Back to Prompt Library
implementation
System Architecture Setup
Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.
Linked challenge: Multi-Hop Medical Research Agent with LlamaIndex and Mixtral 8x22B
Format
Text-first
Lines
1
Sections
1
Linked challenge
Multi-Hop Medical Research Agent with LlamaIndex and Mixtral 8x22B
Prompt source
Original prompt text with formatting preserved for inspection.
1 lines
1 sections
No variables
0 checklist items
Using LlamaIndex, initialize a `SubQuestionQueryEngine` using `Mixtral 8x22B` as the primary LLM. Configure the engine to use a `VectorStoreIndex` for research papers and a `PropertyGraphIndex` for medical entity relationships. Define a custom tool called `medical_search` that the agent can use to perform multi-hop lookups.
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.