Feat: Adds a new feature that enables the LLM to extract a structured table of contents (TOC) directly from plain text. (#10428)

### What problem does this PR solve?

**Adds a new feature that enables the LLM to extract a structured table
of contents (TOC) directly from plain text.**
_This implementation prioritizes efficiency over reasoning — the model
runs in a strictly deterministic mode (thinking disabled) to minimize
latency.
As a result, overall performance may be less optimal, but the extraction
speed and consistency are guaranteed._

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

rag/prompts/toc_from_text_user.md

@@ -0,0 +1,8 @@
+OUTPUT FORMAT
+- Return ONLY the JSON array.
+- Use double quotes.
+- No extra commentary.
+- Keep language of "title" the same as the input.
+
+INPUT
+{{text}}