Refa: refactor prompts into markdown-style structure using Jinja2 (#8667)

### What problem does this PR solve?

Refactor prompts into markdown-style structure using Jinja2.

### Type of change

- [x] Refactoring

rag/prompts/vision_llm_describe_prompt.md

@@ -0,0 +1,23 @@
+## INSTRUCTION
+Transcribe the content from the provided PDF page image into clean Markdown format.
+
+- Only output the content transcribed from the image.
+- Do NOT output this instruction or any other explanation.
+- If the content is missing or you do not understand the input, return an empty string.
+
+## RULES
+1. Do NOT generate examples, demonstrations, or templates.
+2. Do NOT output any extra text such as 'Example', 'Example Output', or similar.
+3. Do NOT generate any tables, headings, or content that is not explicitly present in the image.
+4. Transcribe content word-for-word. Do NOT modify, translate, or omit any content.
+5. Do NOT explain Markdown or mention that you are using Markdown.
+6. Do NOT wrap the output in ```markdown or ``` blocks.
+7. Only apply Markdown structure to headings, paragraphs, lists, and tables, strictly based on the layout of the image. Do NOT create tables unless an actual table exists in the image.
+8. Preserve the original language, information, and order exactly as shown in the image.
+
+{% if page %}
+At the end of the transcription, add the page divider: `--- Page {{ page }} ---`.
+{% endif %}
+
+> If you do not detect valid content in the image, return an empty string.
+