Build a Global Reinsurance Risk Aggregator with LlamaIndex and DeepSeek R1
Global reinsurers like Munich Re and Lloyd's require complex exposure modeling across thousands of multi-jurisdictional treaty documents. Build a retrieval-augmented generation pipeline using LlamaIndex and DeepSeek R1 to analyze treaty risk clauses. Achieve high precision context retrieval and exact clause compliance extraction across reinsurance treaty filings.
What you are building
The core problem, expected build, and operating context for this challenge.
Construct an advanced LlamaIndex RAG system utilizing DeepSeek R1 reasoning to parse, chunk, and index global reinsurance treaty contracts.
How work is evaluated
Evaluates LlamaIndex retrieval precision and loss retention calculation using DeepSeek R1.
Challenge datasets
Public datasets, plus the private datasets you have access to.
How submissions are scored
These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.
retrieval_hit_rate
Required source clauses are present in retrieved contexts.
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
extraction_accuracy
Exact match accuracy on numeric retention amounts and listed exclusions • target: 0.92 • range: 0-1
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
What you should walk away with
Implement hierarchical chunking strategies using LlamaIndex.
Leverage DeepSeek R1 reasoning for complex legal exposure reasoning.
Build metadata-filtered vector indexes over multi-jurisdictional treaties.
Evaluate RAG retrieval accuracy with target hit-rate metrics.
Reference links and supporting material
Corpus of 50 synthetic reinsurance treaty contracts based on Munich Re and Lloyd's standard market clauses.
Challenge setup
Evaluates LlamaIndex retrieval precision and loss retention calculation using DeepSeek R1.
Challenge input
Natural language query specifying hazard type and region
LlamaIndex
Provides structural parsing and vector indexing components.
DeepSeek R1
Delivers extended reasoning over dense legal language.
Evaluated output
JSON containing retention_usd, exclusion_list, and target_clauses
- Required source clauses are present in retrieved contexts.
- Exact match accuracy on numeric retention amounts and listed exclusions • target: 0.92 • range: 0-1
- Benchmark: LegalRAGBench
- Extraction Accuracy target: 0.92
- 1 public reference case
- Python execution harness
- Python sandbox (unavailable on Versalist)
Summary shows the first task, up to three tools, and up to three evidence items. Open the technical recipe to view all configured items.
View technical recipe
Configured tools
- DeepSeek · Required
- Llama Index · Optional
- DeepSeek R1 · Optional
Evaluation contract
- retrieval_hit_rate · Weight 1
- extraction_accuracy · Weight 1
Metrics
- extraction_accuracy · Target 0.92
Benchmarks
- LegalRAGBench
- general
Reference cases
- 1 public reference case
Workflow tasks
- Task 1
Input: Natural language query specifying hazard type and region
Output: JSON containing retention_usd, exclusion_list, and target_clauses
Execution harness: Python
Evaluation tools
- LlamaIndex · RAG Framework
- DeepSeek R1 · Reasoning Model
Recipe freeze marker
No recipe freeze time is recorded.