Self-hosted knowledge management for SMEs: a split-screen Markdown editor whose sections an LLM refines while you write, and RAG question answering over the documents that result. FastAPI + Postgres/pgvector on the back, SvelteKit on the front, everything OpenAI-compatible and self-hostable. Squashed into a single commit; the development history stays local. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01CA43ZJda8Rbp2hKXNy8f6b
19 lines
657 B
Python
19 lines
657 B
Python
"""The authoring API: the model's help while someone writes.
|
|
|
|
Three endpoints under `/documents`, all owner-scoped: refine the section at the
|
|
cursor (streamed), suggest a title for a finished draft, and suggest which
|
|
existing document a capture should extend. What they share is `grounding` — the
|
|
permission-filtered look at what the company already wrote.
|
|
|
|
`suggest-similar` has a static path and is registered before the refine module
|
|
so it cannot be read as a document id.
|
|
"""
|
|
|
|
from fastapi import APIRouter
|
|
|
|
from app.api.authoring import refine, suggest
|
|
|
|
router = APIRouter()
|
|
router.include_router(suggest.router)
|
|
router.include_router(refine.router)
|