Method process_image

GPTOCRGUI.py:112–142

(self, image)

        self.gpt_model = model_name

    def process_image(self, image):
        if not self.client:
            raise Exception("请先设置 API Key 或推理接入点")
        
        base64_img = f"data:image/png;base64,{self.image_encoder.encode_image(image)}"
        
        response = self.client.chat.completions.create(
            model=self.gpt_model,
            messages=[
                {
                    "role": "system",
                    "content": self.system_prompt
                },
                {
                    "role": "user",
                    "content": [
                        {"type": "text", "text": self.user_prompt},
                        {
                            "type": "image_url",
                            "image_url": {"url": f"{base64_img}"}
                        }
                    ],
                }
            ],
            max_tokens=self.max_tokens,
        )
        #debug用
        #print(response)
        markdown_content = response.choices[0].message.content
        markdown_content = re.sub(r'^```markdown\s*\n(.*?)\n```\s*$', r'\1', markdown_content, flags=re.DOTALL)
        return self.markdown_processor.modify_wrappers(markdown_content)

    def process_clipboard_image(self):
        if  not self.process_pre_exist_image: