as the imageurl input and it worked back in April and May. It does not work anymore. I want to send the photo taken by the camera component (without save it in my device gallery) directly to chapgpt to get image description. How can I get this work? Thank you
In case of url method: you have to use direct download url of the image that ends with .PNG .jpeg ....
In case of local files: you have two blocks methods you can use image path directly as list of image paths or convert the image to base64 code then use it in the block
If you still have obstacles about how to use it you can dm me so I can help you
All blocks
How Text Embeddings Will Help You in Your App ?
The GetEmbeddings function within the ChatGPT extension unlocks powerful capabilities for your app by converting text into meaningful numerical representations. Here's how you can benefit:
1. Build a Smarter Search Engine:
-
Problem: Traditional keyword search often fails to understand the context of words. A search for "Apple phone" might not return results containing "iPhone," leading to a poor user experience.
-
Solution:
-
Use GetEmbeddings to pre-calculate embeddings for all searchable content in your app (articles, product descriptions, etc.).
-
When a user searches, get the embedding of their query.
-
Compare the query embedding to your content's embeddings. Content with embeddings closest to the query are likely the most semantically similar, even if they don't share exact keywords.
-
-
Result: Your search becomes more intelligent, returning more relevant results based on meaning rather than just literal word matches.
2. Create a Personalized Recommendation System:
-
Problem: Recommending content solely based on basic categories can be inaccurate. A user who likes "romantic comedies" might not enjoy all films within that genre.
-
Solution:
-
Calculate embeddings for items (movies, products, articles) in your app.
-
Track user interactions (likes, purchases, views).
-
When recommending, find items with embeddings similar to those the user has positively interacted with in the past.
-
-
Result: Your recommendations become more tailored to individual user preferences, leading to increased engagement and satisfaction.
3. Organize Content Effectively:
-
Problem: Dealing with large volumes of uncategorized text data (customer reviews, social media posts) can be overwhelming.
-
Solution:
-
Use GetEmbeddings to obtain embeddings for each piece of text.
-
Apply clustering algorithms (available in various libraries) to group text snippets with similar embeddings.
-
-
Result: Automatically categorize your data based on topics, sentiment, or other patterns revealed by the embeddings, making it easier to analyze and present information to users.
4. Enhance Language Understanding:
-
Problem: Building features that require language comprehension (chatbots, sentiment analysis) is complex.
-
Solution: Embeddings can be used as input features for training machine learning models:
-
Sentiment Analysis: Train a model to classify text as positive, negative, or neutral based on its embedding.
-
Chatbot Improvement: Create a chatbot that understands the intent and meaning behind user messages, resulting in more natural conversations.
-
Check the new price for chat gpt extension 2$ for limited period of time,