A retrieval system does not usually pass an entire document to a language model. It selects smaller pieces. The boundary of each piece affects whether a retrieved passage still contains the definitions, qualifications and context needed to answer a question.
RetrievalRetrieval
Retrieval and evaluation before another layer of automation.
An embedding is a representation produced by a particular model and preprocessing pipeline. Similar vector dimensions do not guarantee compatible representations. Changing the model can change which passages appear close to a query even when the underlying documents stay the same.
RetrievalSemantic search can recognise related wording, while lexical search preserves exact names, identifiers and uncommon terms. Many collections contain both kinds of query. Combining the two can be useful, but the combination needs its own evaluation.
RetrievalA citation is useful only when it points to the passage that supports the associated statement. Linking to a document home page is weaker than preserving the specific section and version used. Retrieval and answer generation should share that evidence identity.
RetrievalA correct answer to yesterday's document can be wrong for today's process. Index freshness describes the delay between a source change and its availability to search. Deletions and access changes are as important as newly added content.
Retrieval