[PAID] 🧠 Gemini Extension to interact with the Gemini-pro model from Google

[Lima]

the "GenerateGeminiContent" block has stopped working, it is giving the following error message: Error processing Gemini API response: No value for index

[Black_Knight]

You can Try the free version of Gemini Extension

@Black_Knight

Aix_file:

Check the comparison between PAID and FREE file

PAID_file
Price: $5.99
PayPal payment URL: Purchase Gemini.aix , After payment you will be directed to the download URL so you do not have to contact me to get the extension file however you can contact me in case of any problems

FREE_file
Gemini_Mini.aix (11.6 KB)

[Taifun]

@Lima

it is giving the following error message: Error processing Gemini API response: No value for index

@Black_Knight What about providing a "nice" error message like "all tokens of the free version are used up. You might consider to upgrade to the paid version of the extension"

Taifun

[Black_Knight]

New Update for adding a new models from Gemini called "gemini-2.0-flash-exp" , "gemini-2.0-flash-thinking-exp" , "gemini-2.0-flash-thinking-exp-1219", "gemini-exp-1206" ,
"learnlm-1.5-pro-experimental"

is a powerful model that will handle more complex tasks try it now using the Extension of Gemini

Gemini Extension

[PAID] Gemini Extension to interact with the Gemini-pro model from Google

[Gemini] The Gemini extension for AI2 allows you to interact with the Google Gemini-Pro and Gemini-Pro-Vesion models and these models that Bard is based on to generate text and control a stream of text generation. Features of the Gemini extension for AI2 : Generate text using the Google Gemini API. Stream generated text in real time. Generate text with images. Encode images to Base64 with the -w0 option. Handle errors gracefully. Benefits of using the Gemini extensio…

Experimental models

Experimental models  |  Gemini API  |  Google AI for...

Mode de réflexion Gemini 2.0 Flash  |  Gemini API...

[fedex]

paid for Gemini.aix today, but I was not directed to the website to download the file.

[Black_Knight]

I sent the files for you in pm
and
I am sorry for your bad situation and my late reply
I recommend at next time you pay you can use pc not phone or use chrome browser

[Black_Knight]

NEW BIG UPDATE FOR GEMINI EXTENSION

@Black_Knight

Function: StreamGenerateGeminiContent

Description:

Stream generate content using the Google Gemini API with optional Code Execution. Provides a streaming response for text and code, with code execution capability.

---

@Black_Knight

---

Function: StreamGenerateGeminiThinkingContent

Description:

Stream generate content using the Gemini 2.0 Flash Thinking model. Retrieves content in chunks for a responsive experience.

---

@Black_Knight

Function: StreamGenerateContentFromPdfUrl

Description:

Stream generate content from a PDF URL using the Google Gemini API (Streaming). Processes a PDF from a URL, uploads it to the Gemini API, and streams the generated content in chunks.

---

@Black_Knight

---

Function: StreamGenerateGeminiStructuredContent

---

Description:

Stream generate structured content using the Google Gemini API. The response will be formatted according to the provided JSON schema. Streams content from Gemini API, enforcing a JSON schema for structured output.

[Black_Knight]

The Most Powerful AI Extension for MIT App Inventor!

This web app showcases just a few of the incredible features of the Gemini API extension—but there’s so much more!

Key Features:
Generate human-like responses
Understand and process natural language
Perform AI-powered text analysis
Enhance your app’s interactivity with smart AI
Create customizable data APIs using the Structured Response feature

And that’s just the beginning! This extension empowers your app with cutting-edge AI capabilities like never before.

Try the Demo Now: https://astounding-beijinho-4cd939.netlify.app/

[Black_Knight]

New Update => (Search the web feature added)

@Black_Knight

StreamGenerateGroundedContent
This function allows you to generate text content from the Google Gemini API by streaming the response. Crucially, it instructs the model to use Google Search for grounding. This means the model will attempt to verify its statements and base its response on up-to-date information found via a web search, often providing more factually accurate and relevant answers.

GotGroundingInfo (sourceUris as YailList, sourceTitles as YailList)

Fires when the API provides metadata about the web sources used for grounding the
response.

This typically happens towards the end of the stream.

sourceUris: A list of URLs (Strings) that the model consulted.

sourceTitles: A corresponding list of page titles (Strings) for the consulted URLs. Use this event to display the sources to the user, perhaps in ListViews or Labels, to show where the information came from.

---

---

GetFaviconUrl
This function constructs and returns a URL that points to the favicon (the small icon often seen in browser tabs) for a given website. It uses Google's public favicon service to find and potentially resize the icon.

[Black_Knight]

How to Build Your Own AI "APIs" in App Inventor—The Easy Way!

Stop Wrestling with Text! Build Your Own AI "APIs" in App Inventor—The Easy Way!

Tired of getting long, messy sentences back from AI and then spending hours trying to pick out the exact piece of information you need with complex text blocks?

Wish you could just ask an AI to do a specific task and get back clean, predictable data ready to plug straight into your app?

Good news! You absolutely can, and it's WAY easier than you think!

Using The Gemini Extension combined with a simple trick—telling Gemini to respond in JSON —you can unlock powerful, custom AI capabilities right within your App Inventor projects.

Think of it like building your own mini-API service, powered by Google's Gemini, without needing any servers or complex coding!

Why is this so EFFECTIVE?

• AI Power on Demand: Need instant translation? A smart summarizer? Sentiment analysis? Keyword extraction? You can build specialized AI "functions" for almost anything.

• Predictable Data: No more guessing! JSON gives you structured data (like {"name": "John", "status": "active"}) that App Inventor handles perfectly.

• Clean Blocks: Your code becomes dramatically simpler and more readable.

Why is this so EASY for App Inventor Developers?

1. You Define the "API Call" in Plain English: Your "API function" is just part of your prompt! You simply tell Gemini what to do AND how to format the answer as JSON.

• Example Prompt: "Translate this to Spanish: '{text_to_translate}'. Respond ONLY with JSON like this: {'translation': '...'}. No extra text!"

2. One Block to Decode: You already have the tool! The standard Web component's JsonTextDecode block instantly turns that clean JSON response into an App Inventor dictionary.

3. Simple Data Access: Use the basic lookup in pairs dictionary block to grab exactly the piece of data you need (e.g., get the value for the translation key).

See this simple example blocks :

That's it! Seriously.

Prompt -> Send with Extension -> Receive Event -> JsonTextDecode -> lookup in pairs -> Use Data!

Forget complicated text parsing or setting up external servers. You leverage the visual blocks you already know to command a powerful AI and get back exactly what you need, neatly packaged.

This method transforms Gemini from just a text generator into a flexible, custom backend service tailor-made for your app's specific needs.

Ready to make your apps smarter and your blocks cleaner? Grab BlackNight's Gemini extension, craft a prompt asking for JSON, and see how easy and effective it is to have your own custom AI service running directly inside App Inventor!

Note : ChatGPT extension has the same feature

[techxsarthak]

Nice trick!
I think its possible to do it with the ChatBot component too?

[Black_Knight]

I don't see the structured output response blocks in your topic!
Could you quote the block image of your extension that achieve this .

For more info, see the meaning of structured outputs

[techxsarthak]

After prompting the AI to respond in json can't we use native dictionary blocks to parse json?

[Black_Knight]

Not exactly like this,
This is the difference between the fixed original JSON response of the gemini API
and the customized json structured inside the original json structure that called structed output "

• Free Text Response:

  • What it is: Normal sentences, like a chat conversation.

  • Problem: Unpredictable format. App Inventor needs complex/fragile text blocks (split, segment) to try and find the data. Often breaks.

• Customized Structured (JSON) Response:

  • What it is: Data organized with specific labels (keys) in a strict format ({"key": "value"}). You tell the AI to use this format.

  • Benefit: Predictable format. App Inventor uses JsonTextDecode + simple dictionary blocks (lookup in pairs) to easily and reliably grab the exact data needed. Much more robust.

[Black_Knight]

To clarify it more, see this example

Example: Translation API using Gemini with Structured Output

Here is the JSON schema that defines the structured output for the translation API based on the provided MIT App Inventor blocks.

---

JSON Schema for Structured Output

{
  "type": "object",
  "properties": {
    "translation": {
      "type": "string",
      "description": "The translated text."
    },
    "original_text": {
      "type": "string",
      "description": "The original input text before translation."
    }
  },
  "required": ["translation", "original_text"]
}

---

How This Schema Works

1. Defines an Object: The response is structured as an object.
2. Includes Two Properties:

• "translation" → Contains the translated text.
• "original_text" → Stores the original text before translation.

3. Required Fields: Ensures that both "translation" and "original_text" are present in every response.

---

Example API Response Matching the Schema

{
  "translation": "Translate this into English",
  "original_text": "ترجم هذا إلى الإنجليزية"
}

Blocks:

This schema ensures that the Gemini API consistently returns structured data, making it easy to parse and use in your MIT App Inventor project.

[Black_Knight]

@techxsarthak you can try this feature inside Google AI Studio

with structured output

without structured output

[techxsarthak]

@Black_Knight

Not exactly like this,
This is the difference between the fixed original JSON response of the gemini API
and the customized json structured inside the original json structure that called structed output

Added a block in GroqText, as I said earlier... was working on an update with new blocks, released it just now.

@Black_Knight

you can try this feature inside Google AI Studio

Same for Groq Playground - GroqCloud. Its JSON mode btw

Added blocks for it in my extension too!

Structured JSON output

RequestCustomStructuredOutput

UserRequest= Question to ask to the AI
customScheme= The json type to generate

For eg.

Output

Yes its now possible with GroqText

@Black_Knight

Here is the JSON schema that defines the structured output for the translation API based on the provided MIT App Inventor blocks.

Btw Gemini extension is also very good!

[Black_Knight]

Good job

[techxsarthak]

Thanks, your extensions are also good as always

[Black_Knight]

New Update

Gemini extension now allows you to create and modify images via instructions using Google's Gemini AI models directly within your App Inventor projects!

@Black_Knight

GenerateImage

Creates a new image from a text description.

• prompt (Text): Description of the desired image.
• apiKey (Text): Google API Key.
• modelName (Text): Image generation model (e.g., "gemini-1.5-flash"). Check Google docs.

EditImage

Modifies an existing image provided as Base64.

• prompt (Text): Instructions for changes.
• inputImageBase64 (Text): Image to edit (Base64 string).
• inputMimeType (Text): MIME type of input image (e.g., "image/jpeg").
• apiKey (Text): Google API Key.
• modelName (Text): Image editing model.

EditImageFromPath

Modifies an existing image using its file path.

• prompt (Text): Instructions for changes.
• inputImagePath (Text): Full path to the image file on device.
• apiKey (Text): Google API Key.
• modelName (Text): Image editing model.

EditMultipleImagesSimple

Advanced editing/generation using multiple input images (URL/Path/Base64) and text.

• prompt (Text): Instructions involving the images.
• imageSourceStrings (List): List of image sources (URLs, paths, or Base64 strings).
• apiKey (Text): Google API Key.
• modelName (Text): Multi-image capable model.

DisplayBase64Image

Helper block to display Base64 image data on an Image component.

• base64Data (Text): Base64 image data (from GotImageResponse).
• mimeType (Text): Image MIME type (from GotImageResponse).
• imageComponent (Component): The Image component to display on.

Event: GotImageResponse

Fires when image generation/editing succeeds.

• imageBase64 (Text): Resulting image as Base64. Empty on failure.
• mimeType (Text): MIME type of the result (e.g., "image/png").
• responseText (Text): Any text from the API (e.g., errors if blocked).
• rawApiResponse (Text): Full JSON response (for debugging).
• imagePath (Text): Path where the result image was saved in app storage (ASD). Empty on failure.

Examples of generating and editing with Gemini