Searches the PRA knowledge base using combined vector similarity search (VSS) and BM25 full-text search to find the most relevant chunks for a user query.
Arguments
- store
A ragnar store object from
build_knowledge_base().- query
Character string. The user's question or query.
- top_k
Integer. Number of chunks to retrieve (default 5).
Value
A character vector of relevant text chunks with source attribution, suitable for injecting into an LLM prompt as additional context.
Examples
if (FALSE) { # \dontrun{
store <- build_knowledge_base()
chunks <- retrieve_context(store, "What is earned value management?")
cat(chunks, sep = "\n---\n")
} # }