Memory error. possible to optimize?

[valentinedwv]

optimization?
Got a memory error,
Tried to allocate 754.2 MB, but only 382.8 MB were available

then tried an what I thought would simplify...
I tried to: drop the multiple: ?subj a ?type .

?subj a ?type .
  {
  ?text ql:contains-entity ?item .
  ?text ql:contains-word "water" .
  }
  UNION
  {
 
  ?text ql:contains-entity ?item .
  ?text ql:contains-word "temperature" .
  }

but got a Cartesian Product Join

2026-05-20 19:50:37.852 - INFO: Requested media types of the result are: "application/qlever-results+json"
2026-05-20 19:50:37.875 - INFO: Query planning done in 32 ms
2026-05-20 19:50:37.911 - INFO: Number of tuples in VALUES clause: 14
2026-05-20 19:50:37.911 - INFO: Number of entries in local vocabulary per column: 4, 10
2026-05-20 19:50:38.108 - INFO: Number of tuples in VALUES clause: 2
2026-05-20 19:50:38.108 - INFO: Number of entries in local vocabulary per column: 0
2026-05-20 19:50:44.795 - WARN: No timeout check has been performed for at least 3,988ms, should be at most 50ms. Checked at Sort.cpp:184 at stage "Sort (internal order) on ?subj".
2026-05-20 19:50:44.878 - WARN: No timeout check has been performed for at least 60ms, should be at most 50ms. Checked at CartesianProductJoin.cpp:131 at stage "Cartesian Product Join".

AI suggests: but get a Missing ql:contains-word statement. A ql:contains-entity statement always also needs corresponding ql:contains-word statement..

?subj a ?type .
?text ql:contains-entity ?item .
  { ?text ql:contains-word "water" }
  UNION
  { ?text ql:contains-word "temperature" }

the initial query

 PREFIX schema: <https://schema.org/>
PREFIX sschema: <https://schema.org/>
PREFIX bds: <http://www.bigdata.com/rdf/search#>
PREFIX ql: <http://qlever.cs.uni-freiburg.de/builtin-functions/>
PREFIX xsd: <http://www.w3.org/2001/XMLSchema#>
PREFIX geo: <http://www.opengis.net/ont/geosparql#>
PREFIX geof: <http://www.opengis.net/def/function/geosparql/>
PREFIX sf: <http://www.opengis.net/ont/sf#>

SELECT DISTINCT ?g ?subj ?name ?description ?url ?datep ?pubname ?temporalCoverage  (GROUP_CONCAT(DISTINCT ?url; SEPARATOR=", ") AS ?disurl)   (GROUP_CONCAT(DISTINCT ?placename; SEPARATOR=", ") AS ?placenames)   (GROUP_CONCAT(DISTINCT ?kw_u; SEPARATOR=", ") AS ?kw)   (GROUP_CONCAT(DISTINCT ?resourceType_u; SEPARATOR=", ") AS ?resourceType)  
WHERE {
  VALUES ?sosType {
    sschema:Dataset
    schema:Dataset
  }
  ?subj a ?sosType .
  VALUES (?type ?resourceType_u) {
    (schema:Dataset "data")
    (sschema:Dataset "data")
    (schema:ResearchProject "researchProject")
    (sschema:ResearchProject "researchProject")
    (schema:SoftwareApplication "tool")
    (sschema:SoftwareApplication "tool")
    (schema:Person "person")
    (sschema:Person "person")
    (schema:Event "event")
    (sschema:Event "event")
    (schema:Award "award")
    (sschema:Award "award")
    (schema:DataCatalog "DataCatalog")
    (sschema:DataCatalog "DataCatalog")
  }
  ?subj a ?type .
  {
  ?subj ?o ?item .
  ?text ql:contains-entity ?item .
  ?text ql:contains-word "water" .
  }
  UNION
  {
  ?subj ?o ?item .
  ?text ql:contains-entity ?item .
  ?text ql:contains-word "temperature" .
  }
  GRAPH ?g {
    ?subj schema:name|sschema:name ?name .
    ?subj schema:description|sschema:description ?description .
  }
  OPTIONAL {?subj sschema:distribution/sschema:url|sschema:subjectOf/sschema:url|schema:distribution/schema:url|schema:subjectOf/schema:url ?url1 .}
  OPTIONAL {?subj schema:datePublished|sschema:datePublished ?datep1 .}
  OPTIONAL {?subj schema:dateCreated|sschema:dateCreated ?datec .}
  OPTIONAL {?subj schema:dateModified|sschema:dateModified ?datem .}
  OPTIONAL {?subj schema:temporalCoverage|sschema:temporalCoverage ?temporalCoverage .}
  OPTIONAL {?subj schema:publisher/schema:name|sschema:publisher/sschema:name|schema:publisher/schema:legalName|sschema:publisher/sschema:legalName ?pub_name .}
  OPTIONAL {?subj schema:spatialCoverage/schema:name|sschema:spatialCoverage/sschema:name|sschema:sdPublisher ?place_name .}
  OPTIONAL {?subj schema:keywords|sschema:keywords ?kwu .}



  BIND (COALESCE(?datec,?datem,?datep1) AS ?datep)
  BIND (IF(BOUND(?pub_name), ?pub_name, "No Publisher") AS ?pubname)
  BIND (IF(BOUND(?place_name), ?place_name, "No Placenames") AS ?placename)
}
GROUP BY ?g ?subj  ?placename  ?datep ?pubname ?url  ?name ?description ?type  ?temporalCoverage ?kw  ?resourceType
LIMIT 10
OFFSET 0

# Qleverfile for Earthcube Decoder/Geocodes, use with https://github.com/ad-freiburg/qlever-control
#
# qlever get-data  # downloads .zip file of size 13 MB, uncompressed to 323 MB
# qlever index     # takes ~10 seconds and ~1 GB RAM (on an AMD Ryzen 9 5900X)
# qlever start     # starts the server (instant)
# removed from ui section: UI_CONFIG = eco

[data]
NAME              = facetsearch
SOURCES           = geocodes_examples geocodes_demo_datasets iris magic earthchem r2r opentopography iedadata wifire cchdo ssdbiodp osmc obis wodb emodnet
BASE_URL          = https://oss.geocodes-aws.earthcube.org/decoder/graphs/latest
GET_DATA_CMD      = for source in ${SOURCES}; do curl -sLo $${source}_release.nq -C - ${BASE_URL}/$${source}_release.nq; done
DESCRIPTION       = eco ${NAME} ${BASE_URL}
TEXT_DESCRIPTION  = eco release graph for ${NAME} sources: ${SOURCES}
FORMAT            = nq


[index]
INPUT_FILES     = *_release.nq
CAT_INPUT_FILES = cat ${INPUT_FILES}
VOCABULARY_TYPE = on-disk-compressed-geo-split
TEXT_INDEX= from_literals_and_text_records
SETTINGS_JSON   = { "num-triples-per-batch": 100000 }
#SETTINGS_JSON   = { "add-text-index": true, "ascii-prefixes-only": false, "num-triples-per-batch": 100000, "vocabulary-type": "on-disk-compressed-geo-split" }
[server]
PORT               = 7019
ACCESS_TOKEN       = ${data:NAME}_7643543846_6dMISzlPrD7i
MEMORY_FOR_QUERIES = 16G
CACHE_MAX_SIZE     = 16G
TIMEOUT            = 360s

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

[ui]
UI_CONFIG = default