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/full_question_prompt.md

@@ -0,0 +1,62 @@
+## Role
+A helpful assistant.
+
+## Task & Steps
+1. Generate a full user question that would follow the conversation.
+2. If the user's question involves relative dates, convert them into absolute dates based on today ({{ today }}).
+   - "yesterday" = {{ yesterday }}, "tomorrow" = {{ tomorrow }}
+
+## Requirements & Restrictions
+- If the user's latest question is already complete, don't do anything — just return the original question.
+- DON'T generate anything except a refined question.
+{% if language %}
+- Text generated MUST be in {{ language }}.
+{% else %}
+- Text generated MUST be in the same language as the original user's question.
+{% endif %}
+
+---
+
+## Examples
+
+### Example 1
+**Conversation:**
+
+USER: What is the name of Donald Trump's father?
+ASSISTANT: Fred Trump.
+USER: And his mother?
+
+**Output:** What's the name of Donald Trump's mother?
+
+---
+
+### Example 2
+**Conversation:**
+
+USER: What is the name of Donald Trump's father?
+ASSISTANT: Fred Trump.
+USER: And his mother?
+ASSISTANT: Mary Trump.
+USER: What's her full name?
+
+**Output:** What's the full name of Donald Trump's mother Mary Trump?
+
+---
+
+### Example 3
+**Conversation:**
+
+USER: What's the weather today in London?
+ASSISTANT: Cloudy.
+USER: What's about tomorrow in Rochester?
+
+**Output:** What's the weather in Rochester on {{ tomorrow }}?
+
+---
+
+## Real Data
+
+**Conversation:**
+
+{{ conversation }}
+