Csaba Toth

[Bug]: AttributeError: 'Candidate' object has no attribute 'grounding_metadata' in intro-grounding-gemini.ipynb

3

### File Name intro-grounding-gemini.ipynb ### What happened? For some reason the step ``` tool = Tool.from_google_search_retrieval(grounding.GoogleSearchRetrieval()) response = model.generate_content(PROMPT, tools=[tool]) print_grounding_response(response) ``` resulted in this. Holt Skinner asked me to...

Function call and tool support

1

Not sure if it's too much to ask for, but will function calls or API tools be supported?

Function calling only considers functions in the first tool?

3

### Description of the bug: Using `gemini-1.5-flash`. Prompt: "What is the weather today?" Tool configuration 1: ``` [ Tool( functionDeclarations: [ FunctionDeclaration( 'fetchWeatherForecast', 'Returns the weather in a given location.',...

[camera] Camera example app doesn't explicitly dispose focusModeControlRowAnimationController in dispose

1

### What package does this bug report belong to? camera ### What target platforms are you seeing this bug on? Android ### Have you already upgraded your packages? Yes ###...

[camera] Camera Example app's setExposureOffset is not robust

1

### What package does this bug report belong to? camera ### What target platforms are you seeing this bug on? Android ### Have you already upgraded your packages? Yes ###...

Support outputDimensionality reduction parameter for embedding models

2

### Description of the feature request: Since `text-embedding-004` the API calls support `outputDimensionality` parameter. That truncates the vector to the given size. See https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/text-embeddings-api#advanced-use ``` { "instances": [ { "content":...

Support `text-multilingual-embedding-002` embedding model

4

### Description of the feature request: https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/text-embeddings-api lists `text-multilingual-embedding-002`, however https://ai.google.dev/gemini-api/docs/models/gemini#text-embedding does not. I can successfully instantiate a `GenerativeModel`, but when I call `embedContent` like I do with `text-embedding-004` it...

[firebase_vertexai]: embedContent calls result in 404

3

### Is there an existing issue for this? - [X] I have searched the existing issues. ### Which plugins are affected? Other ### Which platforms are affected? Android ### Description...

The input's JSON structure doesn't have file name or type, just the base64 payloads in an array

1

``` streamlit==1.39.0 st-multimodal-chatinput==0.2.1 ``` Python version: 3.12.7 The project's example code implies a certain JSON structure the input supposed to yield, I supposed to get file names and types for...

[firebase_vertexai]: Multi tool generative AI calls fail with server error "Request contains an invalid argument"

7

### Is there an existing issue for this? - [X] I have searched the existing issues. ### Which plugins are affected? Other ### Which platforms are affected? Android ### Description...