# Copyright (c) Alibaba Cloud. # # This source code is licensed under the license found in the # LICENSE file in the root directory of this source tree. import os import numpy as np from urllib3.exceptions import HTTPError os.system('pip install dashscope modelscope -U') os.system('pip install gradio==3.*') # os.environ['CUDA_VISIBLE_DEVICES'] = '0,1' from argparse import ArgumentParser from pathlib import Path import copy import gradio as gr import os import re import secrets import tempfile import requests from http import HTTPStatus from dashscope import MultiModalConversation import dashscope API_KEY = os.environ['API_KEY'] dashscope.api_key = API_KEY DEFAULT_CKPT_PATH = 'qwen/Qwen-VL-Chat' REVISION = 'v1.0.4' BOX_TAG_PATTERN = r"([\s\S]*?)" PUNCTUATION = "！？。＂＃＄％＆＇（）＊＋，－／：；＜＝＞＠［＼］＾＿｀｛｜｝～｟｠｢｣､、〃》「」『』【】〔〕〖〗〘〙〚〛〜〝〞〟〰〾〿–—‘’‛“”„‟…‧﹏." def _get_args(): parser = ArgumentParser() parser.add_argument("-c", "--checkpoint-path", type=str, default=DEFAULT_CKPT_PATH, help="Checkpoint name or path, default to %(default)r") parser.add_argument("--revision", type=str, default=REVISION) parser.add_argument("--cpu-only", action="store_true", help="Run demo with CPU only") parser.add_argument("--share", action="store_true", default=False, help="Create a publicly shareable link for the interface.") parser.add_argument("--inbrowser", action="store_true", default=False, help="Automatically launch the interface in a new tab on the default browser.") parser.add_argument("--server-port", type=int, default=7860, help="Demo server port.") parser.add_argument("--server-name", type=str, default="127.0.0.1", help="Demo server name.") args = parser.parse_args() return args def _parse_text(text): lines = text.split("\n") lines = [line for line in lines if line != ""] count = 0 for i, line in enumerate(lines): if "```" in line: count += 1 items = line.split("`") if count % 2 == 1: lines[i] = f'
'
            else:
                lines[i] = f"
" else: if i > 0: if count % 2 == 1: line = line.replace("`", r"\`") line = line.replace("<", "<") line = line.replace(">", ">") line = line.replace(" ", " ") line = line.replace("*", "*") line = line.replace("_", "_") line = line.replace("-", "-") line = line.replace(".", ".") line = line.replace("!", "!") line = line.replace("(", "(") line = line.replace(")", ")") line = line.replace("$", "$") lines[i] = "
" + line text = "".join(lines) return text """ ('/tmp/gradio/1837abb0176495ff182050801ebff1fa9b18fc4a/aiyinsitan.jpg',), None], ['这是谁？', '图中是爱因斯坦，阿尔伯特·爱因斯坦（Albert ' 'Einstein），是出生于德国、拥有瑞士和美国国籍的犹太裔理论物理学家，他创立了现代物理学的两大支柱的相对论及量子力学。'], ['框处里面的人', '图中框内是爱因斯坦的半身照，照片中爱因斯坦穿着一件西装，留着标志性的胡子和蜷曲的头发。'], ['框出里面的人', ('/tmp/gradio/71cf5c2551009fd9a00e0d80bc7ab7fb8de211b5/tmp115aba5d70.jpg',)], [None, '里面的人'], ('介绍一下', '阿尔伯特·爱因斯坦（Albert ' 'Einstein），是出生于德国、拥有瑞士和美国国籍的犹太裔理论物理学家，他创立了现代物理学的两大支柱的相对论及量子力学。他的贡献包括他提出的相对论（尤其是狭义相对论和广义相对论）、量子力学的开创性贡献以及他对于 ' 'gravity 的贡献。爱因斯坦也是诺贝尔奖得主以及美国公民。')] """ def _remove_image_special(text): text = text.replace('', '').replace('', '') return re.sub(r'.*?(|$)', '', text) def _launch_demo(args): uploaded_file_dir = os.environ.get("GRADIO_TEMP_DIR") or str( Path(tempfile.gettempdir()) / "gradio" ) def predict(_chatbot, task_history): chat_query = _chatbot[-1][0] query = task_history[-1][0] if len(chat_query) == 0: _chatbot.pop() task_history.pop() return _chatbot print("User: " + _parse_text(query)) history_cp = copy.deepcopy(task_history) full_response = "" messages = [] content = [] for q, a in history_cp: if isinstance(q, (tuple, list)): content.append({'image': f'file://{q[0]}'}) else: content.append({'text': q}) messages.append({'role': 'user', 'content': content}) messages.append({'role': 'assistant', 'content': [{'text': a}]}) content = [] messages.pop() responses = MultiModalConversation.call( model='qwen-vl-plus', messages=messages, seed=np.random.randint(0, np.iinfo(np.int64).max), top_p=0.001, stream=True, ) for response in responses: if not response.status_code == HTTPStatus.OK: raise HTTPError(f'response.code: {response.code}\nresponse.message: {response.message}') response = response.output.choices[0].message.content response_text = [] for ele in response: if 'text' in ele: response_text.append(ele['text']) elif 'box' in ele: response_text.append(ele['box']) response_text = ''.join(response_text) _chatbot[-1] = (_parse_text(chat_query), _remove_image_special(response_text)) yield _chatbot if len(response) > 1: result_image = response[-1]['result_image'] resp = requests.get(result_image) os.makedirs(uploaded_file_dir, exist_ok=True) name = f"tmp{secrets.token_hex(20)}.jpg" filename = os.path.join(uploaded_file_dir, name) with open(filename, 'wb') as f: f.write(resp.content) response = ''.join(r['box'] if 'box' in r else r['text'] for r in response[:-1]) _chatbot.append((None, (filename,))) else: response = response[0]['text'] _chatbot[-1] = (_parse_text(chat_query), response) full_response = _parse_text(response) task_history[-1] = (query, full_response) print("Qwen-VL-Chat: " + _parse_text(full_response)) # task_history = task_history[-10:] yield _chatbot def regenerate(_chatbot, task_history): if not task_history: return _chatbot item = task_history[-1] if item[1] is None: return _chatbot task_history[-1] = (item[0], None) chatbot_item = _chatbot.pop(-1) if chatbot_item[0] is None: _chatbot[-1] = (_chatbot[-1][0], None) else: _chatbot.append((chatbot_item[0], None)) return predict(_chatbot, task_history) def add_text(history, task_history, text): task_text = text if len(text) >= 2 and text[-1] in PUNCTUATION and text[-2] not in PUNCTUATION: task_text = text[:-1] history = history + [(_parse_text(text), None)] task_history = task_history + [(task_text, None)] return history, task_history, "" def add_file(history, task_history, file): history = history + [((file.name,), None)] task_history = task_history + [((file.name,), None)] return history, task_history def reset_user_input(): return gr.update(value="") def reset_state(task_history): task_history.clear() return [] with gr.Blocks() as demo: gr.Markdown("""\

""") gr.Markdown("""

Qwen-VL-Plus
""") gr.Markdown( """\
This WebUI is based on Qwen-VL-Plus, the upgraded version of Qwen-VL, developed by Alibaba Cloud.
""") gr.Markdown("""
本WebUI基于Qwen-VL-Plus打造，这是Qwen-VL的升级版。
""") gr.Markdown("""\
\ Github  ｜   Qwen-VL 🤖 | 🤗  ｜ Qwen-VL-Chat 🤖 | 🤗  ｜   Qwen-VL-Plus   Web | API
""") chatbot = gr.Chatbot(label='Qwen-VL-Plus', elem_classes="control-height", height=500) query = gr.Textbox(lines=2, label='Input') task_history = gr.State([]) with gr.Row(): addfile_btn = gr.UploadButton("📁 Upload (上传文件)", file_types=["image"]) submit_btn = gr.Button("🚀 Submit (发送)") regen_btn = gr.Button("🤔️ Regenerate (重试)") empty_bin = gr.Button("🧹 Clear History (清除历史)") submit_btn.click(add_text, [chatbot, task_history, query], [chatbot, task_history]).then( predict, [chatbot, task_history], [chatbot], show_progress=True ) submit_btn.click(reset_user_input, [], [query]) empty_bin.click(reset_state, [task_history], [chatbot], show_progress=True) regen_btn.click(regenerate, [chatbot, task_history], [chatbot], show_progress=True) addfile_btn.upload(add_file, [chatbot, task_history, addfile_btn], [chatbot, task_history], show_progress=True) gr.Markdown("""\ Note: This demo is governed by the original license of Qwen-VL. \ We strongly advise users not to knowingly generate or allow others to knowingly generate harmful content, \ including hate speech, violence, pornography, deception, etc. \ (注：本演示受Qwen-VL的许可协议限制。我们强烈建议，用户不应传播及不应允许他人传播以下内容，\ 包括但不限于仇恨言论、暴力、色情、欺诈相关的有害信息。)""") demo.queue().launch( share=args.share, # inbrowser=args.inbrowser, # server_port=args.server_port, # server_name=args.server_name, ) def main(): args = _get_args() _launch_demo(args) if __name__ == '__main__': main()