Nav apraksta

1 Atzari

Lukas Goldschmidt 480cef2fe5 docs update		1 mēnesi atpakaļ
app	d7c46a8fec basic maintenance	1 mēnesi atpakaļ
ontology	d7c46a8fec basic maintenance	1 mēnesi atpakaļ
tests	d7c46a8fec basic maintenance	1 mēnesi atpakaļ
.env.example	00c5616db0 initial commit, scaffolding	1 mēnesi atpakaļ
.gitignore	00c5616db0 initial commit, scaffolding	1 mēnesi atpakaļ
PROJECT.md	480cef2fe5 docs update	1 mēnesi atpakaļ
README.md	480cef2fe5 docs update	1 mēnesi atpakaļ
killserver.sh	00c5616db0 initial commit, scaffolding	1 mēnesi atpakaļ
maintenance.sh	d7c46a8fec basic maintenance	1 mēnesi atpakaļ
requirements.txt	d7c46a8fec basic maintenance	1 mēnesi atpakaļ
resolve_scheme.md	00c5616db0 initial commit, scaffolding	1 mēnesi atpakaļ
restart.sh	00c5616db0 initial commit, scaffolding	1 mēnesi atpakaļ
run.sh	6d58e75824 storage bug fixed	1 mēnesi atpakaļ
tests.sh	00c5616db0 initial commit, scaffolding	1 mēnesi atpakaļ

atlas2-mcp

Python FastMCP server for the atlas2 resolution flow.

Current status

Exposes one tool: resolve()
resolve() now performs the working path:
- store lookup (label/alias)
- Wikidata fallback using wikidata.reconci.link quick-resolve (single-candidate)
- minimal persist to Virtuoso via MCP
- cache hits return the stored result
Store lookup was debugged and made robust by splitting label-first then alias.
Maintenance scaffolding (dry-run CLI) exists to upgrade atlas:needsCuration true entities using:
- ontology/wikidata_subclassof.ttl
- Wikidata entity dumps
- Atlas type bucket inference (Person/Organization/Location/etc.)

1) Create config:

cp .env.example .env

2) Install dependencies:

pip install -r requirements.txt

3) Start:

./run.sh

Server runs on port 8550 and mounts the MCP endpoint at /mcp.