import gradio as gr import os os.system('pip install dashscope -U') import tempfile from pathlib import Path import secrets import dashscope from dashscope import MultiModalConversation, Generation YOUR_API_TOKEN = os.getenv('YOUR_API_TOKEN') dashscope.api_key = YOUR_API_TOKEN math_messages = [] def process_image(image): global math_messages math_messages = [] # reset when upload image uploaded_file_dir = os.environ.get("GRADIO_TEMP_DIR") or str( Path(tempfile.gettempdir()) / "gradio" ) os.makedirs(uploaded_file_dir, exist_ok=True) name = f"tmp{secrets.token_hex(20)}.jpg" filename = os.path.join(uploaded_file_dir, name) image.save(filename) # Use qwen-vl-max-0809 for OCR messages = [{ 'role': 'system', 'content': [{'text': 'You are a helpful assistant.'}] }, { 'role': 'user', 'content': [ {'image': f'file://{filename}'}, {'text': 'Please describe the math-related content in this image, ensuring that any LaTeX formulas are correctly transcribed. Non-mathematical details do not need to be described.'} ] }] response = MultiModalConversation.call(model='qwen-vl-max-0809', messages=messages) os.remove(filename) return response.output.choices[0]["message"]["content"] def get_math_response(image_description, user_question): global math_messages if not math_messages: math_messages.append({'role': 'system', 'content': 'You are a helpful math assistant.'}) math_messages = math_messages[:1] + math_messages[1:][-4:] if image_description is not None: content = f'Image description: {image_description}\n\n' else: content = '' query = f"{content}User question: {user_question}" math_messages.append({'role': 'user', 'content': query}) response = Generation.call( model="qwen2-math-72b-instruct", messages=math_messages, result_format='message', stream=True ) answer = None for resp in response: if resp.output is None: continue answer = resp.output.choices[0].message.content yield answer.replace("\\", "\\\\") print(f'query: {query}\nanswer: {answer}') if answer is None: math_messages.pop() else: math_messages.append({'role': 'assistant', 'content': answer}) def math_chat_bot(image, question): if image is not None: image_description = process_image(image) else: image_description = None yield from get_math_response(image_description, question) css = """ #qwen-md .katex-display { display: inline; } #qwen-md .katex-display>.katex { display: inline; } #qwen-md .katex-display>.katex>.katex-html { display: inline; } """ # Create interface iface = gr.Interface( css=css, fn=math_chat_bot, inputs=[ gr.Image(type="pil", label="upload image"), gr.Textbox(label="input your question") ], outputs=gr.Markdown(label="answer", latex_delimiters=[ {"left": "\\(", "right": "\\)", "display": True}, {"left": "\\begin\{equation\}", "right": "\\end\{equation\}", "display": True}, {"left": "\\begin\{align\}", "right": "\\end\{align\}", "display": True}, {"left": "\\begin\{alignat\}", "right": "\\end\{alignat\}", "display": True}, {"left": "\\begin\{gather\}", "right": "\\end\{gather\}", "display": True}, {"left": "\\begin\{CD\}", "right": "\\end\{CD\}", "display": True}, {"left": "\\[", "right": "\\]", "display": True} ], elem_id="qwen-md"), title="📖 Qwen2 Math Demo", allow_flagging='never', description="""\

""" """\

This WebUI is based on Qwen2-VL for OCR and Qwen2-Math for mathematical reasoning. You can input either images or texts of mathematical or arithmetic problems.
""" ) # Launch gradio application iface.launch()