Gids-gekoppelde quiz · Middelmatig Niveau
Contextuele ophaalquiz
Test contextueel ophalen: documentcontext aan stukjes toevoegen, contextuele inbedding met contextuele BM25, herrangschikking en prompt caching-kosten.
Vraag 1 van 8
Welk probleem lost contextueel ophalen op?
Bekijk elke vraag8 vragen
Antwoorden en uitleg verschijnen terwijl je de quiz doet.
- Welk probleem lost contextueel ophalen op?
- 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
- Hoe wordt de context voor elk deel gegenereerd?
- 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
- Welke twee indexen ontvangen de gecontextualiseerde stuktekst in de aanpak van 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
- In hoeverre hebben contextuele inbedding plus contextuele BM25, volgens de gerapporteerde experimenten van Anthropic, het aantal mislukte ophaalacties in de top 20 ongeveer verminderd?
- About 5 percent
- About 20 percent
- About 90 percent
- About 49 percent
- Waarom maakt prompt caching contextueel ophalen goedkoper?
- 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
- 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
- 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
- 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