Prompt LibraryEngineering
RAG Hybrid Search Configuration Prompt
Configure hybrid (keyword + vector) search weights.
The prompt
Configure a hybrid retrieval pipeline for the corpus below.
Specify:
- Vector model and dimension.
- Keyword indexer (BM25) and preprocessing (stemming, stop-words).
- The fusion method (RRF or weighted) and recommended weights.
- Top-K per retriever before fusion.
- How to handle zero-result queries.
Corpus description: {{corpus}}
Query types: {{queries}}Replace the {{fields}} with your own context and tighten the rules to match your domain.
More Engineering prompts
LLM Reranking Prompt for RAG Retrieval
Use a model as a cross-encoder-style reranker for retrieved chunks.
RAG Chunking Strategy Design Prompt
Design a structure-aware chunking plan for a specific document type.
RAG Answer Grounding Checker Prompt
Verify a generated answer is grounded in retrieved chunks.
