geochat/conversation.py

import dataclasses
from enum import auto, Enum
from typing import List, Tuple
from PIL import Image
from threading import Thread

from geochat.constants import IMAGE_TOKEN_INDEX, DEFAULT_IMAGE_TOKEN, DEFAULT_IM_START_TOKEN, DEFAULT_IM_END_TOKEN
# from llava.conversation import conv_templates, SeparatorStyle
# from llava.model.builder import load_pretrained_model
from geochat.utils import disable_torch_init
from geochat.mm_utils import process_images_demo, tokenizer_image_token, get_model_name_from_path, KeywordsStoppingCriteria
from transformers import StoppingCriteria, StoppingCriteriaList, TextIteratorStreamer,TextStreamer
import torch
import dataclasses
from enum import auto, Enum
from typing import List, Tuple, Any


class SeparatorStyle(Enum):
    """Different separator style."""
    SINGLE = auto()
    TWO = auto()
    MPT = auto()
    PLAIN = auto()
    LLAMA_2 = auto()


@dataclasses.dataclass
class Conversation:
    """A class that keeps all conversation history."""
    system: str
    roles: List[str]
    messages: List[List[str]]
    offset: int
    sep_style: SeparatorStyle = SeparatorStyle.SINGLE
    sep: str = "###"
    sep2: str = None
    version: str = "Unknown"

    skip_next: bool = False

    def get_prompt(self):
        messages = self.messages
        if len(messages) > 0 and type(messages[0][1]) is tuple:
            messages = self.messages.copy()
            init_role, init_msg = messages[0].copy()
            init_msg = init_msg[0].replace("<image>", "").strip()
            if 'mmtag' in self.version:
                messages[0] = (init_role, init_msg)
                messages.insert(0, (self.roles[0], "<Image><image></Image>"))
                messages.insert(1, (self.roles[1], "Received."))
            else:
                messages[0] = (init_role, "<image>\n" + init_msg)

        if self.sep_style == SeparatorStyle.SINGLE:
            ret = self.system + self.sep
            for role, message in messages:
                if message:
                    if type(message) is tuple:
                        message, _, _ = message
                    ret += role + ": " + message + self.sep
                else:
                    ret += role + ":"
        elif self.sep_style == SeparatorStyle.TWO:
            seps = [self.sep, self.sep2]
            ret = self.system + seps[0]
            for i, (role, message) in enumerate(messages):
                if message:
                    if type(message) is tuple:
                        message, _, _ = message
                    ret += role + ": " + message + seps[i % 2]
                else:
                    ret += role + ":"
        elif self.sep_style == SeparatorStyle.MPT:
            ret = self.system + self.sep
            for role, message in messages:
                if message:
                    if type(message) is tuple:
                        message, _, _ = message
                    ret += role + message + self.sep
                else:
                    ret += role
        elif self.sep_style == SeparatorStyle.LLAMA_2:
            wrap_sys = lambda msg: f"<<SYS>>\n{msg}\n<</SYS>>\n\n"
            wrap_inst = lambda msg: f"[INST] {msg} [/INST]"
            ret = ""

            for i, (role, message) in enumerate(messages):
                if i == 0:
                    assert message, "first message should not be none"
                    assert role == self.roles[0], "first message should come from user"
                if message:
                    if type(message) is tuple:
                        message, _, _ = message
                    if i == 0: message = wrap_sys(self.system) + message
                    if i % 2 == 0:
                        message = wrap_inst(message)
                        ret += self.sep + message
                    else:
                        ret += " " + message + " " + self.sep2
                else:
                    ret += ""
            ret = ret.lstrip(self.sep)
        elif self.sep_style == SeparatorStyle.PLAIN:
            seps = [self.sep, self.sep2]
            ret = self.system
            for i, (role, message) in enumerate(messages):
                if message:
                    if type(message) is tuple:
                        message, _, _ = message
                    ret += message + seps[i % 2]
                else:
                    ret += ""
        else:
            raise ValueError(f"Invalid style: {self.sep_style}")

        return ret

    def append_message(self, role, message):
        self.messages.append([role, message])

    def get_images(self, return_pil=False):
        images = []
        for i, (role, msg) in enumerate(self.messages[self.offset:]):
            if i % 2 == 0:
                if type(msg) is tuple:
                    import base64
                    from io import BytesIO
                    from PIL import Image
                    msg, image, image_process_mode = msg
                    if image_process_mode == "Pad":
                        def expand2square(pil_img, background_color=(122, 116, 104)):
                            width, height = pil_img.size
                            if width == height:
                                return pil_img
                            elif width > height:
                                result = Image.new(pil_img.mode, (width, width), background_color)
                                result.paste(pil_img, (0, (width - height) // 2))
                                return result
                            else:
                                result = Image.new(pil_img.mode, (height, height), background_color)
                                result.paste(pil_img, ((height - width) // 2, 0))
                                return result
                        image = expand2square(image)
                    elif image_process_mode in ["Default", "Crop"]:
                        pass
                    elif image_process_mode == "Resize":
                        image = image.resize((336, 336))
                    else:
                        raise ValueError(f"Invalid image_process_mode: {image_process_mode}")
                    max_hw, min_hw = max(image.size), min(image.size)
                    aspect_ratio = max_hw / min_hw
                    max_len, min_len = 800, 400
                    shortest_edge = int(min(max_len / aspect_ratio, min_len, min_hw))
                    longest_edge = int(shortest_edge * aspect_ratio)
                    W, H = image.size
                    if longest_edge != max(image.size):
                        if H > W:
                            H, W = longest_edge, shortest_edge
                        else:
                            H, W = shortest_edge, longest_edge
                        image = image.resize((W, H))
                    if return_pil:
                        images.append(image)
                    else:
                        buffered = BytesIO()
                        image.save(buffered, format="PNG")
                        img_b64_str = base64.b64encode(buffered.getvalue()).decode()
                        images.append(img_b64_str)
        return images

    def to_gradio_chatbot(self):
        ret = []
        for i, (role, msg) in enumerate(self.messages[self.offset:]):
            if i % 2 == 0:
                if type(msg) is tuple:
                    import base64
                    from io import BytesIO
                    msg, image, image_process_mode = msg
                    max_hw, min_hw = max(image.size), min(image.size)
                    aspect_ratio = max_hw / min_hw
                    max_len, min_len = 800, 400
                    shortest_edge = int(min(max_len / aspect_ratio, min_len, min_hw))
                    longest_edge = int(shortest_edge * aspect_ratio)
                    W, H = image.size
                    if H > W:
                        H, W = longest_edge, shortest_edge
                    else:
                        H, W = shortest_edge, longest_edge
                    image = image.resize((W, H))
                    buffered = BytesIO()
                    image.save(buffered, format="JPEG")
                    img_b64_str = base64.b64encode(buffered.getvalue()).decode()
                    img_str = f'<img src="data:image/png;base64,{img_b64_str}" alt="user upload image" />'
                    msg = img_str + msg.replace('<image>', '').strip()
                    ret.append([msg, None])
                else:
                    ret.append([msg, None])
            else:
                ret[-1][-1] = msg
        return ret

    def copy(self):
        return Conversation(
            system=self.system,
            roles=self.roles,
            messages=[[x, y] for x, y in self.messages],
            offset=self.offset,
            sep_style=self.sep_style,
            sep=self.sep,
            sep2=self.sep2,
            version=self.version)

    def dict(self):
        if len(self.get_images()) > 0:
            return {
                "system": self.system,
                "roles": self.roles,
                "messages": [[x, y[0] if type(y) is tuple else y] for x, y in self.messages],
                "offset": self.offset,
                "sep": self.sep,
                "sep2": self.sep2,
            }
        return {
            "system": self.system,
            "roles": self.roles,
            "messages": self.messages,
            "offset": self.offset,
            "sep": self.sep,
            "sep2": self.sep2,
        }


conv_vicuna_v0 = Conversation(
    system="A chat between a curious human and an artificial intelligence assistant. "
           "The assistant gives helpful, detailed, and polite answers to the human's questions.",
    roles=("Human", "Assistant"),
    messages=(
        ("Human", "What are the key differences between renewable and non-renewable energy sources?"),
        ("Assistant",
            "Renewable energy sources are those that can be replenished naturally in a relatively "
            "short amount of time, such as solar, wind, hydro, geothermal, and biomass. "
            "Non-renewable energy sources, on the other hand, are finite and will eventually be "
            "depleted, such as coal, oil, and natural gas. Here are some key differences between "
            "renewable and non-renewable energy sources:\n"
            "1. Availability: Renewable energy sources are virtually inexhaustible, while non-renewable "
            "energy sources are finite and will eventually run out.\n"
            "2. Environmental impact: Renewable energy sources have a much lower environmental impact "
            "than non-renewable sources, which can lead to air and water pollution, greenhouse gas emissions, "
            "and other negative effects.\n"
            "3. Cost: Renewable energy sources can be more expensive to initially set up, but they typically "
            "have lower operational costs than non-renewable sources.\n"
            "4. Reliability: Renewable energy sources are often more reliable and can be used in more remote "
            "locations than non-renewable sources.\n"
            "5. Flexibility: Renewable energy sources are often more flexible and can be adapted to different "
            "situations and needs, while non-renewable sources are more rigid and inflexible.\n"
            "6. Sustainability: Renewable energy sources are more sustainable over the long term, while "
            "non-renewable sources are not, and their depletion can lead to economic and social instability.\n")
    ),
    offset=2,
    sep_style=SeparatorStyle.SINGLE,
    sep="###",
)

conv_vicuna_v1 = Conversation(
    system="A chat between a curious user and an artificial intelligence assistant. "
    "The assistant gives helpful, detailed, and polite answers to the user's questions.",
    roles=("USER", "ASSISTANT"),
    version="v1",
    messages=(),
    offset=0,
    sep_style=SeparatorStyle.TWO,
    sep=" ",
    sep2="</s>",
)

conv_llama_2 = Conversation(
    system="""You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe.  Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.

If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.""",
    roles=("USER", "ASSISTANT"),
    version="llama_v2",
    messages=(),
    offset=0,
    sep_style=SeparatorStyle.LLAMA_2,
    sep="<s>",
    sep2="</s>",
)

conv_llava_llama_2 = Conversation(
    system="You are a helpful language and vision assistant. "
           "You are able to understand the visual content that the user provides, "
           "and assist the user with a variety of tasks using natural language.",
    roles=("USER", "ASSISTANT"),
    version="llama_v2",
    messages=(),
    offset=0,
    sep_style=SeparatorStyle.LLAMA_2,
    sep="<s>",
    sep2="</s>",
)

conv_mpt = Conversation(
    system="""<|im_start|>system
A conversation between a user and an LLM-based AI assistant. The assistant gives helpful and honest answers.""",
    roles=("<|im_start|>user\n", "<|im_start|>assistant\n"),
    version="mpt",
    messages=(),
    offset=0,
    sep_style=SeparatorStyle.MPT,
    sep="<|im_end|>",
)

conv_llava_plain = Conversation(
    system="",
    roles=("", ""),
    messages=(
    ),
    offset=0,
    sep_style=SeparatorStyle.PLAIN,
    sep="\n",
)

conv_llava_v0 = Conversation(
    system="A chat between a curious human and an artificial intelligence assistant. "
           "The assistant gives helpful, detailed, and polite answers to the human's questions.",
    roles=("Human", "Assistant"),
    messages=(
    ),
    offset=0,
    sep_style=SeparatorStyle.SINGLE,
    sep="###",
)

conv_llava_v0_mmtag = Conversation(
    system="A chat between a curious user and an artificial intelligence assistant. "
           "The assistant is able to understand the visual content that the user provides, and assist the user with a variety of tasks using natural language."
           "The visual content will be provided with the following format: <Image>visual content</Image>.",
    roles=("Human", "Assistant"),
    messages=(
    ),
    offset=0,
    sep_style=SeparatorStyle.SINGLE,
    sep="###",
    version="v0_mmtag",
)

conv_llava_v1 = Conversation(
    system="A chat between a curious human and an artificial intelligence assistant. "
           "The assistant gives helpful, detailed, and polite answers to the human's questions.",
    roles=("USER", "ASSISTANT"),
    version="v1",
    messages=(),
    offset=0,
    sep_style=SeparatorStyle.TWO,
    sep=" ",
    sep2="</s>",
)

conv_llava_v1_mmtag = Conversation(
    system="A chat between a curious user and an artificial intelligence assistant. "
           "The assistant is able to understand the visual content that the user provides, and assist the user with a variety of tasks using natural language."
           "The visual content will be provided with the following format: <Image>visual content</Image>.",
    roles=("USER", "ASSISTANT"),
    messages=(),
    offset=0,
    sep_style=SeparatorStyle.TWO,
    sep=" ",
    sep2="</s>",
    version="v1_mmtag",
)

default_conversation = conv_vicuna_v0
conv_templates = {
    "default": conv_vicuna_v0,
    "v0": conv_vicuna_v0,
    "v1": conv_vicuna_v1,
    "vicuna_v1": conv_vicuna_v1,
    "llama_2": conv_llama_2,

    "plain": conv_llava_plain,
    "v0_plain": conv_llava_plain,
    "llava_v0": conv_llava_v0,
    "v0_mmtag": conv_llava_v0_mmtag,
    "llava_v1": conv_llava_v1,
    "v1_mmtag": conv_llava_v1_mmtag,
    "llava_llama_2": conv_llava_llama_2,

    "mpt": conv_mpt,
}

class Chat:
    def __init__(self, model, image_processor,tokenizer, device='cuda:0', stopping_criteria=None):
        self.device = device
        self.model = model
        self.vis_processor = image_processor
        self.tokenizer=tokenizer

        # if stopping_criteria is not None:
        #     self.stopping_criteria = stopping_criteria
        # else:
        #     stop_words_ids = [torch.tensor([2]).to(self.device)]
        #     self.stopping_criteria = StoppingCriteriaList([StoppingCriteriaSub(stops=stop_words_ids)])

    def ask(self, text, conv):
        # import pdb;pdb.set_trace()
        if len(conv.messages) > 0 and conv.messages[-1][0] == conv.roles[0] \
                and conv.messages[-1][1][-9:] == '<image>\n':  # last message is image.
            conv.messages[-1][1] = ' '.join([conv.messages[-1][1], text])
        else:
            conv.append_message(conv.roles[0], text)

    def answer_prepare(self, conv, img_list, max_new_tokens=300, num_beams=1, min_length=1, top_p=0.9,
                       repetition_penalty=1.05, length_penalty=1, temperature=1.0, max_length=2000):
        conv.append_message(conv.roles[1], None)
        prompt = conv.get_prompt()
        # prompt='A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human\'s questions. USER: <image>\n hello ASSISTANT:'
        text_input_ids = tokenizer_image_token(prompt, self.tokenizer, IMAGE_TOKEN_INDEX, return_tensors='pt').unsqueeze(0).to(device=self.device)

        stop_str = conv.sep if conv.sep_style != SeparatorStyle.TWO else conv.sep2
        keywords = [stop_str]
        stopping_criteria = KeywordsStoppingCriteria(keywords, self.tokenizer, text_input_ids)
        current_max_len = text_input_ids.shape[1] + max_new_tokens
        if current_max_len - max_length > 0:
            print('Warning: The number of tokens in current conversation exceeds the max length. '
                  'The model will not see the contexts outside the range.')
        begin_idx = max(0, current_max_len - max_length)
        embs = text_input_ids[:, begin_idx:]

        generation_kwargs = dict(
            input_ids=embs,
            images=img_list[0],
            max_new_tokens=max_new_tokens,
            stopping_criteria=[stopping_criteria],
            num_beams=num_beams,
            do_sample=True,
            min_length=min_length,
            top_p=top_p,
            use_cache=True,
            repetition_penalty=repetition_penalty,
            length_penalty=length_penalty,
            temperature=float(temperature),
        )
        return generation_kwargs

    # def answer(self, conv, img_list, **kargs):
    #     generation_dict = self.answer_prepare(conv, img_list, **kargs)
    #     output_token = self.model_generate(**generation_dict)[0]
    #     output_text = self.model.llama_tokenizer.decode(output_token, skip_special_tokens=True)

    #     output_text = output_text.split('###')[0]  # remove the stop sign '###'
    #     output_text = output_text.split('Assistant:')[-1].strip()

    #     conv.messages[-1][1] = output_text
    #     return output_text, output_token.cpu().numpy()

    def stream_answer(self, conv, img_list, **kargs):
        generation_kwargs = self.answer_prepare(conv, img_list, **kargs)
        
        streamer = TextIteratorStreamer(self.tokenizer,skip_prompt=True, skip_special_tokens=True)
        generation_kwargs['streamer'] = streamer
        # import pdb;pdb.set_trace()
        # output_ids=self.model.generate(*generation_kwargs)
        output=self.model_generate(kwargs=generation_kwargs)
        # thread = Thread(target=self.model_generate, kwargs=generation_kwargs)
        # thread.start()
        return streamer

    def model_generate(self, *args, **kwargs):
        # for 8 bit and 16 bit compatibility
        with torch.inference_mode():
            output = self.model.generate(kwargs['kwargs']['input_ids'],
                                         images=kwargs['kwargs']['images'],
                                         do_sample=False,
                                         temperature=kwargs['kwargs']['temperature'],
                                         max_new_tokens=kwargs['kwargs']['max_new_tokens'],
                                         streamer=kwargs['kwargs']['streamer'],
                                         use_cache=kwargs['kwargs']['use_cache'],
                                         stopping_criteria=kwargs['kwargs']['stopping_criteria'])
            # import pdb;pdb.set_trace()
            # print(output)
            outputs = self.tokenizer.decode(output[0,kwargs['kwargs']['input_ids'].shape[1]:]).strip()
            # print(outputs)
        return output

    def encode_img(self, img_list):
        
        image = img_list[0]
        # image='/share/data/drive_3/kartik/LLaVA/output_images/output.jpg'
        img_list.pop(0)
        if isinstance(image, str):  # is a image path
            raw_image = Image.open(image).convert('RGB')
            image = process_images_demo([raw_image], self.vis_processor)
            # print("raw")
            # image = self.vis_processor(raw_image).unsqueeze(0).to(self.device)
        elif isinstance(image, Image.Image):
            raw_image = image
            image = process_images_demo([raw_image], self.vis_processor )
            image=image.to(device=self.device,dtype=torch.float16)
            # print("Image")
            # image = self.vis_processor(raw_image).unsqueeze(0).to(self.device)
        elif isinstance(image, torch.Tensor):
            if len(image.shape) == 3:
                image = image.unsqueeze(0)
        image = image.to(self.device)

        # image_emb, _ = self.model.encode_img(image)
        img_list.append(image)

    def upload_img(self, image, conv, img_list):
        conv.append_message(conv.roles[0], DEFAULT_IMAGE_TOKEN+'\n')
        img_list.append(image)
        msg = "Received."

        return msg



# if __name__ == "__main__":
#     print(default_conversation.get_prompt())