Kedis ku xidhan hagaha · Dhexdhexaad Heerka

Kediska RAG (CRAG) ee saxda ah

Tijaabooyin sax ah RAG: qiimeeyaha dib u soo celinta, Saxda ah, Ficilada aan saxda ahayn iyo kuwa madmadow, hufnaanta aqoonta, iyo dib-u-dhacyada ganacsiga raadinta webka.

Wadooyinka haga ee la xidhiidhaRAG sax ah
Su'aal 1 ee 8

Waa maxay daciifnimada asaasiga ah ee heerka RAG ee CRAG?

Horudhac su'aal kasta8 su'aalo

Jawaabaha iyo sharraxaadaha waxay soo baxayaan markaad qaadanayso kediska.

  1. Waa maxay daciifnimada asaasiga ah ee heerka RAG ee CRAG?
    • The generator trusts whatever the retriever returns
    • Embeddings are too small
    • Models cannot read long documents
    • Vector databases are too slow
  2. Warqadii asalka ahayd ee CRAG, nooc noocee ah ayaa u adeegay qiimaynta soo celinta?
    • A large GPT-style generator
    • A fine-tuned T5-large model
    • A BM25 index
    • A human reviewer
  3. Muxuu sameeyaa CRAG marka dhammaan dukumentiyada la soo saaray ay hooseeyaan?
    • Answers from the documents anyway
    • Returns an error to the user
    • Discards them, rewrites the query and uses web search
    • Doubles the number of retrieved documents from the same index
  4. Waa maxay ujeeddada tillaabada burburka-ka-dib-soo-celinta?
    • To translate documents into another language
    • To compress embeddings
    • To rank web pages by popularity
    • To split documents into strips and keep only relevant pieces
  5. Marka qiimeeyuhu aanu hubin in ay khusayso, tallaabokee ayay CRAG qaadaysaa?
    • Ambiguous: combine refined internal knowledge with web results
    • Correct: use internal documents only
    • Incorrect: use web results only
    • Stop and ask the user to rephrase
  6. Which statement about CRAG is a misconception according to the guide?
    • It adds cost and latency
    • It can wrap other RAG methods
    • CRAG verifies that the final answer is correct
    • It can use web search as a fallback
  7. What is the trade-off of setting a very strict relevance threshold?
    • Weak documents slip through more often
    • Fallback triggers often, adding web calls and latency
    • The system stops using an evaluator
    • Answers become shorter
  8. Why log which path (Correct, Ambiguous, Incorrect) each query took?
    • It is required by the CRAG license
    • It trains the embedding model automatically
    • It removes the need for thresholds
    • It reveals coverage gaps in the knowledge base worth fixing