Skip to content

Commit

Permalink
Add Qleverfile for DBpedia
Browse files Browse the repository at this point in the history
  • Loading branch information
Hannah Bast committed Aug 9, 2024
1 parent e063df7 commit 807f204
Showing 1 changed file with 31 additions and 0 deletions.
31 changes: 31 additions & 0 deletions src/qlever/Qleverfiles/Qleverfile.dbpedia
Original file line number Diff line number Diff line change
@@ -0,0 +1,31 @@
# Qleverfile for DBpedia, use with https://github.com/ad-freiburg/qlever-control
#
# qlever get-data # ~14 GB, ~850 M triples (as of 30.07.2024)
# qlever index # ~20 min (on an AMD Ryzen 9 5900X)
# qlever start # ~3 sec

[data]
NAME = dbpedia
DATABUS_URL = https://databus.dbpedia.org/dbpedia/collections/latest-core
GET_DATA_CMD = curl -X POST -H "Accept: text/csv" --data-urlencode "query=$$(curl -s -H "Accept:text/sparql" https://databus.dbpedia.org/dbpedia/collections/latest-core)" https://databus.dbpedia.org/sparql | tail -n+2 | sed 's/\r$$//' | sed 's/"//g' | while read -r file; do wget -P rdf-input $$file; done
DESCRIPTION = RDF data from ${DATABUS_URL}

[index]
INPUT_FILES = rdf-input/*
CAT_INPUT_FILES = (cat rdf-input/*.nt; lbzcat -n2 rdf-input/*.bzip2 rdf-input/*.bz2)
SETTINGS_JSON = { "ascii-prefixes-only": true, "num-triples-per-batch": 1000000, "prefixes-external": [""] }
WITH_TEXT_INDEX = false

[server]
PORT = 7012
ACCESS_TOKEN = ${data:NAME}
MEMORY_FOR_QUERIES = 10G
CACHE_MAX_SIZE = 5G

[runtime]
SYSTEM = docker
IMAGE = docker.io/adfreiburg/qlever:latest

[ui]
UI_PORT = 7000
UI_CONFIG = dbpedia

0 comments on commit 807f204

Please sign in to comment.