Pablan, as it stands

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

docker-compose.dev.yml

@@ -0,0 +1,26 @@
+# Dev stack: only Postgres runs in Docker. Backend (uvicorn --reload) and
+# frontend (vite dev) run natively on the host — see `make dev`.
+# Separate project name so a customer-stack smoke test (docker-compose.yml)
+# can run on the same machine without colliding.
+name: pablan-dev
+
+services:
+  postgres:
+    image: pgvector/pgvector:pg18
+    environment:
+      POSTGRES_USER: ${POSTGRES_USER:-pablan}
+      POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:-change-me}
+      POSTGRES_DB: ${POSTGRES_DB:-pablan}
+    ports:
+      - "5432:5432"
+    volumes:
+      # PG18 images expect the mount at /var/lib/postgresql (not .../data)
+      - postgres_dev_data:/var/lib/postgresql
+    healthcheck:
+      test: ["CMD-SHELL", "pg_isready -U $${POSTGRES_USER} -d $${POSTGRES_DB}"]
+      interval: 2s
+      timeout: 5s
+      retries: 15
+
+volumes:
+  postgres_dev_data: