Ikibazo gihuza ibibazo · Hagati Urwego

Inyandiko y'ababyeyi na Ntoya-Kuri-Kugarura Ikibazo

Gerageza gutahura ibintu bito-binini-bigarurwa: uduce twumwana nababyeyi, interuro-idirishya hamwe no kugarura-auto-guhuza, kandi iyo ikubise uduce duto.

Ikibazo 1 Bya 8

Ni ubuhe buryo bwibanze bwo gucuruza bukora buto-nini-yo kugarura?

Reba buri kibazo8 ibibazo

Ibisubizo nibisobanuro bigaragara mugihe ufata ikibazo.

  1. Ni ubuhe buryo bwibanze bwo gucuruza bukora buto-nini-yo kugarura?
    • Embedding models are too slow for large documents
    • Small chunks match precisely but lack context, while large chunks carry context but match poorly
    • Vector databases cannot store documents longer than one page
    • Language models can only read one chunk per request
  2. Muri sisitemu ntoya-nini, niki cyashyizwemo kandi kigashakishwa mugihe cyibibazo?
    • Small child chunks
    • Whole parent documents only
    • Document titles only
    • The model's previous answers
  3. Niba ibice bitatu byagaruwe byabana byose biri mubice bimwe byababyeyi, sisitemu igomba gukora iki?
    • Send all three children and the parent
    • Discard the children because they overlap
    • Send the shared parent once
    • Send only the lowest-scoring child
  4. Nigute LangChain ya ParentDocumentRetriever ibika urwego rwinyandiko?
    • Both levels in a single vector index with no links
    • Parents in the vector store and children discarded
    • Children in a relational table, parents in the model's weights
    • Children in a vector store and parents in a separate document store
  5. Niki gusubiramo interuro-idirishya bigaruka?
    • Only the single matched sentence
    • The matched sentence plus a fixed number of neighboring sentences
    • A random sample of sentences from the document
    • The document's title and summary
  6. What does auto-merging retrieval do when enough leaf chunks from the same parent node are retrieved?
    • It deletes the parent node from the index
    • It asks the user which leaf to keep
    • It replaces the leaf chunks with their shared parent node
    • It re-embeds the leaves as one vector
  7. In which situation does small-to-big retrieval help the least?
    • When the documents are already short
    • When documents are long manuals with sections
    • When meaning depends on surrounding definitions
    • When several matches come from one contract section
  8. Why store a parent_id in each child chunk's metadata?
    • So the model can be fine-tuned on parent IDs
    • To make embeddings smaller
    • To hide parents from the user
    • So expanding a child to its parent is a cheap key-value lookup instead of another search