Dontopedia

RAG system architecture

From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-11.)

RAG system architecture has 5 facts recorded in Dontopedia across 2 references, with 1 live disagreement.

5 facts·3 predicates·2 sources·1 in dispute
Maturity scale raw canonical shape-checked rule-derived certified

Inbound mentions (1)

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.

exemplifiesExemplifies(1)

Other facts (4)

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.

4 facts
PredicateValueRef
Rdf:typeHybrid Search System[1]
Rdf:typeSystem Architecture[2]
Uses Vector SearchMilvus[1]
Uses Document StorageMongodb[1]

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/c39988e0-db33-4984-8c77-56ffcecd919a
ex:HybridSearchSystem
usesVectorSearchbeam/c39988e0-db33-4984-8c77-56ffcecd919a
ex:milvus
usesDocumentStoragebeam/c39988e0-db33-4984-8c77-56ffcecd919a
ex:mongodb
typebeam/241122f8-dc34-4876-8384-3647f4796af6
ex:SystemArchitecture
labelbeam/241122f8-dc34-4876-8384-3647f4796af6
RAG system architecture

References (2)

2 references
  1. ctx:claims/beam/c39988e0-db33-4984-8c77-56ffcecd919a
    • full textbeam-chunk
      text/plain1 KBdoc:beam/c39988e0-db33-4984-8c77-56ffcecd919a
      Show excerpt
      # Vector exists but document does not vector_collection.delete([vec_id]) # Run reconciliation periodically reconcile_data() ``` ### Full Example Script Here is the complete script combining all the steps: ```pyth
  2. ctx:claims/beam/241122f8-dc34-4876-8384-3647f4796af6
    • full textbeam-chunk
      text/plain1 KBdoc:beam/241122f8-dc34-4876-8384-3647f4796af6
      Show excerpt
      self.tokenizer = tokenizer def process_query(self, query, context=None): # Reformulate the query reformulated_query = reformulate_query(query, context) # Process the reformulated query (e.g., retrieve r

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.