OMNEX-VL

QUESTION_TEMPLATE_PCDA = (
    "{Question}\n"
    "Please carefully analyze the pictures (or videos) and problems according to the following requirements"
    "In <prethink> </prethink> tags, carefully analyze the problem and briefly explain the steps to explain the problem and the key thinking direction of reasoning the problem"
    "In <caption> </caption> tags, Please describe the image carefully, paying special attention to the details related to the problem and the reasoning direction of solving the problem"
    "In <think> </think> tags, outline a step-by-step thought process you would use to solve the problem based on the image"
    "In <answer> </answer> tags, give the final answer in a direct format, and it must match the correct answer exactly."
    "Please sort out the output in the format of '<prethink>...</prethink>\n<caption>...</caption>\n<think>...</think>\n<answer>...</answer>' according to the above requirements"
)

TYPE_TEMPLATE = {
    "multiple choice": " Please provide only the single option letter (e.g., A, B, C, D, etc.) within the <answer> </answer> tags.",
    "numerical": " Please provide the numerical value (e.g., 42 or 3.14) within the <answer> </answer> tags.",
    "OCR": " Please transcribe text from the image/video clearly and provide your text answer within the <answer> </answer> tags.",
    "free-form": " Please provide your text answer within the <answer> </answer> tags.",
    "regression": " Please provide the numerical value (e.g., 42 or 3.14) within the <answer> </answer> tags."
}

# prompt = QUESTION_TEMPLATE.format(Question=question) + TYPE_TEMPLATE[...]