memory_create_section
Organize memories by creating section headers for grouping related content without embedding or visualization.
Instructions
Create a new section/subsection header memory.
Section memories are organizational placeholders that:
Are NOT visible in the graph visualization
Are NOT included in duplicate detection
Do NOT compute embeddings or cross-references
Args: content: Title/description of the section section: Parent section name (e.g., "Architecture", "API") subsection: Subsection path (e.g., "endpoints/auth")
Returns: Created section memory with auto-assigned tag "memora/sections"
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| content | Yes | ||
| section | No | ||
| subsection | No |
Output Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Implementation Reference
- memora/server.py:656-694 (handler)The implementation of the `memory_create_section` tool. It creates a memory of type 'section' and assigns it the 'memora/sections' tag. It uses the `_create_memory` helper to persist the memory to the database.
async def memory_create_section( content: str, section: Optional[str] = None, subsection: Optional[str] = None, ) -> Dict[str, Any]: """Create a new section/subsection header memory. Section memories are organizational placeholders that: - Are NOT visible in the graph visualization - Are NOT included in duplicate detection - Do NOT compute embeddings or cross-references Args: content: Title/description of the section section: Parent section name (e.g., "Architecture", "API") subsection: Subsection path (e.g., "endpoints/auth") Returns: Created section memory with auto-assigned tag "memora/sections" """ # Build metadata metadata: Dict[str, Any] = { "type": "section", } if section: metadata["section"] = section if subsection: metadata["subsection"] = subsection # Create with auto-tag tags = ["memora/sections"] try: record = _create_memory(content.strip(), metadata, tags) except ValueError as exc: return {"error": "invalid_input", "message": str(exc)} _schedule_cloud_graph_sync() return {"memory": record}