Back to Prompt Library
implementation
LlamaIndex RAG Pipeline and DSPy Optimization
Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.
Linked challenge: Graph-Based Legal Aid
Format
Text-first
Lines
1
Sections
1
Linked challenge
Graph-Based Legal Aid
Prompt source
Original prompt text with formatting preserved for inspection.
1 lines
1 sections
No variables
0 checklist items
Implement an advanced RAG pipeline using LlamaIndex to retrieve relevant Alaska probate laws and precedents. Describe how you'll chunk documents, choose an embedding model, set up the vector store, and how the retrieval mechanism will feed into the Claude Opus 4.1 agent. Further, explain how DSPy will be used to programmatically optimize prompts and few-shot examples for improved legal accuracy and reduced hallucinations.
Adaptation plan
Keep the source stable, then change the prompt in a predictable order so the next run is easier to evaluate.
Keep stable
Hold the task contract and output shape stable so generated implementations remain comparable.
Tune next
Update libraries, interfaces, and environment assumptions to match the stack you actually run.
Verify after
Test failure handling, edge cases, and any code paths that depend on hidden context or secrets.