quiz bu lëkkale ak tegtal · Diggante Niveau

Quiz ngir seet ci anam wu méngoo

Test seet ci muy tekki: njëkkante ci këyit ci ay pàcc, dugal ci muy tekki ci BM25, rang bu bees, ak njëgu cache bu gaaw.

Yooni njiit yu jëm ciRecuperation contextuelle
Laaj 1 de 8

Ban jafe-jafe la seet ci muy saafara?

Xoolaatal laaj bu nekk8 laaj

Sooy def quiz bi, tontu yi ak leeral yi dañuy feeñ.

  1. Ban jafe-jafe la seet ci muy saafara?
    • Chunks lose information like company or time period when split from their document
    • Embeddings are too expensive to store
    • Language models cannot read tables
    • BM25 cannot handle long queries
  2. naka lañuy defaree contexte bu chunk bu nekk?
    • By copying the document title only
    • A language model reads the whole document and the chunk and writes a short situating explanation
    • By a human editor for every chunk
    • By averaging neighboring embeddings
  3. Ban ñaari limu jot mbindu chunk biñ tënk ci anamu Anthropic?
    • A graph database and a cache
    • A SQL table and a spreadsheet
    • An embedding index and a BM25 keyword index
    • Two separate vector indexes with different models
  4. Sunu sukkandikoo ci jàngat yiñ xamle ci Anthropic, lu tollu ci ñaata la embeddings yu jëm ci BM25 wàññi top-20 njuumte ci seet?
    • About 5 percent
    • About 20 percent
    • About 90 percent
    • About 49 percent
  5. Lan moo waral cache bu gaaw bi gëna xéewale seet ci contexte?
    • It caches the document once and reuses it for every chunk's context call
    • It skips the embedding step
    • It removes the need for BM25
    • It shortens each chunk
  6. Why is keeping BM25 in the pipeline especially useful with added context?
    • BM25 understands synonyms better than embeddings
    • Contexts often add exact identifiers like names, dates or codes that keyword search matches precisely
    • BM25 requires no index
    • BM25 replaces reranking
  7. When might contextual retrieval be unnecessary?
    • When the documents are in English
    • When using a reranker
    • When the knowledge base is small enough to fit in the model's context window
    • When chunks are longer than 50 tokens
  8. Where does the main extra cost of contextual retrieval occur?
    • At query time for every user question
    • In the reranker only
    • In the user's browser
    • At indexing time, with one model call per chunk