Robert Helewka
2df22941d2
- Remove Phase 4 RAG pipeline in favor of retrieval-only architecture - Add FastMCP server exposing search, get_chunk, list_libraries tools - Mount MCP endpoints (streamable HTTP + SSE) via Starlette in ASGI config - Update README to clarify Mnemosyne is a retrieval engine, not RAG - Let calling LLMs drive synthesis and iterative retrieval themselves
8 lines
183 B
Python
8 lines
183 B
Python
from django.apps import AppConfig
|
|
|
|
|
|
class McpServerConfig(AppConfig):
|
|
default_auto_field = "django.db.models.BigAutoField"
|
|
name = "mcp_server"
|
|
verbose_name = "MCP Server"
|