Comandos combinados cue word para extraer visualmente documentos en formato Markdown

Esta directiva se deriva de la directiva Visión Parse que se divide en dos pasos para extraer documentos Markdown.

Consulta de análisis de imágenes (img_analysis.prompt).

Analyze this image and return a detailed JSON description including any text detected, images detected, tables detected, extracted text and confidence score for the extracted text.
Confidence score for the extracted text should be a float value between 0 and 1. If you cannot determine certain details, leave those fields empty.

traducción de palabras clave

分析此图像并返回一个详细的 JSON 描述，其中包括检测到的任何文本、检测到的图像、检测到的表格、提取的文本及其置信度分数。 
提取文本的置信度分数应为介于 0 和 1 之间的浮点值。如果无法确定某些细节，请将这些字段留空。

Plantilla de aviso de formato Markdown (md_prompt.j2).

{% autoescape true %}

Your task is to analyze the given image and extract textual content in markdown format.

{% if confidence_score_text is defined and confidence_score_text is number %}
{% if confidence_score_text > 0.6 %}
- Verify if the extracted text matches with the content in the image: {{ extracted_text|escape|trim }}.
- Ensure markdown text formatting for {{ extracted_text|escape|trim }} is applied properly by analyzing the image.
- Strictly do not change any content in the original extracted text while applying markdown text formatting.
{% else %}
- Please carefully reanalyze the text in the image as the initial confidence score was low.
- Convert the provided image into markdown format and ensure that all content from the image is included.
{% endif %}
{% endif %}

{% if tables_detected is defined and tables_detected|string == "Yes" %}
- Preserve the tabular structure in markdown format using | for columns and - for the header row separator.
- Ensure that the cell values are properly aligned within the table columns and the tabular data is not distorted.
- Maintain the original positioning of the table within the scanned document. Do not include any additional explanations or comments.
{% endif %}

- Preserve markdown text formatting if present such as bold, italics, underlines, headers, bullet points, links or other elements.
- Strictly, do not omit any textual content from the given image and do not include any additional explanations, notes or comments.
- Ensure that the content does not have unnecessary formatting and at the same time, preserve the original formatting as much as possible.
- Strictly, do not generate code fences or backticks like ``` or ```markdown.

{% endautoescape %}

traducción de palabras clave

{% autoescape true %}

您的任务是分析给定的图像，并以 Markdown 格式提取文本内容。

{% if confidence_score_text is defined and confidence_score_text is number %}
{% if confidence_score_text > 0.6 %}
- 验证提取的文本是否与图像内容匹配：{{ extracted_text|escape|trim }}。
- 通过分析图像，确保 {{ extracted_text|escape|trim }} 的 Markdown 文本格式正确应用。
- 在应用 Markdown 文本格式时，严格不要更改原始提取文本中的任何内容。
{% else %}
- 请仔细重新分析图像中的文本，因为初始置信评分较低。
- 将提供的图像转换为 Markdown 格式，并确保图像中的所有内容都被包含。
{% endif %}
{% endif %}

{% if tables_detected is defined and tables_detected|string == "Yes" %}
- 使用 | 表示列，使用 - 表示表头行分隔符，以 Markdown 格式保留表格结构。
- 确保单元格值在表格列中正确对齐，并且表格数据未发生扭曲。
- 保持表格在扫描文档中的原始位置。不要包括任何额外的说明或评论。
{% endif %}

- 如果存在 Markdown 文本格式，例如加粗、斜体、下划线、标题、项目符号、链接或其他元素，请予以保留。
- 严格不要遗漏给定图像中的任何文本内容，也不要包括任何额外的说明、备注或评论。
- 确保内容没有不必要的格式，同时尽可能保留原始格式。
- 严格不要生成代码块或反引号，例如 ``` 或 ```markdown。

{% endautoescape %}

Permítanme analizar todas las variables referenciadas en la plantilla md_prompt.j2:

1. confidence_score_text

{% if confidence_score_text is defined and confidence_score_text is number %}
{% if confidence_score_text > 0.6 %}

• Tipo: numérico (número)
• Finalidad: Almacenar las puntuaciones de confianza para la extracción de texto
• Rango de valores: número en coma flotante entre 0 y 1
• Sirve para determinar si es necesario volver a analizar el texto

2. texto_extraído

{{ extracted_text|escape|trim }}

• Tipo: string(cadena)
• Finalidad: Almacenar el contenido del texto original extraído de la imagen
• Se utilizan dos filtros:
  • escape: escapa caracteres especiales
  • recortar: Eliminar espacios en blanco

3. tablas_detectadas

{% if tables_detected is defined and tables_detected|string == "Yes" %}

• Tipo: string(cadena)
• Finalidad: Identificar si se detecta un formulario
• Valores posibles: "Sí" o "No".

Estas variables provienen del modelo ImageDescription del código (definido en llm.py):

class ImageDescription(BaseModel):
"""Model Schema for image description."""
text_detected: Literal["Yes", "No"]
tables_detected: Literal["Yes", "No"]
extracted_text: str
confidence_score_text: float

Este modelo corresponde a la estructura JSON devuelta por img_analysis.prompt, lo que garantiza la seguridad de tipo y la coherencia de los datos. Estas variables se generan durante la fase de análisis de la imagen (img_analysis.prompt) y luego se pasan a la plantilla de generación de markdown (md_prompt.j2) para su uso.