Radiologist

What it does

The app is a mobile application .This functionality is achieved through the integration of advanced multimodal capabilities, including vision transformation for image analysis and a large language model (LLM) for report generation. The app is developed natively for Android using Jetpack Compose for the UI design, Firebase for authentication, and Firestore for database management
In the app, the Gemini API is utilized to power the chatbot’s content generation capabilities. The GeminiData object manages the interaction with the Gemini API. It includes two primary methods: getResponse and getResponseWithImage
getResponse: This method takes a text prompt and optionally a conversation ID and a timestamp. It uses the "gemini-pro" model to generate a textual response. The method runs the API call in a background thread using withContext(Dispatchers.IO) to ensure smooth UI performance. It returns a Chat object containing the response text or an error message if the API call fails
getResponseWithImage: This method is similar but also handles image data. It takes a text prompt, an image (in the form of a Bitmap), and optionally a conversation ID and a timestamp. Using the "gemini-pro-vision" model, it combines the text and image data to generate a response. The method constructs the input content using the provided image and text, makes the API call in a background thread, and returns a Chat object with the response or an error message