thewarrior

    //I give you a picture of a plate of lobster it will say "A plate of lobster".

    getTextFromImage(image) -> Text

    //I give you a prompt and you return completion ChatGPT style
     getCompletionFromPrompt(text) -> Text

    getAnswerToQuestion(image, question) -> answer 
        text = getTextFromImage(image)
        prompt = mapTextToPrompt(text)
        return getCompletionForPrompt(prompt)

    getAnswerToQuestion(image, question) -> answer 
        text = getEmbeddingFromImage(image)
        embedding = mapEmbeddingToInputEmbeddingForLLM(text)
        return getCompletionForEmbedding(embedding)