Dontopedia

Hnswlib

From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-06.)

Hnswlib has 21 facts recorded in Dontopedia across 3 references, with 3 live disagreements.

21 facts·13 predicates·3 sources·3 in dispute

Mostly:rdf:type(3), f1 score exceeds(3), query latency lower than(2)

Maturity scale raw canonical shape-checked rule-derived certified

Inbound mentions (14)

Other subjects in dontopedia point AT this entity as a value. These are inverse relationships — e.g. "X motherOf this subject" — and answer questions the forward facts can't. Grouped by predicate.

f1ScoreLowerThanF1 Score Lower Than(2)

queryLatencyHigherThanQuery Latency Higher Than(2)

containsMemberContains Member(1)

f1ScoreExceedsF1 Score Exceeds(1)

hasEnginesHas Engines(1)

indexingTimeHigherThanIndexing Time Higher Than(1)

indexingTimeLowerThanIndexing Time Lower Than(1)

isMeasuredForIs Measured for(1)

memoryUsageHigherThanMemory Usage Higher Than(1)

memoryUsageLowerThanMemory Usage Lower Than(1)

queryLatencyLowerThanQuery Latency Lower Than(1)

tiesWithTies With(1)

Other facts (18)

The long tail: predicates that appear too rarely to warrant their own section. Filter or scroll to find a specific one. Each row links to its source.

18 facts
PredicateValueRef
Rdf:typeRetrieval Engine[1]
Rdf:typeRetrieval System[2]
Rdf:typeInformation Retrieval System[3]
F1 Score ExceedsDpr[2]
F1 Score ExceedsFaiss[2]
F1 Score ExceedsQdrant[2]
Query Latency Lower ThanDpr[2]
Query Latency Lower ThanDense Passage Retriever[2]
F1 Score0.82[2]
Query Latency210[2]
Indexing Time310[2]
Memory Usage510[2]
Indexing Time Higher ThanSparse Retrieval[2]
Memory Usage Higher ThanSparse Retrieval[2]
Has Community Support0.88[3]
Has Cost105[3]
Has Moderate Performancetrue[3]
May Offer Other Advantagestrue[3]

Timeline

Timeline axis is valid_time — when each source says the fact was true in the world, not when Dontopedia learned about it. Retracted rows are kept for provenance; coloured stripes indicate the context kind.

typebeam/475e93cf-7217-4357-9d01-d4dc6e10f13a
ex:RetrievalEngine
labelbeam/475e93cf-7217-4357-9d01-d4dc6e10f13a
Hnswlib
typebeam/d26a5287-fb4f-4619-b610-ba0ca857b51f
ex:RetrievalSystem
labelbeam/d26a5287-fb4f-4619-b610-ba0ca857b51f
Hnswlib
f1_scorebeam/d26a5287-fb4f-4619-b610-ba0ca857b51f
0.82
query_latencybeam/d26a5287-fb4f-4619-b610-ba0ca857b51f
210
indexing_timebeam/d26a5287-fb4f-4619-b610-ba0ca857b51f
310
memory_usagebeam/d26a5287-fb4f-4619-b610-ba0ca857b51f
510
f1ScoreExceedsbeam/d26a5287-fb4f-4619-b610-ba0ca857b51f
ex:DPR
f1ScoreExceedsbeam/d26a5287-fb4f-4619-b610-ba0ca857b51f
ex:Faiss
f1ScoreExceedsbeam/d26a5287-fb4f-4619-b610-ba0ca857b51f
ex:Qdrant
queryLatencyLowerThanbeam/d26a5287-fb4f-4619-b610-ba0ca857b51f
ex:DPR
queryLatencyLowerThanbeam/d26a5287-fb4f-4619-b610-ba0ca857b51f
ex:Dense-Passage-Retriever
indexingTimeHigherThanbeam/d26a5287-fb4f-4619-b610-ba0ca857b51f
ex:Sparse-Retrieval
memoryUsageHigherThanbeam/d26a5287-fb4f-4619-b610-ba0ca857b51f
ex:Sparse-Retrieval
hasCommunitySupportbeam/63063c97-1ded-45a2-9117-c21c3bcc4f66
0.88
hasCostbeam/63063c97-1ded-45a2-9117-c21c3bcc4f66
105
hasModeratePerformancebeam/63063c97-1ded-45a2-9117-c21c3bcc4f66
true
mayOfferOtherAdvantagesbeam/63063c97-1ded-45a2-9117-c21c3bcc4f66
true
typebeam/63063c97-1ded-45a2-9117-c21c3bcc4f66
ex:InformationRetrievalSystem
labelbeam/63063c97-1ded-45a2-9117-c21c3bcc4f66
Hnswlib

References (3)

3 references
  1. ctx:claims/beam/475e93cf-7217-4357-9d01-d4dc6e10f13a
    • full textbeam-chunk
      text/plain1 KBdoc:beam/475e93cf-7217-4357-9d01-d4dc6e10f13a
      Show excerpt
      This enhanced report provides a more comprehensive analysis and helps you make a more informed decision about which vector database to use for your RAG system. [Turn 2210] User: I'm trying to evaluate the performance of different sparse re
  2. ctx:claims/beam/d26a5287-fb4f-4619-b610-ba0ca857b51f
    • full textbeam-chunk
      text/plain1 KBdoc:beam/d26a5287-fb4f-4619-b610-ba0ca857b51f
      Show excerpt
      matrix.loc['Dense Passage Retriever', 'f1_score'] = .72 matrix.loc['Sparse Retrieval', 'f1_score'] = 0.92 matrix.loc['Faiss', 'f1_score'] = 0.62 matrix.loc['Hnswlib', 'f1_score'] = 0.82 matrix.loc['Qdrant', 'f1_score'] = 0.72 matrix.loc['D
  3. ctx:claims/beam/63063c97-1ded-45a2-9117-c21c3bcc4f66
    • full textbeam-chunk
      text/plain1 KBdoc:beam/63063c97-1ded-45a2-9117-c21c3bcc4f66
      Show excerpt
      matrix.loc['Dense Passage Retriever', 'community_support'] = 0.85 matrix.loc['Sparse Retrieval', 'community_support'] = 0.95 matrix.loc['Faiss', 'community_support'] = 0.8 matrix.loc['Hnswlib', 'community_support'] = 0.88 matrix.loc['Qdrant

See also

Keep researching

Missing something or suspicious of what's here? Kick off a research session — a Claude agent will investigate, cite its sources, and file new facts into a dedicated context you can review before accepting into the shared view.