[Question]:在进行图片的视觉分析时，使用的是相对路径加载图片的base64？

[LiZiTi]

Do you need to ask a question?

• I have searched the existing question and discussions and this question is not already answered.
• I believe this is a legitimate question, not just a bug or feature request.

Your Question

代码文件：modelprocessors.py 247 行的函数process_multimodal_content：
`
image_path = content_data.get("img_path")
captions = content_data.get("img_caption", [])
footnotes = content_data.get("img_footnote", [])

        # Build detailed visual analysis prompt
        vision_prompt = PROMPTS["vision_prompt"].format(
            entity_name=entity_name
            if entity_name
            else "unique descriptive name for this image",
            image_path=image_path,
            captions=captions if captions else "None",
            footnotes=footnotes if footnotes else "None",
        )

        # If image path exists, try to encode image
        image_base64 = ""
        if image_path and Path(image_path).exists():
            image_base64 = self._encode_image_to_base64(image_path)

`

我发现传递进来的content_data中图片的路径是相对路径，而且函数process_multimodal_content也没有地方去获取存储图片的根路径，导致无法成功加载图片的base64。

Additional Context

No response

[LarFii]

Thanks for the reminder! This issue has been fixed in the latest version of the code.