quiz bu lëkkale ak tegtal · Diggante Niveau
Këyitu waajur ak quiz ngir am ci lu ndaw ba lu mag
Saytu sa xam-xam ci retrieval bu ndaw ba bu mag: chunks xale ak waajur, sentence-window ak retrieval auto-merging, ak kañ lay raw chunks fixe.
Laaj 1 de 8
Lan mooy core compromis bi recuperation bu ndaw ba bu mag di wax?
Xoolaatal laaj bu nekk8 laaj
Sooy def quiz bi, tontu yi ak leeral yi dañuy feeñ.
- Lan mooy core compromis bi recuperation bu ndaw ba bu mag di wax?
- 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
- Ci sistem bu ndaw ba bu mag, lan lañu samp ak seetlu ci waxtu laajte?
- Small child chunks
- Whole parent documents only
- Document titles only
- The model's previous answers
- Sudee ñatti chunk yu doom yiñ jëlee ñoom ñépp bokk nañu ci benn wàllu waajur, lan la sistem bi wara def?
- Send all three children and the parent
- Discard the children because they overlap
- Send the shared parent once
- Send only the lowest-scoring child
- naka la ko LangChain di denc ñaari dayo mbind yi?
- 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
- Luy delloo ci palanteeru frase?
- 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
- 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
- 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
- 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