Upload 2 files

app.py

@@ -0,0 +1,179 @@
+import gradio as gr 
+from transformers import AutoModelForCausalLM,AutoProcessor,pipeline
+from PIL import Image
+import os 
+import tempfile
+import torch
+from pathlib import Path
+import secrets
+
+# Initialise Hugging Face LLM
+model_id="microsoft/Phi-3.5-vision-instruct"
+model=AutoModelForCausalLM.from_pretrained(
+    model_id,
+    trust_remote_code=True,
+    torch_dtype=torch.float16,
+    use_flash_attention_2=False)
+
+processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True, num_crops=16)
+math_messages=[]
+# Function for processing the image 
+def process_image(image,should_convert=False):
+    '''
+    Saves the uploaded image or sketch and then extracts math-related descriptions using the model
+    '''
+    global math_messages
+    math_messages=[]
+    # create a temporary directory for saving images
+    uploaded_file_dir=os.environ.get("GRADIO_TEMP_DIR") or str(Path(tempfile.gettempdir())/"gradio")
+    os.makedirs(uploaded_file_dir,exist_ok=True)
+    # saves the uploaded image as a temporary file
+    name = f"tmp{secrets.token_hex(20)}.jpg"
+    filename = os.path.join(uploaded_file_dir, name)
+    # If the input was a sketch then convert into RGB format
+    if should_convert:
+        new_img = Image.new('RGB', size=(image.width, image.height), color=(255, 255, 255))
+        new_img.paste(image, (0, 0), mask=image)
+        image = new_img
+    # Saves the image in the temporary file
+    image.save(filename)
+    # Calling the model to process images
+    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.'}
+        ]
+    }]
+    prompt = processor.tokenizer.apply_chat_template(
+        messages, tokenize=False, add_generation_prompt=True
+    )
+    # Process the input
+    inputs = processor(prompt, image, return_tensors="pt")
+    
+    # Generate the response
+    generation_args = {
+        "max_new_tokens": 1000,
+        "temperature": 0.2,
+        "do_sample": True,
+    }
+    generate_ids = model.generate(**inputs, eos_token_id=processor.tokenizer.eos_token_id, **generation_args)
+    
+    # Decode the response
+    generate_ids = generate_ids[:, inputs['input_ids'].shape[1]:]
+    response = processor.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
+    return response
+
+# Function to get math-response from the processed image
+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]
+    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})
+    pipe = pipeline("text-generation", model="deepseek-ai/DeepSeek-V2.5-1210", trust_remote_code=True)
+    response=pipe(math_messages)
+    print(response)
+    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})
+# creating the chatbot
+def math_chat_bot(image, sketchpad, question, state):
+    current_tab_index = state["tab_index"]
+    image_description = None
+    # Upload
+    if current_tab_index == 0:
+        if image is not None:
+            image_description = process_image(image)
+    # Sketch
+    elif current_tab_index == 1:
+        print(sketchpad)
+        if sketchpad and sketchpad["composite"]:
+            image_description = process_image(sketchpad["composite"], True)
+    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; }
+"""
+
+def tabs_select(e: gr.SelectData, _state):
+    _state["tab_index"] = e.index
+
+
+# 创建Gradio接口
+with gr.Blocks(css=css) as demo:
+    gr.HTML(
+            """\
+<center><font size=3>This WebUI is based on Qwen2-VL for OCR and Qwen2.5-Math for mathematical reasoning. You can input either images or texts of mathematical or arithmetic problems.</center>"""
+            )
+    state = gr.State({"tab_index": 0})
+    with gr.Row():
+        with gr.Column():
+            with gr.Tabs() as input_tabs:
+                with gr.Tab("Upload"):
+                    input_image = gr.Image(type="pil", label="Upload"),
+                with gr.Tab("Sketch"):
+                    input_sketchpad = gr.Sketchpad(type="pil", label="Sketch", layers=False)
+            input_tabs.select(fn=tabs_select, inputs=[state])
+            input_text = gr.Textbox(label="input your question")
+            with gr.Row():
+                with gr.Column():
+                    clear_btn = gr.ClearButton(
+                        [*input_image, input_sketchpad, input_text])
+                with gr.Column():
+                    submit_btn = gr.Button("Submit", variant="primary")
+        with gr.Column():
+            output_md = 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")
+        submit_btn.click(
+            fn=math_chat_bot,
+            inputs=[*input_image, input_sketchpad, input_text, state],
+            outputs=output_md)
+demo.launch()

requirements.txt

@@ -0,0 +1,8 @@
+gradio
+numpy==1.24.4
+Pillow==10.3.0
+Requests==2.31.0
+torch
+torchvision
+transformers==4.43.0
+accelerate==0.30.0